Position Papers of the 20th Conference on Computer Science and Intelligence Systems

DOI: http://dx.doi.org/10.15439/2025F8176

Citation: Position Papers of the 20th Conference on Computer Science and Intelligence Systems, M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 44, pages 75–80 (2025)

Full text

Abstract. Remaining Useful Life (RUL) estimation of complex machinery is critical for optimizing maintenance schedules and preventing unexpected failures in safety-critical systems. While Transformer architecture has recently achieved state-of-the-art performance on RUL benchmarks, their design often relies on expert tuning or costly Neural Architecture Search (NAS), and their predictions remain opaque to end users. In this work, we integrate a Transformer whose hyperparameters were discovered via evolutionary NAS with a gradient-based explainability method to deliver both high accuracy and transparent, per-prediction insights. Specifically, we adapt the Gradient Explainer algorithm to produce global and local importance scores for each sensor in the C-MAPSS FD001 turbofan dataset. Our analysis shows that the sensors identified as most influential, such as key temperature and pressure measurements, match domain-expert expectations. By illuminating the internal decision process of a complex, NAS-derived model, this study paves the way for trustworthy adoption of advanced deep-learning prognostics in industrial settings.

References

1. E. Zio, “Prognostics and health management (PHM): Where are we and where do we (need to) go in theory and practice,” Rel. Eng. Syst. Saf., vol. 218, Art. 108119, 2022. Available: https://doi.org/10.1016/j.ress.2021.108119.
2. O. Serradilla, E. Zugasti, J. Rodriguez, et al., “Deep learning models for predictive maintenance: a survey, comparison, challenges and prospects,” Appl. Intell., vol. 52, pp. 10934–10964, 2022. Available: https://doi.org/10.1007/s10489-021-03004-y
3. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, … and I. Polosukhin, “Attention is all you need,” Adv. Neural Inf. Process. Syst., vol. 30, 2017. Available: https://doi.org/10.48550/arXiv.1706.03762
4. H. Mo and G. Iacca, “Evolutionary neural architecture search on transformers for remaining useful life prediction,” Mater. Manuf. Process., pp. 1–18, 2023. Available: https://doi.org/10.1080/10426914.2023.2199499
5. A. Saxena, K. Goebel, D. Simon, and N. Eklund, “Damage propagation modeling for aircraft engine run-to-failure simulation,” Proc. Int. Conf. Prognostics Health Manag. (PHM), Denver, CO, USA, pp. 1–9, 2008. Available: https://doi.org/10.1109/PHM.2008.4711414.
6. V. Hassija, V. Chamola, A. Mahapatra, A. Singal, D. Goel, K. Huang, S. Scardapane, I. Spinelli, M. Mahmud, and A. Hussain, “Interpreting black-box models: A review on explainable artificial intelligence,” Cogn. Comput., vol. 16, pp. 45–74, 2024. Available: https://doi.org/10.1007/s12559-023-10179-8
7. A. T. Keleko, B. Kamsu-Foguem, R. H. Ngouna, and A. Tongne, “Health condition monitoring of a complex hydraulic system using deep neural network and DeepSHAP explainable XAI,” Adv. Eng. Softw., vol. 175, Art. 103339, Jan. 2023. Available: https://doi.org/10.1016/j.advengsoft.2022.103339
8. G. Youness and A. Aalah, “An explainable artificial intelligence approach for remaining useful life prediction,” Aerospace, vol. 10, no. 5, pp. 1–23, 2023. Available: https://doi.org/10.3390/aerospace10050474
9. T. Markovic, A. Dehlaghi-Ghadim, M. Leon, A. Balador, and S. Punnekkat, “Time-series anomaly detection and classification with long short-term memory network on industrial manufacturing systems,” Proc. 18th Conf. Comput. Sci. Intell. Syst. (FedCSIS), vol. 35, pp. 171–181, 2023. Available: https://doi.org/10.15439/2023F5263.
10. S. Zhao, Y. Zhang, S. Wang, B. Zhou, and C. Cheng, “A recurrent neural network approach for remaining useful life prediction utilizing a novel trend features construction method,” Measurement, vol. 146, pp. 279–288, 2019. Available: https://doi.org/10.1016/j.measurement.2019.06.004.
11. A. B. Arrieta, N. Díaz-Rodríguez, J. Del Ser, A. Bennetot, S. Tabik, A. Barbado, S. Garcia, S. Gil-Lopez, D. Molina, R. Benjamins, R. Chatila, and F. Herrera, “Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI,” Inf. Fusion, vol. 58, pp. 82–115, Jun. 2020. Available: https://doi.org/10.1016/j.inffus.2019.12.012
12. SHAP (SHapley Additive exPlanations): a game theoretic approach to explain the output of any machine learning model. Available: https://github.com/shap/shap
13. M. Ho, “NAS_transformer: Neural architecture search for transformer-based models,” GitHub repository, 2023. Available: https://github.com/mohyunho/NAS_transformer
14. S. Chakraborty et al., “Interpretability of deep learning models: A survey of results,” Proc. IEEE SmartWorld, San Francisco, CA, USA, pp. 1–6, 2017. Available: https://doi.org/10.1109/UIC-ATC.2017.8397411.
15. M. Sundararajan, A. Taly, and Q. Yan, “Axiomatic attribution for deep networks,” Proc. Int. Conf. Mach. Learn. (ICML), PMLR, 2017. Available: https://doi.org/10.48550/arXiv.1703.01365.