FEMSN: Frequency-Enhanced Multiscale Network for fault diagnosis of rotating machinery under strong noise environments

2025-05-07

AI Summary

To address the challenges of bearing fault feature extraction under strong noise and inaccurate health state assessment in rotating machinery, this paper proposes a frequency-domain enhanced multi-scale CNN model. Methodologically, it introduces three key innovations: (1) a novel Fourier Adaptive Denoising Encoding Layer (FADEL) for adaptive frequency-domain filtering and noise suppression; (2) a Multi-Scale Time-Frequency Fusion (MSTFF) module coupled with a temporal-spectral feature co-enhancement mechanism; and (3) a receptive field expansion distillation layer to improve discriminative feature robustness. The model adopts a lightweight end-to-end architecture. Evaluated on two real-world bearing datasets under strong noise conditions, it achieves an average diagnostic accuracy 4.2% higher than state-of-the-art methods while reducing parameter count by 37%. These results demonstrate both superior accuracy and practical feasibility for industrial deployment.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Rolling bearings are critical components of rotating machinery, and their proper functioning is essential for industrial production. Most existing condition monitoring methods focus on extracting discriminative features from time-domain signals to assess bearing health status. However, under complex operating conditions, periodic impulsive characteristics related to fault information are often obscured by noise interference. Consequently, existing approaches struggle to learn distinctive fault-related features in such scenarios. To address this issue, this paper proposes a novel CNN-based model named FEMSN. Specifically, a Fourier Adaptive Denoising Encoder Layer (FADEL) is introduced as an input denoising layer to enhance key features while filtering out irrelevant information. Subsequently, a Multiscale Time-Frequency Fusion (MSTFF) module is employed to extract fused time-frequency features, further improving the model robustness and nonlinear representation capability. Additionally, a distillation layer is incorporated to expand the receptive field. Based on these advancements, a novel deep lightweight CNN model, termed the Frequency-Enhanced Multiscale Network (FEMSN), is developed. The effectiveness of FEMSN and FADEL in machine health monitoring and stability assessment is validated through two case studies.

Problem

• Diagnose rotating machinery faults in noisy environments
• Extract fault features obscured by noise interference
• Improve robustness of bearing health monitoring methods

Innovation

• Fourier Adaptive Denoising Encoder Layer for noise filtering
• Multiscale Time-Frequency Fusion module for feature extraction
• Distillation layer to expand receptive field