IGBT junction temperature prediction method based on improved ABC-SVR

Abstract

Disclosed is an IGBT junction temperature prediction method based on improved ABC-SVR which comprises the steps of collecting multiple sets of IGBT junction temperature and junction temperature related electrical parameters to serve as a sample data set; improving a formula for searching a nectar source in an artificial bee colony algorithm; optimizing the parameter combination of the support vector regression machine by using an improved artificial bee colony algorithm according to the formula for searching the nectar source to obtain the optimal parameter combination of the IGBT junction temperature prediction support vector regression machine model optimized based on the improved artificial bee colony algorithm; establishing an optimal IGBT junction temperature prediction support vectorregression machine model according to the optimal parameter combination; carrying out training and accuracy judgment on the established optimal IGBT junction temperature prediction support vector regression machine model; and predicting the junction temperature by using the optimal IGBT junction temperature prediction support vector regression machine model. The method has the advantages of few required parameters, simplicity in implementation and high prediction precision, and can be widely applied to application occasions with high IGBT junction temperature measurement difficulty and high required precision.

Description

Technical field [0001] The invention relates to an insulated bipolar transistor (IGBT) junction temperature prediction method based on an improved artificial bee colony algorithm optimization support vector regression machine (ABC-SVR), which is mainly used in the technical field of power IGBT reliability. Background technique [0002] Insulated bipolar transistor (IGBT) combines the advantages of field effect transistor (MOSFET) and bipolar transistor (BJT). It has the characteristics of simple drive, low loss and high voltage resistance. It is used in the fields of new energy, aerospace, and transportation. Has been widely used, the reliability of IGBT has also received increasing attention. [0003] As an important parameter of IGBT reliability, junction temperature has an important impact on the performance of devices and devices: too high a junction temperature will cause semiconductor devices to fail; at the same time, excessive temperature fluctuations will also cause excess...

AI Technical Summary

Problems solved by technology

[0006] The problem to be solved by the present invention is to overcome the shortcomings of the existing IGBT thermal parameter method, such as low junction temperature prediction accuracy, need to extract multiple parameters, and be easily affected by the load, and provide an optimized support vector regression machine based on the improved artificial bee colony algorithm (ABC- SVR) IGBT junction temperature prediction method, the prediction method requires few parameters, simple implementation, high prediction accuracy, and can be widely used in applications where it is difficult to measure the IGBT junction temperature and requires high precision.

Images