Transformer fault diagnosis method and system based on neural network

Abstract

The invention discloses a transformer fault diagnosis method and system based on a neural network, and the method comprises the steps: taking a transformer fault diagnosis result as a target object, carrying out the coding of the target object, setting an initial cluster, and eliminating and updating a new group; selecting an error function calculated each time as a fitness function, initially calculating a fitness population of each population, selecting a new population and eliminating an old population; genetic operators are selected according to the probability, operator selection, crossover operators and mutation operators are carried out in sequence, and a fault diagnosis result is generated. According to the invention, intelligent diagnosis of the fault type and the fault degree of the transformer can be realized, diagnosis of the fault of the transformer is facilitated, and the method has an effective guiding effect on engineering practice.

Description

technical field [0001] The invention belongs to the technical field of transformer fault diagnosis, and in particular relates to a transformer fault diagnosis method and system based on a neural network. Background technique [0002] In the past fault diagnosis of transformers, the coded form of characteristic gas is generally used for fault type diagnosis, and the results are reliable. However, based on the characteristics of the coded ratio operation itself, due to the ambiguity of the fault data itself, the gas content ratio is in the When coding the corresponding boundary of the rule, misjudgment is easy to occur, and the conclusion corresponding to the faulty gas can often not be manually corrected, so there will be a diagnosis error. Therefore, the ability of fault diagnosis to deal with uncertainty is required. The artificial neural network forms a self-learning and adaptive dynamic system by imitating the structure and function of the human brain, adapts to the exte...

AI Technical Summary

Problems solved by technology

[0002] In the previous fault diagnosis of transformers, the coded form of the characteristic gas was generally used to diagnose the fault type after processing, and the result was reliable. However, based on the characteristics of the coded ratio operation itself, due to the ambiguity of the fault data itself, the gas content ratio is in the range of When the corresponding boundaries of the coding rules are used, misjudgments are prone to occur, and the corresponding faulty gas conclusions often cannot be manually corrected, so there will be diagnostic errors

Images