An Advanced Convolutional Neural Network for Bearing Fault Diagnosis under Limited Data

2025-09-13

AI Summary

To address the performance limitation of few-shot bearing fault diagnosis methods caused by scarce high-quality labeled data, this paper proposes an end-to-end few-shot diagnostic framework integrating generative augmentation with contrastive Fourier convolution. Methodologically, it introduces (1) a Conditional Contrastive Latent Reconstruction GAN (CCLR-GAN) that synthesizes high-fidelity, diverse fault vibration samples while mitigating mode collapse; (2) a conditional consistency-based latent space reconstruction coupled with contrastive learning to explicitly model semantic relationships among limited samples; and (3) a 1D Fourier Convolutional Neural Network (1D-FCNN) that overcomes the local receptive field constraint of conventional CNNs, thereby enhancing global frequency-domain feature perception. Experimental results demonstrate absolute accuracy improvements of 32% on the CWRU dataset and 10% on a custom-built experimental rig, with ablation studies confirming the effectiveness of each component.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Feature Construction/Reformulation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

In the area of bearing fault diagnosis, deep learning (DL) methods have been widely used recently. However, due to the high cost or privacy concerns, high-quality labeled data are scarce in real world scenarios. While few-shot learning has shown promise in addressing data scarcity, existing methods still face significant limitations in this domain. Traditional data augmentation techniques often suffer from mode collapse and generate low-quality samples that fail to capture the diversity of bearing fault patterns. Moreover, conventional convolutional neural networks (CNNs) with local receptive fields makes them inadequate for extracting global features from complex vibration signals. Additionally, existing methods fail to model the intricate relationships between limited training samples. To solve these problems, we propose an advanced data augmentation and contrastive fourier convolution framework (DAC-FCF) for bearing fault diagnosis under limited data. Firstly, a novel conditional consistent latent representation and reconstruction generative adversarial network (CCLR-GAN) is proposed to generate more diverse data. Secondly, a contrastive learning based joint optimization mechanism is utilized to better model the relations between the available training data. Finally, we propose a 1D fourier convolution neural network (1D-FCNN) to achieve a global-aware of the input data. Experiments demonstrate that DAC-FCF achieves significant improvements, outperforming baselines by up to 32% on case western reserve university (CWRU) dataset and 10% on a self-collected test bench. Extensive ablation experiments prove the effectiveness of the proposed components. Thus, the proposed DAC-FCF offers a promising solution for bearing fault diagnosis under limited data.

Problem

• Addressing data scarcity in bearing fault diagnosis
• Overcoming mode collapse in data augmentation techniques
• Extracting global features from complex vibration signals

Innovation

• Conditional GAN generates diverse fault data
• Contrastive learning models sample relationships
• 1D Fourier CNN extracts global features