一种电机滚动轴承故障诊断方法、装置、介质和设备
By using continuous wavelet transform and deep transfer network in the fault diagnosis of motor rolling bearings, combined with cross-entropy and fast batch kernel norm loss function, the problem of low diagnostic accuracy of deep learning models under different working conditions is solved, and higher fault diagnosis accuracy and generalization ability are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XI AN JIAOTONG UNIV
- Filing Date
- 2024-06-04
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for diagnosing rolling bearing faults in electric motors often suffer from low diagnostic accuracy due to the lack of independent and identically distributed data distributions, which leads to insufficient accuracy in feature extraction and diagnosis.
Continuous wavelet transform is used to extract time-frequency domain features. Combined with a deep transfer network, a fault diagnosis model is trained by using cross-entropy loss and fast batch kernel norm minimization loss function. Fault diagnosis is performed using time-frequency graphs of source domain data and target domain data. A total loss function is constructed to optimize model performance.
It improves the accuracy of the fault diagnosis model, avoids overfitting to source domain data, enhances the predictive diversity and discriminative power of target domain data, and improves the overall accuracy of fault diagnosis for motor rolling bearings.
Smart Images
Figure CN118643387B_ABST