EXPLAINABLE MACHINE FAILURE PREDICTION FOR SMART MANUFACTURING
DOI:
https://doi.org/10.69980/gqyk9b44Keywords:
Smart manufacturing, predictive maintenance, machine failure prediction, explainable artificial intelligence, machine learningAbstract
Machine failures remain a major challenge in smart manufacturing because unexpected equipment breakdowns reduce production efficiency, increase maintenance costs, and interrupt operational continuity. This study developed an explainable machine learning framework for predicting machine failures using the AI4I 2020 Predictive Maintenance dataset comprising 10,000 machine operating records. A quantitative research design based on secondary data analysis was adopted. Data preprocessing included feature encoding, standardisation, class imbalance handling, and training–testing data partitioning. Multiple supervised machine learning algorithms were developed and compared, while Explainable Artificial Intelligence (XAI) techniques, including SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), were employed to interpret prediction outcomes. The analysis showed that machine failures represented a small proportion of observations, whereas operational variables such as rotational speed, torque, tool wear, and temperature exhibited distinct patterns associated with equipment failure. Heat dissipation, overstrain, and power failures were identified as the most frequent failure mechanisms, indicating the importance of monitoring multiple operational factors simultaneously. The explainability framework improved transparency by identifying the variables contributing most strongly to prediction decisions, thereby supporting more reliable maintenance planning and operational decision-making. The proposed approach demonstrates that combining predictive modelling with interpretable artificial intelligence can strengthen predictive maintenance strategies, minimise unexpected equipment downtime, optimise resource utilisation, and improve the practical adoption of intelligent decision-support systems within smart manufacturing environments.
References
1.Abidi, M. H., Mohammed, M. K., & Alkhalefah, H. (2022). Predictive maintenance planning for industry 4.0 using machine learning for sustainable manufacturing. Sustainability, 14(6), 3387.
2.Achouch, M., Dimitrova, M., Ziane, K., Sattarpanah Karganroudi, S., Dhouib, R., Ibrahim, H., & Adda, M. (2022). On predictive maintenance in industry 4.0: Overview, models, and challenges. Applied sciences, 12(16), 8081.
3.Carmona, P., Dwekat, A., & Mardawi, Z. (2022). No more black boxes! Explaining the predictions of a machine learning XGBoost classifier algorithm in business failure. Research in International Business and Finance, 61, 101649.
4.Chang, T. S., & Bau, D. Y. (2025). eXplainable artificial intelligence (XAI) in business management research: a success/failure system perspective. Journal of Electronic Business & Digital Economics, 4(1), 36-53.
5.Chen, T. C. T. (2023). Explainable artificial intelligence (XAI) in manufacturing. In Explainable Artificial Intelligence (XAI) in Manufacturing: Methodology, Tools, and Applications (pp. 1-11). Cham: Springer International Publishing.
6.Cinar, E., Kalay, S., & Saricicek, I. (2022). A predictive maintenance system design and implementation for intelligent manufacturing. Machines, 10(11), 1006.
7.Çınar, Z. M., Abdussalam Nuhu, A., Zeeshan, Q., Korhan, O., Asmael, M., & Safaei, B. (2020). Machine learning in predictive maintenance towards sustainable smart manufacturing in industry 4.0. Sustainability, 12(19), 8211.
8.Elgnemi, T., Songmene, V., Kouam, J., Jun, M. B., & Samuel, A. M. (2021). Experimental investigation on dry routing of CFRP composite: temperature, forces, tool wear, and fine dust emission. Materials, 14(19), 5697.
9.Falatouri, T., Nasseri, M., Brandtner, P., & Darbanian, F. (2023, July). Shedding light on the black box: explainable AI for predicting household appliance failures. In International Conference on Human-Computer Interaction (pp. 69-83). Cham: Springer Nature Switzerland.
10.Farooq, U., Ademola, M., & Shaalan, A. (2024). Comparative analysis of machine learning models for predictive maintenance of ball bearing systems. Electronics, 13(2), 438.
11.Jamil, M., He, N., Gupta, M. K., Zhao, W., & Khan, A. M. (2022). Tool wear mechanisms and its influence on machining tribology of face milled titanium alloy under sustainable hybrid lubri-cooling. Tribology International, 170, 107497.
12.Kusiak, A. (2024). Federated explainable artificial intelligence (fXAI): a digital manufacturing perspective. International Journal of Production Research, 62(1-2), 171-182.
13.Levin, S. (2024, December). Enhancing predictive maintenance in the industrial sector: A comparative analysis of machine learning models. In AIP Conference Proceedings (Vol. 3243, No. 1, p. 020035). AIP Publishing LLC.
14.Love, P. E., Fang, W., Matthews, J., Porter, S., Luo, H., & Ding, L. (2023). Explainable artificial intelligence (XAI): Precepts, models, and opportunities for research in construction. Advanced Engineering Informatics, 57, 102024.
15.Matzka, S. (2020). AI4I 2020 Predictive Maintenance Dataset. UCI Machine Learning Repository. https://doi.org/10.24432/C5HS5C
16.Merchán-Cruz, E. A., Gabelaia, I., Savrasovs, M., Hansen, M. F., Soe, S., Rodriguez-Cañizo, R. G., & Aragón-Camarasa, G. (2025). Trust by design: An ethical framework for collaborative intelligence systems in Industry 5.0. Electronics, 14(10), 1952.
17.Meriem, H., Nora, H., & Samir, O. (2023). Predictive maintenance for smart industrial systems: a roadmap. Procedia Computer Science, 220, 645-650.
18.Mohammed, N. A., Abdulateef, O. F., Hamad, A. H., & Abdullah, O. I. (2024). Performance analysis of different machine learning algorithms for predictive maintenance. Al-Khwarizmi Engineering Journal, 20(2), 26-38.
19.Pech, M., Vrchota, J., & Bednář, J. (2021). Predictive maintenance and intelligent sensors in smart factory. Sensors, 21(4), 1470.
20.Puthanveettil Madathil, A., Luo, X., Liu, Q., Walker, C., Madarkar, R., & Qin, Y. (2025). A review of explainable artificial intelligence in smart manufacturing. International Journal of Production Research, 63(23), 8654-8697.
21.Ramzan, F., & Reforgiato Recupero, D. (2025, December). A literature review on enhancing predictive maintenance in smart manufacturing industries: fostering human-technology collaboration and overcoming data scarcity limitations with advanced AI models. In Operations Research Forum (Vol. 6, No. 4, p. 181). Cham: Springer International Publishing.
22.ŞAHiN, E., Arslan, N. N., & Özdemir, D. (2025). Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning. Neural computing and applications, 37(2), 859-965.
23.Taşcı, B., Omar, A., & Ayvaz, S. (2023). Remaining useful lifetime prediction for predictive maintenance in manufacturing. Computers & Industrial Engineering, 184, 109566.
24.Thalpage, N. (2023). Unlocking the black box: Explainable artificial intelligence (XAI) for trust and transparency in ai systems. J. Digit. Art Humanit, 4(1), 31-36.
25.Tzionis, G., Mouratidis, P., Kougka, G., Gialampoukidis, I., Vrochidis, S., Kompatsiaris, I., & Vlachopoulou, M. (2025). A review of explainable AI methods and their application in manufacturing systems. Discover Applied Sciences, 8(1), 52.
