基于IPOA-LSSVM模型的高压直流输电线路故障定位  

Fault location of HVDC transmission line via IPOA-LSSVM model

作　　者：商立群[1] 刘晗 郝天奇 李钊 李朝彪 邓力文 SHANG Liqun;LIU Han;HAO Tianqi;LI Zhao;LI Chaobiao;DENG Liwen(College of Electrical and Control Engineering,Xi'an University of Science and Technology,Xi'an 710054,China)

机构地区：[1]西安科技大学电气与控制工程学院,西安710054

出　　处：《南京信息工程大学学报》2024年第5期667-677,共11页Journal of Nanjing University of Information Science & Technology

基　　金：陕西省自然科学基础研究计划(2021JM-393)。

摘　　要：故障定位在长距离高压直流输电系统中起着至关重要的作用.针对线路衰减系数计算不准和二次波头难以捕捉的问题,提出了一种改进鹈鹕优化算法(IPOA)优化最小二乘支持向量(LSSVM)的故障定位模型.根据行波衰减原理,推导故障距离和线路两端线模分量模极大值比的计算公式,发现二者具有非线性关系.使用LSSVM泛化二者之间的关系,将改进后的POA算法对LSSVM的关键参数进行寻优,建立IPOA-LSSVM故障定位模型.通过在两端采集故障信号,对其进行小波变换得到首波头幅值比作为模型的输入量,故障距离作为输出量进行仿真验证.仿真结果表明,该模型不受过渡电阻和故障类型的影响,能够可靠准确地定位.Fault location is crucial for the long-distance HVDC transmission systems.Here,a fault location model using the Improved Pelican Optimization Algorithm(IPOA)to optimize the Least Squares Support Vector Machine(LSSVM)is provided to address the issues of imprecise attenuation coefficient computation and challenging second-ary wave head capture.First,in accordance with the traveling wave attenuation concept,the formulas of the fault dis-tance and the modulus maximum ratio of the line mode components at both ends of the line are derived,revealing a nonlinear relationship between them,which is then generalized by LSSVM.Second,the IPOA is employed to optimize the key parameters of LSSVM,thereby constructing the IPOA-LSSVM fault location model.After performing wavelet transform on the fault signals collected at both ends,the amplitude ratio of the first wave head is obtained and then input into the proposed model to output the fault distance as simulation verification.Simulation results show that the proposed model can locate fault reliably and accurately regardless of transition resistance and fault type.

关 键 词：故障定位 高压直流输电系统 首波头幅值比 改进鹈鹕优化算法 最小二乘支持向量机 

分 类 号：TM755[电气工程—电力系统及自动化]