Train traction inverter insulated gate bipolar transistor life loss estimation method

By combining table look-up method and BP neural network, the loss prediction model and junction temperature equivalent thermal resistance network model of insulated gate bipolar transistor module are constructed, which solves the difficulty of obtaining real-time electrical parameters for life loss calculation of IGBT modules in the prior art and The problem of large errors achieves more accurate life loss estimation, improving the accuracy and convenience of calculations.

CN119066943APending Publication Date: 2024-12-03GUANGDONG UNIV OF TECH
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202410944793.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

When calculating the life loss of the train traction inverter IGBT module, the prior art has the problem that real-time electrical parameters are difficult to obtain and calculation results are large errors, especially the impact of the modulation ratio and power factor of the IGBT on the loss is not fully considered.

Method used

Using a combination of table look-up method and BP neural network, the loss prediction model of insulated gate bipolar transistor module and the junction temperature equivalent thermal resistance network model are constructed. By collecting the traction force, rotation speed and initial junction temperature of the train motor, the power loss is calculated and The junction temperature calculation is performed and the life loss value is finally calculated.

Benefits of technology

It significantly improves the accuracy of power loss calculation of IGBT modules, enhances the accuracy of junction temperature calculation results, and achieves more accurate life loss estimation through the combination of neural network and equivalent thermal resistance network, and is convenient to operate, with only The traction force and speed output by the traction motor can be accurately estimated.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066943A_ABST
    Figure CN119066943A_ABST
Patent Text Reader

Abstract

The invention discloses a method for estimating life loss of an insulated gate bipolar transistor (IGBT) of a train traction inverter. The method comprises the following steps of: constructing an IGBT module loss prediction model; constructing an IGBT module junction temperature equivalent thermal resistance network model; the current traction force and rotating speed of a train motor are collected, the initial junction temperature is set, the parameters are input into the loss prediction model, and power loss data are obtained; inputting power loss data into the module junction temperature equivalent thermal resistance network model for junction temperature calculation to obtain junction temperature fluctuation data; wherein the junction temperature output by the junction temperature equivalent thermal resistance network model is used as the input for predicting the power loss next time; and calculating the service life loss value of the insulated gate bipolar transistor module by using the junction temperature fluctuation data. According to the method, the service life loss value of the IGBT module can be calculated with relatively high accuracy through combined calculation of the neural network and the equivalent thermal resistance network.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of insulated gate bipolar transistors, and in particular to a method for estimating the life loss of an insulated gate bipolar transistor of a train traction inverter. Background Art

[0002] As the core component of train traction inverter, the reliability of insulated gate bipolar transistor (IGBT) plays a vital role in the safe operation of the train.

[0003] The junction temperature variation amplitude and average junction temperature are important parameters that determine the life of the IGBT module. Therefore, to calculate the life loss of the IGBT, it is first necessary to calculate the junction temperature of the train traction inverter IGBT module.

[0004] The existing literature on the method of calculating the junction temperature of the IGBT module of the train traction inverter is: first calculate the heat loss of the power module, then establish the equivalent thermal circuit model of the traction converter, and then simulate the process of the module junction temperature changing with time. There are two main methods for calculating the power loss of IGBT in the existing literature. The first is to use the IGBT power loss calculation formula (formula method); the second is to obtain a series of IGBT loss data at different currents and temperatures in Infineon's IPOSIM software (table lookup method). Since the formula calculation method simplifies the working environment and relies on accurate parameter estimation, there is a certain error between the result and the calculation result of the IPOSIM software. For the table lookup method, most of the current literature only considers the changes in temperature and current when the IGBT is working, and does not fully consider the influence of other parameters such as the modulation ratio and power factor of the IGBT on the loss. Moreover, the table lookup method requires a large amount of experimental data support, and the loss data needs to be re-measured or calculated for each new working condition, so there may be certain limitations in its use.

[0005] The Chinese invention patent with application number 202010142434.0 discloses a neural network-based IGBT junction temperature prediction method. This method requires the collection of real-time parameters of the IGBT module during real-time operation, including the phase current peak, switching frequency and ambient temperature of the inverter where the IGBT module is located; for inverters that have been installed on site, there are no corresponding measurement conditions. Summary of the invention

[0006] In order to solve the technical problems that the real-time electrical parameters required for calculation of IGBT junction temperature in the prior art IGBT life loss estimation are difficult to obtain and the calculation result has large errors, the present invention proposes a method for estimating the life loss of insulated gate bipolar transistors of train traction inverters. The technical solution adopted by the present invention is specifically as follows:

[0007] A first aspect of the present invention provides a method for estimating the life loss of an insulated gate bipolar transistor of a train traction inverter, the method comprising:

[0008] Construct an insulated gate bipolar transistor module loss prediction model;

[0009] Construct the junction temperature equivalent thermal resistance network model of the insulated gate bipolar transistor module;

[0010] Collecting the current traction force and speed of the train motor and setting the initial junction temperature, inputting the current traction force, speed and initial junction temperature into the insulated gate bipolar transistor module loss prediction model to obtain power loss data of the insulated gate bipolar transistor module;

[0011] Inputting the power loss data of the insulated gate bipolar transistor module into the insulated gate bipolar transistor module junction temperature equivalent thermal resistance network model to calculate the junction temperature, and obtaining the junction temperature fluctuation data of the insulated gate bipolar transistor module; wherein the junction temperature output by the insulated gate bipolar transistor module junction temperature equivalent thermal resistance network model each time is used as the input for predicting the power loss of the insulated gate bipolar transistor module next time;

[0012] The life loss value of the insulated gate bipolar transistor module is calculated using the junction temperature fluctuation data.

[0013] As a preferred solution, the method for constructing an insulated gate bipolar transistor module loss prediction model includes:

[0014] The operating electrical parameters and corresponding junction temperature of the insulated gate bipolar transistor module of the train motor at different torques and speeds are obtained by combining the historical operating data of the train motor with the table lookup method;

[0015] The operating electrical parameters of the insulated gate bipolar transistor module at different torques and speeds and the corresponding junction temperature are used for software simulation to obtain the historical power loss data of the insulated gate bipolar transistor module;

[0016] The preset BP neural network is trained using the historical power loss data of the insulated gate bipolar transistor module to obtain a trained BP neural network; wherein the torque and speed of the train motor and the current insulated gate bipolar transistor junction temperature are used as inputs of the BP neural network, and the historical power loss data of the insulated gate bipolar transistor module is used as output of the BP neural network.

[0017] The operating electrical parameters of the insulated gate bipolar transistor module include motor stator current, modulation coefficient and power factor.

[0018] As a preferred solution, a method for constructing an insulated gate bipolar transistor module junction temperature equivalent thermal resistance network model includes:

[0019] The Foster model is used to calculate the junction temperature. The Foster model includes a junction-shell module, a shell-heat sink module and a heat sink-environment module. The output end of the junction-shell module is connected to the input end of the shell-heat sink module, and the output end of the shell-heat sink module is connected to the input end of the heat sink-environment module. The power loss data of the insulated gate bipolar transistor is used as the input of the junction-shell module, and the output of the heat sink-environment module is the current junction temperature data.

[0020] As a preferred solution, the junction-shell module includes a resistor R1, a resistor R2, a resistor R3, a resistor R4, a capacitor C1, a capacitor C2, a capacitor C3 and a capacitor C4; the resistor R1, the resistor R2, the resistor R3 and the resistor R4 are connected in series, and the resistor R1, the resistor R2, the resistor R3 and the resistor R4 are respectively connected in parallel with the capacitor C1, the capacitor C2, the capacitor C3 and the capacitor C4; the shell-radiator module includes a resistor R5 and a capacitor C5, and the resistor R5 is connected in parallel with the capacitor C5; the radiator-environment module includes a resistor R6 and a capacitor C6, and the resistor R5 is connected in parallel with the capacitor C5.

[0021] As a preferred solution, the method for calculating the life loss value of the insulated gate bipolar transistor module using the junction temperature fluctuation data includes:

[0022] Obtaining an average junction temperature according to the junction temperature fluctuation data;

[0023] Calculating the number of power cycles of the insulated gate bipolar transistor module using the average junction temperature;

[0024] The life loss value of the insulated gate bipolar transistor module is calculated by using the power cycle number of the insulated gate bipolar transistor module.

[0025] As a preferred solution, the method for obtaining the average junction temperature according to the junction temperature fluctuation data includes:

[0026] According to the junction temperature fluctuation data, the maximum junction temperature data T is obtained. jmax , the maximum junction temperature data T jmax Substitute the following formula to calculate the average junction temperature T m :

[0027] Tm=Tmaxx-ATj / 2

[0028] Where, ΔT j is the junction temperature difference, T jmax is the maximum junction temperature data, T m is the average junction temperature.

[0029] As a preferred solution, the calculation formula for obtaining the number of power cycles of the insulated gate bipolar transistor module by using the average junction temperature is:

[0030]

[0031] Among them, N f is the number of power cycles of the IGBT module; A is a constant related to product characteristics, geometry, and test methods; R is the air constant; Q is the activation energy related to the material, and the values ​​of Q and α are determined by the specific IGBT model.

[0032] As a preferred solution, the calculation formula for calculating the life loss value of the insulated gate bipolar transistor module by using the power cycle number of the insulated gate bipolar transistor module is:

[0033]

[0034] R is the life loss value of the insulated gate bipolar transistor module.

[0035] A second aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the aforementioned method for estimating the life loss of an insulated gate bipolar transistor of a train traction inverter.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention combines the table lookup method and the BP neural network to take into account all electrical parameters of the IGBT during operation, thereby improving the accuracy of the IGBT module power loss calculation, thereby significantly enhancing the accuracy of the junction temperature calculation results, and further calculating more accurate IGBT life loss data;

[0038] The present invention combines the neural network with the equivalent thermal resistance network, which not only has the accuracy of the neural network loss calculation, but also combines the time continuity of the equivalent thermal resistance network. Compared with other methods that only use the neural network calculation or only use the equivalent thermal resistance network, the result is more accurate.

[0039] The present invention can achieve accurate estimation of IGBT life loss only through the two parameters of traction force and speed output by the traction motor. This method not only ensures the high efficiency of calculation, but also shows remarkable convenience in operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A flow chart of a method for estimating the life loss of an insulated gate bipolar transistor of a train traction inverter provided in this embodiment;

[0041] Figure 2 The overall flow chart of the method for estimating the life loss of an insulated gate bipolar transistor provided in this embodiment;

[0042] Figure 3 This is a schematic diagram of the Foster model structure provided in this embodiment. DETAILED DESCRIPTION

[0043] The accompanying drawings are only used for illustrative purposes and are not to be construed as limiting the present invention;

[0044] It should be clear that the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of the present application.

[0045] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0046] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0047] In addition, in the description of this application, unless otherwise specified, "multiple" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0048] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0049] Example 1

[0050] Please refer to Figure 1 as well as Figure 2 This embodiment provides a method for estimating the life loss of an insulated gate bipolar transistor of a train traction inverter, the method comprising:

[0051] S1: Construct an IGBT module loss prediction model;

[0052] S2: Construct an equivalent thermal resistance network model of the junction temperature of the insulated gate bipolar transistor module;

[0053] S3: Collect the current traction force Te and speed n of the train motor and set the initial junction temperature, input the current traction force Te, speed n and initial junction temperature into the IGBT module loss prediction model, and obtain the power loss data P of the IGBT module. loss ;

[0054] Specifically, the initial junction temperature is an ambient temperature value;

[0055] More specifically, the ambient temperature value is 25°C.

[0056] S4: inputting the power loss data of the insulated gate bipolar transistor module into the insulated gate bipolar transistor module junction temperature equivalent thermal resistance network model to calculate the junction temperature, and obtaining the junction temperature fluctuation data of the insulated gate bipolar transistor module; wherein, the junction temperature output by the insulated gate bipolar transistor module junction temperature equivalent thermal resistance network model each time is used as the input for predicting the power loss of the insulated gate bipolar transistor module next time;

[0057] S5: Calculate the life loss value of the insulated gate bipolar transistor module using the junction temperature fluctuation data.

[0058] In a specific embodiment, a method for constructing an insulated gate bipolar transistor module loss prediction model includes:

[0059] The operating electrical parameters and corresponding junction temperature of the insulated gate bipolar transistor module of the train motor at different torques and speeds are obtained by combining the historical operating data of the train motor with the table lookup method;

[0060] The operating electrical parameters of the insulated gate bipolar transistor module at different torques and speeds and the corresponding junction temperature are used for software simulation to obtain the historical power loss data of the insulated gate bipolar transistor module;

[0061] Specifically, the operating electrical parameters of the insulated gate bipolar transistor module under different torques and speeds and the corresponding junction temperatures are input into the IPOSIM software for simulation to obtain the historical power loss data of the insulated gate bipolar transistor module.

[0062] The preset BP neural network is trained using the historical power loss data of the insulated gate bipolar transistor module to obtain a trained BP neural network; wherein the torque and speed of the train motor and the current insulated gate bipolar transistor junction temperature are used as inputs of the BP neural network, and the historical power loss data of the insulated gate bipolar transistor module is used as output of the BP neural network.

[0063] In a specific embodiment, the operating electrical parameters of the insulated gate bipolar transistor module include the motor stator current I, the modulation coefficient cos and the power factor m.

[0064] In a specific embodiment, a method for constructing an insulated gate bipolar transistor module junction temperature equivalent thermal resistance network model includes:

[0065] The Foster model (equivalent thermal resistance network model) is used to calculate the junction temperature. The Foster model includes a junction-shell module, a shell-heat sink module and a heat sink-environment module. The output end of the junction-shell module is connected to the input end of the shell-heat sink module, and the output end of the shell-heat sink module is connected to the input end of the heat sink-environment module. The power loss data of the insulated gate bipolar transistor is used as the input of the junction-shell module, and the output of the heat sink-environment module is the current junction temperature data.

[0066] In a specific embodiment, please refer to Figure 3 The junction-shell module includes a resistor R1, a resistor R2, a resistor R3, a resistor R4, a capacitor C1, a capacitor C2, a capacitor C3 and a capacitor C4; the resistor R1, the resistor R2, the resistor R3 and the resistor R4 are connected in series, and the resistor R1, the resistor R2, the resistor R3 and the resistor R4 are connected in parallel with the capacitor C1, the capacitor C2, the capacitor C3 and the capacitor C4 respectively; the shell-heat sink module includes a resistor R5 and a capacitor C5, and the resistor R5 is connected in parallel with the capacitor C5; the heat sink-environment module includes a resistor R6 and a capacitor C6, and the resistor R5 is connected in parallel with the capacitor C5.

[0067] In a specific embodiment, a method for calculating the life loss value of an insulated gate bipolar transistor module using the junction temperature fluctuation data includes:

[0068] Obtaining an average junction temperature according to the junction temperature fluctuation data;

[0069] Calculating the number of power cycles of the insulated gate bipolar transistor module using the average junction temperature;

[0070] The life loss value of the insulated gate bipolar transistor module is calculated by using the power cycle number of the insulated gate bipolar transistor module.

[0071] In a specific embodiment, a method for obtaining an average junction temperature according to the junction temperature fluctuation data includes:

[0072] According to the junction temperature fluctuation data, the maximum junction temperature data T is obtained. jmax , the maximum junction temperature data T jmax Substitute the following formula to calculate the average junction temperature T m :

[0073] Tm=Tjmax-ATj / 2

[0074] Where, ΔT j is the junction temperature difference, T jmax is the maximum junction temperature data, T m is the average junction temperature.

[0075] In a specific embodiment, the calculation formula for obtaining the number of power cycles of the insulated gate bipolar transistor module by using the average junction temperature is:

[0076]

[0077] Among them, N f is the number of power cycles of the IGBT module; A is a constant related to product characteristics, geometry, and test methods; R is the air constant; Q is the activation energy related to the material, and the values ​​of Q and α are determined by the specific IGBT model.

[0078] In a specific embodiment, the calculation formula for calculating the life loss value of the insulated gate bipolar transistor module by using the power cycle number of the insulated gate bipolar transistor module is:

[0079]

[0080] R is the life loss value of the insulated gate bipolar transistor module.

[0081] Example 2

[0082] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of a method for estimating the life loss of an insulated gate bipolar transistor of a train traction inverter in Embodiment 1 are implemented.

[0083] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for estimating the life loss of insulated gate bipolar transistors of a train traction inverter, characterized in that: The method comprises: Construct an insulated gate bipolar transistor module loss prediction model; Construct the junction temperature equivalent thermal resistance network model of the insulated gate bipolar transistor module; Collecting the current traction force and speed of the train motor and setting the initial junction temperature, inputting the current traction force, speed and initial junction temperature into the insulated gate bipolar transistor module loss prediction model to obtain power loss data of the insulated gate bipolar transistor module; Inputting the power loss data of the insulated gate bipolar transistor module into the insulated gate bipolar transistor module junction temperature equivalent thermal resistance network model to calculate the junction temperature, and obtaining the junction temperature fluctuation data of the insulated gate bipolar transistor module; wherein the junction temperature output by the insulated gate bipolar transistor module junction temperature equivalent thermal resistance network model each time is used as the input for predicting the power loss of the insulated gate bipolar transistor module next time; The life loss value of the insulated gate bipolar transistor module is calculated using the junction temperature fluctuation data.

2. A method for estimating the life loss of an insulated gate bipolar transistor of a train traction inverter according to claim 1, characterized in that: The method for constructing an IGBT module loss prediction model includes: The operating electrical parameters and corresponding junction temperature of the insulated gate bipolar transistor module under different torques and speeds of the train motor are obtained by combining the historical operation data of the train motor with the table lookup method; The operating electrical parameters of the insulated gate bipolar transistor module at different torques and speeds and the corresponding junction temperature are used for software simulation to obtain the historical power loss data of the insulated gate bipolar transistor module; The preset BP neural network is trained using the historical power loss data of the insulated gate bipolar transistor module to obtain a trained BP neural network; wherein the torque and speed of the train motor and the current insulated gate bipolar transistor junction temperature are used as inputs of the BP neural network, and the historical power loss data of the insulated gate bipolar transistor module is used as output of the BP neural network.

3. A method for estimating the life loss of insulated gate bipolar transistors of a train traction inverter according to claim 2, characterized in that: The operating electrical parameters of the insulated gate bipolar transistor module include motor stator current, modulation coefficient and power factor.

4. The method for estimating the life loss of an insulated gate bipolar transistor of a train traction inverter according to claim 1, characterized in that: The method for constructing the junction temperature equivalent thermal resistance network model of the insulated gate bipolar transistor module includes: The Foster model is used to calculate the junction temperature. The Foster model includes a junction-shell module, a shell-heat sink module and a heat sink-environment module. The output end of the junction-shell module is connected to the input end of the shell-heat sink module, and the output end of the shell-heat sink module is connected to the input end of the heat sink-environment module. The power loss data of the insulated gate bipolar transistor is used as the input of the junction-shell module, and the output of the heat sink-environment module is the current junction temperature data.

5. A method for estimating the life loss of insulated gate bipolar transistors of a train traction inverter according to claim 4, characterized in that: The junction-shell module includes a resistor R1, a resistor R2, a resistor R3, a resistor R4, a capacitor C1, a capacitor C2, a capacitor C3 and a capacitor C4; the resistor R1, the resistor R2, the resistor R3 and the resistor R4 are connected in series, and the resistor R1, the resistor R2, the resistor R3 and the resistor R4 are connected in parallel with the capacitor C1, the capacitor C2, the capacitor C3 and the capacitor C4 respectively; the shell-radiator module includes a resistor R5 and a capacitor C5, and the resistor R5 is connected in parallel with the capacitor C5; the radiator-environment module includes a resistor R6 and a capacitor C6, and the resistor R5 is connected in parallel with the capacitor C5.

6. The method for estimating the life loss of insulated gate bipolar transistors of a train traction inverter according to claim 1, characterized in that: The method for calculating the life loss value of the insulated gate bipolar transistor module using the junction temperature fluctuation data includes: Obtaining an average junction temperature according to the junction temperature fluctuation data; Calculating the number of power cycles of the insulated gate bipolar transistor module using the average junction temperature; The life loss value of the insulated gate bipolar transistor module is calculated by using the power cycle number of the insulated gate bipolar transistor module.

7. A method for estimating the life loss of insulated gate bipolar transistors of a train traction inverter according to claim 6, characterized in that: The method for obtaining the average junction temperature according to the junction temperature fluctuation data includes: According to the junction temperature fluctuation data, the maximum junction temperature data T is obtained. jmax , the maximum junction temperature data T jmax Substitute the following formula to calculate the average junction temperature T m : T m = jmax -ΔT j / 2 Where, ΔT j is the junction temperature difference, T jmax is the maximum junction temperature data, T m is the average junction temperature.

8. A method for estimating the life loss of insulated gate bipolar transistors of a train traction inverter according to claim 7, characterized in that: The calculation formula for obtaining the number of power cycles of the insulated gate bipolar transistor module by using the average junction temperature is: Among them, N f is the number of power cycles of the IGBT module; A is a constant related to product characteristics, geometry, and test methods; R is the air constant; Q is the activation energy related to the material, and the values ​​of Q and α are determined by the specific IGBT model.

9. A method for estimating the life loss of insulated gate bipolar transistors of a train traction inverter according to claim 8, characterized in that: The calculation formula for calculating the life loss value of the insulated gate bipolar transistor module by using the power cycle number of the insulated gate bipolar transistor module is: R is the life loss value of the insulated gate bipolar transistor module.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for estimating the life loss of an insulated gate bipolar transistor of a train traction inverter as described in any one of claims 1 to 8 are implemented.

Citation Information

Patent Citations

  • A method and a device for obtaining loss power of an insulated gate bipolar transistor

    CN109558681A

  • Life prediction method of IGBT device based on semi-physical simulation platform

    CN110147578A

  • Locomotive traction distribution method and device for reducing life loss of IGBT module

    CN112896200A

  • Vehicle power module junction temperature estimation method and device, electronic equipment and storage medium

    CN116702601A