针对中性点箝位型(NPC)三电平逆变器开路故障诊断计算复杂、准确率低等问题，提出一种基于小波包变换和支持向量机(SVM)的故障诊断方法。采用小波包变换将具有各自时频特征的故障信号分解为若干个频段，并重构提取小波包能量作为故障特征向量；将该故障特征向量作为SVM的输入量，运用交叉验证径向基核函数，通过训练数据集得到多类SVM模型，将随机选取的测试集输入训练好的模型中。仿真试验结果表明，该方法可对IGBT开路故障进行诊断并具有更高的故障识别准确率。

A fault diagnosis method based on wavelet packet transform and support vector machine (SVM) is proposed to solve the problem of complex calculation and low accuracy in the open-circuit fault diagnosis of neutral point clamped (NPC) three-level inverter. The wavelet packet transform is used to decompose the fault signals with their timefrequency characteristics into several frequency bands, and the wavelet packet energy is extracted as the fault feature vector. The fault feature vector is taken as the input of SVM, the radial basis kernel function is used for cross-validation, and multiple SVM models are obtained through training the data set. Finally, the randomly selected test set is input into the trained model. Simulation results show that the method can diagnose the IGBT open-circuit fault and has higher fault recognition accuracy.

辽宁省教育厅科学研究项目（JDL2019011）