基于小波包奇异谱熵和WOA-SVM的GIS放电故障诊断

GIS Discharge Fault Diagnosis Based on Wavelet Packet Singular Spectral Entropy and WOA-SVM

为实现气体绝缘开关设备(GIS)放电故障诊断并提高诊断正确率,提出了一种基于小波包奇异谱熵和鲸鱼优化算法优化支持向量机(WOA-SVM)的GIS放电故障诊断方法。首先,提取GIS放电时的特高频信号的小波包奇异谱熵作为特征向量;然后,采用WOA寻优找到SVM的最优参数,建立准确的分类模型;最后,通过试验模拟GIS典型的放电故障,采用网格搜索参数的SVM、粒子群优化参数的SVM以及所提的WOA-SVM三种算法对GIS放电故障类型进行识别。结果表明所提的WOA-SVM算法故障识别正确率更高、适应度更好且收敛速度更快。

To achieve fault diagnosis of gas-insulated switchgear(GIS)and improve diagnostic accuracy,this paper proposed a GIS discharge fault diagnosis method based on wavelet packet singular spectrum entropy and whale optimization algorithm optimized support vector machine(WOA-SVM).First,the wavelet packet singular spectrum entropy of the ultra-high frequency signals during GIS discharge was extracted as feature vectors.Then,WOA was used to find the optimal parameters for SVM,establishing an accurate classification model.Finally,experiments simulating typical GIS discharge faults were conducted,and three algorithms-SVM with grid search parameters,SVM with particle swarm optimization,and the proposed WOA-SVM-were applied to identify GIS discharge fault types.The results showed that the proposed WOA-SVM algorithm achieved higher fault identification accuracy,better fitness,and faster convergence.