The reliable storage of spring potential energy is a prerequisite for ensuring the correct closing and opening operations of a circuit breaker. A fault identification method for circuit breaker energy storage mechanism, combined with the current-vibration signal entropy weight characteristic and grey wolf optimization-support vector machine (GWO-SVM), is proposed by analyzing the energy conversion and transmission relationship between control loop, motor, transmission component, and spring. First, the current envelope is denoised in the modulus maxima wavelet domain, the time-domain feature is extracted via a Hilbert transform (HT), and the kurtosis is calculated. Second, the energy method is used to select K parameters, the objective function optimization method is used to select α for variational mode decomposition (VMD), the intrinsic mode function (IMF) is obtained by decomposing the vibration signal with VMD and the permutation entropy characteristics of IMFs are extracted. Third, the characteristic of current and vibration signals for classification are edited by the entropy weight method, and the corresponding weights are provided in accordance with the sample information amount and importance. Finally, the currentvibration entropy weight characteristics are constructed and sent to the SVM model for learning and training. The GWO algorithm is used to optimize the parameters of the SVM model based on the mixed kernel function, which reduces adverse effects from the model parameters' choice of circuit breaker fault diagnosis. The results show that the overall diagnostic accuracy for the experimental samples reaches 100% and has good generalization capability based on the current-vibration entropy weight characteristic and the GWO-SVM method. INDEX TERMS Current-vibration, entropy weight characteristic, grey wolf optimization-support vector machine (GWO-SVM), variational mode decomposition (VMD).

Aiming at the problem that some traditional high voltage circuit breaker fault diagnosis methods were over-dependent on subjective experience, the accuracy was not very high and the generalization ability was poor, a fault diagnosis method for energy storage mechanism of high voltage circuit breaker, which based on Convolutional Neural Network (CNN) characteristic matrix constructed by sound-vibration signal ,was proposed. In this paper, firstly, the morphological filtering was used for background noise cancellation of sound signal, and the time scale alignment method based on kurtosis and envelope similarity were proposed to ensure the synchronism of the sound-vibration signal. Secondly, the Pearson correlation coefficient was used to construct two-dimensional image characteristic matrix for the expanded sound-vibration signal. Finally, the characteristic matrix was trained by utilizing CNN. Local Response Normalization (LRN) and core function decorrelation were utilized to improve the structure of CNN model, which reduced the bad impact of large data fluctuation of energy storage process on the diagnostic accuracy of circuit breaker energy storage mechanism. Compared with the traditional method, the proposed method has obvious advantages, whose total accurate rate up to 98.2 % and generalization performance is excellent.

No abstract

The vibration signals generated by the transmission and impact of circuit breaker mechanical components have chaotic characteristics and using conventional signal processing method is difficult to distinguish the abnormal operation process quickly and accurately. Based on the mutual information method and the Cao algorithm, the delay time and the embedding dimension of the phase space reconstruction parameters are calculated and optimized according to the chaotic characteristics of the vibration signals. The singular value order energy (SVOE) and the singular value energy entropy (SVEE) are obtained by decomposing the phase space reconstruction matrix, which is determined by the optimal phase space reconstruction parameters, and the support vector machines (SVM) are used to identify the states of the circuit breaker in operation. The experimental results show that the combination phase space reconstruction and singular value decomposition (PSR-SVD) can accurately extract the characteristics of the vibration signal of the circuit breaker, and the genetic algorithm (GA)-improved SVM can quickly and effectively identify the circuit breaker defect types, which solves the problems of path distortions, energy leaks, modal aliasing, and lack of samples in existing diagnostic methods.