Dynamic weighted hybrid clustering algorithm based circuit breaker fault diagnosis method

Abstract

The invention discloses a dynamic weighted hybrid clustering algorithm based circuit breaker fault diagnosis method. The method includes the following steps: (1) capturing the energy changes of mechanical drive during the operation of a circuit breaker by utilizing three-axis vibration and two-way sound signals, decomposing the signals through local mean, and extracting the approximate entropy ofeach PF component as the characteristic quantity of a circuit breaker vibration signal; (2) optimizing the initialized clustering center of fuzzy kernel clustering by utilizing the maximum density peak decision of a density peak clustering algorithm, and considering different influences of different characteristics and different samples on clustering results; (3) performing checking on a clustering number K through a cluster validity index MIA; (4) inputting correctly classified characteristics into a multi-level classifier of a support vector machine to perform training; and (5) finding the optimal parameter of the support vector machine through mesh generation, and inputting test data samples to perform final fault classification prediction so that classification accuracy rates can be obtained;. The method has advantaged of being fast in fault diagnosis speed and high in accuracy rate.

Description

technical field [0001] The invention belongs to the technical field of electric engineering, and in particular relates to a circuit breaker fault diagnosis method based on a dynamic weighted hybrid clustering algorithm. Background technique [0002] Circuit breaker fault diagnosis technology collects circuit breaker action data, extracts characteristic parameters by means of signal processing, and finally establishes a diagnosis or prediction model by an intelligent algorithm to evaluate the working state of a circuit breaker. With the development of technology, the artificial intelligence algorithm of the circuit breaker has been developed rapidly. [0003] Fuzzy kernel clustering, as a pattern recognition method of unsupervised learning, plays an important role in fault diagnosis. In recent years, among many fuzzy clustering algorithms, kernel fuzzy c means clustering (kernel fuzzy c means, KFCM) is developed from fuzzy c mean clustering (FCM), and the idea of ​​kernel fu...

AI Technical Summary

Problems solved by technology

In recent years, among many fuzzy clustering algorithms, kernel fuzzy c means clustering (kernel fuzzy c means, KFCM) is developed from fuzzy c mean clustering (FCM), and the idea of ​​kernel function is introduced into FCM, which is The most important and one of the most popular algorithms, for the traditional fuzzy kernel mean clustering random selection of the initial clustering center can not obtain the global optimal and easy to produce consistent clustering when the clustering center is close or coincident, there is no difference in treatment The different effects of features on clustering and other issues; therefore, a method is needed to improve the fault diagnosis rate and improve the efficiency of fault diagnosis, and provide a new means for the fault diagnosis method of circuit breakers

Images