基于资源分配网络的电网故障诊断方法研究  

Research on Power Grid Fault Diagnosis Based on Resource Allocating Network

作　　者：刘晓琴[1] 王大志[1] LIU Xiao-qin;WANG Da-zhi(College of Information Science and Engineering,Northeastern University,Shenyang 110819,China)

机构地区：[1]东北大学信息科学与工程学院,沈阳110819

出　　处：《控制工程》2019年第1期6-11,共6页Control Engineering of China

基　　金：省自然科学基金资助项目(201602472)

摘　　要：针对电网故障,仅依靠开关量状态信息进行诊断,复杂故障情况下会影响诊断结果的准确性。提出一种模型预测和资源分配网络(Resource Allocating Network,RAN)的故障诊断方法,将引入的电气量信息与开关量相结合共同诊断故障。首先用RAN网络处理断路器状态和故障区域之间的关系,然后根据模型预测方法得出电气量建立逻辑推理规则,验证每一个候选故障,最后得出结论。以算例做仿真,验证了该方法的有效性。Aiming at the power grid fault,it can only depend on the state information of the switch,and the accuracy of the diagnostic results can be affected by complex fault conditions.The method of model prediction and resource allocating network is proposed,which is based on the combination of electric quantity and switch quantity information.Firstly,the relationship between the state of the circuit breaker and the fault area is treated by ARN network.Then according to the model prediction method,the electric quantity is obtained to establish the logical inference rule,verifying each candidate fault,and finally the conclusion is got.Simulation is done to verify the validity of this method.

关 键 词：模型预测 资源分配网络 故障诊断 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]