摘要
分析了三电平变频器发生故障的原因,并将2只IGBT开路故障进行分类,为各类故障进行编码。选择逆变电路3个桥臂的相电压信号作为研究对象,利用d-q变换将三相电压信号转换为两相以减少故障信息的维数,通过傅立叶变换提取不同故障下的特征向量;建立一个4层的BP神经网络并进行故障诊断,将特征向量作为输入,对应故障的编码作为输出,对网络进行训练仿真,实现并验证了采用BP神经网络对三电平变频器故障诊断的可行性和准确性。
The reason of the fault of three-level inverter was analyzed,the open circuit fault of two IGBTs was classified,and all kinds of faults were coded.Taking the phase voltage signals of three bridge arms of the inverter circuit as the research object,and the three-phase voltage signals were converted into two phases by using the d-q transformation to reduce the dimension of the fault information,and the feature vectors under different faults were extracted by Fourier transform.A four-layer BP neural network was established and fault diagnosis was carried out.The network was trained and simulated with the feature vector as input,and the corresponding fault code as output.The feasibility and accuracy of fault diagnosis of three-level inverter using BP neural network were realized and verified.
作者
王丽华
方旭东
韩素敏
郑书晴
WANG Lihua;FANG Xudong;HAN Sumin;ZHENG Shuqing(Department of Mechanical Engineering and Automation, Tianjin Vocational Institute, Tianjin 300410, China;Zhaogu II Mine,Henan Energy and Chemical Industry Group Co.,Ltd., Xinxiang Henan 453600,China;School of Electrical Engineering and Automation,Henan Polytechnic University,Jiaozuo Henan 454000,China)
出处
《机床与液压》
北大核心
2020年第9期187-191,共5页
Machine Tool & Hydraulics
基金
国家重点研发计划专项项目(2016YFC0600906)
河南省控制工程重点学科开放基金资助项目(KG2011-08)。
