CN-116702675-B - Power module junction temperature estimation method and device, electronic equipment and storage medium

CN116702675BCN 116702675 BCN116702675 BCN 116702675BCN-116702675-B

Abstract

The invention provides a junction temperature estimation method, a device, electronic equipment and a storage medium of a power module, wherein the method comprises the steps of acquiring current working condition data and current cycle residual life of a target power module, inputting switching frequency, voltage data, current data and temperature data in the current working condition data into a preset electrothermal network model so as to enable the electrothermal network model to output the current junction temperature, iteratively training the current junction temperature estimation neural network model based on the current working condition data, the current cycle residual life and the current junction temperature, obtaining a new junction temperature estimation neural network model after training, and updating the junction temperature estimation neural network model of a corresponding vehicle end of the target power module so as to estimate the junction temperature of the power module; the reliability and the accuracy of the electrothermal network model and the junction temperature estimation neural network model are improved, the calculation amount of the junction temperature estimation of the vehicle-end power module is reduced, and the load rate of the vehicle-mounted ECU is reduced.

Inventors

LIU LI
WEI FANYI
CHEN JIAN
CHEN YANG

Assignees

深蓝汽车科技有限公司

Dates

Publication Date: 20260505
Application Date: 20230531

Claims (9)

1. The power module junction temperature estimation method is characterized by comprising the following steps of: acquiring current working condition data and current period residual life of a target power module, wherein the working condition data comprise switching frequency, voltage data, current data and temperature data; inputting switching frequency, voltage data, current data and temperature data in the current working condition data into a preset electrothermal network model so that the electrothermal network model outputs the current junction temperature, wherein the electrothermal network model is built based on a thermal impedance value of the target power module, and the thermal impedance value is changed; The method comprises the steps of carrying out iterative training on a current junction temperature estimation neural network model based on current working condition data, current cycle residual life and current junction temperature to obtain a new junction temperature estimation neural network model after training, updating the junction temperature estimation neural network model of a vehicle end corresponding to the target power module to carry out junction temperature estimation of the power module, wherein updating the junction temperature estimation neural network model of the vehicle end corresponding to the target power module comprises the steps of determining the actual residual life of the target power module based on the historical junction temperature output by the electric heating network model and the current junction temperature, calculating the life attenuation degree of the target power module based on the current cycle residual life and the actual residual life, and if the life attenuation degree reaches a preset threshold value, sending the actual residual life and the new junction temperature estimation neural network model to the vehicle end to enable the vehicle end to determine the actual residual life as the next cycle residual life, and carrying out estimation on the next cycle junction temperature of the target power module through the new junction temperature estimation neural network model.
2. The power module junction temperature estimation method of claim 1, wherein determining an actual remaining life of the target power module based on the current junction temperature and a historical junction temperature output by the electrothermal network model comprises: acquiring a plurality of historical junction temperatures output by the electrothermal network model; fitting the plurality of historical junction temperatures and the current junction temperature to obtain a junction temperature curve, and counting the junction temperature curve by adopting a rain flow counting method to obtain at least one group of thermal stress and the power cycle times under each group of thermal stress, wherein the thermal stress comprises junction temperature fluctuation quantity and average junction temperature; Inputting the fluctuation amount of the junction temperature and the average junction temperature in each group of thermal stress into a life model, so that the life model outputs the failure power cycle times under each group of thermal stress, and the life model is built based on the fluctuation amount of the junction temperature and the average junction temperature; And taking the ratio of the power cycle times and the failure power cycle times under each group of thermal stress as a fatigue damage value corresponding to each group of thermal stress, and calculating based on the fatigue damage value corresponding to each group of thermal stress to obtain the actual residual life.
3. The power module junction temperature estimation method according to claim 2, wherein if the lifetime degradation degree reaches a preset threshold value, the power module junction temperature estimation method further comprises: Calculating to obtain a new thermal impedance value based on the current loss power, the temperature data in the current working condition data and the average junction temperature in each group of thermal stress so as to update the thermal impedance value in the electrothermal network model, wherein the current loss power is obtained based on the switching frequency, the voltage data and the current data in the current working condition data; Or alternatively, the first and second heat exchangers may be, And calculating new thermal impedance values based on the input power and the temperature data in the current working condition data and the average junction temperature in each group of thermal stress so as to update the thermal impedance values in the electrothermal network model, wherein the working condition data also comprises the input power.
4. A method for estimating junction temperature of a power module according to any one of claims 1 to 3, wherein the method for establishing the electrothermal network model comprises: establishing a power loss model for calculating a loss power based on the switching frequency, the voltage data, and the current data; establishing a thermal network model for calculating junction temperature based on the loss power, the thermal impedance value and the temperature data; And coupling the power loss model and the thermal network model to obtain the electrothermal network model so as to calculate junction temperature.
5. A method for estimating a junction temperature of a power module according to any one of claims 1 to 3, wherein iteratively training a current junction temperature estimated neural network model based on the current operating condition data, the current cycle remaining life and the current junction temperature to obtain a trained new junction temperature estimated neural network model comprises: And taking the residual life of the current period, the water pump rotating speed, the switching frequency, the bus voltage, the collector current and the cooling water temperature in the current working condition data as input values, taking the current junction temperature as an output value, and performing iterative training on the current junction temperature estimation neural network model to obtain the new junction temperature estimation neural network model, wherein the working condition data also comprises the water pump rotating speed, the voltage data comprises the bus voltage, and the current data comprises the collector current.
6. A power module junction temperature estimation method according to any one of claims 1-3, characterized in that the power module junction temperature estimation method comprises, before establishing the electrothermal network model: Acquiring the pressure drop of the target power module, wherein the pressure drop of the power module represents the aging degree of the power module; performing an aging experiment on a sample power module until the pressure drop of the sample power module reaches the pressure drop of the target power module, wherein the model of the target power module is the same as that of the sample power module; and calculating a thermal impedance value of the sample power module based on the junction temperature, the shell temperature and the input power of the sample power module to be used as the thermal impedance value of the target power module so as to establish the electrothermal network model.
7. A power module junction temperature estimation device, characterized in that the power module junction temperature estimation device comprises: The acquisition module is used for acquiring current working condition data and current period residual life of the target power module, wherein the working condition data comprise switching frequency, voltage data, current data and temperature data; The calculation module is used for inputting the switching frequency, the voltage data, the current data and the temperature data in the current working condition data into a preset electrothermal network model so that the electrothermal network model outputs the current junction temperature, the electrothermal network model is built based on the thermal impedance value of the target power module, and the thermal impedance value is changed; the training module is used for carrying out iterative training on the current junction temperature estimation neural network model based on the current working condition data, the current cycle residual life and the current junction temperature to obtain a new trained junction temperature estimation neural network model; The updating module is used for updating the junction temperature estimation neural network model of the vehicle end corresponding to the target power module to estimate the junction temperature of the power module, wherein updating the junction temperature estimation neural network model of the vehicle end corresponding to the target power module comprises the steps of determining the actual residual life of the target power module based on the historical junction temperature output by the electric heating network model and the current junction temperature, calculating the life attenuation degree of the target power module based on the current period residual life and the actual residual life, and sending the actual residual life and the new junction temperature estimation neural network model to the vehicle end if the life attenuation degree reaches a preset threshold value so that the vehicle end can determine the actual residual life as the residual life of the next period, and estimating the junction temperature of the target power module in the next period through the new junction temperature estimation neural network model.
8. An electronic device, the electronic device comprising: One or more processors; Storage means for storing one or more programs that, when executed by the one or more processors, cause the electronic device to implement the power module junction temperature estimation method of any of claims 1-6.
9. A computer readable storage medium, having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to perform the power module junction temperature estimation method according to any of claims 1-6.

Description

Power module junction temperature estimation method and device, electronic equipment and storage medium Technical Field The application relates to the technical field of vehicle power modules, in particular to a method and a device for estimating junction temperature of a power module, electronic equipment and a storage medium. Background New energy automobiles have been rapidly developed in recent years. The reliability and safety of the power device, which is used as the core of the motor control system, determine whether the whole motor control system operates efficiently. The IGBT (Insulated Gate Bipolar Transistor ) module is also called a power module, has the characteristics of high input impedance, high on-current and high withstand voltage value, and plays a role in the motor control system. The reliability of the IGBT module is more and more affected by junction temperature while the power level and the switching frequency are improved. Therefore, junction temperature is a key parameter for IGBT module state detection. Chinese patent CN107025364B discloses a junction temperature prediction method of an IGBT module, by establishing a high-order heat capacity thermal resistance model of the IGBT module, calculating power loss in a certain period to calculate the junction temperature in the period of the IGBT module, where the scheme does not consider the change of the thermal impedance of the IGBT module, the reliability of the junction temperature estimation of the IGBT module is not sufficient, and the high-order heat capacity thermal resistance model has a large calculated amount, and is applied to a vehicle end, which easily occupies a large amount of calculation resources at the vehicle end, and increases the load rate of a vehicle-mounted ECU (Electronic Control Unit ). Disclosure of Invention In view of the above drawbacks of the prior art, the present application provides a method, an apparatus, an electronic device, and a storage medium for estimating a junction temperature of a power module, so as to solve the technical problems that the related thermal network technology does not consider the change of thermal impedance, the reliability of estimating the junction temperature of an IGBT module is insufficient, the computing resources of the thermal network technology occupy a large amount, and the load rate of a vehicle-mounted ECU is increased. The application provides a junction temperature estimation method based on a power module, which comprises the steps of obtaining current working condition data and current cycle residual life of a target power module, wherein the working condition data comprise switching frequency, voltage data, current data and temperature data, inputting the switching frequency, the voltage data, the current data and the temperature data in the current working condition data into a preset electrothermal network model so that the electrothermal network model outputs the current junction temperature, establishing the electrothermal network model based on a thermal impedance value of the target power module, wherein the thermal impedance value is changed, carrying out iterative training on the current junction temperature estimation neural network model based on the current working condition data, the current cycle residual life and the current junction temperature, obtaining a new junction temperature estimation neural network model after training, and updating the junction temperature estimation neural network model of a corresponding vehicle end of the target power module so as to carry out junction temperature estimation of the power module. In an embodiment of the application, the switching frequency, the voltage data, the current data and the temperature data in the current working condition data are input into a preset electrothermal network model, so that after the electrothermal network model outputs the current junction temperature, the power module junction temperature estimation method comprises the steps of determining the actual remaining life of the target power module based on the historical junction temperature output by the electrothermal network model and the current junction temperature, calculating the life attenuation degree of the target power module based on the current period remaining life and the actual remaining life, and if the life attenuation degree reaches a preset threshold, sending the actual remaining life and the new junction temperature estimation neural network model to a vehicle end, so that the vehicle end determines the actual remaining life as the remaining life of the next period, and estimating the junction temperature of the next period of the target power module through the new junction temperature estimation neural network model. In an embodiment of the application, the actual residual life of the target power module is determined based on the historical junction temperature and the current junction temperature output