Method for calculating temperature of IGBT module based on BP neural network

Abstract

The invention provides a method for calculating the temperature of an IGBT module based on a BP neural network, and the method comprises the following steps: S1, building a sample set, and enabling the data of the sample set to comprise the loss data of all power elements in the IGBT module and the corresponding junction temperature data; S2, establishing a structure of a BP neural network by taking the loss data as input and the junction temperature data as expected output; S3, performing network training on the BP neural network; S4, inputting the loss data into the trained BP neural network, and calculating actual output; S5, comparing the actual output with the expected output, and judging whether an error is within a preset range or not: S6, if so, performing simulation prediction byusing a current BP neural network; and S7, if not, adjusting the structure of the current BP neural network, and returning to the step S3. According to the method, the junction temperature requirementof the IGBT module can be accurately obtained in real time.

Description

technical field [0001] The invention relates to the technical field of power electronics, in particular to a method for calculating the temperature of an IGBT module based on a BP neural network. Background technique [0002] The IGBT module is used in the electric drive system of electric vehicles. It must deal with the frequent start-up and emergency stop of electric vehicles. At this time, it often works under the harsh conditions of power fluctuations. Therefore, the IGBT module needs to withstand alternating thermal stress shocks, making the IGBT module Fatigue, aging and failure are prone to occur, increasing the probability of failure. Therefore, the reliability of the IGBT module is related to the safe operation of electric vehicles. Only by mastering the operating status parameters of the modules in real time can scientific and accurate predictions be made to avoid major accidents. [0003] The study found that due to the different thermal expansion coefficients o...

AI Technical Summary

Problems solved by technology

[0004] In the past, there have been many studies and applications on the junction temperature of IGBT modules, most of which expounded the calculation of junction temperature by establishing a thermal network, and the selection of thermal nodes in the thermal network is closely related to the structure of the IGBT module, and the change of the IGBT structure needs to be evaluated. Availability of the network, even redesigning the hot network, a huge amount of work

At the same time, as the device ages, parameters such as thermal resistance and thermal capacitance in the thermal network will change to a certain extent, and the junction temperature obtained at this time is no longer accurate.

Therefore, this method has certain limitations in the application of real-time monitoring of junction temperature, and it is necessary to consider a new method to calculate the junction temperature

Images