基于BP神经网络的开关电源电路故障诊断  

Research on the fault diagnosis of switch power supply circuit based on BP neural network

作　　者：乔维德 QIAO Weide(Department of Scientific Research and Development Planning,Wuxi Open University,Wuxi 214011,China)

机构地区：[1]无锡开放大学科研与发展规划处,江苏无锡214011

出　　处：《河南工程学院学报(自然科学版)》2025年第1期45-51,共7页Journal of Henan University of Engineering:Natural Science Edition

摘　　要：针对开关电源电路的非线性故障问题,搭建了基于小波包分解与反向传播(BP)神经网络的开关电源电路故障诊断模型,采用小波包分解提取开关电源逆变电路故障特征向量,应用萤火虫-粒子群算法及改进BP算法优化训练BP神经网络。仿真实验证明,该方法可以迅速、准确地实现开关电源电路的故障诊断。Aimed at the nonlinearity fault problems of switch power supply circuits,a fault diagnosis model for switch power supply circuits based on wavelet packet decomposition and back propagation(BP)neural network is built.The wavelet packet decomposition method is applied to extract the fault feature vector of the switch power supply inverter circuit,and the firefly particle swarm algorithm and improved BP algorithm are applied to optimize and train the BP neural network.Simulation experiments have shown that this method can achieve rapid and accurate diagnosis of switch power supply circuits.

关 键 词：小波包分解 开关电源电路 BP神经网络 

分 类 号：TN711[电子电信—电路与系统]