Mechanical Fault Diagnosis of High Voltage Circuit Breakers Utilizing VMD and Optimal SVM Classifier

Mechanical fault diagnosis of high voltage circuit breakers (HVCBs) based on vibration signal analysis is one of the most significant issues in improving the reliability and reducing the outage cost for power systems. This paper proposes a fault diagnosis method based on the combination of variational mode decomposition (VMD) and the grid search (GS) optimization support vector machine (SVM). Firstly, the original multi-component vibration signal is decomposed into a set of single-component intrinsic mode functions (IMFs) by using VMD. Secondly, the feature entropy vector is calculated by combining the Hilbert transform and information entropy. Finally, based on the k-fold cross-validation (K-CV), GS was applied to seek for the optimal internal parameters of the SVM classifier. Compared with the traditional fault diagnosis method, the model method of VMD-GS-SVM has obvious advantages, which improves the precision of mechanical fault diagnosis and the universality of application.