多策略改进蜉蝣算法在变压器故障诊断中的应用

Application of Multi-strategy Improved Mayfly Algorithm in Transformer Fault Diagnosis

为提高支持向量机在变压器故障诊断的准确率,提出了一种多策略改进蜉蝣算法优化支持向量机的故障诊断方法,并通过利用螺旋函数、正余弦自适应权重优化改进后的蜉蝣算法,得到支持向量的最佳参数c和g。通过3个测试函数对改进后的算法进行仿真对比,实验表明改进后的算法具有较高的寻优精度和较快的收敛速度。将提出的故障诊断方法运用到实际DGA故障数据中,结果表明该方法能有效提高变压器故障诊断的准确率和缩短运行时间。

In order to improve the accuracy of support vector machine in transformer fault diagnosis,a multi-strategy improved mayfly algorithm is proposed to optimize the support vector machine for fault diagnosis,and the optimal parameters of support vectors c and g are obtained by optimizing the improved may fly algorithm by using the spiral function,positive cosine adaptive weights.The improved algorithm is simulated and compared with three test functions,and the experiments show that the improved algorithm has high optimization accuracy and faster convergence speed.The fault diagnosis method proposed in this paper is applied to the actual DGA fault data,and the results show that the method can effectively improve the accuracy of transformer fault diagnosis and shorten the operation time.