基于特性识别的IGBT器件健康状态评估方法

The Insulated Gate Bipolar Transistor (IGBT) is a critical component of power electronic equipment, and the health of the IGBT device is of utmost importance to ensure the reliability and stability of the power system. This paper proposes a method for assessing the health status of IGBT device based on characteristics identification. Firstly, a finite element model of the IGBT device is established to analyze the performance of bond-wire and solder layer under the power cycling condition. Secondly, the IGBT device under solder layer failure and bond-wire failure are simulated, and the characteristics parameters of the IGBT device under different aging degree are analyzed. Finally, an adaptive network-based fuzzy inference system (ANFIS) algorithm is used to establish the IGBT device health status assessment model, and power cycling test data is used to verify the accuracy of the health state evaluation model, which reaches more than 94.8%. The results show that the proposed method can effectively evaluate the health status of IGBT device.