High-voltage circuit breaker fault diagnosis method based on improved BP neural network

Abstract

The invention discloses a high-voltage circuit breaker fault diagnosis method based on an improved BP neural network. The method specifically comprises the steps of classifying collected samples, withclass tags, of a high-voltage circuit breaker into training samples and test samples, then building a BP neural network model based on a breeding algorithm and a particle swarm optimization algorithm, and after the training samples are used for performing training, performing decoding to generate new connection weight and threshold value; performing control by applying an iteration controller, enabling the two algorithms to carry out information interaction every multiple generations, and obtaining an optimal global parameter, wherein contents of the information interaction is relevant information of an optimal particle seed; and decoding an obtained global optimal solution, replacing all weight value and threshold value parameters of an original BP neural network, building an optimized high-voltage circuit breaker fault model, performing fault classification on the test samples, and outputting a result. According to the method, the BA and PSO algorithms are used for replacing an error back propagation-based network learning process to optimize the connection weight and the threshold value of the BP neural network, so that the fault diagnosis precision is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis methods for high-voltage circuit breakers, and relates to a fault diagnosis method for high-voltage circuit breakers based on an improved BP neural network. Background technique [0002] The high-voltage circuit breaker plays a dual role of control and protection in the distribution network system, and its operating status directly determines the operation of the entire power system. Therefore, it is of great significance to carry out fault diagnosis on high voltage circuit breakers. A variety of diagnostic methods have been proposed, which involve various artificial intelligence algorithms, such as: fuzzy control and radial basis neural network. Among them, fuzzy control can use precise mathematical tools to clarify fuzzy concepts or natural language, but there are certain human factors in the determination process of its membership function and fuzzy rules; radial basis neural network p...

AI Technical Summary

Problems solved by technology

But there are also disadvantages such as easy to fall into local minimum and slow network convergence.

Images