基于改进粒子群优化神经网络的电力变压器故障诊断

为了提高电力变压器故障诊断的准确性,采用了一种自适应变异粒子群优化神经网络的方法,用于BP网络的权值优化。并根据变压器的故障特征,用优化好的BP网络进行故障诊断。该算法修正了粒子个体行动,克服了标准粒子群和BP网络易陷入局部极小的问题。实例仿真结果表明,该方法具有较好的分类效果,具有一定的实用性。

Power Transformer Fault Diagnosis Based on Neural Networks with Improved Particle Swarm Optimization

In order to improve the accuracy of fault diagnosis of power transformer,a method of neural networks optimized by adaptive mutation particle swarm optimization(AMPSO) is adopted,in which the improved PSO is combined with the BP algorithm to optimize the weight of BP neural network.According to transformer fault feature,the fault diagnosis is accomplished via the optimized neural network.This algorithm amends individual particle’s act,and overcomes the problem that the basic PSO and BP network are vulnerable to local minima.Simulation results show that the method is of better classification effectiveness and practicality.