remaining useful life; Industry 4.0; Explainable AI
Résumé :
[en] Accurately estimating Remaining Useful Life (RUL) in industrial systems is crucial for optimizing maintenance strategies and extending the lifespan of assets. Data-driven RUL models leverage machine learning (ML) algorithms to extract patterns from operational data, excelling in capturing complex relationships. Despite advancements in RUL prognosis models, the black-box nature of machine learning algorithms poses challenges for industrial users, hindering trust and adoption.
Explainable Artificial Intelligence (XAI) methods offer promising solutions by making complex models transparent and interpretable. This paper focuses on applying XAI methods to enhance trust in machine learning models for RUL prognosis. We emphasize a quantitative assessment of explanation mechanisms, including metrics such as consistency and robustness. Our study contributes to developing more trustworthy and reliable predictive maintenance strategies.
We evaluate XAI methods explaining RUL models applied to a real-world scenario of industrial furnace data. Our findings aim to provide valuable insights for industrial practitioners, guiding them in selecting RUL prognosis techniques.
Centre de recherche :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SerVal - Security, Reasoning & Validation
Disciplines :
Sciences informatiques
Auteur, co-auteur :
BENGUESSOUM, Kaouther ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal
DE PAULA LOURENCO, Raoni ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal
Bourel, Vincent
KUBLER, Sylvain ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal
Co-auteurs externes :
no
Langue du document :
Anglais
Titre :
Through the Lens of Explainability: Enhancing Trust in Remaining Useful Life Prognosis Models
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., Samek, W.: On pixel-wise ex- planations for non-linear classifier decisions by layer-wise relevance propa- gation. PloS one, 10(7), e0130140 (2015)
Berghout, T., Benbouzid, M.: A systematic guide for predicting remaining useful life with machine learning. Electronics 11(7), 1125 (2022)
Bhatt, U., Weller, A., Moura, J.M.F.: Evaluating and aggregating feature-based model explanations. arXiv preprint arXiv:2005.00631 (2020)
Chalasani, P., Chen, J., Chowdhury, A.R., Wu, X., Jha, S.: Concise explanations of neural networks using adversarial training. In: International Conference on Machine Learning, pp. 1383–1391. PMLR (2020)
Cheng, Y., Kui, H., Jun, W., Zhu, H., Shao, X.: A convolutional neural network based degradation indicator construction and health prognosis using bidirectional long short-term memory network for rolling bearings. Adv. Eng. Inform. 48, 101247 (2021)
Gao, Z., Ma, C., Zhang, J., Weijun, X.: Enhanced on- line sequential parallel extreme learning machine and its application in remaining useful life prediction of integrated modular avionics. IEEE Access 7, 183479–183488 (2019)
Hedström, A., et al.: Quantus: an explainable AI toolkit for responsible evaluation of neural network explanations and beyond. J. Mach. Learn. Res. 24(34), 1–11 (2023)
Woo Hong, C., Lee, C., Lee, K., Ko, M.-S., Kim, D.E., Hur, K.: Remaining useful life prognosis for turbofan engine using explainable deep neural networks with dimensionality reduction. Sensors 20(22), 6626 (2020)
Hurley, N., Rickard, S.: Comparing measures of sparsity. IEEE Trans. Inf. Theory 55(10), 4723–4741 (2009)
Khan, T., Ahmad, K., Khan, J., Khan, I., Ahmad, N.: An explainable regression framework for predicting remaining useful life of machines. In: 2022 27th International Conference on Automation and Computing (ICAC), pp. 1–6. IEEE (2022)
Khazaee, M., Banakar, A., Ghobadian, B., Mirsalim, M.A., Minaei, S.: Remaining useful life (RUL) prediction of internal combustion engine timing belt based on vibration signals and artificial neural network. Neural Comput. Appl. 33, 7785–7801 (2021)
Li, J., Li, X., He, D.: A directed acyclic graph network combined with CNN and LSTM for remaining useful life prediction. IEEE Access 7, 75464–75475 (2019)
Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Ma, M., Mao, Z.: Deep-convolution-based LSTM network for remaining useful life prediction. IEEE Trans. Industr. Inf. 17(3), 1658–1667 (2020)
A.K. Bin Mohd Nor, Rao Pedapait, S., Muhammad, M.: Explainable AI (XAI) for PHM of industrial asset: a state-of-the-art, prisma-compliant systematic review. arXiv preprint arXiv:2107.03869 (2021)
Ribeiro, M.T., Singh, S., Guestrin, C.: “why should i trust you?” Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
Shi, J., Zhong, J., Zhang, Y., Xiao, B., Xiao, L., Zheng, Y.: A dual attention LSTM lightweight model based on exponential smoothing for remaining useful life prediction. Reliability Eng. Syst. Saf. 243, 109821 (2024)
Wang, B., Lei, Y., Yan, T., Li, N., Guo, L.: Recurrent convolutional neural network: a new framework for remaining useful life prediction of machinery. Neurocomputing 379, 117–129 (2020)
Wang, Y., Li, Y., Zhang, Y., Yang, Y., Liu, L.: RUSHAP: a unified approach to interpret deep learning model for remaining useful life estimation. In: 2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing), pp. 1–6. IEEE (2021)
Ji-Yan, W., Min, W., Chen, Z., Li, X., Yan, R.: A joint classification-regression method for multi-stage remaining useful life prediction. J. Manuf. Syst. 58, 109–119 (2021)
Yeh, C.-K., Hsieh, C.-Y., Suggala, A., Inouye, D.I., Ravikumar, P.K.: On the (in) fidelity and sensitivity of explanations. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Zhao, K., Zhang, J., Chen, S., Wen, P., Ping, W., Zhao, S.: Remaining useful life prediction method based on convolutional neural network and long short-term memory neural network. In: 2023 Prognostics and Health Management Conference (PHM), pp. 336–343. IEEE (2023)
