To address the problem of mechanical defect identification in a high-voltage circuit breaker (HVCB), this paper studies the circuit breaker vibration signal and proposes a method of feature extraction based on phase-space reconstruction of the vibration substages. To locate mechanical defects in circuit breakers, vibration signals are divided into different substages according to the time sequence of the parts of the circuit breakers. The largest Lyapunov exponent (LLE) of the vibration signals’ substages is calculated, and then the substages are reconstructed in high-dimensional phase space. The geometric features of the phase trajectory mean center distance (MCD) and vector diameter offset (VDO) are calculated, and the LLE, MCD, and VDO are selected as the three fault identification features of the vibration substages. The eigenvalue anomaly rate of each substage of the vibration signal under defect state are calculated and analyzed to locate the vibration substage of the mechanical defect. Finally, a fault diagnosis model is constructed by a support vector machine (SVM), and the common mechanical defects of circuit breakers simulated in the laboratory are effectively identified.

In response to the lack of generality in feature extraction using modal decomposition methods and the susceptibility of diagnostic performance to parameter selection in traditional mechanical fault diagnosis of high-voltage circuit breaker operating mechanisms, this paper proposes a Global-Local feature extraction method based on Generalized S-Transform (S-Translate) combined with Gray Level Co-Occurrence Matrix (GLCM) and complemented by Maximum Relevance and Minimum Redundancy (mRMR) feature selection. The GL (Global-Local)-mRMR-KELM fault diagnosis model is proposed, which employs the Kernel Extreme Learning Machine (KELM). In this model, the original time-frequency domain features and the time-frequency features of the Generalized S-Transform matrix of vibration signals under different states of the circuit breaker are first extracted as global features. Then, the GLCM is obtained to extract texture features as local features. Finally, the mRMR and KELM are comprehensively applied to perform feature selection and classification on the dataset, thereby accomplishing the fault diagnosis of the circuit breaker’s operating mechanism. In this study, the 72.5 kV SF₆ circuit breaker operating mechanism is taken as the research object, and three types of mechanical faults are simulated to obtain a vibration signal. Experimental results verify the effectiveness of the proposed GL-mRMR-KELM model, achieving a diagnostic accuracy of 96%. This research provides a feasible approach for the fault diagnosis of circuit breaker operating mechanisms.