This is an open access article under the CC BY license: 

 
 

 

 

 
Al-Khwarizmi 

Engineering 

Journal 

 

                         Al-Khwarizmi Engineering Journal  

           ISSN (printed): 1818 – 1171, ISSN (online): 2312 – 0789 

Vol. 20, No. 4, December (2024), pp. 70-88 
 

 

Defect Detection Using Thermography Camera Techniques:  

A review 
 

Hussein N. AL-Jubori1*,  Izzat AL-Darraji2   and Houssem Jerbi3 
1,2 Department of Automated Manufacturing, Al-Khwarizmi College of Engineering, University of Baghdad, Iraq 

3Department of Industrial Engineering, College of Engineering, University of Ha'il, Hail 81481, Saudi Arabia 
*Corresponding Author, s Email: hussein.Najeh2204@kecbu.uobaghdad.edu.iq 

 
(Received 13 July 2023; Revised 24 February 2024; Accepted 11 August 2024; Published 1 December 2024) 

https://doi.org/10.22153/kej.2024.03.002 
 

 

Abstract 

 
Individuals across different industries, including but not limited to agriculture, drones, pharmaceuticals and 

manufacturing, are increasingly using thermal cameras to achieve various safety and security goals. This widespread 

adoption is made possible by advancements in thermal imaging sensor technology. The current literature provides an in-

depth exploration of thermography camera applications for detecting faults in sectors such as fire protection, 

manufacturing, aerospace, automotive, non-destructive testing and structural material industries. The current discussion 

builds on previous studies, emphasising the effectiveness of thermography cameras in distinguishing undetectable defects 

by the human eye. Various methods for defect detection, including temperature analysis and image processing algorithms, 

are thoroughly presented. The factors contributing to the effectiveness of thermography cameras are explored, along with 

their advantages over traditional inspection methods. The literature review highlights the diverse applications of 

thermography cameras in fault detection. The review highlights the remarkable transformation brought by thermal camera 
technology in mechanical system fault detection, leading to improved maintenance practices. These cameras can detect 

unseen irregularities, enable non-invasive testing and support hands-on system maintenance, making them indispensable 

tools for ensuring mechanical systems operate efficiently, reliably and safely. With the continuous advancement of 

technology, the integration of Industry 4.0 and IoT technologies will further enhance the capabilities of thermal cameras, 

ensuring elevated performance across different domains. In electrical systems, thermal cameras allow for the early 

identification of faults, enabling proactive maintenance to mitigate risks. Additionally, by assessing structural integrity, 

thermal cameras can detect thermal and insulation inefficiencies, leading to improved energy efficiency.  

 

Keywords: Thermography camera; defect detection; temperature analysis; image processing 

 

1. Introduction 
 

A thermal image camera (TIC) is a type of imaging 

device designed to detect and capture infrared 

radiation emitted by objects, subsequently 
converting this thermal energy into a visible image. 

TICs operate by measuring the thermal energy 

emitted from objects within their field of view. The 

amount of infrared radiation emitted increases 
proportionally with the temperature of an object, 

resulting in a corresponding increase in the 

brightness of the object as observed in the thermal 
image. This technology has a wide range of 

applications across diverse industries, such as 

manufacturing and building inspection. However, 
the literature reveals that many researchers have 

approached this subject from various perspectives. 

One crucial aspect of remote structural monitoring 

is the application of machine learning (ML) for 
detecting fatigue damage in glass–epoxy 

composites through thermal imaging. This 

technique plays a key role in remote structural 
monitoring, providing a reliable method for the 

safety evaluation and optimisation of composite 

structures and components [1]. However, the 

precise characterisation of fatigue-induced damage 

mailto:hussein.Najeh2204@kecbu.uobaghdad.edu.iq
https://doi.org/10.22153/kej.2024.03.002


   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

71 

hotspots, encompassing their dimensions, 

morphology, spatial distribution, hysteresis-induced 

thermal effects and subsurface temperature profiles, 
through the application of surface thermal imaging 

techniques, continues to pose remarkable 

challenges in current research. The objective was to 

assess the theoretical accuracy of hotspot 
characterisation using an ML model trained on 

artificially generated thermal images derived from 

3D finite element models with increasing levels of 
complexity. Incorporating fatigue damage as an 

inherent heat source has been shown to effectively 

mitigate the impact of thermal image noise and 

other uncertainties related to heat transfer. The 
study demonstrates that ML can effectively and 

precisely retrieve the heat influx, depths and 

geometry of the heat source from the initial thermal 
images of composite materials. The prediction 

accuracies achieved ranged from 85% to 99%. The 

study also analysed the impact of variations in the 
size of the training set and image resolution on the 

level of prediction error. The results presented make 

a substantial contribution towards the development 

of precise and effective techniques for detecting 
fatigue damage in fibre composite materials 

remotely. In [2], two deep learning methodologies 

were examined for the purpose of restoring initial 
temperature profiles from thermographic images in 

the context of non-destructive material testing is 

examined. Initially, a deep neural network (DNN) 
was trained in an end-to-end manner, where the 

surface temperature measurements were directly 

inputted into the DNN. Subsequently, the surface 

temperature measurements were transformed into 
virtual waves, a novel concept in thermography, 

which were subsequently utilised as input for the 

DNN. A data generation system is devised and a 
dataset comprising 100,000 synthetic images 

depicting temperature measurements are produced 

to demonstrate the efficacy of the aforementioned 

techniques. Various model-based reconstruction 
techniques, such as Abel transformation, curvelet 

denoising and synthetic aperture focusing methods, 

were examined in time and frequency domains to 
establish an appropriate baseline. These methods 

are considered to be state-of-the-art in the field. 

Furthermore, a tangible model was generated to 
facilitate assessment of entirely novel real-life data. 

According to the findings of multiple experiments, 

the end-to-end as well and hybrid approaches 

exhibited superior performance compared to the 
baseline in terms of reconstruction accuracy. The 

end-to-end methodology, in particular, exhibited 

superior computational efficiency and demanded 
minimal domain expertise. The utilisation of the 

hybrid approach necessitated a substantial amount 

of expertise in the relevant field and incurred higher 

computational costs compared to the end-to-end 

approach. The use of virtual waves has been proven 
to be a crucial aspect in simplifying the intricate 

process of end-to-end reconstruction. 

Consequently, superior reconstructions were 

achieved with the same number of training samples 
compared to the traditional end-to-end 

methodology. Furthermore, this approach 

facilitated the implementation of more condensed 
network structures and the integration of pre-

existing knowledge, such as sparsity and non-

negativity. The technique presented is particularly 

suited for non-invasive, two-dimensional 
examinations, specifically in scenarios where the 

amplitudes along objects remain constant, as in the 

case of metallic wires. In [3], a deep thermal 
imaging model was explored to investigation its 

application in close-range automated recognition, 

aimed at enhancing the understanding of people and 
universal technologies within their surroundings. 

The study employed a low-cost mobile thermal 

camera to collect thermal textures, which were then 

classified into distinct material types using a deep 
neural network. This approach proved highly 

effective in the absence of ambient light sources or 

direct material contact. Additionally, the use of a 
deep learning network eliminated the need for 

manually designing a feature set for various 

materials. The performance of the system was 
assessed based on its capability to identify 32 

distinct material types across indoor and outdoor 

settings. The methodology employed yielded 

recognition accuracies exceeding 98% in a sample 
of 14,860 images depicting 15 indoor materials and 

exceeding 89% in a sample of 26,584 images 

depicting 17 outdoor materials. However, the 
discussion of the potential real-time applications of 

this technology in human–computer interaction 

applications and its prospective avenues for further 

development is also observed. In [4], the researchers 
introduced a neural network based on deep learning 

and region convolution for detecting obscured 

objects. The identification of buried objects in 
thermal images involves using a region of interest 

selection technique with a bounding box. The 

experimental findings indicate that thermal images 
of buried objects exhibit temperature fluctuations 

due to changes in the heat-carrying capacity of the 

surrounding soil. The neural network approach 

proposed in this study demonstrated a 90% accuracy 
rate in predicting the locations of buried objects in 

thermal images. This method has the potential to be 

applied to land mine detection through thermal 
image processing techniques. The conditions of 

machines and other systems can be realised by 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

72 

creating and classifying features that summarise the 

measured signal attributes. At present, professionals 

within their specialised domains formulate these 
characteristics using their expertise. Thus, the 

efficacy and utility of the system are contingent 

upon the expertise of practitioners in the relevant 

fields of physics or statistics. Additionally, if new 
and supplementary circumstances arise, specialists 

must incorporate innovative feature extraction 

techniques. In the study presented in [5], the authors 
explored a technique from the sub-discipline of 

feature learning, namely deep learning, using 

convolutional neural networks (CNNs), to address 

the limitations of traditional feature engineering. 
The goal was to assess the feasibility and 

methodology of using deep learning techniques to 

automatically evaluate the operational state of 
machinery through the analysis of infrared thermal 

video data. This goal demonstrated the effectiveness 

of the proposed system in detecting various 
conditions in rotating machinery with high accuracy 

(95% and 91.67% for machine fault detection and 

oil level prediction, respectively) using infrared 

thermal data. Notably, the system does not require 
extensive knowledge of the underlying physics, 

which may simplify the condition monitoring 

process using intricate sensor data. Additionally, the 
use of trained neural networks enables the 

identification of important areas within infrared 

thermal images that are associated with particular 
conditions, potentially yielding novel physical 

insights. In [6], researchers introduced a thermal 

imaging process for assessing the electrical 

equipment status. They explored a broader range of 
anomalies compared to other thermographic 

surveys. Numerous fault conditions have been 

determined to cause considerable heat dissipation, 
whilst some fault conditions have been found to 

result in even lower levels of heat dissipation 

compared to that of normal equipment. These 

conditions indicate a complex segmentation 
challenge. A pre-processing procedure, where the 

data is segregated into two discrete categories based 

on the thermal condition of the equipment, 
specifically denoted as the ‘cold’ and ‘hot’ states, is 

implemented to address this issue. Subsequently, 

the segmentation process is conducted through the 
implementation of random forest and AdaBoost 

classifiers, employing a sliding window technique, 

whilst considering interpretable ML principles. 

Furthermore, a novel collection of infrared images, 
featuring transformers and three-phase induction 

motors, has been generated. The method under 

consideration was evaluated using an identical 
dataset, resulting in outcomes that are currently 

unparalleled. The implementation of deep learning 

for automatic damage detection necessitates a 

comprehensive data repository that encompasses 

intricate pavement conditions. The presented study 
introduced a novel model for detecting surface 

damage by fusing thermal and RGB images. In [7], 

researchers investigated how detection outcomes 

are impacted by input data and network 
configurations across thermal, MSX, fused image 

and RGB systems. The findings indicate that the 

accuracy of damage detection in the fused image 
can reach up to 98.34%. Additionally, the use of an 

augmented dataset improved the stability of the 

detection model, resulting in a precision of 98.35%, 

recall of 98.34% and F1-score of 98.34%. In [8, 9], 
researchers introduced a deep learning model that 

integrates TIC for detecting humans trapped in 

emergency situations, such as smoky fires, where 
visibility is notably reduced. The instantaneous 

results can be communicated to command centres as 

valuable data, enabling prompt rescue operations 
and ensuring the safety of firefighters before 

engaging in hazardous, smoke-filled fire scenarios. 

The application of deep learning methodologies, 

supported by comprehensive datasets that 
incorporate intricate pavement characteristics, has 

been proven effective in quickly identifying 

pavement deterioration. Additionally, the use of 
low-cost infrared imaging technology, coupled with 

deep learning methodologies, has been shown to be 

an effective means for detecting pavement damage, 
particularly in cases where temperature variations 

are present. Previous studies using pavement data 

collected under sunny conditions and analysed 

through the SA-ResNet deep learning methodology 
achieved a predictive accuracy of 96.47%. In [10, 

11], researchers focused on applying deep learning 

frameworks to datasets containing photographs 
taken during winter and summer sunny conditions 

to compare the predictive sensitivity, recall and 

precision scores. The findings of these studies 

indicate that moderate-resolution IR-T imaging 
cameras perform more reliably in summer than in 

winter conditions, as they yield higher predictive 

accuracy during warmer months. The studies also 
recommended the use of these cameras in such 

conditions due to their cost-effectiveness. 

Researchers in objective studies [12, 13] explored 
automatic variations in cognitive evaluation tasks 

between a healthy control (HC) and a mild 

Alzheimer’s disease (AD) group to detect the 

condition in real time. Group differences were also 
examined using an artificial intelligence (AI) model 

based on thermal infrared imaging (IRI) technology. 

Using IRI technology, the researchers conducted 
non-invasive observations of autonomic activity 

and its associated thermoregulatory manifestations 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

73 

without affecting the psychophysiological state of 

the participants, thereby facilitating free 

communication with physicians. In this regard, 
overdependence on human experts is likely to be 

diminished. 

 

 

2. Applications 

 
Thermal cameras have proven to be effective 

tools for detecting defects across various industries. 

Their capability to gather and visualise the thermal 
energy generated by objects allow them to identify 

defects that may not be visible to the human eye. An 

overview of the application of thermal cameras in 

defect detection, as presented in Figure 1, is 
introduced in detail in the following subsections.  

 

 
 

Fig. 1. Defect detection-based thermal camera 

applications 

 

 

2.1 Mechanical Systems 

 
Thermal imaging technology plays a crucial role 

in identifying anomalies in mechanical systems and 

equipment. Detecting temperature variations can 

help identify issues such as bearing faults [14], 

misalignments [15], worn-out parts [16] and 
inadequate lubrication [17]. Timely detection of 

these defects can notably enhance the maintenance 

process. Mechanical systems are essential in a 
variety of industries, including manufacturing and 

aerospace. Ensuring optimal performance and 

minimising downtime are essential factors for 
achieving efficient operation in these sectors. This 

phenomenon is due to any potential defect in 

mechanical components, which can lead to a 

corresponding failure in the operational processes, 
ultimately affecting the overall efficiency and 

reliability of the system. Consequently, the use of 

thermal cameras has become an effective tool for 

non-destructive testing (NDT) of defects in 
mechanical systems [18]. The capability of thermal 

cameras to sense the temperature on the exterior of 

mechanical components allows them to detect 
potential defects at an early stage [19]. In addition, 

thermal cameras can continuously monitor and 

record the temperature of mechanical components 

whilst they are in operation. This capability enables 
the identification of heat-related issues caused by 

many factors such as wear and friction. Standard 

cameras cannot detect these temperature variations. 
Thus, the importance of thermal cameras in 

detecting defects in mechanical system components 

is widely considered. The reliability and longevity 
of mechanical systems are noticeably improved 

when mechanical issues are promptly identified and 

proactive maintenance strategies are implemented. 

Insights gained from thermal imaging allow for 
effective preventative maintenance, enabling the 

timely servicing or replacement of components 

before they approach critical failure levels. The 
incorporation of thermal cameras within the 

framework of Industry 4.0 and the Internet of 

Things (IoT) [20] introduces novel opportunities for 
identifying faults in mechanical systems. Intelligent 

and predictive maintenance systems can be 

developed by combining thermal imaging, sensor 

data and advanced analytics. These systems possess 
the capability to predict potential failures, optimise 

maintenance schedules and facilitate data-driven 

decision-making for the management of mechanical 
assets. 

 

2.2 Electrical Systems 
 

Electrical systems play a crucial role in 

numerous industries, including energy generation, 
delivery and circulation. Detecting defects in these 

systems is essential for identifying potential issues 

such as damaged interconnections [21], strained 

circuitry [22] and heat-generating components [23]. 
Thermal cameras are invaluable tools in preventing 

electrical malfunctions, improving energy 

efficiency and ensuring the reliability and safety of 
electrical systems. By identifying areas of elevated 

temperature, these cameras help pinpoint potential 

failures before they lead to more substantial 
problems [24]. All the thermal information obtained 

by thermal cameras can be recorded, allowing it to 

be monitored offline for onboard digital twin 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

74 

applications as well as for offline digital twin 

systems [25]. Hence, the application of thermal 

cameras is now recognised as a viable technique for 
detecting and diagnosing defects in electrical 

systems, thereby promoting preventive maintenance 

and minimising the likelihood of failures. The 

timely recognition of such defects enables 
immediate reconditioning measures, thereby 

preventing potential damage to equipment, 

electrical fires or interruptions in the power supply 
[26]. The application of a proactive approach 

advantageously reduces downtime and maintenance 

costs but also increases the operational lifespan of 

electrical equipment. Along with reducing potential 
risks, thermal imaging also facilitates the 

identification of electrical components operating at 

high temperatures. Furthermore, thermal cameras 
play a crucial role in the examination of electricity 

delivery and energy optimisation within electrical 

systems. By optimising energy consumption, these 
cameras substantially contribute to cost reduction, 

energy waste minimisation and overall 

improvement in the sustainability of electrical 

systems. During quality control and inspection 
processes, thermal cameras are invaluable tools. 

The incorporation of thermal imaging, sensors and 

advanced analytics can enhance smart supervision 
systems. These systems possess the capability to 

consistently evaluate the condition and operational 

efficiency of electrical components, detect 
deviations from normal behaviour and trigger 

notifications or automated actions as required. The 

incorporation of this technology improves the 

effectiveness of maintenance operations, reduces 
the likelihood of human error and enables the 

implementation of a predictive maintenance 

strategy. 
 

2.3 Structural Materials 
 

Buildings are constructed using various 

structural materials, which may develop defects 

under certain conditions. Ensuring the safety of 
these buildings depends on detecting and addressing 

these defects [31]. Thermal imaging technology is 

extensively used to identify defects in structural 

materials across different types of structures, 
including buildings [27], bridges [28] and pipelines 

[29]. By monitoring and investigating temperature 

changes on the surface, detecting issues such as 
leaks, moisture and structural deficiencies becomes 

practicable [30]. Thus, thermal inspections serve as 

a valuable tool for evaluating structural integrity, 
detecting hidden flaws and expediting timely 

repairs or maintenance activities. Researchers have 

widely utilised thermographic cameras for 

inspecting structural materials to identify obscure 

faults in the human eye. Thermal cameras can help 

detect air breakthroughs or unfit insulation due to 
their capability to collect and detect energy emitted 

from surfaces of structural materials. The collected 

thermal variations are indicators of heat dissipation 

or absorption that may increase structural material 
discomfort. Thermal cameras have facilitated 

insulation maintenance to improve thermal 

conditions and energy efficiency by detecting heat 
leaks. Individuals using thermal cameras can detect 

numerous building faults. For instance, they can 

help identify damaged insulations that lead to 

uneven temperature distributions, high cooling and 
heating costs and energy loss. Therefore, thermal 

cameras can help individuals offer regular building 

updates to enhance energy-saving effectiveness and 
cost reductions. Individuals also find thermal 

cameras essential in detecting breakthrough 

moisture. Structural materials contain water, 
thereby increasing their potential for corrosion, 

mould emergence and drop, which negatively 

impact buildings’ safety. With thermal imaging 

technology embedded into thermal cameras, 
individuals can detect temperature variations caused 

by moisture infiltration, helping to mitigate 

potential risks. Typically, these temperature 
variations serve as a precaution for potential 

moisture breakthroughs, giving building managers 

or maintenance teams the opportunity to address the 
issue before it escalates. Thermal camera imaging is 

also highly effective for detecting structural issues 

such as delamination, gaps or cracks in buildings. 

Thus, temperature variations in buildings serve as 
indicators of hidden faults that require immediate 

attention to prevent potential hazards, including 

fatalities. The above information regarding thermal 
cameras is a crucial resource for professionals in the 

inspection and structural engineering fields. Such 

information can help in assessing the severity of 

faults within buildings, enabling the development of 
effective strategies for reinforcement and repair to 

meet safety and structural integrity standards.    

 

2.4 Manufacturing and Quality Control 
 

Different industrial players have applied thermal 
imaging technology to improve product process 

efficiency and meet quality control requirements. 

The technology helps manufacturing companies to 
produce quality goods, minimise waste and promote 

sustainable manufacturing operations, thereby 

meeting the requirements. With this technology, 
manufacturing firms can detect faults sufficiently 

early to avoid compromising customer satisfaction 

[32]. Production and quality control in companies 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

75 

have been substantially improved through thermal 

imaging technology, which offers non-destructive 

and non-contact methods for inspection. [33]. Using 
this technology in cameras gives them the capability 

to detect temperature variations, which are key 

indicators of hidden irregularities that might affect 

product quality [34]. Thermal cameras can detect 
hidden material flaws, including but not limited to 

insufficient bonding, cracks, delamination and 

porosity, by evaluating temperature fluctuations. If 
such faults are left unattended, then the performance 

and quality of products are more likely to be notably 

compromised, lowering customer satisfaction. 

Therefore, the use of thermal cameras in the 
manufacturing sector aims to provide quality 

assurance and verification [35].  

By examining thermal patterns using these 
cameras, firms can assess compliance, uniformity 

and consistency of products before they are released 

into the market for consumption. Thermal imaging 
aids firms in detecting discrepancies in meeting 

desired quality standard by assessing variations in 

thermal signatures. This information is crucial 

because it allows entities to plan training 
programmes that raise awareness of compliance 

with quality standards, ensuring customer 

satisfaction and increased profits. In contrast, 
physical measurements or visual examinations used 

in conventional testing require disassembly and 

destructive sampling, methods that are associated 
with high material wastage and elevated costs [36]. 

With thermal cameras, non-destructive and non-

contact testing can be performed on various 

materials and products without compromising their 
structural integrity.  

 

2.5 Non-Destructive Testing 
 

Non-destructive testing (NDT) widely employs 

thermal imaging cameras to identify faults, 
including material cracks, inclusions or voids, 

without causing damage to the products. Industries 

such as automotive, manufacturing and aerospace 
have adopted NDT techniques to ensure that their 

products meet safety and quality standards. These 

techniques are crucial in ensuring that the structures 

and materials produced are safe, reliable and of high 
veracity [37]. By using these techniques, companies 

can evaluate product components without the need 

for disassembly or causing damage. Thermal 
cameras have become increasingly recognised in the 

NDT field as valuable tools due to their non-

invasive and non-contact inspection capabilities, 
allowing for the detection of temperature 

fluctuations that indicate potential issues. These 

cameras use thermal imaging technology to identify 

anomalies such as separations, fractures, foreign 

materials and empty spaces [38, 39]. Defects are 

often associated with varying thermal 
characteristics compared to the surrounding 

environment, creating detectable thermal variations 

that can be identified using thermal imaging 

technology. Thermal cameras are also useful for 
studying material homogeneity, density and 

composition by analysing temperature distributions 

across surfaces, thereby helping to identify faults. In 
the field of NDT-related welding inspection, 

thermal cameras play an important role in 

evaluating weld joint quality by assessing thermal 

variations along the material. These variations can 
reveal possible faults, such as cracks, minimal 

fusion or porosity. Inspectors in this field benefit 

from thermal imaging because it helps them detect 
temperature deviations in welded materials, 

highlighting the quality of the welding process. 

 

2.6 Pipeline Inspection 
 

Pipeline systems are considered critical 
infrastructures for loading different fluids across 

long distances, including water, gas and oil. 

Therefore, pipeline safety must be consistently 
maintained to limit potential issues such as leaks 

[40]. Particularly, thermal cameras are used to 

inspect pipelines to find leaks or defects by 

monitoring the temperature distribution along the 
pipeline. Thermal inspections make it easier to 

identify problems, thereby improving the integrity 

and condition of pipeline systems [41, 42]. Notably, 
using thermal cameras to inspect pipelines is an 

effective technology for monitoring defects and 

ensuring the safe functioning of these systems. The 

flow of fluids within the pipeline leads to 
temperature fluctuations on the pipe’s surface. 

Thermal cameras are capable of detecting 

deviations in temperature and providing visual 
guidance to potential leakage points. The obtained 

data enables personnel to expeditiously detect and 

identify leaks, facilitating prompt repairs. Hotspots 
may also indicate other issues in pipelines, such as 

the presence of localised fluid obstructions [43]. 

This information assists operators in identifying 

possible problematic regions and implementing 
appropriate remedial steps, such as investigating 

fluid flow problems, to prevent them from 

escalating into more substantial difficulties. 
Thermal cameras are essential tools for monitoring 

and inspecting corrosion and erosion regions in 

pipelines [44]. Over time, corrosion and erosion can 
weaken the strength of pipe walls, posing a risk to 

the overall structural integrity of the pipeline. With 

the timely identification of thermal fluctuations, 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

76 

individuals can detect faults early and formulate 

maintenance strategies to address and prevent 

progressive failures. Scholars have found thermal 
cameras beneficial in assessing the structural 

integrity of pipeline coatings. These coatings often 

protect pipes from corrosion and other forms of 

damage. However, coatings may deteriorate over 
time due to the effect of mechanical issues (stress) 

or environmental conditions. In these 

circumstances, thermal cameras become crucial 
tools, as they assess temperature variations caused 

by coatings faults (such as inadequate coverage or 

delamination). Using temperature deviation 

visualisations, individuals can identify specific 
areas on pipes or walls where coatings have been 

compromised, allowing for targeted evaluations and 

repairs to maintain the protective integrity of the 
coatings. Inspecting insulated or underground pipes 

is made more efficient and non-intrusive with 

thermal cameras, which are capable of identifying 

hidden problems. Integrated thermal imaging 

technology detects thermal fluctuations on the 
exterior of pipes or their insulation, helping to locate 

faults, leaks or hot spots. The data collected from 

thermal cameras can be used for continuous 
monitoring of the conditions of pipes, eliminating 

the need for excavation or disassembly.  

 

2.7 Fire Protection 
 

Fire is a significant hazard to humans, animals, 
birds, tangible assets and the surrounding 

environment. The early detection of fire is vital 

because it expedites effective suppression and 

management of associated fire incidents. The 
enhancement of fire alarm systems and fire 

prevention instruments may be realised through 

their integration in environments characterised by 
substantial heat generation. Thermal imaging 

cameras are used inside fire protection systems to 

detect thermal irregularities, facilitating the rapid 

identification and control of flames. Thermal 
cameras are increasingly becoming recognised as 

essential tools in fire detection systems due to their 

capability to provide improved capabilities for early 
fire detection. The identification of temperature 

variations becomes possible by using thermal 

imaging technology, possibly serving as an 
indicator of fires [45]. In contrast to traditional 

smoke or flame detectors, thermal imaging 

technology assumes control over the identification 

of fires via the detection of heat fluctuations. This 
capability facilitates early detection before the sight 

of flames or smoke, which, in turn, enables fast 

response, including actions such as departure, 
putting out fires and control measures, reducing the 

likelihood of fire spread. Thermal cameras have 

shown notable use in the identification of fires that 

exhibit no apparent smoke or arise in environments 
with restricted visual perception [46]. The 

aforementioned characteristic provides thermal 

cameras with distinct advantages in situations 

where relying only on smoke detection may be 
inappropriate, such as in large open rooms, factories 

or high places. Additionally, thermal cameras 

provide continuous fire detection during the day and 
night. Furthermore, in contrast to human operators, 

thermal cameras are advantageous due to their 

resistance to tiredness or oversights, facilitating 

continuous monitoring of the area of interest for 
temperature irregularities. The continuous 

monitoring system ensures rapid identification and 

resolution of fires, even in situations where human 
supervision is impractical. Thermal cameras allow 

individuals to acquire thermal images to use in 

identifying the amount and the exact location of a 
fire to guide the actions of emergency responders 

towards improved fire suppression efforts.  

 

2.8 Automotive and Aerospace Industries 

 
The aerospace and automotive industries are 

increasingly adopting thermal cameras in detecting 

defects. These cameras can identify faults in the 

engine, the braking system, the exhaust system and 
other components. Through routine thermal 

inspection in the two industries, safety and 

performance have been improved as maintenance 
costs have been minimised. The sectors remain 

strict on surveillance and assessment of procedures 

to ensure safety is prioritised and commodities are 

effective and reliable. The thermal imaging 
technology on thermal cameras allows individuals 

to capture temperature fluctuations, indicating 

suboptimal functioning or irregularities linked to 
engines [47]. Thermal cameras also use embedded 

thermal imaging technology to monitor the cooling 

and exhaust systems of the engine to detect parts 

with high temperatures, leaks and other areas of 
concern to guide the maintenance team towards 

performing timely procedures to promote safety. 

Data from such evaluations assists engineers in 
assessing engine performance and efficiency. 

Thermal cameras have also been widely applied in 

thermal analysis and mapping of the aerospace and 
automotive industries [48]. These cameras can 

visualise temperature variations, allowing for the 

generation of thermal maps of various systems and 

components, including the propulsion, electrical 
and braking systems. Thermal maps allow engineers 

to study heat distribution to various systems and 

components, thereby identifying areas of concern 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

77 

and those with a high risk of overheating. Such 

collected data serves as the starting point for the 

optimisation of component designs, heat dissipation 
and thermal insulation and thermal veracity. The 

thermal cameras help identify and assess 

automotive and aerospace malfunctions. The 

thermal imaging technology aids the cameras in 
identifying temperature irregularities, which could 

indicate additional problems. The industry players 

also use the TIC to detect problems such as 
defective wiring, malfunctioning sensors and 

overheating of electrical connections. Using their 

non-invasive capability, thermal cameras rapidly 

identify faults, thereby diminishing operational 
interruptions and augmenting maintenance 

procedures. Thermal cameras equally help ascertain 

thermal and human comfort in the automotive and 
aerospace design domains. They also use thermal 

imaging technology to assess temperature 

distributions and thermal and human comfort levels 
within vehicle or aircraft cabins. Such information 

is vital in optimising air conditioning, ventilation 

and heating systems to ensure comfortability and 

safety of humans in those cabins, increasing their 
satisfaction. Human factors are also examined using 

thermal cameras in the cockpit design and seating 

areas to optimise ergonomic designs of the 
aerospace and automotive interiors and enhance 

comfort.   

 

3. Thermographic Cameras Effectiveness 
 

Thermographic cameras, which have been 
applied across numerous domains, have been 

proven effective. As shown in Figure 2, various 

factors that contribute to the effectiveness of 

thermographic cameras are explored in this section, 
and their benefits over conventional inspection 

approaches are clarified. 

 

 
 

Fig.2. Thermographic camera factors 

 

A major benefit of thermography cameras lies in 

their non-destructive and non-contact assessment 

capability. They can record various thermal patterns 

and temperature fluctuations without having direct 

contact with the item being examined. In contrast, 

conventional inspection techniques require close 

contact with the item or material under 

investigation. Notably, thermography cameras are 

useful in understanding the faultiness of sensitive 

and fragile constructions or materials because their 

non-destructive nature guarantees that the item 

would remain undamaged. These cameras have 

made it possible to conduct real-time and rapid 

inspections to identify abnormalities in items or 

materials [49]. In the contemporary market, the 

latest thermography cameras are faster at collecting 

data and offer high-resolution thermal image 

capabilities due to advancements in technology. 

With these capabilities, operators and other 

inspectors can quickly identify problems in 

materials, accelerating the pace of inspections and 

facilitating prompt resolution of issues. Some 

industrial processes and operations, especially in 

dynamic contexts, require real-time monitoring to 

detect anomalies. In these cases, thermography 

cameras are invaluable because they provide 

continuous, real-time monitoring. These cameras 

have found widespread use across different 

domains, including environmental monitoring, 

electrical inspections, medicinal applications, 

building inspections and mechanical system 

diagnostics. They are useful in these fields due to 

their capacity to help individuals detect varying 

thermal patterns and temperature changes, raising 

the curiosity of wanting to investigate systems and 

materials further for abnormalities, inefficiencies or 

defects. Resolution and sensitivity have been 

enhanced in the current thermography cameras, 

guaranteeing thorough and precise system and 

material evaluations. Owing to their increased 

sensitivity, the cameras can record thermal 

variations per minute, improving their capability to 

aid in the identification of small abnormalities. 

Based on their superior resolution, thermography 

cameras capture detailed and accurate thermal 

images of thermal patterns and temperature 

distribution in systems and materials. The resolution 

and sensitivity of the thermograph cameras 

determine their capability to assess problems in 

various applications. These cameras have become 

increasingly popular in fault detection because they 

support quantitative and qualitative analyses [50]. 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

78 

Individuals have found the cameras excellent in 

using refined image processing software and 

algorithms to transform thermal images into useful 

data (thermal gradients or readings). Through 

quantitative analysis, thermal cameras can 

accurately and impartially detect thermal variations, 

enabling more informed decision-making. Their 

capability to read and analyse data in real time 

allows them to efficiently identify problems and 

guide individuals in pinpointing their root cause.    

 
4. Defect Detection Techniques 
 

Many industrial players conduct thorough 

investigations to identify defects in their systems 

and materials using various approaches, including 
but not limited to image processing algorithms and 

temperature analysis. The advancement of 

thermography camera technology, its superior 
resolution and its capability to integrate imaging 

modalities have been key topics of discussion. 

Through its non-destructive techniques, thermal 

cameras offer considerable advantages in 
identifying defects in various constructions and 

materials. The following section highlights and 

elaborates on the common thermography defect 
detection techniques.    

 

 

4.1 Active Thermography 
 

Active thermography is known to apply external 

energy sources, such as heat, to trigger a thermal 
reaction in materials under investigation. This 

approach is widely used because it helps discover 

underlying faults that the human eye may overlook. 
Lock-in and pulsed thermography are two 

commonly applied active thermography methods 

[51]. In pulsed thermography, a material’s surface 

is exposed to a heat pulse, and the thermograph 
camera records the reaction. Thermal responses 

occur due to changes in the heat transmission 

mechanism caused by abnormalities. Normally, 
inclusions, delamination and voids can be identified 

from thermal images taken before and after the heat 

pulse. In lock-in thermography, the modulation 
frequency is synchronised with the thermography 

camera’s capture rate whilst applying a controlled 

light or heat source to the targeted substrate. This 

approach enhances flaw detection by isolating the 
thermal response of the faults from the background 

noise. The approach is vital for identifying 

underlying faults in metallic structures, such as 
concealed corrosion or fractures. 

4.2 Passive Thermography 

 

Passive, ambient or natural thermography relies 
on thermal variations in materials to identify faults 

without an external energy source. The technique 

applies the surface temperature variations to 

determine material faults. This approach is often 
used in electrical inspections, quality control and 

building inspections [52]. The method applies 

thermal contrast analysis in examining surface 
thermal variations to identify faults in materials. 

The different faults, such as cavities, hotspots or 

fractures, which are linked to distinct temperature 

changes and can be identified from thermal images, 
help analyse materials and draw conclusions. 

Thermal contrast analysis is commonly used in 

electrical connection inspections to identify 
overheating components and in building inspections 

to detect moisture incursion. Infrared imaging is a 

widely used passive thermography technique that 
captures images of temperature variations in 

materials. This technique relies on detecting 

temperature fluctuations to identify faults such as 

thermal bridging, air leaks and insulating gaps. This 
method is particularly effective for moisture 

detection, building energy audits and insulation 

assessments due to its superior spatial resolution.    
 

 

4.3 Combined Techniques 

 

In some cases, passive and active thermography 

techniques can be combined to ensure thorough 

fault detection. When combined, the two 
approaches aid in detecting a greater variety of 

flaws, thereby increasing the precision of defect  

characterisation. Transient thermography merges 
the benefits of passive and active thermography 

techniques by introducing a heat pulse and 

recording the consequent thermal reaction of 

materials.  
The combined method is commonly used in 

inspecting composite materials, evaluating 

aerospace components and inspecting concrete 
structures to identify subsurface and surface faults. 

Vibrothermography is employed to capture thermal 

images whilst inducing vibrations in materials. 
Flaws in materials often affect their thermal 

reactivity, resulting in varying thermal patterns. For 

composite materials, coatings and adhesives, 

vibrothermography can easily detect 
bonding/debonding/delamination. Table 1 displays 

a comparison of the thermography techniques. 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

79 

Table 1 

Main features of thermographic camera techniques 

 

 

5. Discussion 
 

Thermographic cameras have numerous benefits 

compared to traditional inspection methods across 

different industrial domains. This section discusses 

the key findings and implications of using 
thermographic cameras for defect detection, as well 

as potential challenges and areas for future research. 

Thermographic cameras possess various advantages 
that substantially enhance their effectiveness in 

detecting defects. Thermographic cameras facilitate 

non-invasive and contactless examinations, thereby 

safeguarding the structural soundness of the 
scrutinised entity whilst offering remarkable 

revelations regarding its state. This advantage is of 

considerable importance, especially when dealing 
with delicate or sensitive materials and structures. 

Thermographic cameras offer efficient and 

instantaneous defect detection capabilities in real 
time. The rapid capture of temperature variations 

and thermal patterns using this technology 

facilitates the prompt detection and evaluation of 

defects, resulting in reduced inspection durations 

and facilitating the timely implementation of 

corrective measures. Figure 3 depicts the thermal 
image obtained by an FLIR T335 camera at the 

workshop of the Ministry of Higher Education, 

University of Baghdad, automated manufacturing 
department of a 3D printer’s heater whilst the 3D 

printer is running. Notably, the temperature range of 

the obtained region is between 26.8 °C and 109 °C. 

Another example of the capability of a thermal 
image to monitor high temperatures, as shown in 

Figure 4, is obtained using an FLIR T335 camera at 

a workshop of the Ministry of Higher 
Education/University of Baghdad/automated 

manufacturing department, which was used whilst 

the furnace was running and the temperature of the 

obtained region ranged between 35.6 °C and 263 
°C. 

 

Thermography 

techniques 

Method Key features Applications 

Active Thermography Uses an external energy 

source (heat or light) to 
induce a thermal reaction 

in the material. 

Pulsed Thermography: 

Brief heat pulse to 
surface, records thermal 

response for flaw 

detection. - Lock-in 

Thermography: 

Synchronises camera with 

modulated heat or light 

source for improved flaw 

detection. 

Finding underlying flaws 

such as delamination, voids 
or inclusions. 

Passive Thermography Relies on detecting 

natural or ambient 

temperature fluctuations 
in the material without an 

external energy source. 

Thermal Contrast 

Analysis: Examines 

surface temperature 
changes to identify 

thermal differences 

caused by defects. - 

Infrared Imaging: 

Measures material surface 

temperature variations for 

abnormality detection. 

Quality control, building 

inspections, electrical 

inspections, moisture 
detection, insulation 

evaluations and energy 

audits. 

Combined Techniques Integrates active and 

passive thermography 

methods to enhance flaw 

identification capabilities. 

-Transient Thermography: 

Uses brief heat pulse and 

records subsequent 

thermal reaction over time 

for comprehensive 
analysis.  

- Vibrothermography: 

Utilises thermal imaging 

with induced vibrations to 

detect flaws. 

Inspection of composite 

materials, testing of 

aerospace components, 

assessing concrete structures 

and specific fault 
identification in structures or 

materials. 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

80 

 
 

 
 

Fig. 3. Capturing thermal image of 3D printer heater 

 

 
 

 
 

Fig. 4. Capturing thermal image of furnace 

 

 

Online weld quality monitoring is realised using 

thermal image analyses to automatically identify 

defects. The temperature variance was computed for 

each row and column. Figure 5 displays the variance 
plot. The temperature variance was computed for 

each individual pixel in the row and column. The 

resulting values are presented in the provided figure. 
These statistical graphs facilitated the identification 

and localisation of anomalies.  

 

 
 

Fig. 5. Variation in a thermogram frame [53] 

 
 

Figure 6 illustrates the contrast between a 

thermograph picture of a healthy induction motor 
and a thermograph image of a damaged induction 

motor. These differences allow for the application 

of an analysis. The video underwent analysis using 
the commercial programme FLIR ResearchIR 

MAX to extract the temperatures within the 

specified zones. Considering the high volume of 

data in the video (30 frames per second), an analysis 
was conducted on a per-minute basis, assuming that 

the temperature remains constant without abrupt 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

81 

changes. Two different supply frequencies, 40 and 

60 Hz, were used to examine their behaviour. These 

frequencies were programmed or set up in the 
frequency inverter. The zones were examined, and 

the graphs were generated, as shown in Figure 6. 

 

 
 

Fig. 6. Thermograph image of the induction motor: (a) 

No defect; (b) Damaged [54] 

 
 

Steel fracture detection often relies on vision-

based methods. Identifying any surface 
imperfections becomes possible when analysing the 

images captured by the camera. Photographic 

images are inherently limited in their capability to 
appropriately reveal the interior aspects of things. 

As presented in Figure 7, fractures in steel sheets 

can be identified by integrating CNNs with infrared 

thermal imaging. 

 
 
Fig. 7. Convolutional neural networks with infrared 

thermal imaging [55] 

Thermographic cameras have demonstrated their 

versatility as multifaceted instruments, exhibiting 

utility across diverse industries, including 
manufacturing, construction, electrical systems and 

aerospace. The adaptability of thermographic 

cameras to various materials, structures and types of 

defects is emphasised by their versatility. The 
progress in thermographic camera technology has 

resulted in enhanced sensitivity and resolution, 

facilitating the identification of minimal 
temperature fluctuations and the augmentation of 

the precision and intricacy of thermal images. Such 

an improvement is crucial because it will elevate 

fault detection and characterisation in systems and 
materials. Thermographic cameras are beneficial in 

detecting and characterising system or material 

faults. However, recognising and addressing the 
limitations of these cameras is crucial. The 

emissivity and reflective properties of materials 

under investigation impact the effectiveness of the 
thermographic camera to a large extent. Surfaces 

with low emissivity and high reflectivity are likely 

to alter thermal patterns, diminishing the capability 

of the camera to assist in fault detection. Remedial 
actions (using emissivity correction methods or 

anti-reflective coatings) are required under such 

circumstances. Thermal image interpretation 
requires appropriate analysis techniques and 

expertise. During thermal image interpretation, the 

camera settings, environmental conditions and 
material properties must be considered to attain 

precise and accurate fault detections and 

characterisations. Substantial data could be 

extracted from the thermal images by applying 
sophisticated software and algorithms. The 

standardisation and calibration of thermographic 

cameras are crucial in ensuring that defect detection 
achieves high precision and is satisfactorily 

dependable. Regular camera calibration and strict 

compliance with standardised protocols are 

necessary to achieve high result compatibility and 
consistency. The development and implementation 

of industrial-wide measures and standards to guide 

defect detection and thermographic camera 
calibration are critical in ensuring reliable and 

consistent inspection results. Future research should 

focus on prioritising camera resolution in various 
aspects. Advancements in image processing 

methods are expected to augment the fault detection 

capabilities of thermographic cameras. Similarly, 

the advancement of algorithms to facilitate 
automatic flaw detection, quantitative image 

analysis and image fusion is expected to optimise 

the accuracy and precision of flaw detection. 
Integrating thermographic cameras into X-rays or 

visual inspections is expected to provide 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

82 

complementary and comprehensive flaw detection 

capabilities. Further investigations into different 

inspection methods could help improve the 
reliability and precision of fault identification. 

Various materials exhibit varying response 

characteristics due to distinct thermal properties. 

Further research in the development and 
advancement of flaw detection through 

thermographic cameras is also expected to improve 

methodologies aimed at addressing specific 
material needs, thereby improving their efficiency. 

Inspection process optimisation can be released by 

understanding the thermal properties of materials 

and tailoring them to an appropriate flaw detection 
technique. Performance evaluations in real-world 

situations are critical in assessing the effectiveness 

of the flaw detection methodology when 
thermographic cameras are adopted. In this regard, 

a comprehensive field testing and validation 

experiment should be implemented. The experiment 
should consider the different types of flaws; 

cameras should be tested using various materials 

and in different environmental conditions. This 

experiment is expected to elucidate the suitability 
and barriers to thermographic camera use in 

studying real-world defect situations. Thermal data 

interpretation and the potential avenues for ensuring 
automated abnormality detection have been 

reviewed. The literature review has contributed to 

the field of thermographic camera technology and 
its techniques, emphasising the need for additional 

research aimed at improving the availability and 

effectiveness of the NDT approach. The thermal 

camera applications highlighted in this review 
revealed the application of thermal imaging 

technology for detecting flaws in systems and 

materials in different industrial domains, as shown 
in Table 2. Thermal cameras are crucial in proactive 

maintenance, achieving enhanced product quality 

and improving safety across diverse sectors by 

effectively detecting thermal irregularities and 
identifying concealed flaws. 

 
Table 2 

Summary of the applications of thermal cameras in 
defect detection 

Application Description 

Electrical Systems Detects loose connections, 

overloaded circuits and 

overheating components in 

electrical systems 

Mechanical 

Components 

Identifies defects such as 

bearing faults, misalignments 

and inadequate lubrication in 

machinery 

Structural Materials Detects heat leaks, moisture 

intrusion and insulation 

deficiencies in buildings and 

structures 
Manufacturing and 

Quality Control 

Identifies defects such as 

cracks, delamination and 

voids in products during 

manufacturing processes 

Non-Destructive 

Testing (NDT) 

Detects defects such as 

cracks, voids or inclusions in 

materials without damaging 

the inspected object 

Pipeline Inspection Identifies leaks, blockages 

and temperature anomalies in 

pipelines, ensuring their 

integrity 
Fire Protection Detects heat sources and 

anomalies for early fire 

detection and prevention 

Automotive and 

Aerospace 

Industries 

Detects faults in critical 

components, optimising 

performance and improving 

safety 

 
 

Table 2 summarises various thermal camera 

applications in the fault detection domain. Specific 

domains where this technology has been applied, 
along with the types of faults it has been used to 

detect, have been highlighted. Various industries 

have demonstrated the efficacy of thermal cameras 
in detecting flaws. These cameras have been utilised 

in detecting and displaying thermal energy 

emissions from materials, which helps in 
identifying various flaws. Various findings 

regarding the use of thermal cameras in flaw 

detection have been documented. They provide 

supplementary capabilities for evaluating 
temperature variations to detect defects such as 

excessive heat, insulation inefficiencies, structural 

defects and leakages. Individuals can use thermal 
cameras to identify flaws and direct their actions to 

reduce them, thereby enhancing the overall 

reliability and accuracy of systems. Through 
contactless and non-invasive approaches, thermal 

cameras can detect flaws without damaging systems 

or materials. As such, they help avoid direct 

physical contact with the materials under 
inspection, preventing interference with ongoing 

activities that could jeopardise performance and 

accuracy. Moreover, the NDT capabilities 
embedded in thermal cameras allow for the 

evaluation of crucial structural components whilst 

conserving their integrity. With thermal cameras, 

individuals and entities can detect flaws earlier, 
facilitating proactive approaches towards timely 

and continuous maintenance. Such proactive 

approaches help minimise costly downtime and 
breakdowns. Prompt fault detection is essential 

because entities have the opportunity to implement 



   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

83 

focused repairs, thereby enhancing financial 

savings, minimising potential safety risks and 

addressing minimal productivity. Different 
industrial domains, including but not limited to 

pipeline inspection, electrical systems, mechanical 

components, manufacturing and structural 

materials, have witnessed thermal camera 
applications. The adaptability of the systems 

requires firms to identify faults across different 

environments to tailor specific assessments and 
action points towards addressing the faults for 

enhanced productivity. Thermal cameras support 

various technology integrations, such as 3D 

imaging, AI and image processing algorithms, 
augmenting the capabilities of defect detection. 

Such integrations ensure the cameras perform 

automated fault detection, improving the precision 
and accuracy of the results. The use of thermal 

cameras to detect faults is a critical starting point for 

improving the safety and reliability of materials and 
systems across different industrial domains. They 

play a vital role in accident prevention, preserving 

structural integrity and mitigating risks by 

identifying various hazards, such as structural 
weaknesses, electric faults and mechanical failures, 

which could worsen if left unattended. 

 

 

6. Conclusions 

 

Different industries have applied thermal 

cameras to detect material or system defects. 
Through the use of non-destructive properties, 

hidden fault discovery and improved detection 

accuracy and performance, industries have realised 
reduced maintenance costs, substantial financial 

savings, heightened safety and reliability. Future 

research into defect recognition algorithms and 
advancements in thermal camera technology is 

expected to further enhance the capabilities of 

thermographic cameras, expanding their application 

in fault detection. The advantages of using 
thermographic camera-based defect detection are 

evident across a wide range of applications. 

Mechanical systems have revolutionised flaw 
detection and maintenance across industries using 

thermal cameras. Thermal cameras can detect early 

anomalies, enable non-destructive testing and 

facilitate predictive maintenance, making them 
essential tools for improving the dependability, 

security and effectiveness of mechanical systems. 

The integration of technologies such as the IoT and 
Industry 4.0 can further improve defect detection 

and asset management. This integration will 

improve mechanical systems across industries. 

Thermal cameras in electrical systems have also 

revolutionised defect detection, preventive 

maintenance and risk reduction. They can identify 
flaws, assess structural soundness and improve 

energy conservation in structural materials. 

Additionally, these cameras reveal heat leaks, 

moisture intrusions, insulation issues and other 
irregularities. In manufacturing and quality control, 

they help identify defects, monitor processes and 

ensure quality. Thermal imaging technology 
reduces waste and promotes sustainable 

manufacturing due to its non-destructive nature. In 

NDT, thermal cameras help identify defects and 

corrosion and can execute structural evaluations and 
material analyses. They can also detect leaks, 

hotspots, corrosion, buried or insulated pipelines 

and examine coating integrity. Thermal cameras in 
fire detection systems improve fire detection, 

especially in low-smoke or low-visibility 

environments. In the automotive and aerospace 
industries, they are useful for engine and component 

testing, thermal mapping and analysis, fault 

detection and diagnosis, composite material 

inspection, thermal comfort and human factors. 
Pulsed and lock-in thermography can detect 

subsurface defects. However, passive thermography 

methods such as thermal contrast analysis and 
infrared imaging can identify surface defects, and 

transient and vibro-thermography can help detect a 

wide range of defects. The next steps should include 
advanced image processing, alternative inspection 

methods, material-specific approaches and 

extensive field testing and validation. Overall, 

focusing on these areas can improve the defect 
detection capabilities of thermographic cameras, 

making them useful across industries. 

 

 

References 
 

[1] Ali Sarhadi, Rodrigo Q. Albuquerque, Martin 

Demleitner, Holger Ruckdäschel, Martin A. 
Eder, Machine learning based thermal imaging 

damage detection in glass-epoxy composite 

materials, Composite Structures, Volume 295, 
2022, 115786, ISSN 0263-8223, 

https://doi.org/10.1016/j.compstruct.2022.1157

86. 

[2] Péter Kovács, Bernhard Lehner, Gregor 
Thummerer, Günther Mayr, Peter Burgholzer, 

Mario Huemer; Deep learning approaches for 

thermographic imaging. Journal of Applied 
Physics 21 October 2020; 128 (15): 155103. 

https://doi.org/10.1063/5.0020404. 

https://doi.org/10.1063/5.0020404


   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

84 

[3] Youngjun Cho, Nadia Bianchi-Berthouze, 

Nicolai Marquardt, and Simon J. Julier. 2018. 

Deep Thermal Imaging: Proximate Material 
Type Recognition in the Wild through Deep 

Learning of Spatial Surface Temperature 

Patterns. In Proceedings of the 2018 CHI 

Conference on Human Factors in Computing 
Systems (CHI '18). Association for Computing 

Machinery, New York, NY, USA, Paper 2, 1–

13. https://doi.org/10.1145/3173574.3173576. 
[4] C. N. Naga Priya, S. D. Ashok, Bhanshidar Maji, 

and K. S. Kumaran, “Deep Learning Based 

Thermal Image Processing Approach for 

Detection of Buried Objects and Mines”, Eng. J., 
vol. 25, no. 3, pp. 61-67, Mar. 2021. 

[5] O. Janssens, R. Van de Walle, M. Loccufier and 

S. Van Hoecke, "Deep Learning for Infrared 

Thermal Image Based Machine Health 

Monitoring," in IEEE/ASME Transactions on 

Mechatronics, vol. 23, no. 1, pp. 151-159, Feb. 

2018, doi: 10.1109/TMECH.2017.2722479. 

[6] M. Najafi, Y. Baleghi, S. A. Gholamian and S. 

Mehdi Mirimani, "Fault Diagnosis of Electrical 

Equipment through Thermal Imaging and 

Interpretable Machine Learning Applied on a 

Newly-introduced Dataset," 2020 6th Iranian 

Conference on Signal Processing and Intelligent 

Systems (ICSPIS), Mashhad, Iran, 2020, pp. 1-7, 

doi: 10.1109/ICSPIS51611.2020.9349599. 

[7] Chen, C.; Chandra, S.; Han, Y.; Seo, H. Deep 

Learning-Based Thermal Image Analysis for 

Pavement Defect Detection and Classification 

Considering Complex Pavement Conditions. 

Remote Sens. 2022, 14, 106. 

https://doi.org/10.3390/rs14010106. 

[8] Najah, A., Mustafa, F. F., & Hacham, W. S. 

(2021). Building a High Accuracy Transfer 

Learning-Based Quality Inspection System at 

Low Costs. Al-Khwarizmi Engineering 

Journal, 17(1), 1–12. 

https://doi.org/10.22153/kej.2021.12.001. 

[9] Tsai, P.-F.; Liao, C.-H.; Yuan, S.-M. Using Deep 

Learning with Thermal Imaging for Human 

Detection in Heavy Smoke Scenarios. Sensors 

2022, 22, 5351. 

https://doi.org/10.3390/s22145351. 

[10] Mary, Ali Hussien, Zubaidah Bilal Kadhim, 

and Zainab Saad Sharqi. "Face recognition and 

emotion recognition from facial expression 

using deep learning neural network." IOP 

Conference Series: Materials Science and 

Engineering. Vol. 928. No. 3. IOP Publishing, 

2020. 

[11] Chandra, S.; AlMansoor, K.; Chen, C.; Shi, Y.; 

Seo, H. Deep Learning Based Infrared Thermal 

Image Analysis of Complex Pavement Defect 

Conditions Considering Seasonal Effect. 

Sensors 2022, 22, 9365. 

https://doi.org/10.3390/s22239365.  

[12] Hardan, F., & R. J. Almusawi, A. . (2022). 

Developing an Automated Vision System for 

Maintaing Social Distancing to Cure the 

Pandemic. Al-Khwarizmi Engineering 

Journal, 18(1), 38–50. 

https://doi.org/10.22153/kej.2022.03.002. 

[13] Chiara Filippini, David Perpetuini, Daniela 

Cardone, Antonio Maria Chiarelli and 

Arcangelo Merla, Thermal infrared imaging 

and artificial intelligence techniques can 

support mild Alzheimer disease diagnosis, 

CEUR Workshop Proceedings, Vol-2804, 

2020. 

[14] A. Guedidi, A. Guettaf, A. J. M. Cardoso, W. 

Laala and A. Arif, "Bearing Faults 

Classification Based on Variational Mode 

Decomposition and Artificial Neural 

Network," 2019 IEEE 12th International 

Symposium on Diagnostics for Electrical 

Machines, Power Electronics and Drives 

(SDEMPED), Toulouse, France, 2019, pp. 

391-397, doi: 

10.1109/DEMPED.2019.8864830. 

[15] Min Hao, "Characteristics of misalignment 

fault in rotor systems based on frequency 

analysis," 2011 International Conference on 

Computer Science and Service System (CSSS), 

Nanjing, China, 2011, pp. 3893-3895, doi: 

10.1109/CSSS.2011.5972166. 

[16] H. -C. Lee, Y. -C. Chang and Y. -S. Huang, "A 

Reliable Wireless Sensor System for 

Monitoring Mechanical Wear-Out of Parts," in 

IEEE Transactions on Instrumentation and 

Measurement, vol. 63, no. 10, pp. 2488-2497, 

Oct. 2014, doi: 10.1109/TIM.2014.2312498. 

[17] F. Imad, F. Nagi and S. K. Ahmed, 

"Investigating lubrication properties using 

pulse-echo ultrasound technique," 2012 IEEE 

International Conference on Control System, 

Computing and Engineering, Penang, 

Malaysia, 2012, pp. 166-170, doi: 

10.1109/ICCSCE.2012.6487135. 

[18] Achouch, M.; Dimitrova, M.; Ziane, K.; 

SattarpanahKarganroudi, S.; Dhouib, R.; 

Ibrahim, H.; Adda, M. On Predictive 

Maintenance in Industry 4.0: Overview, 

https://doi.org/10.22153/kej.2021.12.001
https://doi.org/10.22153/kej.2022.03.002


   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

85 

Models, and Challenges. Appl. Sci. 2022, 12, 

8081. https://doi.org/10.3390/app12168081. 

[19] Grujić, K. A Review of Thermal Spectral 

Imaging Methods for Monitoring High-

Temperature Molten Material Streams. 

Sensors 2023, 23, 1130. 

https://doi.org/10.3390/s23031130. 

[20] Georgios Tsaramirsis, Antreas Kantaros, Izzat 

Al-Darraji, Dimitrios Piromalis, Charalampos 

Apostolopoulos, Athanasia Pavlopoulou, 

Muath Alrammal, Zamhar Ismail, Seyed M. 

Buhari, Milos Stojmenovic, HatemTamimi, 

PrincyRandhawa, Akshet Patel, FazalQudus 

Khan, "A Modern Approach towards an 

Industry 4.0 Model: From Driving 

Technologies to Management", Journal of 

Sensors, vol. 2022, Article ID 5023011, 18 

pages, 2022. 

https://doi.org/10.1155/2022/5023011. 

[21] X. Zhou and T. Schoepf, "Characteristics of 

Overheated Electrical Joints Due to Loose 

Connection," 2011 IEEE 57th Holm 

Conference on Electrical Contacts (Holm), 

Minneapolis, MN, USA, 2011, pp. 1-7, doi: 

10.1109/HOLM.2011.6034795. 

[22] B. Wei, A. Marzàbal, J. Perez, R. Pinyol, J. M. 

Guerrero and J. C. Vásquez, "Overload and 

Short-Circuit Protection Strategy for Voltage 

Source Inverter-Based UPS," in IEEE 

Transactions on Power Electronics, vol. 34, 

no. 11, pp. 11371-11382, Nov. 2019, doi: 

10.1109/TPEL.2019.2898165. 

[23] M. A. Rahman and I. Pranoto, "Review on 

Current Thermal Issue and Cooling 

Technology Development on Electric Vehicles 

Battery," 2020 6th International Conference on 

Science and Technology (ICST), Yogyakarta, 

Indonesia, 2020, pp. 1-6, doi: 

10.1109/ICST50505.2020.9732879. 

[24] Hongzhao Li, "Thermal Fault Detection and 

Diagnosis of Electrical Equipment Based on 

the Infrared Image Segmentation Algorithm", 

Advances in Multimedia, vol. 2021, Article ID 

9295771, 7 pages, 2021. 

https://doi.org/10.1155/2021/9295771. 

[25] Sheng Han, Fan Yang, Gang Yang, Bing Gao, 

Na Zhang, Dawei Wang, Electrical equipment 

identification in infrared images based on ROI-

selected CNN method, Electric Power Systems 

Research, Volume 188, 2020, 106534, ISSN 

0378-7796, 

https://doi.org/10.1016/j.epsr.2020.106534. 

[26] Cubukcu, A. Akanalci, Real-time inspection 

and determination methods of faults on 

photovoltaic power systems by thermal 

imaging in Turkey, Renewable Energy, 

Volume 147, Part 1, 2020, Pages 1231-1238, 

ISSN 0960-1481, 

https://doi.org/10.1016/j.renene.2019.09.075. 

[27] Toughness and failure of volcanic edifices, 

Tectonophysics, Volume 471, Issues 1–2, 

2009, Pages 27-35, ISSN 0040-1951, 

https://doi.org/10.1016/j.tecto.2009.03.001. 

[28] Zheda Zhu, Spencer E. Quiel, 

NegarElhamiKhorasani, Bivariate structural-

fire fragility curves for simple-span overpass 

bridges with composite steel plate girders, 

Structural Safety, Volume 100, 2023, 102294, 

ISSN 0167-4730, 

https://doi.org/10.1016/j.strusafe.2022.102294. 

[29] ixin Yan, Ruotong Yao, Jingyuan Zhao, Kaili 

Chen, LirongDuan, Tian Wang, Shujun Zhang, 

Jinping Guan, ZhaozhuZheng, Xiaoqin Wang, 

Zekun Liu, Yi Li, Gang Li, Implantable nerve 

guidance conduits: Material combinations, 

multi-functional strategies and advanced 

engineering innovations, Bioactive Materials, 

Volume 11, 2022, Pages 57-76, ISSN 2452-

199X, 

https://doi.org/10.1016/j.bioactmat.2021.09.030. 

[30] Ham, Y., Golparvar-Fard, M. 3D Visualization 

of thermal resistance and condensation 

problems using infrared thermography for 

building energy diagnostics. Vis. in Eng. 2, 12 

(2014). https://doi.org/10.1186/s40327-014-

0012-0 

[31] Shima Taheri, A review on five key sensors for 

monitoring of concrete structures, 

Construction and Building Materials, Volume 

204, 2019, Pages 492-509, ISSN 0950-0618, 

https://doi.org/10.1016/j.conbuildmat.2019.01.172. 

[32] Al-Sahib, Nabeel K. Abid, Hussam K. Abdul 

Ameer, and SaifGhazy Faisal Ibrahim. 

"Monitoring and quality control of stud 

welding." Al-Khwarizmi Engineering 

Journal 5.1 (2009): 53-70. 

[33] Tao, Y.H.; Fitzgerald, A.J.; Wallace, V.P. 

Non-Contact, Non-Destructive Testing in 

Various Industrial Sectors with Terahertz 

Technology. Sensors 2020, 20, 712. 

https://doi.org/10.3390/s20030712. 

[34] A.A. Gowen, B.K. Tiwari, P.J. Cullen, K. 

McDonnell, C.P. O'Donnell, Applications of 

thermal imaging in food quality and safety 

https://doi.org/10.3390/app12168081
https://doi.org/10.3390/s23031130
https://doi.org/10.1155/2022/5023011
https://doi.org/10.1155/2021/9295771
https://doi.org/10.1016/j.epsr.2020.106534
https://doi.org/10.1016/j.renene.2019.09.075
https://doi.org/10.1016/j.tecto.2009.03.001
https://doi.org/10.1016/j.strusafe.2022.102294
https://doi.org/10.1016/j.bioactmat.2021.09.030
https://doi.org/10.1186/s40327-014-0012-0
https://doi.org/10.1186/s40327-014-0012-0
https://doi.org/10.1016/j.conbuildmat.2019.01.172
https://doi.org/10.3390/s20030712


   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

86 

assessment, Trends in Food Science & 

Technology, Volume 21, Issue 4, 2010, Pages 

190-200, ISSN 0924-2244, 

https://doi.org/10.1016/j.tifs.2009.12.002. 

[35] Imani, F., Chen, R., Diewald, E., Reutzel, E., 

and Yang, H. (September 18, 2019). "Deep 

Learning of Variant Geometry in Layerwise 

Imaging Profiles for Additive Manufacturing 

Quality Control." ASME. J. Manuf. Sci. Eng. 

November 2019; 141(11): 111001. 

https://doi.org/10.1115/1.4044420. 

[36] Shuxian Nian, Tina Pham, Carl Haas, Nadine 

Ibrahim, Daeun Yoon, Hana Bregman, A 

functional demonstration of adaptive reuse of 

waste into modular assemblies for structural 

applications: The case of bicycle frames, 

Journal of Cleaner Production, Volume 348, 

2022, 131162, ISSN 0959-6526, 

https://doi.org/10.1016/j.jclepro.2022.131162. 

[37] Peter Trampus, VjeraKrstelj, Giuseppe 

Nardoni, NDT integrity engineering – A new 

discipline, Procedia Structural Integrity, 

Volume 17, 2019, Pages 262-267, ISSN 2452-

3216, https://doi.org/10.1016/j.prostr.2019.08.035. 

[38] Lixin Wu, Chengyu Cui, NaiguangGeng, 

Jinzhuang Wang, Remote sensing rock 

mechanics (RSRM) and associated 

experimental studies, International Journal of 

Rock Mechanics and Mining Sciences, 

Volume 37, Issue 6, 2000, Pages 879-888, 

ISSN 1365-1609, https://doi.org/10.1016/S1365-

1609(99)00066-0. 

[39] Gamal ElMasry, Ramadan ElGamal, Nasser 

Mandour, Pere Gou, Salim Al-Rejaie, Etienne 

Belin, David Rousseau, Emerging thermal 

imaging techniques for seed quality evaluation: 

Principles and applications, Food Research 

International, Volume 131, 2020, 109025, 

ISSN 0963-9969, 

https://doi.org/10.1016/j.foodres.2020.109025. 

[40] MingjiangXie, Zhigang Tian, A review on 

pipeline integrity management utilizing in-line 

inspection data, Engineering Failure Analysis, 

Volume 92, 2018, Pages 222-239, ISSN 1350-

6307, 

https://doi.org/10.1016/j.engfailanal.2018.05.0

10. 

[41] Park, S., Lim, H., Tamang, B. et al. A 

Preliminary Study on Leakage Detection of 

Deteriorated Underground Sewer Pipes Using 

Aerial Thermal Imaging. Int J Civ Eng 18, 

1167–1178 (2020). 

https://doi.org/10.1007/s40999-020-00521-8 

[42] AngelikiKylili, Paris A. Fokaides, 

PetrosChristou, Soteris A. Kalogirou, Infrared 

thermography (IRT) applications for building 

diagnostics: A review, Applied Energy, 

Volume 134, 2014, Pages 531-549, ISSN 

0306-2619, 

https://doi.org/10.1016/j.apenergy.2014.08.00

5. 

[43] Adegboye, M.A.; Fung, W.-K.; Karnik, A. 

Recent Advances in Pipeline Monitoring and 

Oil Leakage Detection Technologies: 

Principles and Approaches. Sensors 2019, 19, 

2548. https://doi.org/10.3390/s19112548. 

[44] S. Timashev and A. Bushinskaya, Diagnostics 

and Reliability of Pipeline Systems, vol. 30. 

2016. 

[45] San-Miguel-Ayanz, J., Ravail, N. Active Fire 

Detection for Fire Emergency Management: 

Potential and Limitations for the Operational 

Use of Remote Sensing. Nat Hazards 35, 361–

376 (2005). https://doi.org/10.1007/s11069-

004-1797-2. 

[46] T.T. Aralt, A.R. Nilsen, Automatic fire 

detection in road traffic tunnels, Tunnelling 

and Underground Space Technology, Volume 

24, Issue 1, 2009, Pages 75-83, ISSN 0886-

7798, https://doi.org/10.1016/j.tust.2008.04.001. 

[47] Stephen Vidas, PeymanMoghadam, 

HeatWave: A handheld 3D thermography 

system for energy auditing, Energy and 

Buildings, Volume 66, 2013, Pages 445-460, 

ISSN 0378-7788, 

https://doi.org/10.1016/j.enbuild.2013.07.030. 

[48] Andoga, R.; Főző, L.; Schrötter, M.; Češkovič, 

M.; Szabo, S.; Bréda, R.; Schreiner, M. 

Intelligent Thermal Imaging-Based 

Diagnostics of Turbojet Engines. Appl. Sci. 

2019, 9, 2253. 

https://doi.org/10.3390/app9112253 

[49] Aline Kirsten Vidal de Oliveira, 

MohammadrezaAghaei, Ricardo Rüther, 

Aerial infrared thermography for low-cost and 

fast fault detection in utility-scale PV power 

plants, Solar Energy, Volume 211, 2020, Pages 

712-724, ISSN 0038-092X, 

https://doi.org/10.1016/j.solener.2020.09.066. 

[50] Abdulateef, O. F., & Salman, L. A. (2015). 

Thermal Field Analysis of Oblique Machining 

Process with Infrared Image for AA6063-

T6. Al-Khwarizmi Engineering Journal, 11(1), 

1–10.  

https://doi.org/10.1016/j.tifs.2009.12.002
https://doi.org/10.1115/1.4044420
https://doi.org/10.1016/j.jclepro.2022.131162
https://doi.org/10.1016/j.prostr.2019.08.035
https://doi.org/10.1016/S1365-1609(99)00066-0
https://doi.org/10.1016/S1365-1609(99)00066-0
https://doi.org/10.1016/j.foodres.2020.109025
https://doi.org/10.1016/j.engfailanal.2018.05.010
https://doi.org/10.1016/j.engfailanal.2018.05.010
https://doi.org/10.1007/s40999-020-00521-8
https://doi.org/10.1016/j.apenergy.2014.08.005
https://doi.org/10.1016/j.apenergy.2014.08.005
https://doi.org/10.3390/s19112548
https://doi.org/10.1007/s11069-004-1797-2
https://doi.org/10.1007/s11069-004-1797-2
https://doi.org/10.1016/j.tust.2008.04.001
https://doi.org/10.1016/j.enbuild.2013.07.030
https://doi.org/10.3390/app9112253


   Hussein N. AL-Jubori                                      Al-Khwarizmi Engineering Journal, Vol. 20, No.4, P.P. 70- 88 (2024) 

87 

[51] O. Breitenstein, W. Warta, and M. 

Langenkamp, Lock-In Thermography: Basics 

and Use for Evaluating Electronic Devices and 

Materials. 2011. 

[52] Raja, BNK, Miramini, S, Duffield, C, Sofi, M, 

Mendis, P, Zhang, L. The influence of ambient 

environmental conditions in detecting bridge 

concrete deck delamination using infrared 

thermography (IRT). Struct Control Health 

Monit. 2020; https://doi.org/10.1002/stc.2506. 

[53] U. Sreedhar, C.V. Krishnamurthy, Krishnan 

Balasubramaniam, V.D. Raghupathy, S. 

Ravisankar, Automatic defect identification 

using thermal image analysis for online weld 

quality monitoring, Journal of Materials 

Processing Technology, Volume 212, Issue 7, 

2012, Pages 1557-1566, ISSN 0924-0136, 

https://doi.org/10.1016/j.jmatprotec.2012.03.002. 

[54] C. Morales-Perez, J. Rangel-Magdaleno, H. 

Peregrina-Barreto, J. Ramirez-Cortes and E. 

Vazquez-Pacheco, "Bearing Fault Detection 

Technique by using Thermal Images: A case of 

Study," 2019 IEEE International 

Instrumentation and Measurement Technology 

Conference (I2MTC), Auckland, New 

Zealand, 2019, pp. 1-6, doi: 

10.1109/I2MTC.2019.8826953. 

[55] J. Yang, W. Wang, G. Lin, Q. Li, Y. Sun and 

Y. Sun, "Infrared Thermal Imaging-Based 

Crack Detection Using Deep Learning," 

in IEEE Access, vol. 7, pp. 182060-182077, 

2019, doi: 10.1109/ACCESS.2019.2958264. 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

https://doi.org/10.1002/stc.2506
https://doi.org/10.1016/j.jmatprotec.2012.03.002


 (2024) 70-88، صفحة 4، العدد20مجلة الخوارزمي الهندسية المجلد             حسين ناجح حميد                                                           

 

88 

 

 

 اكتشاف العيوب باستخدام تقنيات كاميرا التصوير الحراري: مراجعة األدبيات

 3جربي سامح  ،   2عزة عبدالرزاق عبدالكريم  ،*1حسين ناجح حميد
 2،1 قسم هندسة التصنيع المؤتمت، كلية الهندسة الخوارزمي، جامعة بغداد

 3 كلية الهندسة، جامعة الحائل، المملكة العربية السعودية
   hussein.Najeh2204@kecbu.uobaghdad.edu.iq*البريد االلكتروني:

 

 

 ةالخالص

المثال ال الحصر، بسبب التقدم في تكنولوجيا مستشعرات التصوير الحراري, تستخدم الكاميرات الحرارية في مختلف المجاالت، بما في ذلك على سبيل  

األدبيات الحالية الزراعة والطائرات بدون طيار واألدوية والتصنيع، ومن أجل تحقيق أهداف مختلفة تتعلق بالسالمة واألمن. في هذه الدراسة سيتم استكشاف 
لحماية من الحرائق، والتصنيع، والفضاء بعمق لتوضيح تطبيقات كاميرات التصوير الحراري في اكتشاف األخطاء في مجموعة واسعة من التطبيقات، مثل ا

لى فعالية كاميرات والسيارات، واالختبارات غير المدمرة، وصناعات المواد اإلنشائية. تتوسع المناقشة الحالية حول نتائج الدراسات السابقة، مع التركيز ع

بشرية. تم عرض طرائق مختلفة للكشف عن العيوب، بما في ذلك تحليل التصوير الحراري في التمييز بين العيوب غير القابلة لالكتشاف من خالل الرؤية ال

عند مقارنتها درجة الحرارة وخوارزميات معالجة الصور، بدقة. ثم تمت دراسة العوامل التي تسهم في فعالية كاميرات التصوير الحراري وتوضيح مميزاتها 

 .ير الذي أحدثته تقنية الكاميرا الحرارية في اكتشاف أخطاء النظام الميكانيكي لتحسين الصيانةبطرائق الفحص التقليدية. أشارت هذه الدراسة إلى التحول الكب

ال غنى عنها لضمان  نظًرا ألن هذه الكاميرات يمكنها تحديد المخالفات غير المرئية والسماح باالختبارات والصيانة العملية للنظام، فقد تطورت لتصبح أدوات

بكفاية وموثوقية وبقائها آمنة. واشارت الدراسة ايضا انه يمكن تحسين التكنولوجيا الكاميرات الحرارية بشكل أكبر من خالل الجمع  عمل األنظمة الميكانيكية

ائية، مكنت وإنترنت األشياء، مما يضمن أداًء مرتفعًا للنظام الميكانيكي عبر المجاالت المختلفة. عند استخدامها في األنظمة الكهرب 4.0بين تقنيات الصناعة 

ة الهيكلية، يمكن الكاميرات الحرارية األفراد من تحديد األخطاء للتخطيط للصيانة المبكرة التي ترمي إلى تخفيف المخاطر. بفضل قدرتها على تقييم السالم

  .للكاميرات الحرارية تحديد أوجه القصور في الحرارة والعزل، مما يؤدي إلى تحسين كفاية استخدام الطاقة

 

mailto:hussein.Najeh2204@kecbu.uobaghdad.edu.iq

	https://doi.org/10.22153/kej.2024.03.002