基于GWO-LSSVM的直流故障电弧诊断方法  

DC Fault Arc Diagnosis Method Based on GWO-LSSVM

作　　者：刘树鑫 刘丙泽 邢朝建 明欣 周厚霖 吕先锋 LIU Shuxin;LIU Bingze;XING Zhaojian;MING Xin;ZHOU Houlin;LU Xianfeng(Key Lab of Special Electric Machines and High Voltage Appliances(Shenyang University of Technology),Shenyang 110870,China)

机构地区：[1]特种电机与高压电器教育部重点实验室(沈阳工业大学),辽宁沈阳110870

出　　处：《电器与能效管理技术》2025年第1期14-22,共9页Electrical & Energy Management Technology

基　　金：辽宁省科技重大专项(2020JH1/10100012);国网科技项目(5100-202113396A-0-0-00)。

摘　　要：针对直流故障电弧在不同工况下识别准确率不高的问题,提出基于灰狼优化算法的最小二乘支持向量机(GWO-LSSVM)对多负载工况下的直流电弧进行故障诊断。首先,应用改进的自适应噪声完备集合经验模态分解(ICEEMDAN),对参考高铁站混合负载得到的不同工况下直流电弧电流信号进行本征模态函数(IMF)分解。其次,进行筛选得到相关分量,结合多尺度排列熵(MPE)构造特征向量。最后,针对诊断模型的收敛速度较慢及模型倾向于陷入局部最优解的问题,应用GWO算法优化的LSSVM模型进行故障状态的识别。实验结果表明,准确率达到98.33%。通过与其他算法对比,证实所提方法的高效性。In order to solve the problem that the identification accuracy of DC arc faults is not high under different working conditions,a gray wolf optimization least squares support vector machine(GWO-LSSVM)is proposed to diagnose DC arc under multi-load conditions.Firstly,the improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN)is applied to perform the intrinsic mode function(IMF)decomposition on the DC arc current signals obtained from the mixed load of the reference high-speed railway station under the different operating conditions.Secondly,the relevant components are screened and combined with multi-scale permutation entropy(MPE)to construct the feature vectors.Finally,in response to the slow convergence speed of the diagnostic model and the tendency of the model to fall into the local optima,the LSSVM model optimized by GWO is applied for the fault state recognition.The experimental results show that the accuracy reaches 98.33%.By comparing with other algorithms,the efficiency of the proposed method has been confirmed.

关 键 词：直流故障电弧 多尺度排列熵 灰狼优化算法 故障诊断 

分 类 号：TM501.2[电气工程—电器]