Three-level T-type inverter fault diagnosis method based on GASF and CNN

• Main Authors: JIANG DESONG, LIN ANHUI, WANG RONGJIE, SI YUPENG, CUI YABO, WANG YICHUN
• Format: Patent
• Language: Chinese; English
• Published: 09.09.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING

The invention proposes a three-level T-type inverter fault diagnosis method based on GASF and CNN, and the method comprises the steps: carrying out the polar coordinate coding of a time sequence current signal at an output end of an inverter through a Grubrum summation angle field algorithm, carrying out the Grubrum matrix transformation through a generation angle, converting the Grubrum matrix into a Grubrum matrix graph, and carrying out the fault diagnosis of a three-level T-type inverter through a Grubrum summation angle field algorithm. The method comprises the following steps: taking a Grubrum matrix graph as the input of a convolutional neural network, adaptively extracting features, avoiding the uncertainty and complexity of manually extracting the features, and finally classifying the fault features extracted by the CNN by using an Adam optimized softmax classifier, thereby realizing the fault diagnosis of the inverter. 本发明提出一种基于GASF和CNN的三电平T型逆变器故障诊断方法，先通过格拉姆求和角场算法，将逆变器输出端的时序电流信号进行极坐标编码，然后利用生成角度进行格拉姆