基于径向基函数神经网络的在线分布式故障诊断系统

ON-LINE DISTRIBUTED FAULT SECTION ESTIMATION SYSTEM WITH RADIAL BASIS FUNCTION NEURAL NETWORK

作者建议使用分布式智能系统解决大规模电力网络的实时故障诊断问题 ,并为此提出了一种新的基于最小度排序的图形分割方法 ,它能够将大规模电力网络有效地分割为给定数目的连通子网络 ,并且各子网络的故障诊断负担近似相等 ,同时每个子网络边界元件的数目最小。然后用径向基函数神经网络完成各子网络的故障诊断。所提出的分布式智能故障诊断系统已使用稀疏存储技术编程实现 ,并在 IEEE14母线、30母线和 118母线系统中进行了仿真研究。

In this paper it is presented to use distributed intelligent system to implement the on line Fault Section Estimation (FSE) which is important and still not solved for large scale power networks. A novel multi way graph partitioning method based on weighted minimum degree reordering is proposed for effectively partitioning the large scale power network into desired number of connected sub networks where the FSE burdens and minimum frontier elements are quasi balanced, then Radial Basis Function Neural Network (RBF NN) is applied to accomplish the FSE of each sub network. The proposed distributed intelligent FSE method is implemented by programming with sparse storage technique and is simulated on IEEE 14 bus, 30 bus and 118 bus systems respectively. Computer simulation results show that the fault diagnosis problem in large scale power network can be effectively solved by the proposed FSE system.