基于差分进化算法优化模糊Petri网的电力变压器故障诊断

摘要

In order to improve the accuracy of power transformer fault diagnosis, a transformer fault diagnosis algorithm based on Fuzzy Petri nets which is optimized by differential evolution algorithm is proposed. In order to overcome the shortcomings of adaptive and self-learning ability of fuzzy Petri nets and determine the parameters of fuzzy Petri nets effectively, an improved difference optimization algorithm is introduced. The differential evolution algorithm uses the chaotic optimization initial value and the weight, threshold and credibility parameters of the fuzzy Petri net are optimized through the three processes of mutation, intersection and selection. The premature disturbance is added in the later stage of optimization, and the optimized model is used for fault diagnosis of power transformers. The analysis of the example shows that compared with the existing methods, the accuracy of the algorithm is obviously improved, and the parameter optimization convergence speed is faster, which has certain application value in practical engineering.%为提高电力变压器故障诊断的准确率,提出了一种基于差分进化算法优化模糊Petri网的变压器故障诊断算法.该算法为消除模糊Petri网存在自适应和自学习能力差的缺点,有效地确定模糊Petri网的各项参数值,引入了改进的差分优化算法.差分进化算法使用混沌优化初始值,通过变异、交叉、选择3个过程对模糊Petri网的权值、阈值和可信度参数进行优化,并在优化后期加入了早熟扰动,使用优化后的模型对电力变压器进行故障诊断.通过算例分析表明,该算法与现有方法相比,准确率有明显提高,且参数优化收敛速度较快,在实际工程中具有一定的应用价值.