针对电力电子技术中三相桥式全控整流电路中晶闸管的故障问题提出了基于BP神经网络故障诊断的方法。借助Matlab仿真软件建立了三相桥式全控整流电路的仿真模型。通过仿真试验提取出用于BP神经网络训练的学习样本,并确定出用于不同类故障的三层的BP神经网络结构。仿真结果表明了该方法的有效性。
This paper proposed a fault diagnosis method based on back propagation (BP) neural network for thyristors fault of three-phase full-bridge controlled rectifier in the power electronic technology. A simulation model of three-phase full-bridge controlled rectifier was setup with Matlab software. The learning samples for training BP neural network was obtained by simulating the different fault types of thyristors in the rectifier, and the three-layer BP neural networks for different fault types were constructed. The simulation results demonstrate that this method is valid.