Harnessing  Machine  Learning  for  Predictive  Maintenance  in  IoT-Based Smart Manufacturing Environments

Amna  Sarwar; Usama  Ahmed; Muzzamil  Mustafa; Muneeb Ali  Muzzaffar; Muhammad Zulkifl Hasan; Muhammad Zunnurain Hussain

doi:10.32350/umt-air.42.01

Amna Sarwar University of Wah, Pakistan
Usama Ahmed University of Management and Technology, Lahore, Pakistan
Muzzamil Mustafa University of Management & Technology, Lahore, Pakistan
Muneeb Ali Muzzaffar University of Central Punjab, Lahore, Pakistan
Muhammad Zulkifl Hasan University of Central Punjab, Lahore, Pakistan
Muhammad Zunnurain Hussain Bahria University Lahore Campus, Pakistan

DOI: https://doi.org/10.32350/umt-air.42.01

Keywords: big data analytics, decision trees, Industry 4.0, Internet of Things (IoT), machine learning (ML), neural networks, predictive maintenance

Abstract

Abstract Views: 0

Industry 4.0 can be considered as a revolution in the industrial sector changing the reality since anew age of smart manufacturing has been introduced that integrates digital technologies including the Internet of Things (IoT), big data analytics, and machine learning (ML).One of the most unlike abilities in transformation is the application of predictive maintenance approach,that is, MLto improve the productivity and efficiency of manufacturing.The current study aimed to prepare a case for anML-basedtool in order topredict the need for maintenance within the Industry 4.0.The study discussedthe information generation from the sensor quantified by ML algorithms followed by the prediction of the equipment to fail prior to its actual failure.Therefore, it minimizesthe duration of downtime and decreasesthe maintenance costs.Key ML techniques,such as regression analysis, neural networks, and decision trees are evaluated to determine their effectiveness in diagnosing and predicting the equipment anomalies.Moreover, the current study reported anotherkey finding that it summarizes case studies from different industries in which predictive maintenance systems based on ML have been implemented successfully.These systemsreflected the substantial increase in production efficiency alongside significant cost reductions.Subsequently, the study also covered relevant topics pertainingto data quality, capacity of the model,and real-time processing difficulty.Additionally, the study at hand alsoaccentuatedthe role of MLas a revolutionary tool to provide maintenance solutions based on predictive analysis. This promotes Industry 4.0 as a manufacturing paradigm aimedat systematic and efficient processes.

Downloads

Download data is not yet available.

References

T. R. Mohan, J. P. Roselyn, R. A. Uthra, D. Devaraj, and K. Umachandran, "Intelligent machine learning based total productive maintenance approach for achieving zero downtime in industrial machinery," Comput. Indust.Eng.,vol. 157, Art. no. 107267, July 2021, doi: https://doi.org/10.1016/j.cie.2021.107267.[2]K. Kumar, D. Zindani, and J. P. Davim, Industry 4.0: Developments towards the fourth industrial revolution. Springer, 2019.[3]K. Witkowski, "Internet of things, big data, industry 4.0–innovative solutions in logistics and supply chains management," Proc.Eng.,vol. 182, pp. 763–769, 2017, doi: https://doi.org/10.1016/j.proeng.2017.03.197.[4]M. Nacchia, F. Fruggiero, A. Lambiase, and K. Bruton, "A systematic mapping of the advancing use of machine learning techniques for predictive maintenance in the manufacturing sector," Appl.Sci.,vol. 11, no. 6, Art. no.2546, 2021, doi: https://doi.org/10.3390/app11062546.[5]P. C. Sen, M. Hajra, and M. Ghosh, "Supervised classification algorithms in machine learning: A survey and review," in Emerg.Technol. Model. Graph., 2020, pp. 99–111. [6]K. Liulys, "Machine learning application in predictive maintenance," in Open Conf. Elect. Elect. Inform. Sci., Apr. 2019,pp. 1–4. [7]K. Maharana, S. Mondal, and B. Nemade, "A review: Data pre-processing and data augmentation techniques," Glob.Trans.Proc.,vol. 3, no. 1, pp. 91–99, June 2022, doi: https://doi.org/10.1016/j.gltp.2022.04.020.

Sarwar et al.19Department of Information SystemsVolume 4 Issue 2, Fall 2024[8]K. Rahul and R. K. Banyal, "Detection and correction of abnormal data with optimized dirty data: a new data cleaning model," Int.J. Inform.Technol. Dec.Making,vol. 20, no. 2, pp. 809–841, 2021, doi: https://doi.org/10.1142/S0219622021500188.[9]O. Janssens, R. Van de Walle, M. Loccufier, and S. Van Hoecke, "Deep learning for infrared thermal image based machine health monitoring," IEEE/ASME Trans. Mechat.,vol. 23, no. 1, pp. 151–159, 2017, doi: https://doi.org/10.1109/TMECH.2017.2722479. [10]T. Huuhtanen and A. Jung, "Predictive maintenance of photovoltaic panels via deep learning," in 2018 IEEE Data Sci. Workshop, June 2018, pp. 66–70, doi: https://doi.org/10.1109/DSW.2018.8439898.[11]Z. Panet al., "Cognitive acoustic analytics service for Internet of Things," in 2017 IEEE Int.Conf.Cognit.Comput., 2017, pp. 96–103, doi: https://doi.org/10.1109/IEEE.ICCC.2017.20.[12]A. Jimenez-Cortadi, I. Irigoien, F. Boto, B. Sierra, and G. Rodriguez, "Predictive maintenance on the machining process and machine tool," Appl.Sci.,vol. 10, no. 1,Art. no. 224, Dec. 2019, doi: https://doi.org/10.3390/app10010224.[13]W. Luo, T. Hu, Y. Ye, C. Zhang, and Y. Wei, "A hybrid predictive maintenance approach for CNC machine tool driven by Digital Twin," Robot.Comput.-Integrat.Manufac.,vol. 65, Art. no. 101974, Oct. 2020, doi: https://doi.org/10.1016/j.rcim.2020.101974. [14]F. Arena, M. Collotta, L. Luca, M. Ruggieri, and F. G. Termine, "Predictive maintenance in the automotive sector: A literature review," Math.Comput.Appl.,vol. 27, no. 1, Art. no.2, Dec. 2021, doi: https://doi.org/10.3390/mca27010002.[15]A. O. Adewusi, A. M. Komolafe, E. Ejairu, I. A. Aderotoye, O. O. Abiona, and O. C. Oyeniran, "The role of predictive analytics in optimizing supply chain resilience: a review of techniques and case studies," Int.J.Manag.Entrep.Res.,vol. 6, no. 3, pp. 815–837, Mar. 2024, doi: https://doi.org/10.51594/ijmer.v6i3.938.[16]Y. Ding, T. Xia, M. Huang, Y. Zheng, R. Miao, and L. Xi, "Predictive maintenance and upgrade scheduling for production line under multi-period product-service paradigm," Eng.Optimiz.,vol. 55, no. 10, pp. 1723–1741, 2023, doi: https://doi.org/10.1080/0305215X.2022.2122457. [17]I. Stanton, K. Munir, A. Ikram, and M. El‐Bakry, "Predictive maintenance analytics and implementation for aircraft: Challenges and opportunities," Syst.Eng.,vol. 26, no. 2, pp. 216–237, Mar. 2023, doi: https://doi.org/10.1002/sys.21651.[18]A. Theissler, J. Pérez-Velázquez, M. Kettelgerdes, and G. Elger, "Predictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry," Reliab.Eng Syst.Safety,vol. 215, Art. no.107864, Nov. 2021, doi: https://doi.org/10.1016/j.ress.2021.10

Harnessing Machine Learning for Predictive...20UMT Artificial Intelligence ReviewVolume 4 Issue 2, Fall 20247864.[19]S. D. Hiwase and P. Jagtap, "Predictive maintenance of automotive component using digital twin model," SAE Tech.Paper, 2022, doi: https://doi.org/10.4271/2022-28-0075. [20]M. K. Thomas and S. Sumathi, "Design of software-oriented technician for vehicle’s fault system prediction using AdaBoost and random forest classifiers," Int.J.Eng.Sci.Technol.,vol. 14, no. 1, pp. 28–51, Aug. 2022, doi: https://doi.org/10.4314/ijest.v14i1.4.[21]R. Espinosa, H. Ponce, and S. Gutiérrez, "Click-event sound detection in automotive industry using machine/deep learning," Appl.Soft Comput.,vol. 108,Art. no. 107465, Sep. 2021, doi: https://doi.org/10.1016/j.asoc.2021.107465. [22]A. Asayesh, A. W. Malik, and S. K. Das, "Disseminating over-the-air updates via intelligent labeling in multi-tier networks," in 2024 IEEE Int.Conf.Pervasive Comput. Commun.Workshops Other AffiliatEvents, Mar. 2024, pp. 714–719, doi: https://doi.org/10.1109/PerComWorkshops59983.2024.10503576. [23]R. Rosatiet al., "From knowledge-based to big data analytic model: a novel IoT and machine learning based decision support system for predictive maintenance in Industry 4.0," J. Intell.Manufac.,vol. 34, no. 1, pp. 107–121, 2023, doi: https://doi.org/10.1007/s10845-022-01960-x. [24]A. Bemani and N. Björsell, "Aggregation strategy on federated machine learning algorithm for collaborative predictive maintenance," Sensors,vol. 22, no. 16, Art. no. 6252, Aug. 2022, doi: https://doi.org/10.3390/s22166252. [25]O. Serradilla, E. Zugasti, J. Rodriguez, and U. Zurutuza, "Deep learning models for predictive maintenance: a survey, comparison, challenges and prospects," Applied Intelligence, vol. 52, no. 10, pp. 10934–10964, Jan. 2022, doi: https://doi.org/10.1007/s10489-021-03004-y. [26]P. Nunes, J. Santos, and E. Rocha, "Challenges in predictive maintenance–A review," CIRP J. Manufact.Sci.Technol.,vol. 40, pp. 53–67, Feb. 2023, doi: https://doi.org/10.1016/j.cirpj.2022.11.004.[27]N. Abosata, S. Al-Rubaye, G. Inalhan, and C. Emmanouilidis, “Internet of things for system integrity: A comprehensive survey on security, attacks and countermeasures for industrial applications,”Sensors, vol. 21, no. 11, Art. no. 3654, May 2021, doi: https://doi.org/10.3390/s21113654.[28]A. Bousdekis, “A review of data-driven decision-making methods for industry 4.0 maintenance applications,”Electronics, vol. 10, no. 7, Art. no.828, Mar. 2021, doi: https://doi.org/10.3390/electronics10070828.[29]A. Theissler, J. Pérez-Velázquez, M. Kettelgerdes, and G. Elger, “Predictive maintenance enabled by machine learning: use cases and challenges in the automotive industry,”Reliabil.Eng.Syst.Saf., vol. 215, Art. no. 107864, Nov. 2021, doi:

Sarwar et al.21Department of Information SystemsVolume 4 Issue 2, Fall 2024https://doi.org/10.1016/j.ress.2021.107864.[30]B. Dhamodharan, “Optimizing industrial operations: a data-driven approach to predictive maintenance through machine learning,”Int.J.Mach.Learn. Sustain.Develop., vol. 3, no. 1, pp. 31–44, Mar. 2021. [31]E. Zio, “Prognostics and health management(PHM): Where are we and where do we (need to) go in theory and practice,”Reliabil.Eng. Syst.Saf., vol. 218, Art. no. 108119, Feb. 2022, doi: https://doi.org/10.1016/j.ress.2021.108119.[32]J. Wang, C. Xu, J. Zhang, and R. Zhong, “Big data analytics for intelligent manufacturing systems: areview,”J. Manufact.Syst., vol. 62, pp. 738–752, June2021, doi: https://doi.org/10.1016/j.jmsy.2021.03.005.[33]V.T.Nguyen, P. Do, A. Vosin, and Benoît Iung, “Artificial-intelligence-based maintenance decision-making and optimization for multi-state component systems,” vol. 228, pp. 108757–108757, Sep. 2022, doi: https://doi.org/10.1016/j.ress.2022.108757.