PILOT: Physics-Informed Optimized LightGBM for Edge-Based Predictive Maintenance

Abstract

In Industry 4.0 applications, predictive maintenance is one of the frequently used methods for optimizing equipment reliability and maintenance costs. This paper proposes a new framework for edge-based machine fault detection, Physics-Informed Optimized LightGBM for Edge-Based Predictive Maintenance (PILOT), using a public dataset, AI4I 2020. The approach derives physics-informed interaction features from sensor data and uses Optuna to optimize the LightGBM hyperparameters. To ensure a fair comparison, the proposed model is compared with a known reference study from the literature. Experimental results show that the proposed approach provides a relative improvement of 0.51% in accuracy, 7.52% in precision, 11.12% in recall, and 9.40% in F1 score compared to the basic LightGBM model. To test the suitability of deployment for edge environments, the compared models were deployed on a Raspberry Pi 4 device. The results confirm the suitability of the proposed model for edge environments with a 5ms prediction time, even though it requires additional training and prediction time compared to other models.

Keywords

• Predictive maintenance
• Edge computing
• LightGBM
• Physics-Informed machine learning
• Hyperparameter optimization

Ethical Statement

Ethics committee approval was not required for this study, as it did not involve human participants or animals.

References

1. 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), Article 8081. https://doi.org/10.3390/app12168081
2. Bouabdallaoui, Y., Lafhaj, Z., Yim, P., Ducoulombier, L., & Bennadji, B. (2021). Predictive maintenance in building facilities: A machine learning-based approach. Sensors, 21(4), Article 1044. https://doi.org/10.3390/s21041044
3. Bousdekis, A., Apostolou, D., & Mentzas, G. (2020). Predictive maintenance in the 4th Industrial Revolution: Benefits, business opportunities, and managerial implications. IEEE Engineering Management Review, 48(1), 57–62. https://doi.org/10.1109/EMR.2019.2958037
4. 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), Article 8211. https://doi.org/10.3390/su12198211
5. García-Méndez, S., de Arriba-Pérez, F., Leal, F., Veloso, B., Malheiro, B., & Burguillo-Rial, J. C. (2025). An explainable machine learning framework for railway predictive maintenance using data streams from the Metro Operator of Portugal. Scientific Reports, 15(1), Article 27495. https://doi.org/10.1038/s41598-025-08084-1
6. Golec, M., Gill, S. S., Cuadrado, F., Parlikad, A. K., Xu, M., Wu, H., & Uhlig, S. (2024). ATOM: AI-powered sustainable resource management for serverless edge computing environments. IEEE Transactions on Sustainable Computing, 9(6), 817–829. https://doi.org/10.1109/TSUSC.2023.3348157
7. Golec, M., Wu, H., Ozturac, R., Parlikad, A. K., Cuadrado, F., Gill, S. S., & Uhlig, S. (2025). CAPTAIN: A testbed for co-simulation of scalable serverless computing environments for AIoT enabled predictive maintenance in Industry 4.0. IEEE Internet of Things Journal, 12(16), 32283–32295. https://doi.org/10.1109/JIOT.2024.3488283
8. Golec, M., Melhem, S. B., Ozturac, R., & Alrabaee, S. (2026). TAM: Temporal attention for edge-oriented short-term load forecasting. In 2026 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE) (pp. 616–619). IEEE. https://doi.org/10.1109/CCECE68150.2026.11610164

9. Hector, I., & Panjanathan, R. (2024). Predictive maintenance in Industry 4.0: A survey of planning models and machine learning techniques. PeerJ Computer Science, 10, Article e2016. https://doi.org/10.7717/peerj-cs.2016
10. Hosseinzadeh, A., Chen, F. F., Shahin, M., & Bouzary, H. (2023). A predictive maintenance approach in manufacturing systems via AI-based early failure detection. Manufacturing Letters, 35, 1179–1186. https://doi.org/10.1016/j.mfglet.2023.08.125
11. Khemani, K., & Qureshi, A. N. (2026). AI-driven predictive maintenance for connected vehicles using environmental context integration evaluated through simulation benchmarking and field validation. Discover Vehicles, 2, Article 19. https://doi.org/10.1007/s44465-026-00023-2
12. Kumar, R. S., Singh, A. R., Narayana, P. L., Chandrika, V. S., Bajaj, M., & Zaitsev, I. (2025). Hybrid machine learning framework for predictive maintenance and anomaly detection in lithium-ion batteries using enhanced random forest. Scientific Reports, 15(1), Article 6243. https://doi.org/10.1038/s41598-025-90810-w
13. Matzka, S. (2020). Explainable artificial intelligence for predictive maintenance applications. In 2020 Third International Conference on Artificial Intelligence for Industries (AI4I) (pp. 69–74). IEEE. https://doi.org/10.1109/AI4I49448.2020.00023
14. Perumallaplli, R. (2021). Predictive maintenance in cloud infrastructure: A machine learning framework. SSRN, Article 5228213. https://doi.org/10.2139/ssrn.5228213
15. Qahtani, A. M. (2026). A leakage-aware and reproducible evaluation framework for predictive maintenance classification. International Journal of Advanced Computer Science and Applications, 17(3), 942–951. https://doi.org/10.14569/IJACSA.2026.0170383
16. Ranaweera, P., Jurcut, A. D., & Liyanage, M. (2021). Survey on multi-access edge computing security and privacy. IEEE Communications Surveys & Tutorials, 23(2), 1078–1124. https://doi.org/10.1109/COMST.2021.3062546
17. Riccio, C., Menanno, M., Zennaro, I., & Savino, M. M. (2024). A new methodological framework for optimizing predictive maintenance using machine learning combined with product quality parameters. Machines, 12(7), Article 443. https://doi.org/10.3390/machines12070443
18. Sahli, A., Evans, R., & Manohar, A. (2021). Predictive maintenance in Industry 4.0: Current themes. Procedia CIRP, 104, 1948–1953. https://doi.org/10.1016/j.procir.2021.11.329
19. Shah, H. R., Haley, B., & Abdelfattah, E. (2024). Application of machine learning models for predictive analytics on AI4I 2020. In 2024 IEEE 15th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) (pp. 506–511). IEEE. https://doi.org/10.1109/UEMCON62879.2024.10772412
20. Silvestri, L., Forcina, A., Introna, V., Santolamazza, A., & Cesarotti, V. (2020). Maintenance transformation through Industry 4.0 technologies: A systematic literature review. Computers in Industry, 123, Article 103335. https://doi.org/10.1016/j.compind.2020.103335
21. Stupina, A. A., Kukartseva, S. V., & Stepantsevich, M. N. (2026). Application of graph neural networks for structural dependency analysis in industrial digital twins using the UCI AI4I 2020 predictive maintenance dataset. In 2026 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM) (pp. 1155–1159). IEEE. https://doi.org/10.1109/ICIEAM69213.2026.11549674
22. Zonta, T., Da Costa, C. A., da Rosa Righi, R., De Lima, M. J., Da Trindade, E. S., & Li, G. P. (2020). Predictive maintenance in the Industry 4.0: A systematic literature review. Computers & Industrial Engineering, 150, Article 106889. https://doi.org/10.1016/j.cie.2020.106889