摘要
现有双端输电线路故障测距方法或依赖于线路模型和线路参数,亦或依赖于大量历史故障数据。为了解决上述问题,该文首先分析总结了分布参数模型和Π型线路模型的测距原理,根据线路故障前后的两端正序电压和正序电流构造了双端输电线路的测距函数;然后在此基础上提出了一种基于人工神经网络与网络迁移的双端输电线路非同步故障测距算法,所提算法不依赖于线路模型和线路参数;最后在Matlab/Simulink平台上搭建了500kV输电线路仿真模型,验证了所提算法的正确性和可靠性。理论分析和仿真结果表明,所提算法测距精度高,且不受故障位置、故障类型、过渡电阻、故障初相角、负荷电流以及非同步数据等因素的影响。此外,所提算法基于网络迁移思想充分利用了线路的大量正常数据和少量故障数据,在线路参数变化不超过±1%时仍有较高的测距精度。
The current algorithms of the two-terminal transmission line fault location rely either on the line models and the line parameters,or on the large amounts of historical fault data.To solve this problem,first by summarizing the fault location principles of the distributed parameter model and the Π-type model,this paper establishes the fault location function of the two-terminal transmission line according to the positive sequence voltage and the positive sequence current before and after a fault.Then,an asynchronous fault location algorithm is proposed for the two-terminal transmission lines based on the artificial neural network and the network migration but without depending on the line model and the line parameters.Finally,a simulation model of the 500kV transmission line is built on the Matlab/Simulink,verifying the correctness and reliability of the proposed algorithm.The theoretical analysis and simulation results show that the proposed algorithm has higher accuracy without being affected by the factors such as the fault locations,the fault types,the transition resistance,the fault initial phase angles,the load current and the asynchronous data.In addition,by making full use of a large amount of normal data and a small amount of fault data of the lines based on the idea of the network migration,the proposed algorithm still has a higher accuracy when the line parameters change within the range of less than ±1%.
作者
陈晓龙
孙丽蓉
李永丽
李斌
CHEN Xiaolong;SUN Lirong;LI Yongli;LI Bin(Key Laboratory of Smart Grid(Tianjin University),Ministry of Education,Nankai District,Tianjin 300072,China)
出处
《电网技术》
EI
CSCD
北大核心
2023年第12期5169-5180,共12页
Power System Technology
基金
国家自然科学基金委员会–国家电网公司智能电网联合基金资助项目(U2066210)。
关键词
双端输电线路
故障测距
人工神经网络
网络迁移
非同步数据
two-terminal transmission lines
fault location
artificial neural network
network migration
asynchronous data
