Implementing Explainable Artificial Intelligence for Predictive Maintenance Decision Making in Industry 4.0
Keywords:
Explainable Artificial Intelligence (XAI), Predictive Maintenance, SHAP, LIME, Machine LearningAbstract
Predictive Maintenance (PdM) has become an important application of Artificial Intelligence (AI) in modern manufacturing environments, enabling organizations to predict equipment failures, optimize maintenance schedules, and improve operational efficiency. Despite their high predictive performance, many AI-based predictive maintenance models operate as black-box systems, limiting transparency and reducing user trust in maintenance recommendations. This study aims to implement Explainable Artificial Intelligence (XAI) techniques within predictive maintenance systems to improve model interpretability and support more transparent maintenance decision-making. Industrial equipment data collected from IoT sensors, including vibration, temperature, pressure, and runtime measurements, together with historical maintenance records, were analyzed using machine learning and deep learning models, namely Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Long Short-Term Memory (LSTM). Model performance was evaluated using Accuracy, Precision, Recall, and F1-score metrics, while explanation effectiveness was assessed through interpretability analysis and expert validation involving maintenance engineers, production managers, and reliability specialists. The results demonstrate that the proposed XAI-enabled predictive maintenance framework achieves high predictive performance, with the LSTM model obtaining the highest accuracy of 95.1%, outperforming RF and XGBoost models. Furthermore, SHAP and LIME successfully identified vibration and temperature as the most influential factors contributing to equipment failure predictions and provided understandable explanations for individual maintenance decisions. These findings suggest that integrating Explainable AI into predictive maintenance systems enhances model transparency, supports effective decision-making, and promotes the practical adoption of AI technologies in industrial environments.
References
Ali, M., Ul-Hamid, A., Alhems, L. M., & Saeed, A. (2020). Review of common failures in heat exchangers–Part I: Mechanical and elevated temperature failures. Engineering Failure Analysis, 109, 104396.
Buhrmester, V., Münch, D., & Arens, M. (2021). Analysis of explainers of black box deep neural networks for computer vision: A survey. Machine Learning and Knowledge Extraction, 3(4), 966–989.
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.
Cummins, L., Sommers, A., Ramezani, S. B., Mittal, S., Jabour, J., Seale, M., & Rahimi, S. (2024). Explainable predictive maintenance: A survey of current methods, challenges and opportunities. IEEE Access, 12, 57574–57602.
Dieber, J., & Kirrane, S. (2020). Why model why? Assessing the strengths and limitations of LIME. ArXiv Preprint ArXiv:2012.00093.
Doshi-Velez, F., Kortz, M., Budish, R., Bavitz, C., Gershman, S., O’Brien, D., Scott, K., Schieber, S., Waldo, J., & Weinberger, D. (2017). Accountability of AI under the law: The role of explanation. ArXiv Preprint ArXiv:1711.01134.
Dowling, A., O’Dwyer, J., & Adley, C. C. (2015). Lime in the limelight. Journal of Cleaner Production, 92, 13–22.
Drakaki, M., Karnavas, Y. L., Tziafettas, I. A., Linardos, V., & Tzionas, P. (2022). Machine learning and deep learning based methods toward industry 4.0 predictive maintenance in induction motors: State of the art survey. Journal of Industrial Engineering and Management (JIEM), 15(1), 31–57.
Ebersbach, S. (2007). Artificial intelligent system for integrated wear debris and vibration analysis in machine condition monitoring. James Cook University.
Feng, D.-C., Wang, W.-J., Mangalathu, S., & Taciroglu, E. (2021). Interpretable XGBoost-SHAP machine-learning model for shear strength prediction of squat RC walls. Journal of Structural Engineering, 147(11), 4021173.
Fritz, H. M., Blount, C., Sokoloski, R., Singleton, J., Fuggle, A., McAdoo, B. G., Moore, A., Grass, C., & Tate, B. (2007). Hurricane Katrina storm surge distribution and field observations on the Mississippi Barrier Islands. Estuarine, Coastal and Shelf Science, 74(1–2), 12–20.
Kalusivalingam, A. K., Sharma, A., Patel, N., & Singh, V. (2021). Leveraging SHAP and LIME for enhanced explainability in AI-driven diagnostic systems. International Journal of AI and ML, 2(3).
Keleko, A. T., Kamsu-Foguem, B., Ngouna, R. H., & Tongne, A. (2022). Artificial intelligence and real-time predictive maintenance in industry 4.0: a bibliometric analysis. AI and Ethics, 2(4), 553–577.
Lee, J. (1995). Machine performance monitoring and proactive maintenance in computer-integrated manufacturing: review and perspective. International Journal of Computer Integrated Manufacturing, 8(5), 370–380.
Lipowski, E. E. (2008). Developing great research questions. American Journal of Health-System Pharmacy, 65(17), 1667–1670.
Minh, D., Wang, H. X., Li, Y. F., & Nguyen, T. N. (2022). Explainable artificial intelligence: a comprehensive review. Artificial Intelligence Review, 55(5), 3503–3568.
Naqvi, S. A. A., Tennankore, K., Vinson, A., Roy, P. C., & Abidi, S. S. R. (2021). Predicting kidney graft survival using machine learning methods: prediction model development and feature significance analysis study. Journal of Medical Internet Research, 23(8), e26843.
Nicolas, A., Messner, M. C., & Sham, T.-L. (2021). A method for predicting failure statistics for steady state elevated temperature structural components. International Journal of Pressure Vessels and Piping, 192, 104363.
Paliari, I., Karanikola, A., & Kotsiantis, S. (2021). A comparison of the optimized LSTM, XGBOOST and ARIMA in Time Series forecasting. 2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA), 1–7.
Plante, T., Nejadpak, A., & Yang, C. X. (2015). Faults detection and failures prediction using vibration analysis. 2015 IEEE AUTOTESTCON, 227–231.
Qadir, A. (2025). THE FUTURE OF CYBER-PHYSICAL SYSTEMS: INTEGRATING AI, IOT, AND CLOUD FOR INDUSTRIAL REVOLUTION 5.0. Frontiers in Multidisciplinary Studies, 2(01), 43–53.
Rahman, M., Cao, Y., Sun, X., Li, B., & Hao, Y. (2021). Deep pre-trained networks as a feature extractor with XGBoost to detect tuberculosis from chest X-ray. Computers & Electrical Engineering, 93, 107252.
Raju, D., Su, X., Patrician, P. A., Loan, L. A., & McCarthy, M. S. (2015). Exploring factors associated with pressure ulcers: a data mining approach. International Journal of Nursing Studies, 52(1), 102–111.
Walker, C. M., Agarwal, V., Lin, L., Hall, A. C., Hill, R. A., Mortenson, T. J., & Lybeck, N. J. (2023). Explainable artificial intelligence technology for predictive maintenance. Idaho National Laboratory (INL), Idaho Falls, ID (United States).
Wang, Z., Zhang, J., Jiang, Z., Mao, Z., Chang, K., & Wang, C. (2021). Quantitative misalignment detection method for diesel engine based on the average of shaft vibration and shaft shape characteristics. Measurement, 181, 109527.
Xu, X., Lei, Y., & Li, Z. (2019). An incorrect data detection method for big data cleaning of machinery condition monitoring. IEEE Transactions on Industrial Electronics, 67(3), 2326–2336.
Yechevskyi, А., Maksymova, S., & Sotnik, S. (2025). Analysis of the data collection process about products at different stages of production.
Zemmouchi-Ghomaria, L. (n.d.). Explainable AI for predictive maintenance: A review and standardized evaluation framework.
Zheng, H., Yuan, J., & Chen, L. (2017). Short-term load forecasting using EMD-LSTM neural networks with a Xgboost algorithm for feature importance evaluation. Energies, 10(8), 1168.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ghazanfer Muhazzim, Mochtar Radhitya
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
