基于噪声、边缘与难度感知的多视角轴承故障诊断方法
By constructing a noise-aware multi-scale expansion-gated modulator and a boundary edge-aware module, and combining it with a difficulty-aware clustering-guided reverse distillation strategy, the shortcomings of existing bearing fault diagnosis methods in noise, edge, and difficulty perception are solved, and efficient fault diagnosis in complex environments is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ANHUI UNIV OF SCI & TECH
- Filing Date
- 2025-12-19
- Publication Date
- 2026-07-17
AI Technical Summary
Existing bearing fault diagnosis methods based on two-dimensional time-frequency representation have weak fault pulse discrimination capabilities under noise interference, convolution operations destroy the boundary topology, and lack targeted optimization for both easy and difficult samples, resulting in limited robustness and accuracy of the model in complex industrial environments.
A noise-aware multi-scale dilatation-gated modulator is constructed to enhance noise discrimination capability, a boundary edge sensing module is designed to suppress convolution boundary artifacts, and a difficult-aware clustering-guided retrodistillation strategy is used to optimize easy and difficult samples, forming a multi-view bearing fault diagnosis method (MVPNet).
This technology enhances fault feature discrimination capabilities in high-noise environments, suppresses convolution boundary artifacts, strengthens fault edge response, and optimizes both easy and difficult samples, significantly improving bearing fault diagnosis performance and achieving high accuracy and robustness.
Smart Images
Figure CN121859082B_ABST