摘要
对 BP神经网络的容错性进行了研究 ,将网络的容错能力与测试样本所形成的模糊区的大小相对应 ,通过消除模糊区来提高网络的容错能力。针对南昌 50 0 k V变电站自动化系统 ,开发了变电站的实时故障诊断系统。该系统以 3层前向 BP网络作为故障诊断的核心部分 ,以开关动作信息、保护动作信息等作为人工神经网络的输入。同时结合专家系统 ,利用其推理判断能力 ,对变电站运行方式进行识别 。
The fault-tolerance performance of BP neural network (NN) is studied firstly. The fault-tolerance performance is corresponding to the fuzzy area formed by detecting samples, and the fault-tolerance performance is enhanced by eliminating fuzzy area. A substation real-time fault diagnosis system is developed on the basis of Nanchang 500 kV automation substation. Triple layers BP NN is the core of fault diagnosis system in which inputs include the alarming information of tripped breaker, protection information and so on. Because of its inference capability, expert system is used in the system to recognize substation operational modes and modify some output of ANN.
出处
《电力系统自动化》
EI
CSCD
北大核心
2001年第9期45-47,共3页
Automation of Electric Power Systems
关键词
BP神经网络
容错性
专家系统
变电站
报警
信息处理系统
Alarm systems
Automation
Electric substations
Expert systems
Fuzzy control
Neural networks