Toward End-to-End Bearing Fault Diagnosis for Industrial Scenarios with Spiking Neural Networks

2024-08-17

arXiv.org

AI Summary

Existing spiking neural network (SNN)-based bearing fault diagnosis methods suffer from weak encoding capability, heavy reliance on manual preprocessing, and performance limitations imposed by non-spiking-oriented architectures. To address these issues, this paper proposes an end-to-end multi-scale residual attention SNN framework. The method processes raw vibration signals directly—eliminating handcrafted feature extraction and complex preprocessing. It innovatively integrates a lightweight attention mechanism both into the encoding module and within spiking neurons themselves, biologically emulating dendritic filtering to enable interpretable multi-scale temporal modeling. Evaluated on the MFPT and JNU datasets, the framework achieves significantly improved diagnostic accuracy, reduces energy consumption by over 42%, and maintains robust accuracy above 96.5% under strong noise conditions. It thus delivers high accuracy, ultra-low power consumption, and exceptional noise robustness—demonstrating strong potential for industrial edge deployment.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Spiking neural networks (SNNs) transmit information via low-power binary spikes and have received widespread attention in areas such as computer vision and reinforcement learning. However, there have been very few explorations of SNNs in more practical industrial scenarios. In this paper, we focus on the application of SNNs in bearing fault diagnosis to facilitate the integration of high-performance AI algorithms and real-world industries. In particular, we identify two key limitations of existing SNN fault diagnosis methods: inadequate encoding capacity that necessitates cumbersome data preprocessing, and non-spike-oriented architectures that constrain the performance of SNNs. To alleviate these problems, we propose a Multi-scale Residual Attention SNN (MRA-SNN) to simultaneously improve the efficiency, performance, and robustness of SNN methods. By incorporating a lightweight attention mechanism, we have designed a multi-scale attention encoding module to extract multiscale fault features from vibration signals and encode them as spatio-temporal spikes, eliminating the need for complicated preprocessing. Then, the spike residual attention block extracts high-dimensional fault features and enhances the expressiveness of sparse spikes with the attention mechanism for end-to-end diagnosis. In addition, the performance and robustness of MRA-SNN is further enhanced by introducing the lightweight attention mechanism within the spiking neurons to simulate the biological dendritic filtering effect. Extensive experiments on MFPT and JNU benchmark datasets demonstrate that MRA-SNN significantly outperforms existing methods in terms of accuracy, energy consumption and noise robustness, and is more feasible for deployment in real-world industrial scenarios.

Problem

• Enhancing SNN efficiency for bearing fault diagnosis
• Eliminating complex preprocessing in fault feature extraction
• Improving robustness and accuracy in industrial applications

Innovation

• Multi-scale Residual Attention SNN for fault diagnosis
• Lightweight attention mechanism for efficient feature encoding
• Spiking neurons with dendritic filtering for robustness