基于改进遗传算法的配电网故障诊断  

Fault Diagnosis of Distribution Network Based on Genetic Algorithm

作　　者：杨伟[1] 刘娅琳[2] 吴军基[1] 

机构地区：[1]南京理工大学动力学院,江苏南京210094 [2]国电南瑞科技股份有限公司,江苏南京210003

出　　处：《长沙电力学院学报（自然科学版）》2005年第1期25-30,共6页JOurnal of Changsha University of electric Power:Natural Science

摘　　要：针对传统配电网故障诊断系统的不足,提出基于改进GA的配电网故障诊断方法.提出节点表示配电网络的模型描述方法,将配电网基本组成元件归纳为进线断路器、开关和线路3类.在实现拓扑分区的基础上,深入研究适应度函数和遗传算子及参数等的改进.仿真实验表明该方法的有效性和高容错性.In order to get rid of the disadvantages of traditional fault diagnosis method, a fault diagnosis program for distribution network based on improved genetic algorithm is presented.A distribution network configurations through node-denoted network method has been advanced. Then network components have been classified into three types: incoming circuit breakers, switches and lines. Using network topology partition results,the improvement of fitness function, GA operators,parameters and so on has been researched. The results of simulation test show this algorithm has high efficiency and fault-tolerance.

关 键 词：配电网 故障定位与隔离 故障恢复 遗传算法 

分 类 号：TM711[电气工程—电力系统及自动化]