基于麻雀搜索算法优化概率神经网络的变压器故障诊断

Fault Diagnosis of Transformer Based on Probabilistic Neural Network Optimized by Sparrow Search Algorithm

针对依照经验选取平滑因子导致概率神经网络模型故障诊断正确率不高的问题,提出了一种基于麻雀搜索算法优化概率神经网络(PNN)的变压器故障诊断方法。该方法引入麻雀搜索算法来优化概率神经网络中的平滑因子,然后将优化得到的平滑因子赋给PNN,从而得到优化后的变压器故障诊断模型。仿真结果表明,与优化前的PNN网络及PSO-PNN网络相比,所提方法具有更高的故障诊断准确率,适用于变压器故障诊断。

Aiming at the problem that the probabilistic neural network model's fault diagnosis accuracy is not high due to the selection of smoothing factors according to experience,a transformer fault diagnosis method based on probabilistic neural network(PNN)optimized by sparrow search algorithm is proposed.The sparrow search algorithm is introduced to optimize the smoothing factor in the probabilistic neural network,and then the smoothing factor is assigned to PNN to obtain the optimized transformer fault diagnosis model.The simulation results show that compared with the PNN network before optimization and PSO-PNN network,the proposed method has higher fault diagnosis accuracy and is suitable for transformer fault diagnosis.