标题:
线路故障测距的人工智能算法研究A Fault Locator for Transmission Line Based on Artificial Intelligent Algorithm
作者:
邹宇
关键字:
多支路线路, 叠加原理, 故障测距, 遗传算法, 人工智能算法Transmission Lines with Multi-Branch, The Principle of Superposition, Fault Location, Genetic Algorithm, Artificial Intelligence Algorithm
期刊名称:
《Smart Grid》, Vol.6 No.2, 2016-04-11
摘要:
本文提出了一种基于智能算法的动态故障测距算法，用于带有多支路的输电线路故障测距。该算法通过测量输电线两侧的电流、电压值，得到相对应的判别指标，从而可预先识别出故障对应的区域；然后将非故障分支进行等效，得到合并后的电气量；再对故障处的分支应用基于遗传算法的双端测距法进行初步的测距，并利用神经网络算法对所得到的测距结果进行进一步的调整，提高了线路故障的测距精度。本文所提出的计算方法只需使用变电站故障后状态下所测得的电压和电流值，并继承了基于遗传算法的故障测距方法的优点，不受故障点位置与过渡电阻的影响，且减小了线路参数偏差对最后结果的影响。使用PSCAD对所提出的方法进行验证，结果表明所提出方法的正确性和高精度性。
Considering the transmission line with multi-branch, a dynamic fault location algorithm based on intelligent algorithm is presented in this paper. Based on the measured voltage and current at two terminals, a discrimination index is proposed by which the faulted section can be located first. After that the equivalent voltage and current at the branch node is obtained by the equivalent calculation of the healthy branches. It corrects the results of fault location method based on genetic algorithm by the way of neural network algorithm, with the ranging accuracy improved when there are faults at two terminals of transmission line. The proposed algorithm only demands the measured voltage and current on the two terminals, and inherits the advantages of fault location method based on genetic algorithm, which is independent of fault type, fault resistance at fault point, etc., the influence on ranging accuracy by line parameters deviation is greatly reduced. The proposed method is simulated by PSCAD, and the results verified the correctness and high precision of the algorithm.