Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 21 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET LEVERAGING MACHINE LEARNING TO OPTIMIZE PRODUCTION PROCESSES AND CAPACITY IN THE BREWERY INDUSTRY. 1Eze Ukamaka J Ndubuisis, 2Paul-Darlington Ibemezie, 3Daniel Ikechukwu Egu and 4Okolotu G.I. 1,2,3Madonna University, Nigeria 4Department of Agricultural Engineering, Faculty of Engineering, Delta State University of Science and Technology, P.M.B. 05, Ozoro, Nigeria. DOI: https://doi.org/10.5281/zenodo.15024347 Abstract: The decrease in the production capacity that had crippled business activities that mostly depend on soft drinks to run their daily activities was overcame by introducing leveraging machine learning to optimize production processes and capacity in the brewery industry, to perfectly achieve this, it was done in this approach, characterizing and establishing the causes of poor production capacity in a brewery industry, designing a conventional SIMULINK model for production processes in the brewery industry, designing leverage machine learning rule base that will reduce the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity, training ANN in the designed machine learning rule base for effective reduction of the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity, designing a SIMULINK model for leverage machine learning, developing an algorithm that will implement the process, designing a SIMULINK model for leveraging machine learning to optimize production processes and capacity in the brewery industry and validating and justifying the percentage improvement in the production capacity of a brewery industry with and without leveraging machine learning. The results obtained were, that the conventional inefficient Process Control and Automation cause of poor production capacity in the brewery industry was 20%. On the other hand, when leveraging machine learning was introduced in the system, it drastically reduced inefficient Process Control and Automation caused poor production capacity in the brewery industry to 17.34% thereby enhancing the production capacity, the conventional Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry was10%. Meanwhile, when leveraging machine learning was incorporated into the system, it decisively reduced Lengthy Fermentation and Maturation Times caused by poor production capacity in the brewery industry to 8.7% and the conventional production capacity in the brewery industry was 50000 bottles of drink. On the other hand, when leveraging machine learning was inculcated in the system, it simultaneously enhanced the production capacity in the brewery industry to 6500 bottles of drink. Finally, with these results obtained, it showed that production capacity in the brewery industry was optimized by 33%. mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 22 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Keywords; learning, leveraging, machine, processes, production 1.1 Introduction The brewery industry is highly competitive, with manufacturers continually seeking ways to optimize production processes, minimize waste, and maximize production capacity. Traditional methods of process optimization in breweries rely heavily on manual observations, fixed schedules, and historical data that may not adapt swiftly to changing conditions (Rathore & Tiwari, 2020). In recent years, machine learning (ML) has emerged as a transformative technology in industrial manufacturing, offering advanced data-driven solutions that significantly improve process control and forecasting capabilities (Zhou et al., 2021). Machine learning algorithms can analyze large volumes of production data in real time, providing insights that enhance decision-making, streamline operations, and improve resource utilization (Wuest et al., 2019). The brewery industry, due to its complex manufacturing processes involving various stages such as fermentation, bottling, and packaging, is uniquely positioned to benefit from machine learning applications. These algorithms can optimize fermentation times, monitor quality control in real time, and adjust operations dynamically based on demand and resource availability (Oliveira & Cunha, 2019). Furthermore, machine learning supports predictive maintenance, reducing equipment downtime and minimizing disruptions in production cycles (Agrawal et al., 2020). Given the need for sustainable operations, machine learning also contributes to achieving energy efficiency, which aligns with industry goals to minimize environmental impact (Lydon et al., 2021). However, integrating machine learning into brewery production faces several challenges, including the need for significant data infrastructure, skilled personnel, and an understanding of the nuances in applying AI-based solutions to traditional processes (Singh & Kumar, 2021). Despite these challenges, the potential benefits have spurred research into developing tailored ML models that address the specific needs of the brewing industry. This study aims to explore how machine learning can be effectively leveraged to optimize production processes and increase capacity within breweries, ultimately contributing to a more sustainable, efficient, and competitive brewing industry. 2.0 Methodology To characterize and establish the causes of poor production capacity in the brewery industry. Here's an example of how poor production capacity in the brewery industry can be characterized by causes, with percentages and their corresponding impact in terms of bottles of drinks produced per day: Table characterized and established causes of poor production capacity in a brewery industry mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 23 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Cause of Poor Production Capacity Impact (%) Impact (Number of Bottles per Day) Inefficient Process Control and Automation 20% 10,000 fewer bottles Equipment Downtime and Maintenance Issues 25% 12,500 fewer bottles Variability in Raw Material Quality 10% 5,000 fewer bottles Suboptimal Scheduling and Resource Allocation 15% 7,500 fewer bottles Lengthy Fermentation and Maturation Times 10% 5,000 fewer bottles Limited Data Utilization and Real-Time Analytics 8% 4,000 fewer bottles Energy Constraints and Environmental Regulations 7% 3,500 fewer bottles Labor Shortages and Skill Gaps 5% 2,500 fewer bottles Total Production Impact 100% 50,000 fewer bottles i) The table indicates the estimated contribution of each cause to the reduction in production capacity, expressed as a percentage and in terms of the reduction in bottles of drinks produced per day. ii) These values are estimates and may vary based on the specific brewery’s production environment and operational parameters. To design a conventional SIMULINK model for production processes in the brewery industry mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 24 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Figure 1.0 Designed conventional SIMULINK model for production processes in the brewery industry The results obtained were shown in figures 9.0 to 11.0 STTATION 1 TRANSFER AND LOADING STATION 2 FILLING STATION 3 CAPPING Variability in Raw Material Quality In1 Out1 UNFILLED BOTTLES In 1 O u t 1 Total Production Impact In1Out1 In1 Out1 Out2 Subsystem2 In1 Out1 In 1 O u t 1 In1 Out1 Subsystem Suboptimal Scheduling and Resource Allocation In1 Out1 Scope 6 Scope 5 NO OF FILLED BOTLES 5e+004 NO OF CRATES In 1 O u t 1 Limited Data Utilization and Real -Time Analytics In1 Out1 Lengthy Fermentation and Maturation Times In1 Out1 Labor Shortages and Skill Gaps In1 Out1 Inefficient Process Control and Automation In1 Out1 FILL ING SYSTEM In 1 O u t 1 Equipment Downtime and Maintenance Issues In1 Out1 Energy Constraints and Environmental Regulations In1 Out1 EMPTY BOTTLES In 1 O u t 1 Display 9 5e+004 Display 8 5 Display 7 7 Display 6 8 Display 5 10 Display 4 15 Display 3 10 Display 2 25 Display 1 4165 Display 20 CONVENTIONAL 1 CAPPING SYSTEMI In 1 O u t 1 CAPPING In1 Out1 Out2 mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 25 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET To design machine learning rule base that will reduce the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity Figure 2.0 Machine learning Fuzzy inference system Machine learning fuzzy inference system was designed as shown in figure 2.0 to reduce the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity This has three inputs of causes of poor production capacity, total production capacity and detecting sensor. It also has an output of result. mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 26 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Figure 3.0 Machine learning rule base Machine learning rule base was also designed to reduce the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity These rules were extensively elucidated in table 2 mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 27 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Table 2. 0: Machine learning rule base The comprehensive rules of designed machine learning rule base, that will reduce the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity is shown in table 2.0 1 IF CAUSES OF POOR PRODUCTION CAPACITY IS HIGH REDUCE AND TOTAL PRODUCTION CAPACITY IS LOW IMPROVE AND DETECTING SENSOR IS NOT EFFECTIVE RECTIFY THEN RESULT IS POOR PRODUCTION CAPACITY IN BREWERY INDUSTRY 2 IF CAUSES OF POOR PRODUCTION CAPACITY IS PARTIALLY HIGH REDUCE AND TOTAL PRODUCTION CAPACITY IS PARTIALLY LOW IMPROVE AND DETECTING SENSOR IS PARTIALLY NOT EFFECTIVE RECTIFY THEN RESULT IS POOR PRODUCTION CAPACITY IN BREWERY INDUSTRY 3 IF CAUSES OF POOR PRODUCTION CAPACITY IS HIGH REDUCE AND TOTAL PRODUCTION CAPACITY IS PARTIALLY LOW IMPROVE AND DETECTING SENSOR IS NOT EFFECTIVE RECTIFY THEN RESULT IS POOR PRODUCTION CAPACITY IN BREWERY INDUSTRY 4 IF CAUSES OF POOR PRODUCTION CAPACITY IS LOW RETAIN AND TOTAL PRODUCTION CAPACITY IS HIGH RETAIN AND DETECTING SENSOR IS EFFECTIVE RETAIN THEN RESULT IS HIGH PRODUCTION CAPACITY IN BREWERY INDUSTRY mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 28 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Figure 4.0: Operational application of the four rules To train ANN in the designed machine learning rule base for effective reduction of the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity, was shown in the operation of the four rules I figure 4.0 Out 1 1 Demux Demux Demux Demux Zero Firing Strength ? > 0 Total Firing Strength TOTALPRODUCTIONCAPACITY Input MF Switch Rule 4 Rule Rule 3 Rule Rule 2 Rule Rule 1 Rule RESULT Output MF MidRange -C- Demux Defuzzification 1 COA DETECTINGSENSOR Input MF CausesofPoorProductionCapacity Input MF AggMethod 1 max In1 1 mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 29 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Fig 5 trained ANN in the designed machine learning rule base for effective reduction of the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity ANN was trained twenty times in four rules 20 x4 = 80 eighty rules that looks identical like human brain. . Figure 6.0: Result obtained during the training 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 0.2 0.3 0.4 0.5 0.6 0.7 0.8 W(i,1) W (i ,2 ) LEVERAGING MACHINE LEARNING TO OPTIMIZE PRODUCTION PROCESSES AND CAPACITY IN THE BREWERY INDUSTRY y{1}x{1} Input 1 Neural Network x{1} y {1} Display 1.2 mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 30 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Figure 7.0: Designed SIMULINK model for leverage machine learning This will be integrated in figure 1.0 to obtain the results shown in figures 9.0 to11.0 To develop an algorithm that will implement the process, we have to go through the following process- 1. Characterize and establish the causes of poor production capacity in a brewery industry. 2. Identify inefficient Process Control and Automation 3. Identify Equipment Downtime and Maintenance Issues 4. Identify Variability in Raw Material Quality 5. Identify Suboptimal Scheduling and Resource Allocation 6. Identify Lengthy Fermentation and Maturation Times 7. Identify Limited Data Utilization and Real-Time Analytics 8. Identify Energy Constraints and Environmental Regulations 9. Identify Labor Shortages and Skill Gaps 10. Identify Total Production Impact 11. Design a conventional SIMULINK model for production processes in the brewery industry and integrate 2 through 10 12. Design leverage machine learning rule base that will reduce the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity. 13. Train ANN in the designed machine learning rule base for effective reduction of the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity 14. Design a SIMULINK model for leverage machine learning y{1}x{1} Input 1 powergui Continuous Video Viewer Video Viewer ImageImageImage A B C A B C Subsystem1 In1 In2 In3 Out1 Connection PortSubsystem In1 In2 Out1 Connection Port Raised Cosine Receive Filter Square root Neural Network x{1} y {1} Gaussian Noise Generator Gaussian Fuzzy Logic Controller From Multimedia File vipfly .avi V: 240 x320 , 15 fps Image Display 1 1.2 Display 1.33 0 Clock AWGN Channel AWGN In1 1 mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 31 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET 15. Integrate 12 through 14 16. Integrate 15 in 11 17. Do the causes of poor production capacity in a brewery industry reduce? 18. IF NO go to 16 19. IF YES go to 23 20. Does the production capacity in a brewery industry improve? 21. IF NO go to16 22. IF YES go to 23 23. Optimized production processes and capacity in the brewery industry. 24. Stop 25. End To design a SIMULINK model for leveraging machine learning to optimize production processes and capacity in the brewery industry. mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 32 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET STTATION 1 TRANSFER AND LOADING STATION 2 FILLING STATION 3 CAPPING y{1}1x{1}1 Input 1 powergui Continuous Video Viewer Video Viewer ImageImageImage Variability in Raw Material Quality In1 Out1 UNFILLED BOTTLES In 1 O u t1 Total Production Impact In1Out1 A B C A B C In1 Out1 Out2 Subsystem4 In1 In2 In3 Out1 Connection PortSubsystem3 In1 In2 Out1 Connection Port Subsystem2 In1 Out1 In 1 O u t1 In1 Out1 Subsystem Suboptimal Scheduling and Resource Allocation In1 Out1 Scope 6 Scope 5 Raised Cosine Receive Filter Square root Neural Network 1 x{1} y {1} NO OF FILLED BOTLES 5e+004 NO OF CRATES In 1 O u t1 Limited Data Utilization and Real -Time Analytics In1 Out1 Lengthy Fermentation and Maturation Times In1 Out1 Labor Shortages and Skill Gaps In1 Out1 Inefficient Process Control and Automation In1 Out1 Gaussian Noise Generator Gaussian Fuzzy Logic Controller 1 From Multimedia File vipfly .avi V: 240 x320 , 15 fps Image FILL ING SYSTEM In 1 O u t1 Equipment Downtime and Maintenance Issues In1 Out1 Energy Constraints and Environmental Regulations In1 Out1 EMPTY BOTTLES In 1 O u t1 Display 9 6.65e+004 Display 8 4.336 Display 7 6.07 Display 6 6.937 Display 5 8.671 Display 4 13 .01 Display 3 8.671 Display 2 21 .68 Display 12 1.2 Display 11 1.33 Display 1 4165 Display 17 .34 0 Clock CAPPING SYSTEMI In 1 O u t1 CAPPING In1 Out1 Out2 AWGN Channel AWGN In1 1 mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 33 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Fig 8 designed SIMULINK model for leveraging machine learning to optimize production processes and capacity in the brewery industry. The results obtained were as shown in figure 9.0 to 11.0 To validate and justify the percentage improvement in the production capacity of a brewery industry with and without leveraging machine learning To find percentage improvement in the reduction of inefficient Process Control and Automation cause of poor production capacity in brewery industry with leveraging machine learning Conventional inefficient Process Control and Automation =20% Leveraging machine learning inefficient Process Control and Automation =17.34% %improvement in the reduction of inefficient Process Control and Automation cause of poor production capacity in brewery industry with leveraging machine learning= Conventional inefficient Process Control and Automation - Leveraging machine learning inefficient Process Control and Automation %improvement in the reduction of inefficient Process Control and Automation cause of poor production capacity in brewery industry with leveraging machine learning= 20% - 17.34% %improvement in the reduction of inefficient Process Control and Automation cause of poor production capacity in brewery industry with leveraging machine learning=2.66% To find percentage improvement in the reduction of Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry with leveraging machine learning Conventional Lengthy Fermentation and Maturation Times =10% Leveraging machine learning Lengthy Fermentation and Maturation Times =8.7% %improvement in the reduction of Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry with leveraging machine learning= Conventional Lengthy Fermentation and Maturation Times - Leveraging machine learning Lengthy Fermentation and Maturation Times %improvement in the reduction of Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry with leveraging machine learning=10% - 8.7% %improvement in the reduction of Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry with leveraging machine learning=1.3% To find percentage improvement in the production capacity in brewery industry with leveraging machine learning Conventional production capacity =50,000bottles Leveraging machine learning production capacity =6, 6500bottles %improvement in the production capacity in brewery industry with leveraging machine learning= mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 34 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Leveraging machine learning production capacity - Conventional production capacity x 100% Conventional production capacity 1 %improvement in the production capacity in brewery industry with leveraging machine learning= 6, 6500bottles - 50,000bottles x100% 50,000bottles 1 %improvement in the production capacity in brewery industry with leveraging machine learning=33% 3.0 4.0 Results and Discussions Table 3 comparison of conventional and leveraging machine learning inefficient Process Control and Automation cause of poor production capacity in brewery industry Time (days) Conventional inefficient Process Control and Automation cause of poor production capacity in brewery industry (%) Leveraging machine learning inefficient Process Control and Automation cause of poor production capacity in brewery industry (%) 1 20 17.34 2 20 17.34 3 20 17.34 4 20 17.34 10 20 17.34 mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 35 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Figure 9.0: Comparison of conventional and leveraging machine learning inefficient Process Control and Automation cause of poor production capacity in brewery industry The conventional inefficient Process Control and Automation cause of poor production capacity in brewery industry was20%. On the other hand, when leveraging machine learning was introduced in the system, it drastically reduced inefficient Process Control and Automation cause of poor production capacity in brewery industry to17.34% thereby enhancing the production capacity. 1 2 3 4 5 6 7 8 9 10 17 17.5 18 18.5 19 19.5 20 in e f f ic ie n t P r o c e s s C o n t r o l a n d A u t o m a t io n c a u s e o f p o o r p r o d u c t io n c a p a c it y in b r e w e r y in d u s t r y ( % ) Time (days) Conventional inefficient Process Control and Automation cause of poor production capacity in brewery industry (%) Leveraging machine learning inefficient Process Control and Automation cause of poor production capacity in brewery industry (%) mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 36 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Table 4 comparison of conventional and leveraging machine learning Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry Time (days) Conventional Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry (%) Leveraging machine learning Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry (%) 1 10 8.7 2 10 8.7 3 10 8.7 4 10 8.7 10 10 8.7 Figure 10.0: comparison of conventional and leveraging machine learning Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry The conventional Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry was10%. Meanwhile, when leveraging machine learning was incorporated in the system, it decisively 1 2 3 4 5 6 7 8 9 10 8.5 9 9.5 10 L e n g th y F e rm e n ta ti o n a n d M a tu ra ti o n T im e s c a u s e o f p o o r p ro d u c ti o n c a p a c it y i n b re w e ry i n d u s tr y ( % ) Time (days) Conventional Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry (%) Leveraging machine learning inefficient Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry (%) mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 37 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET reduced Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry to 8.7%. Table 5 comparison of conventional and leveraging machine learning production capacity in brewery industry Time (days) Conventional production capacity in brewery industry (bottles) Leveraging machine learning production capacity in brewery industry (bottles) 1 50000 6 6500 2 50000 6 6,500 3 50000 6 6,500 4 50000 6 6,500 10 50000 6 6,500 Fig 11 comparison of conventional and leveraging machine learning production capacity in brewery industry The conventional production capacity in brewery industry was 50000bottles of drink. On the other hand, when leveraging machine learning was inculcated in the system, it simultaneously enhanced the production capacity in a brewery industry to6 6500 bottles of drink. Finally, with these results obtained, it showed that production capacity in a brewery industry was optimized by 33%. 1 2 3 4 5 6 7 8 9 10 5 5.2 5.4 5.6 5.8 6 6.2 6.4 6.6 6.8 x 10 4 p ro d u c ti o n c a p a c it y i n b re w e ry i n d u s tr y ( b o tt le s ) Time (days) Conventional production capacity in brewery industry (bottles) Leveraging machine learning production capacity in brewery industry (bottles) mailto:topacademicjournals@gmail.com Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 38 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET 4.0 Conclusion The consistent poor production capacity experienced in a brewery industry is anchored on these factors, inefficient Process Control and Automation, Equipment Downtime and Maintenance Issues, Variability in Raw Material Quality, Suboptimal Scheduling and Resource Allocation, Lengthy Fermentation and Maturation Times, Limited Data Utilization and Real-Time Analytics, Energy Constraints and Environmental Regulations, Labor Shortages and Skill Gaps coupled with Total Production Impact. This was overcame by introducing leveraging machine learning to optimize production processes and capacity in the brewery industry, to perfectly achieve this, it was done in the approach, characterizing and establishing the causes of poor production capacity in a brewery industry, designing a conventional SIMULINK model for production processes in the brewery industry, designing leverage machine learning rule base that will reduce the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity, training ANN in the designed machine learning rule base for effective reduction of the causes of poor production capacity in a brewery industry and simultaneously increase the production capacity, designing a SIMULINK model for leverage machine learning, developing an algorithm that will implement the process, designing a SIMULINK model for leveraging machine learning to optimize production processes and capacity in the brewery industry and validating and justifying the percentage improvement in the production capacity of a brewery industry with and without leveraging machine learning. The results obtained were, the conventional inefficient Process Control and Automation cause of poor production capacity in brewery industry was20%. On the other hand, when leveraging machine learning was introduced in the system, it drastically reduced inefficient Process Control and Automation cause of poor production capacity in brewery industry to17.34% thereby enhancing the production capacity, the conventional Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry was10%. Meanwhile, when leveraging machine learning was incorporated in the system, it decisively reduced Lengthy Fermentation and Maturation Times cause of poor production capacity in brewery industry to 8.7% and the conventional production capacity in brewery industry was 50000bottles of drink. On the other hand, when leveraging machine learning was inculcated in the system, it simultaneously enhanced the production capacity in a brewery industry to6 6500 bottles of drink. Finally, with these results obtained, it showed that production capacity in a brewery industry was optimized by 33%. REFERENCES Agrawal, A., Gans, J. S., & Goldfarb, A. (2020). Machine learning, process control, and industrial production. MIT Press. Lydon, M., Kim, J., & Yang, C. (2021). Machine learning in manufacturing: An overview of applications in process optimization. Journal of Manufacturing Processes, 54, 112–128. https://doi.org/10.1016/j.jmapro.2020.11.029 mailto:topacademicjournals@gmail.com https://doi.org/10.1016/j.jmapro.2020.11.029 Academic Journal of Science, Engineering and Technology Vol. 10, Issue 1; January -February 2025; ISSN: 2837-2964 Impact Factor: 7.67 1252 Columbia Rd NW, Washington DC, United States https://topjournals.org/index.php/AJSET/index; mail: topacademicjournals@gmail.com 39 | A c a d e m i c J o u r n a l o f S c i e n c e , E n g i n e e r i n g a n d T e c h n o l o g y | https://topjournals.org/index.php/AJSET Oliveira, J., & Cunha, L. M. (2019). Smart breweries: Applications of machine learning in beer production. Food Engineering Reviews, 11(2), 75–89. https://doi.org/10.1007/s12393-019-09167-4 Rathore, A., & Tiwari, M. K. (2020). Advanced manufacturing technologies for the brewery industry. Industrial Journal of Brewing, 126(3), 345–360. https://doi.org/10.1111/ijbc.12352 Singh, S., & Kumar, S. (2021). Challenges in AI and machine learning applications in traditional industries. AI in Manufacturing Journal, 4, 23–35. https://doi.org/10.1016/j.aim.2020.12.001 Wuest, T., Weimer, D., Irgens, C., & Thoben, K. D. (2019). Machine learning in manufacturing: Advantages, challenges, and applications. Production Engineering, 13(2), 175–187. https://doi.org/10.1007/s11740- 019-00847-3 Zhou, B., Dai, W., & Yang, H. (2021). Machine learning for smart manufacturing: A literature review. Journal of Manufacturing Science and Engineering, 143(4), 1–13. https://doi.org/10.1115/1.4049023 mailto:topacademicjournals@gmail.com https://doi.org/10.1007/s12393-019-09167-4 https://doi.org/10.1111/ijbc.12352 https://doi.org/10.1016/j.aim.2020.12.001 https://doi.org/10.1007/s11740-019-00847-3 https://doi.org/10.1007/s11740-019-00847-3 https://doi.org/10.1115/1.4049023