Temporal max pooling for robust multi-class fault diagnosis of PMSM-based drive modules at unseen sensor locations

In vibration-based fault diagnosis of permanent magnet synchronous motor (PMSM) drive modules, sensor relocation can induce distribution shifts that degrade classification performance and increase diagnostic errors. This study evaluates whether a lightweight diagnostic model trained at a single sensor location can retain diagnostic reliability at unseen locations under physically induced disturbances. An in-house triaxial vibration dataset was constructed using five PMSM drive modules representing five diagnostic conditions, four sensor locations, and five disturbance patterns.

A compact one-dimensional convolutional neural network–bidirectional long short-term memory (1D-CNN–BiLSTM) backbone requiring 20.20 M multiply-accumulate operations per input segment was evaluated using Raw inference, temporal majority voting, temporal moving average, and temporal max pooling (TMP). Separate speed-specific models using the same architecture, preprocessing, and evaluation protocol were examined at 500, 750, and 1000 rpm with a representative temporal window of 20 predictions. Across the two strictly unseen sensor locations, TMP improved classification accuracy over Raw inference by 6.55–20.05 percentage points, with FAR of 0.00–1.26% and MAR of 0.20–5.06%.

These results indicate that max-based temporal aggregation can improve cross-location diagnostic reliability while suppressing false and missed alarms without target-location training data or additional training-time adaptation under the present experimental setting. This work was supported by the Technology Innovation Program (RS-2024-00508462, Development of High Power Efficiency Smart Gate Drivers and AI-Based Irregular Fault Detection Technology) funded by the Ministry of Trade, Industry and Resources (MOTIR, Korea). Department of Advanced Robotics, University of Science and Technology (UST), Daejeon, Republic of Korea Department of Robot Applications, Korea Institute of Machinery and Materials (KIMM), Daegu, Republic of Korea Donggyu Youn, Deokgi Jeung, Minki Sin, Subin Joo, Hyukjin Lee, Bohyun Ahn & Jang Ho Cho Department of Diagnostic Sensors, Korea Institute of Machinery and Materials (KIMM), Daegu, Republic of Korea J.H.C., D.Y., D.J., M.S., S.J., H.L., B.A., and K.-H.L. are named inventors on pending Korean patent application No. 10-2026-0153570, entitled “SYSTEM FOR FAULT DIAGNOSIS OF DRIVE MODULE AND METHOD FOR FAULT DIAGNOSIS USING THE SAME,” filed by Korea Institute of Machinery and Materials (KIMM), which is related to the fault-diagnosis technology described in this manuscript.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material.

If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. Youn, D., Lee, YJ., Jeung, D. et al.

Temporal max pooling for robust multi-class fault diagnosis of PMSM-based drive modules at unseen sensor locations. Sci Rep (2026). https://doi.org/10.1038/s41598-026-73197-0 DOI: https://doi.org/10.1038/s41598-026-73197-0