Neural Factorization-based Bearing Fault Diagnosis

TL;DR

The paper tackles bearing fault diagnosis in high-speed trains where traditional methods struggle under complex conditions. It introduces a Neural Factorization-based Classification (NFC) framework that embeds time-series data into mode-specific latent features and fuses them via CP or Tucker tensor factorizations for end-to-end learning from raw signals. Two instantiations, CP-NFC and Tucker-NFC, are proposed, with empirical results on the CWRU bearing dataset showing Tucker-NFC achieving top performance and outperforming traditional methods. The work provides practical guidance for diagnostic strategy selection and offers a scalable, parameter-efficient approach for industrial bearing monitoring.

Abstract

This paper studies the key problems of bearing fault diagnosis of high-speed train. As the core component of the train operation system, the health of bearings is directly related to the safety of train operation. The traditional diagnostic methods are facing the challenge of insufficient diagnostic accuracy under complex conditions. To solve these problems, we propose a novel Neural Factorization-based Classification (NFC) framework for bearing fault diagnosis. It is built on two core idea: 1) Embedding vibration time series into multiple mode-wise latent feature vectors to capture diverse fault-related patterns; 2) Leveraging neural factorization principles to fuse these vectors into a unified vibration representation. This design enables effective mining of complex latent fault characteristics from raw time-series data. We further instantiate the framework with two models CP-NFC and Tucker-NFC based on CP and Tucker fusion schemes, respectively. Experimental results show that both models achieve superior diagnostic performance compared with traditional machine learning methods. The comparative analysis provides valuable empirical evidence and practical guidance for selecting effective diagnostic strategies in high-speed train bearing monitoring.

Figures (2)

• Figure 1: An illustration example of the proposed classification framework. The time series input is embedded into two different mode feature space.
• Figure 2: CP-based and TD-based Feature Fusion Schemes.