NMEKNet: noise-robust open-set condition recognition for industrial pump units under limited samples
- 1 October 2026
- journal article
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (19) , 195512
Abstract
Industrial pump units require condition recognition models that remain reliable under measurement noise and can reject health states that are not observed during training. Existing methods usually focus on noise-robust feature extraction, limited-sample classification, or unknown-state detection separately, leaving their joint interaction insufficiently explored. This paper proposes NMEKNet, a noise-robust open-set condition recognition framework for industrial pump units under limited samples. The feature extractor employs a multi-scale depthwise residual convolutional neural network, in which parallel depthwise separable convolutions and residual fusion capture short impact transients, modulation patterns, and wider temporal variations from multi-channel vibration segments. To improve robustness to controlled signal-to-noise ratio (SNR)-induced noise variation, online signal-to-noise-ratio jitter and Noise-domain MixStyle expose the network to input perturbations and feature-statistic shifts during training. For open-set recognition, a known-only calibrated Energy-kNN scoring rule combines classifier energy with feature-neighbour distance to integrate global classifier evidence and local feature-manifold support. Experiments on the Royal Netherlands Navy Electric Pump test bench and a self-built laboratory pump-loop platform under few-shot and controlled low-SNR settings show that NMEKNet provides stable known-state recognition and effective unknown-state rejection. Sensitivity and cross-SNR calibration analyses further demonstrate the robustness of the main parameter settings while revealing the limitations of transferring a fixed threshold across severe noise shifts. The results indicate that multi-scale representation learning, noise-domain regularisation, and validation-calibrated Energy-kNN scoring are suitable for controlled industrial pump-unit monitoring, while validation under non-Gaussian interference and broader field conditions remains future work.Keywords
Funding Information
- National Natural Science Foundation of China (52172367)
This publication has 35 references indexed in Scilit:
- Spatial-channel collaborative multi-scale graph interaction deep transfer learning for unsupervised rotating machinery fault diagnosisEngineering Applications of Artificial Intelligence, 2026
- Domain generalization for rotating machinery fault diagnosis: A surveyAdvanced Engineering Informatics, 2024
- Few-shot fault diagnosis for machinery using multi-scale perception multi-level feature fusion image quadrant entropyAdvanced Engineering Informatics, 2024
- Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and BenchmarksInternational Journal of Computer Vision, 2024
- A systematic literature review of deep learning for vibration-based fault diagnosis of critical rotating machinery: Limitations and challengesJournal of Sound and Vibration, 2024
- Motor current and vibration monitoring dataset for various faults in an E-motor-driven centrifugal pumpData in Brief, 2023
- Cross-domain open-set fault diagnosis using prototype learning and extreme value theoryApplied Acoustics, 2023
- LiConvFormer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attentionExpert Systems with Applications, 2023
- Few-shot fault diagnosis of rolling bearing under variable working conditions based on ensemble meta-learningDigital Signal Processing, 2022
- Recent advances in the application of deep learning for fault diagnosis of rotating machinery using vibration signalsArtificial Intelligence Review, 2022