摘要
针对三电平逆变器电路拓扑结构复杂,电路具有较强的非线性特征问题,提出一种基于小波包分析和量子神经网络的三电平逆变器开路故障诊断方法。采用三电平逆变器上、中、下桥臂电压作为测量信号,通过小波包方法对桥臂输出电压信号进行分析,获取故障信号小波节点系数;计算各节点小波能量谱特征并进行归一化处理,得到IGBT不同故障状态下的故障特征;利用故障特征训练量子神经网络,并对其进行测试以确定故障类别;通过实验平台验证了算法可行性。实验结果表明:提出的方法适用于三电平逆变器故障诊断,具有工程参考价值。
The three-level inverter has complex topology,and the circuit has strong nonlinear characteristics.To solve the problem of fault diagnosis of IGBT power device in inverter,a fault diagnosis method based on wavelet packet analysis and quantum neural network is proposed.First,the upper,middle and lower arm voltages of ANPC three-level inverter are used as the measurement signals.Then the wavelet packet method is used to analyze the output voltage signals of the bridge arm to obtain the wavelet nodes coefficients of the fault signals;Secondly,the wavelet energy spectrums of each node are calculated and normalized to obtain the fault features of the power switch element in different fault states;Finally,the quantum neural network is trained by the fault features and tested to determine the fault types.The experimental results show that the method proposed in this paper is suitable for three-level inverter fault diagnosis and has a certain engineering reference value.
作者
丁毅
何怡刚
李兵
崔介兵
DING Yi;HE Yigang;LI Bing;CUI Jiebing(College of Electrical Engineering and Automation,Hefei University of Technology,Hefei 230009,China)
出处
《重庆理工大学学报（自然科学）》
CAS
北大核心
2021年第4期152-158,共7页
Journal of Chongqing University of Technology：Natural Science
基金
国家自然科学基金项目(51777050)
装备预先研究重点项目(41402040301)。
