摘要
为了解决故障诊断中特征变化量在正常运行值两侧变化分别对应不同故障类型的问题,提出了一种扩展隶属函数结构,将传统的隶属度值域从[0,+1]扩展到[-1,+1]。将此方法用于改进模糊神经网络诊断模型,可以有效减小模型复杂程度。通过输电线路故障选线仿真证实了该方法的有效性。
In the fault diagnosis model, in order to deal with the problem that the variables varying around their normal values,with different side corresponding different fault type, an extended membership function is presented in this paper, which extends the value range of the normal membership function from [0,+1] to [-1, + 11. This method can reduce the complexity of the fault diagnosis model. The diagnosis result of simulation of discriminating the faulted lines proves the validity of this method.
出处
《电力系统及其自动化学报》
CSCD
北大核心
2005年第5期50-54,共5页
Proceedings of the CSU-EPSA
关键词
隶属函数
模糊神经网络
输电线路
故障选线
membership function
fuzzy neural network
transmission line
discriminating the faulted lines