摘要
针对小电流接地系统中单相接地故障选线这一未彻底解决的难题,提出一种基于改进粒子群算法(Particle Swarm Optimization,PSO)优化模糊神经网络(Fuzzy Neural Networks,FNN)的配电网故障选线方法:通过调整粒子群的适应度函数和自适应惯性权值,利用改进PSO先对网络初始参数、权值进行一次优化,后使用BP算法进行二次优化。讨论模糊神经网络、传统PSO优化的模糊神经网络及不同网络结构对网络性能的影响。研究结果表明改进PSO优化模糊神经网络的选线效果明显优于模糊神经网络和传统PSO优化模糊神经网络,能够快速、准确、可靠的选取故障线路。
Aiming at the problem of single-phase grounding fault line selection in small current grounding system that did not be solved thoroughly. This paper presents a fault line selection method of power distribution network based on improved Particle Swarm Optimization（PSO） to optimize Fuzzy Neural Network. By improving the fitness function and adaptive inertia weight of PSO, initial parameters and weights are optimized firstly, using the BP method to optimize the second time. The influence of Fuzzy Neural Network, the traditional PSO optimization of Fuzzy Neural Network and different network structures to network performance are discussed. The results of the study illustrate the improved PSO to optimize Fuzzy Neural Network is better than Fuzzy Neural Network and traditional PSO to optimize Fuzzy Neural Network in the term of line selection effect, can accurately, effectively, reliablely find fault line.
出处
《电气技术》
2016年第3期30-35,共6页
Electrical Engineering
基金
国家自然科学基金资助项目(51177036)
安徽省自然科学基金资助项目(1408085MKL13)
关键词
小电流接地系统
单相接地
改进PSO
模糊神经网络
small current grounding system
single-phase grounding
improved PSO
Fuzzy Neural Network
