登录    |    注册

您好,欢迎来到中国测试科技资讯平台!

首页> 《中国测试》期刊 >本期导读>循环神经网络输电线路双端故障测距方法

循环神经网络输电线路双端故障测距方法

177    2021-09-23

¥0.50

全文售价

作者:余晓1, 吕飞鹏1, 张国星2, 刘友波1Q

作者单位:1. 四川大学电气工程学院,四川 成都 610041;
2. 中国电力工程顾问集团西北电力设计院有限公司,陕西 西安 710075


关键词:深度学习;输电线路;故障测距;循环神经网络;智能测距


摘要:

针对传统人工智能算法用于输电线路故障测距时泛化能力不足导致测距精度不高的问题,提出一种基于循环神经网络(recurrent neural network,RNN)的输电线路双端故障测距方法。首先通过仿真模拟不同故障模式下线路两端的电压、电流信号作为输入特征,对数据进行预处理后构造样本集,构建RNN模型用样本集进行训练和测试,使模型充分学习输入数据的深层特征,进而对故障距离进行较好的学习预测,最终获取高精度的故障测距模型。本文通过对IEEE10机39节点模型进行仿真试验及对某供电局管辖范围220 kV线路故障数据的测试,结果表明该模型较浅层模型具有更高的测距精度和更好的抗噪性能。


Two-terminal fault location algorithm for transmission lines based on recurrent neural network
YU Xiao1, Lü Feipeng1, ZHANG Guoxing2, LIU Youbo1
1. Department of Electrical Engineering, Sichuan University, Chengdu 610041, China;
2. Northwest Electric Power Design Institute Co., Ltd. of China Power Engineering Consulting Group, Xi’an 710075, China
Abstract: Aiming at the problem of low accuracy of fault location caused by insufficient generalization ability of traditional artificial intelligence algorithm in fault location of transmission lines. A method based on the recurrent neural network (RNN) is proposed for transmission line double terminal fault location. Firstly, the voltage and current signals at both ends of the line in different fault modes are simulated, and the sample set is constructed after preprocessing the data. The sample set will be used as the input to train and test the RNN model. The model can fully learn the deep features of the input data, and then perform better learning and prediction of fault location. Finally, a high precision fault location model is obtained. In this paper, the simulation tests of the standard model of 39 nodes system for IEEE 10 machines and the test results of 220 kV transmission line fault data within the jurisdiction of a power supply bureau show that the model has higher accuracy of fault location and better anti-noise performance than shallow model.
Keywords: deep learning;transmission line;fault location;recurrent neural network;intelligent location
2021, 47(9):119-125  收稿日期: 2020-10-20;收到修改稿日期: 2020-12-11
基金项目: 国家自然科学基金项目资助(51977133)
作者简介: 余晓(1996-),女,云南昭通市人,硕士研究生,专业方向为电力系统微机保护与人工智能
参考文献
[1] 李振兴, 田斌, 李振华, 等. 适用于单/双回线的双端非同步故障测距方法[J]. 电力系统自动化, 2016, 40(22): 105-110
[2] 张峰, 梁军, 李建超, 等. 基于初始反极性行波检测的单端故障测距算法[J]. 电力系统自动化, 2013, 37(4): 108-113
[3] 王海港, 谢民, 孙月琴, 等. 输电线路双端故障测距时域算法实用研究[J]. 电力系统保护与控制, 2016, 44(22): 142-147
[4] 高艳丰, 朱永利, 闫红艳, 等. 一种新型的输电线路双端行波故障定位方法[J]. 电力系统保护与控制, 2016, 44(8): 8-13
[5] 邓丰, 曾祥君, 马士聪, 等. 基于分布式行波检测的广域网络故障定位方法[J]. 电网技术, 2017, 41(4): 1300-1310
[6] 靳夏宁, 汪芙平, 王赞基. 基于PMU动态同步相量测量的故障测距[J]. 电网技术, 2013, 37(10): 2932-2937
[7] YUSUFF A A, JIMOH A A, MUNDA J L. Fault location in transmission lines based on stationary wavelet transform, determinant function feature and support vector regression[J]. Electric Power Systems Research, 2014, 110: 73-83
[8] 费春国, 李春信. 基于电压振幅和支持向量回归机的高压电力输电线故障定位[J]. 电力系统保护与控制, 2018, 46(13): 27-32
[9] ALEXANDRE P A D S, ANTONIO C S L, SUZANA M S. Fault location on transmission lines using complex-domain neural networks[J]. International Journal of Electrical Power and Energy Systems, 2012, 43(1): 720-727
[10] DASGUPTA A, NATH S, DAS A. Transmission line fault classification and location using wavelet entropy and neural network[J]. Electric Power Components & Systems, 2012, 40(15): 1676-1689
[11] FATHABADI, HASSAN. Novel filter based ANN approach for short-circuit faults detection, classification and location in power transmission lines[J]. International Journal of Electrical Power & Energy Systems, 2016, 74: 374-383
[12] 严勤, 邓高峰, 胡涛, 等. 基于深度循环神经网络的异常用电检测方法[J]. 中国测试, 2021, 47(7): 99-104
[13] 曹梦舟, 张艳. 基于卷积-长短期记忆网络的电能质量扰动分类[J]. 电力系统保护与控制, 2020, 48(2): 86-92
[14] 刘恒勇, 史帅彬, 徐旭辉, 等. 一种关联RNN模型的非侵入式负荷辨识方法[J]. 电力系统保护与控制, 2019, 47(13): 162-170
[15] 丁石川, 厉雪衣, 杭俊, 等. 深度学习理论及其在电机故障诊断中的研究现状与展望[J]. 电力系统保护与控制, 2020, 48(8): 172-187