Quantitative Evaluation of Mechanical Defects for Circuit Breakers Based on Self‐Adaptive Fault Feature Tracking

ABSTRACT Many researchers are committed to improving the diagnosis accuracy and solving the few‐shot problem on circuit breakers (CBs). However, the research on the vibration transmission mechanism of the fault is insufficient, which makes it difficult to find the potential design defects of CBs through vibration. This study proposes a quantitative evaluation method of mechanical defects, which can track and quantify mechanical defects caused by faults adaptively. The fault feature tracking based on ResNet‐SHAP can locate the fault feature area in the time–frequency domain and generate the feature distribution maps of faults. Then, the feature factor F is defined to represent the energy of the fault feature. By weighted allocation and extracting positive F , the mechanical defect feature maps are formed. After time–frequency space reconstruction and contact travel matching, the mechanical defects are traced. Experiments show that the quantitative evaluation of mechanical defects has a strong action sequence and structural correlation, and is expandable to different structures of CBs. In addition, it is found that fault feature tracking can adaptively find latent fault features and has strong stability.