摘要
把专家知识与神经网络计算相结合，用变压器原副边正序和负序电流分量的方向进行变压器的故障诊断，克服了传统的二次谐波制动特性差动保护在涌流伴随故障状态下的动作延时，能正确识别变压器的内部故障、励磁涌流、外部故障及空载合于内部故障等不同状态。用此原理构成的变压器保护动作时间最快可为半个周期，可适合于任意连接方式的双绕组变压器，且不受系统参数的影响，具有广泛的实用性和很强的容错能力，大量仿真结果证明了此方法的优越性。
Combining the expert knowledge and the artificial neural network (ANN) calculation, a new method is proposed based on the directions of positive and negative sequence currents on primary and secondary sides of a trans former to identify its different states. It is superior to the traditional transformer differential protective principle with second harmonic restraint and has no delay when a no-load transformer switches on an internal fault. It can correctly identify, within half cycle from the fault inception, the internal faults, magnetizing inrush current state. external faults and switching on the internal faults of a no-load transformer. In addition, this method is suitable for the two-winding transformers with any type of connections and less influenced by the system parameters. It has broad availability and high fault tolerant ability- A lot of simulations were given to demonstrate its superiority.
出处
《电力系统自动化》
EI
CSCD
北大核心
1999年第24期20-22,27,共4页
Automation of Electric Power Systems
关键词
变压器
故障诊断
神经网络
电力系统
neural network,inrush current,fault identification,transformer
