Interpretable Sensor Importance-Based Multi-Sensor Integration for Condition Monitoring of Rotating Machinery
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Accurate condition monitoring of rotating machinery requires integrating multi-sensor data to capture fault-related information distributed across sensing locations. While attention-based deep learning models can assess sensor importance, their lack of transparency limits industrial adoption. This study proposes an interpretable sensor importance-based multi-sensor integration framework combining a CNN-inspired kernel sharing strategy, a Transformer encoder for local and global feature extraction, and a channel attention mechanism for dynamic sensor weighting. Attention weight in Transformer encoder was analyzed in frequency domain to reveals spectral components influencing sensor importance evaluation. Validation on a pump testbed with various speeds conditions shows superior fault diagnosis accuracy, robustness to unseen conditions, and clear alignment between high-weight sensors and known fault frequencies, supporting trustworthy AI-driven condition monitoring in practice.
##plugins.themes.bootstrap3.article.details##
Sensor integration, Rotating machinery fault diagnosis, Interpretability, Attention mechanism, Sensor importance evaluation
Hou, Y., Wang, J., Chen, Z., Ma, J., & Li, T. (2023). Diagnosisformer: An efficient rolling bearing fault diagnosis method based on improved transformer. Engineering Applications of Artificial Intelligence, 124, 106507. https://doi.org/10.1016/j.engappai.2023.106507
Kim, S., Lee, J., Park, K., Choi, H., & Kang, M. (2025). Fault-relevance-based, multi-sensor information integration framework for fault diagnosis of rotating machineries. Mechanical Systems and Signal Processing, 232, 112742. https://doi.org/10.1016/j.ymssp.2025.112742
Lee, J., Wu, F., Zhao, W., Ghaffari, M., Liao, L., & Siegel, D. (2014). Prognostics and health management design for rotary machinery systems – Reviews, methodology and applications. Mechanical Systems and Signal Processing, 42, 314–334. https://doi.org/10.1016/j.ymssp.2013.06.004
Li, Y., Zhou, Z., Sun, C., Chen, X., & Yan, R. (2024). Variational attention-based interpretable transformer network for rotary machine fault diagnosis. IEEE Transactions on Neural Networks and Learning Systems, 35, 6180–6193. https://doi.org/10.1109/TNNLS.2022.3202234
Liu, R., Yang, B., Zio, E., & Chen, X. (2018). Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing, 108, 33–47. https://doi.org/10.1016/j.ymssp.2018.02.016
Wu, H., Triebe, M. J., & Sutherland, J. W. (2023). A transformer-based approach for novel fault detection and fault classification/diagnosis in manufacturing: A rotary system application. Journal of Manufacturing Systems, 67, 439–452. https://doi.org/10.1016/j.jmsy.2023.02.018
Xu, Y., Chen, Y., Zhang, H., Feng, K., Wang, Y., Yang, C., & Ni, Q. (2023). Global contextual feature aggregation networks with multiscale attention mechanism for mechanical fault diagnosis under non-stationary conditions. Mechanical Systems and Signal Processing, 203, 110724. https://doi.org/10.1016/j.ymssp.2023.110724
This work is licensed under a Creative Commons Attribution 3.0 Unported License.