Utilizing machine learning for predictive maintenance of production machinery in small and medium enterprises
Keywords:
Predictive maintenance, Machine learning, K-nearest neighbor, Decision tree, Random forestAbstract
Predictive maintenance involves the early detection of potential machine failures and subsequent maintenance to prevent such failures. Machine learning is a pertinent statistical method for predictive maintenance, enabling the early detection of machine failures and the implementation of preventive measures through a model. The development of the machine learning model commences with data collection from the machine, encompassing vibration, acceleration, machine temperature, and machine sound, facilitated by a microcontroller equipped with sensors. Subsequently, the data undergoes cleaning, including removing outliers or missing values and standardization. Data is partitioned into 70% allocated for training and 30% for testing. After determining hyperparameters and their values through hyperparameter tuning, the training data is utilized to train machine learning models, such as K-nearest neighbor, decision tree, and random forest models. Post-training, the models are evaluated using the remaining test data, employing performance metrics such as accuracy, precision, recall, and F1-score. The random forest model excels due to its utilization of a substantial number of trees for predictions and the full exploitation of the variables which F1-score is 91.22%. The best-performing model is subsequently deployed into a monitoring system, providing real-time machine condition predictions. The deployment results validate the accurate prediction of machine failures.
References
[1] R. Quatrini, E., Costantino, F., Di Gravio, G., Patriarca, “Condition-based maintenance-an extensive literature review,” Machines, vol. 8, no. 31, pp. 1–28, 2020.
[2] G. Zonta, T., da Costa, C., da Rosa,R., Jose de Lima, M., da Trindade,E., Pyng Li, “Predictive maintenance in the industry 4.0: A systematic literature review,” Computers & Industrial Engineering, vol. 150, pp. 1–17, 2020.
[3] G. A. Susto, A. Schirru, S. Pampuri, S. McLoone, and A. Beghi, “Machine learning for predictive maintenance: A multiple classifier approach,” IEEE Transactions on Industrial Informatics, vol. 11, no. 3, pp. 812–820, 2015, doi: 10.1109/TII.2014.2349359.
[4] L. Puryani., Chalida,N., Soepardi,A., Chaeron,M., Nafisah, “Improving the job shop scheduling algorithm to minimize total penalty cost considering maintenance activity,” OPSI, vol. 17, no. 2, pp. 355–367, 2024, doi: https://doi.org/10.31315/opsi.v17i2.12291.
[5] M. M. Ardhianto and R. Sumarwanto, “Analisa predictive berbasis supervised machine learning terhadap kerusakan peralatan pembangkit,” Jurnal Teknologi Elekterika, vol. 19, no. 2, pp. 143–148, 2022.
[6] V. Bahrudin,A., Setiawan,I., Arifin,M.M., Fipiana,W.I., Lusia, “Analysis of preventive maintenance breakdown maintenance on production achievement in the food seasoning industry,” OPSI, vol. 14, no. 2, pp. 253–261, 2021, doi: https://doi.org/10.31315/opsi.v14i2.5540.
[7] J. Mahendra,I.G.O., Atmaji,F.T.D., Alhilman, “Proposes maintenance policy design on paving molding machine using Reliability and Risk Centered Maintenance (RRCM) method at PT XYZ,” OPSI, vol. 14, no. 2, pp. 231–243, 2021, doi: https://doi.org/10.31315/opsi.v14i2.5477.
[8] T. P. Carvalho, F. A. A. M. N. Soares, R. Vita, R. da P. Francisco, J. P. Basto, and S. G. S. Alcalá, “A systematic literature review of machine learning methods applied to predictive maintenance,” Computers and Industrial Engineering, vol. 137, no. August, 2019, doi: 10.1016/j.cie.2019.106024.
[9] M. & M. M. Pandey, J.S., Ahn, C. Lee, A., “Recent advances in the application of natural fiber based composites,” Macromolecular Materials and Engineering, vol. 295, no. 11, pp. 975–989, 2019.
[10] M. Montero-Jimenez, J.J., Scwartz, S., Vingerhoeds, R., Grabot, B., Salaun, “Towards multi-model approaches to predictive maintenance: a systematic literature survey on diagnostics and prognostics,” Journal Manufacturing System, vol. 56, pp. 536–557, 2020.
[11] S. Dayo-Olupona,O., Genc, B., Celik, T., Bada, “Adoptable approaches to predictive maintenance in mining industry: An overview,” Resources Policy, vol. 86, p. 104291, 2023.
[12] A. P. Sahba, R., Radfar, R., Ghatari, A.R., Ebrahimi, “Development of industry 4.0 predictive maintenance architecture for broadcasting chain,” Advanced Engineering Informatics, vol. 49, pp. 1–11, 2021.
[13] D. Pratiwi,A.I., Sihombing,B., Sayuti,M., Pradana,N., Adetia, “DMB machine reliability analysis through failure mode effect analysis and reliability block,” OPSI, vol. 14, no. 1, pp. 81–88, 2021, doi: https://doi.org/10.31315/opsi.v14i1.4745.
[14] H. B. Shin, J.H., Jun, “On condition based maintenance policy,” Journal Computational Design and Engineering, vol. 2, pp. 119–127, 2015.
[15] S. S. Zhang, Y., Ren, S., Liu Y., “A big data analytics architecture for cleaner manufacturing and maintenance processes of complex products,” Journal Clean Production, vol. 142, pp. 626–641, 2017.
[16] NH. Wang, Y., Gogu C., Binaud, N., Bes C., Haftka RT., Kim, “A cost-driven predictive maintenance policy for structural airframe maintenance,” Chinese Journal of Aeronautics, vol. 30, no. 3, pp. 1242–1257, 2017.
[17] A. R. Mohanty, Machinery Condition Monitoring: Principles and Practices. Boca Raton: CRC Press, 2014.
[18] B. Putra,S.S.W., Rahmawati, “Raw mill machine effective measurement through the Total Production Maintenance (TPM) Implementation,” OPSI, vol. 15, no. 2, pp. 153–163, 2022, doi: https://doi.org/10.31315/opsi.v15i2.7729.
[19] Felecia, “Fuzzy logic reliability centered maintenance,” Jurnal Teknik Industri, vol. 16, no. 2, pp. 121–126, 2014.
[20] K. B. Jayaswal, P., Wadhawani, A.K., Mulchandani, “Machine fault signature analysis,” International Journal of Rotating Machinery, vol. 2008, pp. 1–10, 2008.
[21] E. Zhu, J., He, D., Bechhoefer, “Survey of lubrication oil condition monitoring, diagnostics and prognostics techniques and systems,” Journal of Chemical Science and Technology, vol. 2, no. 3, pp. 100–115, 2013.
[22] R. Gangsar,P., Tiwari, “Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art-review,” Mechanical Systems and Signal Processing, vol. 144, pp. 1–37, 2020.
[23] A. Schwendemann, S., Amjad, Z., Sikora, “A survey of machine-learning techniques for condition monitoring and predictive maintenance of bearings in grindings machines,” Computers in Industry, vol. 125, pp. 1–17, 2021.
[24] I. El Naqa and M. J. Murphy, “Machine learning in radiation oncology,” Machine Learning in Radiation Oncology, pp. 3–11, 2015, doi: 10.1007/978-3-319-18305-3.
[25] J. Q. K.Wang., J.Xu., S. Zhang., Tan, “Towards low-budget energy efficiency design in additive manufacturing based on variational scale-aware transfromer,” Clean Production, vol. 393, pp. 136–168, 2023.
[26] T.M.Mitchell, Machine learning. New York: McGraw-Hill, 2007.
[27] T. P. Carvalho, F. A. A. M. N. Soares, R. Vita, R. da P. Francisco, J. P. Basto, and S. G. S. Alcalá, “A systematic literature review of machine learning methods applied to predictive maintenance,” Computers and Industrial Engineering, vol. 137, no. August, 2019, doi: 10.1016/j.cie.2019.106024.
[28] I. Arena, S., Florian, E., Sgarbossa, F., Sølvsberg, E., Zennaro, “A conceptual framework for machine learning algorithm selection for predictive maintenance,” Engineering Applications of Artificial Intelligence, vol. 133, pp. 1–15, 2024.
[29] Y. Chen, C., Fu, H., Zheng, Y., Tao, F., Liu, “The advance of digital twin for predictive maintenance: The role and function of machine learning,” Journal of Manufacturing Systems, vol. 71, pp. 581–594, 2023.
[30] S. Ray, “A quick review of machine learning algorithms- A review,” in Proc. Int. Conf. Mach. Learn. Big Data, Cloud Parallel Comput. Trends, Prespectives Prospect. Com. 2019, 2019, pp. 35–39.
[31] F. Chac´on, A.M., Ramírez, I.S., M´arquez, “K-nearest neighbour and K-fold cross-validation used in wind turbines for false alarm detection,” Sustainable Futures, vol. 6, pp. 100–132, 2023.
[32] D. Das, Oguzhan., Das-Bagci, Duygu., Birant, “Machine learning for fault analysis in rotating machinery: A comprehensive review,” Heliyon, vol. 9, pp. 1–34, 2023.
[33] N. Z. Wang,B., Gong, “Stealing hyperparameters in machine learning,” in IEEE Symposium on Security and Privacy, 2018, pp. 36–52.
[34] C. Ashmore,R., Calinescu, R., Paterson, “Assuring the machine learning lifecycle: desiderata, methods and challenges,” ACM Computing Surveys, vol. 54, no. 5, pp. 111–139, 2021.
[35] Y. Peksen, M.F., Yurtsever,U., Uyaroglu, “Enhancing electrical panel anomaly detection for predictive maintenance with machine learning and IoT,” Alexandria Engineering Journal, vol. 96, pp. 112–123, 2024.
[36] J. Díaz-Ramírez, “Machine learning and deep learning,” Ingeniare, vol. 29, no. 2, pp. 182–183, 2021.
[37] B.Mahesh, “Machine learning algorithms-a review,” International Journal of Science and Research (IJSR), vol. 9, no. 1, pp. 381–386, 2018.
[38] V. Nasteski, “An overview of the supervised machine learning methods,” Horizons, vol. 4, pp. 51–62, 2017.
Downloads
Published
Issue
Section
License
Authors who publish articles in this journal agree to the following conditions:
- Copyright remains with the author and gives the Opsi journal the right as a priority to publish its articles with Creative Commons Attribution 4.0 International license. Which allows articles to be shared with acknowledgement of the author of the article and this journal as the place of publication.
- Authors can distribute their articles on a non-exclusive basis (e.g. in university repositories or books) with notification or acknowledgement of publication in Opsi journals.
- Authors are allowed to post their work online (e.g. on a personal website or in a university repository) before and after the submission process (see The Effect of Open Access)
This work is Licensed Under a Creative Commons Attribution 4.0 International license.