摘要
为了提高谐振型逆变电源工作的可靠性以及故障诊断的准确性,提出将神经网络算法应用到逆变器故障诊断当中。以谐振型电源的逆变器回路为例,对其故障进行分析,通过神经网络模型的建立以及样本的学习,并结合神经网络反向传播(BP)算法对逆变器输出的电流波形进行了分析,达到对逆变器故障有效诊断的目的,使得诊断的准确性得到了很大提高;最终通过实验对该方法进行了验证,结果表明该方法能够对谐振型逆变电源的故障进行有效的诊断,同时也为以后同类型的诊断提供了参考。
In order to improve the reliability of resonant inverter power supply and the accuracy of fault diagnosis,the neural network algorithm is applied to the fault diagnosis of inverter. Resonance type inverter power supply circuit,for example,the fault is analyzed,through the establishment of the neural network model,and sample study,and combined with back propagation neural network algorithm(BP algorithm) of the inverter output current waveform is analyzed,the realization of the aim of effective for inverter fault diagnosis,the diagnostic accuracy has been greatly improved;In the end of this method is verified through the experiment,the results show that the method can carry on the effective of resonance type inverter power supply fault diagnosis, but also provides reference for the diagnosis of the same type.
作者
马晓辉
毕雪芹
张立广
Ma Xiaohui;Bi Xueqin;Zhang Liguang(College of Electronic Information Engineering,Xi'an Technological University,Xi'an 710021,China)
出处
《电子测量技术》
2018年第21期89-94,共6页
Electronic Measurement Technology
基金
陕西省教育厅专项科研计划项目(17JK0375)资助
关键词
神经网络
故障诊断
谐振型电源
反向传播算法
neural network
fault diagnosis
resonant power source
back propagation algorithm
