Skip to main navigation Skip to search Skip to main content

Mechanism-Aware Low-Rank Sparse Neural Unrolling for Incipient Bearing Anomaly Detection

  • Yunpeng Liu
  • , Hongkai Jiang
  • , Wenxin Jiang
  • , Zhenning Li
  • , Enrico Zio
  • Northwestern Polytechnical University Xian
  • Polytechnic University of Milan
  • Tsinghua University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Intelligent anomaly detection with deep learning is promising for mechanical systems. However, it is struggling due to its 'black-box' issue and opacity. Model-driven sparse representation provides a clearer physical meaning, whereas its parameters and threshold operators are usually tuned manually and are sensitive to industrial noise. In this paper, a mechanismaware low-rank sparse unrolling network (LRSU-Net) is proposed for incipient bearing anomaly detection. Firstly, vibration signals are formulated with low-rank and sparse components, where stationary operating backgrounds and transient fault impulses are considered separately. Based on this formulation, the iterative optimization process is unrolled into a feed-forward network via the half quadratic splitting algorithm. Secondly, a low-rank estimation module is designed to suppress periodic operational components and provide a cleaner residual space for weak impulse extraction. Thirdly, an adaptive convex proximal network is constructed to learn the sparse estimation operator. It preserves the adaptive ability of non-convex sparse regularization while keeping the convexity of proximal mapping. The proposed method is validated on the NASA IMS bearing run-to-failure dataset. Experimental results indicate that LRSU-Net improves incipient anomaly detection under strong interference. Moreover, the reconstructed sparse components are consistent with fault characteristic frequencies.

Original languageEnglish
Title of host publication2026 the 8th International Conference on System Reliability and Safety Engineering, SRSE 2026
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages214-220
Number of pages7
ISBN (Electronic)9798319515704
DOIs
StatePublished - 2026
Event8th International Conference on System Reliability and Safety Engineering, SRSE 2026 - Xi'an, China
Duration: 7 Aug 2026 → 10 Aug 2026

Publication series

Name2026 the 8th International Conference on System Reliability and Safety Engineering, SRSE 2026

Conference

Conference8th International Conference on System Reliability and Safety Engineering, SRSE 2026
Country/TerritoryChina
CityXi'an
Period7/08/26 → 10/08/26

Keywords

  • algorithm unrolling
  • incipient bearing anomaly detection
  • low-rank sparse unrolling network
  • sparse representation

Fingerprint

Dive into the research topics of 'Mechanism-Aware Low-Rank Sparse Neural Unrolling for Incipient Bearing Anomaly Detection'. Together they form a unique fingerprint.

Cite this