CN116702675A - Power module junction temperature estimation method and device, electronic equipment and storage medium - Google Patents

Power module junction temperature estimation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN116702675A
CN116702675A CN202310635986.9A CN202310635986A CN116702675A CN 116702675 A CN116702675 A CN 116702675A CN 202310635986 A CN202310635986 A CN 202310635986A CN 116702675 A CN116702675 A CN 116702675A
Authority
CN
China
Prior art keywords
junction temperature
current
power module
network model
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310635986.9A
Other languages
Chinese (zh)
Inventor
刘立
魏凡翼
陈健
陈扬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Deep Blue Automotive Technology Co ltd
Original Assignee
Deep Blue Automotive Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Deep Blue Automotive Technology Co ltd filed Critical Deep Blue Automotive Technology Co ltd
Priority to CN202310635986.9A priority Critical patent/CN116702675A/en
Publication of CN116702675A publication Critical patent/CN116702675A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/30—Circuit design
    • G06F30/36—Circuit design at the analogue level
    • G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K7/00—Measuring temperature based on the use of electric or magnetic elements directly sensitive to heat ; Power supply therefor, e.g. using thermoelectric elements
    • G01K7/16—Measuring temperature based on the use of electric or magnetic elements directly sensitive to heat ; Power supply therefor, e.g. using thermoelectric elements using resistive elements
    • G01K7/22—Measuring temperature based on the use of electric or magnetic elements directly sensitive to heat ; Power supply therefor, e.g. using thermoelectric elements using resistive elements the element being a non-linear resistance, e.g. thermistor
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/26—Testing of individual semiconductor devices
    • G01R31/2601—Apparatus or methods therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2115/00—Details relating to the type of the circuit
    • G06F2115/02—System on chip [SoC] design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04—Ageing analysis or optimisation against ageing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/08—Thermal analysis or thermal optimisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Nonlinear Science (AREA)
  • Power Conversion In General (AREA)

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.

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-state current and high voltage resistance, and plays a role in 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 method for predicting junction temperature of an IGBT module, by establishing a high-order thermal resistance model of the IGBT module, calculating power loss in a certain period to calculate the junction temperature of the IGBT module in the period, 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 thermal resistance model has a large calculation 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 following steps: 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; and 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 junction temperature estimation neural network model after training, and updating the junction temperature estimation neural network model of the corresponding vehicle end of the target power module to carry out power module junction temperature estimation.
In an embodiment of the present application, the switching frequency, the voltage data, the current data and the temperature data in the current working condition data are input to a preset electrothermal network model, so that after the electrothermal network model outputs the current junction temperature, the power module junction temperature estimation method includes: determining the actual residual life of the target power module based on the historical junction temperature and the current junction temperature output by the electrothermal network model; calculating the life attenuation degree of the target power module based on the current period residual life and the actual residual life; and if the life attenuation degree reaches a preset threshold, transmitting the actual remaining life and the new junction temperature estimation neural network model to a vehicle end so that the vehicle end can determine 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 present application, determining the actual remaining life of the target power module based on the historical junction temperature and the current junction temperature output by the electrothermal network model includes: 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.
In an embodiment of the present application, if the lifetime degradation degree reaches a preset threshold, the power module junction temperature estimation method further includes: 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 calculating a new thermal impedance value 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 value in the electrothermal network model, wherein the working condition data also comprises the input power.
In an embodiment of the present application, the method for establishing the electrothermal network model includes: 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.
In an embodiment of the present application, performing iterative training on the current junction temperature estimated neural network model based on the current working condition data, the current cycle remaining life and the current junction temperature to obtain a trained new junction temperature estimated neural network model, including: 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.
In an embodiment of the application, before the electrothermal network model is built, the power module junction temperature estimation method includes: 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.
In an embodiment of the present application, there is further provided a power module junction temperature estimation device, including: 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; and the updating module is used for updating the junction temperature estimation neural network model of the corresponding vehicle end of the target power module so as to estimate the junction temperature of the power module.
In an embodiment of the present application, there is also provided an electronic device including: one or more processors; and a 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 as described above.
In an embodiment of the present application, there is also provided 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 as described above.
The application has the beneficial effects that: the application provides a junction temperature estimation method, a device, electronic equipment and a storage medium based on a power module, wherein the junction temperature estimation method considers the influence of service life attenuation on a thermal impedance value and junction temperature, a thermoelectric network model is pre-established based on the changed thermal impedance value, junction temperature calculation is carried out through the changed thermoelectric network model, reliability of the thermoelectric network model is improved, further accuracy of the junction temperature calculation of the thermoelectric network model is ensured, iterative training is carried out on the current junction temperature estimation neural network model based on current working condition data, current cycle residual service life and current junction temperature output by the thermoelectric network model, the junction temperature estimation neural network model of a vehicle end is updated, reliability of the junction temperature estimation neural network model is improved, further accuracy of junction temperature calculation of a target power module by the vehicle end is ensured, calculation amount of junction temperature estimation of the vehicle end power module is reduced, and load factor of the vehicle-mounted ECU is reduced.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is evident that the drawings in the following description are only some embodiments of the present application and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the drawings:
FIG. 1 is a schematic diagram of an exemplary embodiment of a method for estimating junction temperature of a power module;
FIG. 2 is a flow chart illustrating a method of estimating junction temperature of a power module according to an exemplary embodiment of the application;
FIG. 3 is a flow chart illustrating the vehicle side estimation of the IGBT module junction temperature according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a junction temperature estimation neural network model according to an embodiment of the present application;
FIG. 5 is a flow chart illustrating a client-server interaction according to an embodiment of the present application;
FIG. 6 is a flow chart illustrating actual remaining life calculation according to an embodiment of the present application;
FIG. 7 is a flow chart illustrating a server-side estimated IGBT module junction temperature and neural network training according to an embodiment of the application;
FIG. 8 is a block diagram of a power module junction temperature estimation device according to an exemplary embodiment of the present application;
fig. 9 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the application.
Detailed Description
Further advantages and effects of the present application will become readily apparent to those skilled in the art from the disclosure herein, by referring to the accompanying drawings and the preferred embodiments. The application may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present application. It should be understood that the preferred embodiments are presented by way of illustration only and not by way of limitation.
It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present application by way of illustration, and only the components related to the present application are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
It should be noted that, in the present application, "first", "second", and the like are merely distinguishing between similar objects, and are not limited to the order or precedence of similar objects. The description of variations such as "comprising," "having," etc., means that the subject of the word is not exclusive, except for the examples shown by the word.
It should be understood that the various numbers and steps described in this disclosure are for convenience of description and are not to be construed as limiting the scope of the application. The magnitude of the present application reference numerals does not mean the order of execution, and the order of execution of the processes should be determined by their functions and inherent logic.
In the following description, numerous details are set forth in order to provide a more thorough explanation of embodiments of the present application, it will be apparent, however, to one skilled in the art that embodiments of the present application may be practiced without these specific details, in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the embodiments of the present application.
The IGBT module mainly includes an IGBT chip, a solder layer, a copper-clad ceramic substrate, a bottom plate, and the like. Along with the fluctuation of load and operation condition, the temperature fluctuation of the IGBT chip is larger, and the heat emitted by the IGBT chip is conducted to the cooling system from top to bottom. Thermal expansion coefficient mismatch between each layer of material in the IGBT module can lead to the generation of thermal stress and mechanical stress, accelerates the ageing process of module, causes solder layer fatigue, bonding line crackle even breaks away from, finally leads to IGBT module to become invalid. Therefore, the IGBT module junction temperature is a key parameter for IGBT module state detection. The junction temperature of the IGBT module is also called as the junction temperature of the power module or the junction temperature of the IGBT, which refers to the highest temperature when the IGBT chip operates, and the service life evaluation of the IGBT module depends on accurate junction temperature detection. The quantitative research on the relationship between the service life of the IGBT module and the junction temperature of the IGBT module mainly comprises a physical model method and an analytical model method. In actual conditions, the physical model is difficult to extract the stress of each layer in the device, special instruments and equipment are needed, and the model precision is difficult to prove. The analytical model method takes the interior as a whole, and indirectly reflects the process of creep damage of the material caused by damage accumulation of internal thermal stress through measuring external parameters. The thermal network method is used as the most common analytical model, and the junction temperature of the IGBT module is estimated by calculating the average power loss of the IGBT module. However, the fatigue damage caused by load current impact to the IGBT module in the working process of the IGBT module is not considered in the hot network method, namely, the thermal resistance value in the hot network is not updated, which can cause the estimated junction temperature of the IGBT module to be smaller than the actual result along with the attenuation of the service life of the IGBT module. Secondly, a great amount of calculation resources are needed to be occupied for estimating the junction temperature of the IGBT module by a hot network method on line, and the load rate of the vehicle-mounted ECU is improved.
To solve the above problems, embodiments of the present application respectively provide a power module junction temperature estimation method, a power module junction temperature estimation apparatus, an electronic device, a computer-readable storage medium, and a computer program product, and these embodiments will be described in detail below.
Referring to fig. 1, fig. 1 is a schematic diagram illustrating an implementation environment of a method for estimating a junction temperature of a power module according to an exemplary embodiment of the application.
As shown in fig. 1, the implementation environment may include a vehicle end 101 and a service end 102, where the service end 102 may be an independent physical server, may be a server cluster or a distributed system formed by a plurality of physical servers, and may also be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network, content distribution network), and basic cloud computing services such as big data and an artificial intelligence platform, which are not limited herein. The vehicle end 101 collects current working condition data of the target power module in a sensor mode and the like, and sends the current working condition data of the target power module and the current period residual life to the server end 102, so that the server end 102 carries out iterative training on the current junction temperature estimation neural network model. Note that the remaining life of the target power module in the current cycle is stored in the vehicle end 101.
The server 102 obtains current operating condition data and current cycle remaining life of the target power module, where the operating condition data includes switching frequency, voltage data, current data, and temperature data; inputting switching frequency, voltage data, current data and temperature data in current working condition data into a preset electrothermal network model so that the electrothermal network model outputs the current junction temperature, and the electrothermal network model is built based on a thermal impedance value of a target power module, wherein the thermal impedance value is changed; and 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, and updating the junction temperature estimation neural network model of the target power module corresponding to the vehicle end 101 to carry out power module junction temperature estimation. Therefore, the technical scheme of the embodiment of the application establishes the electrothermal network model in advance at the service end based on the changed thermal impedance value, calculates the junction temperature through the changed electrothermal network model, improves the reliability of the electrothermal network model, further ensures the accuracy of the junction temperature calculation of the electrothermal network model, iteratively trains 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 output by the electrothermal network model, updates the junction temperature estimation neural network model of the vehicle end, improves the reliability of the junction temperature estimation neural network model, further ensures the accuracy of the junction temperature calculation of the target power module by the vehicle end, reduces the calculation amount of the junction temperature estimation of the power module of the vehicle end, and reduces the load rate of the vehicle-mounted ECU.
It should be noted that, the power module junction temperature estimation method provided in the embodiment of the present application is generally executed by the server 102, and the corresponding power module junction temperature estimation device is generally disposed in the server 102.
Referring to fig. 2, fig. 2 is a flowchart illustrating a method for estimating junction temperature of a power module according to an exemplary embodiment of the application. The method may be applied to the implementation environment shown in fig. 1, and specifically executed by the server 102 in the implementation environment. It should be understood that the method may be applied to other exemplary implementation environments and be specifically executed by devices in other implementation environments, and the implementation environments to which the method is applied are not limited by the present embodiment.
As shown in fig. 2, in an exemplary embodiment, the power module junction temperature estimation method at least includes steps S210 to S230, which are described in detail as follows:
step S210, current working condition data and current period residual life of the target power module are obtained.
In one embodiment of the application, the vehicle end collects current working condition data of the target power module through a sensor and the like, wherein the working condition data comprises switching frequency, voltage data, current data and temperature data, the voltage data at least comprises one of conduction voltage drop and bus voltage, the current data at least comprises one of collector current and load current, and the temperature data at least comprises one of shell temperature and cooling water temperature of the target power module. The vehicle end can actively upload the collected current working condition data and the stored current period residual life to the server end in real time or periodically, or the server end can send an acquisition request to the vehicle end in real time or periodically to acquire the current working condition data and the current period residual life, which is not limited herein. The cooling water is also called a cooling liquid, and may be specifically pure water, or other liquid medium such as oil or glycol, which is not limited herein.
Step S220, 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 the electrothermal network model outputs the current junction temperature.
In one embodiment of the present application, an electrothermal network model is preset in the server, the electrothermal network model is built based on the thermal impedance value of the target power module, and the thermal impedance value is changed, which increases with the decay of the lifetime of the target power module. Generally, the IGBT module fluctuates in junction temperature due to the variation of load current, and the current impacts the IGBT module to generate thermal stress to interact between the layers of structures, and fatigue damage is generated by cyclic reciprocation, which ultimately leads to device failure. The thermal resistance value of the IGBT module also increases with the decay of the lifetime. If the change of the thermal impedance value in the process is not considered, the finally calculated junction temperature of the IGBT module is smaller and deviates from the actual situation. Therefore, the embodiment of the application establishes the electrothermal network model in advance based on the changed thermal impedance value, and calculates the junction temperature through the electrothermal network model, the switching frequency, the voltage data, the current data and the temperature data, so that the reliability of the electrothermal network model can be ensured, and the accuracy of the electrothermal network model in junction temperature calculation is further ensured.
In one embodiment of the present application, the method for establishing the electrothermal network model includes: 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 an electrothermal network model so as to calculate the junction temperature.
In the embodiment, a power loss model of a digital twin IGBT module corresponding to a target power module is established, the power loss model is used for calculating on-state loss power and switching loss power of the target power module, and further loss power is obtained, wherein the on-state loss power is related to on-voltage drop in voltage data and collector current in current data, the switching loss power is related to switching frequency, bus voltage in the voltage data and load current in current data, and the loss power consists of the on-state loss power and the switching loss power. Therefore, the equation for the power loss model is as follows:
wherein P is loss To lose power, P cond To be on-state to consume power, P sw For switching power loss, U ce To turn on the voltage drop, I c For the collector current, m is the modulation ratio,r is the power factor T Is IGBT internal resistance, f sw For switching frequency, E on To turn on energy E off To turn off the energy, U dc Is the bus voltage, U nom At rated voltage, I m For load current, I nom Is rated current. It should be noted that, the modulation ratio, the power factor and the IGBT internal resistance are relatively fixed parameters, and the variation is not great in practical application, and the on-state energy, the off-state energy, the rated voltage and the rated current can be obtained through a calibration test or an IGBT data manual corresponding to the target power module.
And establishing a thermal network model of the digital twin IGBT module corresponding to the target power module, wherein the junction temperature of the target power module is related to the loss power, the thermal impedance value and the shell temperature, so that the equation of the thermal network model is as follows:
T j ＝P loss Z th +T c (2)
Wherein T is j Junction temperature, P loss To lose power, Z th Is a thermal impedance value, T c Is the shell temperature.
Coupling the power loss model and the thermal network model, establishing a corresponding electrothermal network model, and estimating the junction temperature of the target power module by using the electrothermal network model, for example: the switching frequency, the voltage data, the current data and the temperature data in the current working condition data are input into an electric heating network model, the power loss model calculates the current conduction loss power according to the conduction voltage drop and the collector current in the current working condition data, calculates the current switching loss power according to the switching frequency, the bus voltage and the load current in the current working condition data, determines the sum of the current conduction loss power and the current switching loss power as the current loss power, and the thermal network model calculates the current junction temperature according to the thermal impedance value, the shell temperature in the current working condition data and the current loss power output by the power loss model.
In addition, because the shell temperature and the cooling water temperature have a linear relation, a thermal network model can be built based on the loss power, the thermal impedance value and the cooling water temperature, so that the thermal network model can calculate the current junction temperature according to the thermal impedance value, the cooling water temperature in the current working condition data and the current loss power output by the power loss model.
In one embodiment of the application, the power module junction temperature estimation method comprises the following steps of: acquiring the voltage drop of a target power module, wherein the voltage drop of the power module represents the aging degree of the power module; performing an aging experiment on the 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, and taking the thermal impedance value as a thermal impedance value of the target power module to establish an electrothermal network model.
In the embodiment, the sample power module is subjected to an aging experiment through power circulation, heating is stopped when the temperature reaches the upper limit and heating is started when the temperature reaches the lower limit, and the circulating thermal stress continuously impacts the sample power module, so that the aging purpose is achieved. And observing the pressure drop of the sample power module in the aging experiment process, if the pressure drop of the sample power module reaches the pressure drop of the target power module, stopping heating, measuring the junction temperature, the shell temperature and the input power of the sample power module in the cooling process, taking the input power of the sample power module as the loss power of the sample power module, calculating the thermal impedance value of the sample power module according to the loss power, the junction temperature and the shell temperature of the sample power module and the formula (2), taking the thermal impedance value as the thermal impedance value of the target power module, and establishing an electrothermal network model based on the thermal impedance value. When the IGBT module is heated with a fixed current and reaches a thermal equilibrium state, the power loss is the same as the input power. In addition, transient thermal impedance values under different aging degrees, namely thermal impedance values under different aging degrees, can be obtained according to the magnitude of the damage accumulation degree, so as to obtain a residual life-thermal impedance value curve.
Step S230, performing 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 junction temperature estimation neural network model after training, and updating the junction temperature estimation neural network model of the corresponding vehicle end of the target power module to perform power module junction temperature estimation.
In one embodiment of the application, the service life attenuation of the IGBT module influences the junction temperature of the IGBT module, and the accuracy of the neural network depends on a large number of data training sets with differences, so that the neural network model trained by real parameters under the non-actual driving working condition is under-fitted. Therefore, the residual life, the switching frequency, the voltage data, the current data and the temperature data can be taken as characteristic parameters of the neural network, the junction temperature is taken as output of the neural network, the neural network is trained, the trained neural network is determined to be a junction temperature estimated neural network model, and then the current junction temperature estimated neural network model is iteratively trained through the residual life in the current period, the current junction temperature, the switching frequency in the current working condition data, the voltage data, the current data and the temperature data. According to the embodiment of the application, the influence of the service life attenuation of the target power module on the junction temperature of the target power module is considered, the actual working condition data of the automobile is combined, the data sample size is large and has variability, the junction temperature estimation neural network model can be trained more accurately, the reliability of the junction temperature estimation neural network model is improved, the accuracy of junction temperature calculation of the target power module by the automobile end is further ensured, the calculation amount of junction temperature estimation of the automobile end power module is reduced, and the load rate of the vehicle-mounted ECU is reduced.
In this embodiment, the server may periodically send the trained new junction temperature estimation neural network model to the vehicle end, so that the vehicle end performs power module junction temperature estimation through the new junction temperature estimation neural network model. For example: the service end uploads the new junction temperature estimation neural network model to an OTA (Over the Air) platform every 1 day, and pushes an upgrade package of the new junction temperature estimation neural network model to the vehicle end through the OTA platform so as to upgrade and update the junction temperature estimation neural network model of the vehicle end.
For the vehicle end, the power module junction temperature estimation is carried out through the current junction temperature estimation neural network model in the current period, and the power module junction temperature estimation is carried out through the new junction temperature estimation neural network model in the next period, so that the calculated amount of the vehicle end can be reduced, and the calculation load of the vehicle-mounted chip is reduced.
In another embodiment of the present application, the iterative training is performed on the current junction temperature estimated neural network model based on the current working condition data, the current cycle remaining life and the current junction temperature, to obtain a trained new junction temperature estimated neural network model, including: and performing iterative training on the current junction temperature estimation neural network model by taking the current cycle residual life, the switching frequency, the bus voltage, the collector current and the cooling water temperature in the current working condition data as input values and the current junction temperature as output values to obtain a new junction temperature estimation neural network model, wherein the working condition data also comprises the rotating speed of the water pump, the voltage data comprises the bus voltage, and the current data comprises the collector current.
In this embodiment, the rotational speed of the water pump refers to the rotational speed of the pump of the cooling water in the cooling system of the target power module, and since the rotational speed of the water pump also affects the junction temperature of the IGBT module, the switching frequency, the bus voltage, the collector current, the cooling water temperature, and the remaining life are used as characteristic parameters of the neural network, and at the same time, the rotational speed of the water pump is also used as characteristic parameters of the neural network, the junction temperature is used as output of the neural network, the neural network is trained, the trained neural network is determined as a junction temperature estimated neural network model, and then the current junction temperature estimated neural network model is iteratively trained by the switching frequency, the bus voltage, the collector current, the cooling water temperature, and the rotational speed of the water pump in the current cycle remaining life, the current junction temperature, and the current operating condition data. According to the embodiment of the application, the rotation speed of the water pump is used as one input quantity of iterative training, so that the accuracy of a new junction temperature estimation neural network model is further improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a vehicle end estimating an IGBT module junction temperature according to an embodiment of the application. As shown in fig. 3, the flow of estimating the junction temperature of the IGBT module at the vehicle end is as follows: the vehicle end collects the switching frequency f under the real-time working condition sw Collector current I c Bus voltage U dc The motor rotation speed n and the cooling water temperature T cool Will f sw 、I c 、U dc 、n、T cool And IGBT module current lifetime c 1 Current life c input to vehicle end 1 The junction temperature estimation neural network is the current junction temperature estimation neural network model, so that the junction temperature estimation neural network model calculates the junction temperature T of the IGBT module j And output.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a junction temperature estimation neural network model according to an embodiment of the application. As shown in fig. 4, the input layer of the junction temperature calculation neural network is the switching frequency f sw Collector current I c Bus voltage U dc The motor rotation speed n and the cooling water temperature T cool And IGBT module current lifetime c 1 The output layer is junction temperature T output by the electrothermal network model j . The switching frequency f under the real-time working condition sw Collector current I c Bus voltage U dc The motor rotation speed n and the cooling water temperature T cool And IGBT module current lifetime c 1 As characteristic parameters of the neural network, junction temperature T calculated according to the electrothermal network model is calculated j And as the output of the neural network, performing iterative training on the neural network under the current service life, namely the current junction temperature estimation neural network model, so as to obtain a new round of IGBT module junction temperature estimation neural network, namely a new junction temperature estimation neural network model.
In one embodiment of the present application, after step S220, the power module junction temperature estimation method includes: determining the actual residual life of the target power module based on the historical junction temperature and the current junction temperature output by the electrothermal network model; calculating the life attenuation degree of the target power module based on the current period residual life and the actual residual life; if the life attenuation degree reaches a preset threshold, the actual remaining life and a new junction temperature estimation neural network model are sent to the vehicle end, so that the vehicle end can determine the actual remaining life as the remaining life of the next period, and the junction temperature of the next period of the target power module is estimated through the new junction temperature estimation neural network model.
In this embodiment, when the life attenuation of the target power module is relatively slight, the estimation error of the junction temperature between the new and old junction temperature estimation neural network models is relatively small, and when the life attenuation of the target power module is relatively serious, the estimation error of the new and old junction temperature estimation neural network models is relatively large, and if the junction temperature estimation neural network model of the vehicle end is updated frequently, the long-term bandwidth resource occupation is easy to cause. Therefore, whether a new junction temperature estimation neural network model needs to be pushed to the vehicle end can be judged according to the service life attenuation degree of the target power module. The actual remaining life of the target power module can be determined according to the rain flow counting method and the life model, further the life attenuation degree of the target power module is determined, the difference between the remaining life of the current period and the actual remaining life can be used as the life attenuation degree, when the life attenuation degree reaches a preset threshold, the new junction temperature estimation neural network model is pushed to the vehicle end, and meanwhile the remaining life of the next period is pushed to the vehicle end, so that the vehicle end estimates the junction temperature of the next period of the target power module according to the new junction temperature estimation neural network model and by adopting the remaining life of the next period. It should be noted that, the time duration of the current period and the next period is not necessarily the same, but is determined according to the life attenuation degree, and when the life attenuation degree reaches the preset threshold, it indicates that the junction temperature estimation of the vehicle end to the target power module enters the next period from the current period. The preset threshold may be 2%, or other value, without limitation. According to the embodiment of the application, the updating time of the junction temperature estimation neural network model of the vehicle end is determined according to the service life attenuation degree of the target power module, so that the reliability and the accuracy of the junction temperature estimation of the target power module of the vehicle end can be ensured, and the occupation of bandwidth resources can be reasonably reduced.
Referring to fig. 5, fig. 5 is a flowchart illustrating a peer-to-server interaction according to an embodiment of the present application. As shown in fig. 5, the automobile end (automobile end) is responsible for sending real-time working condition data (including current working condition data and current cycle remaining life) to the big data platform end (service end), receiving a new junction temperature estimation neural network model pushed by the OTA platform and performing offline IGBT module junction temperature calculation. The big data platform end is in charge of receiving real-time working condition data sent by the automobile end, calculating junction temperature of the IGBT module under the current service life on line, updating the current junction temperature estimation neural network model, and determining service life attenuation degree of the IGBT module. When the service life attenuation degree reaches a preset threshold, the big data platform end sends a pushing request to the automobile end, and the automobile end determines whether to update the junction temperature estimation neural network model. If so, the new junction temperature estimation neural network model is updated to the automobile end through the OTA platform, so that the automobile end estimates the junction temperature of the IGBT module in the next period through the new junction temperature estimation neural network model.
In one embodiment of the application, determining the actual remaining life of the target power module based on the historical junction temperature and the current junction temperature output by the electrothermal network model includes: acquiring a plurality of historical junction temperatures output by an electrothermal network model; fitting a 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 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, wherein 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 the 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.
Referring to fig. 6, fig. 6 is a flowchart illustrating actual remaining life calculation according to an embodiment of the present application.
As shown in fig. 6, the actual remaining life calculation flow is as follows:
1. the rain flow counting method is used for carrying out fatigue load statistics (namely, thermal stress of each group and power circulation times under the thermal stress) on a junction temperature history curve. By using the rain flow counting method, the historical data of junction temperature (a plurality of historical junction temperatures and the current junction temperature) is subjected to average stress (average junction temperature T) according to the basic factors of power cycle jm ) Stress fluctuation amount (junction temperature fluctuation amount DeltaT) j ) Classifying, counting to obtain various stresses with different time and counting according to the corresponding rain flow and time to obtain a cycle number, so as to obtain a stress-cycle number curve, and providing data for researching fatigue damage. The rain flow counting method comprises the following specific processes:
1)T j indicating junction temperature, deltaT j Indicating the fluctuation amount of junction temperature T jm Indicating the average junction temperature. The "rain flow" starts from the starting point and flows downwards along the curve from the maximum point of the junction temperature history curve in sequence.
2) The "rain stream" starts flowing from a certain extreme point and falls when flowing to the extreme point until encountering an extreme point larger than its initial point, and stops flowing.
3) In the process of dropping the 'rain stream', once the 'rain stream' flowing down last is encountered, the 'rain stream' flowing track forms a cycle, and the number of cycles and the amplitude of each cycle are recorded.
4) Counting all the loops meeting the regulations, splicing the rest data, and repeating the three steps.
5) Statistics of the respective stress conditions (thermal stress of the respective groups) DeltaT j And T jm The number of power cycles below.
2. And establishing a Lesit life model based on a power cycle experiment and a damage accumulation rule. Considering the fluctuation amount DeltaT of junction temperature j Average junction temperature T jm Influence of two parameters on IGBT module, lesit life model is built based on power cycle experiment and damage accumulation rule, and calculation of life model is publicThe formula is as follows:
wherein N is f For failure cycle times, A and alpha are fitting parameters, deltaT j E is the fluctuation of junction temperature α Is the activation energy of 9.89×10 of the material -20 J，k B Is Boltzmann constant 1.38X10 -23 J·K -1 ，T jm Is the average junction temperature.
Delta T under different stress conditions j And T jm Substituting into formula (3) to obtain each stress condition DeltaT j And T jm The number of power cycles to failure when the lower IGBT fails.
3. Calculating the actual remaining life c 2 . And (5) corresponding the fatigue load obtained through statistics to a life model, and calculating the actual residual life of the target power module. First, the junction temperature fluctuation amount DeltaT is summarized j And average junction temperature T jm Corresponding times of the power cycle failure, a three-dimensional histogram is obtained, wherein the Z axis represents the times of the power cycle failure N f The X-axis represents the fluctuation amount DeltaT of junction temperature j The Y-axis represents the average junction temperature T jm The delta T under the junction temperature history curve obtained by statistics is calculated j And T jm Corresponding to the life model, respectively calculating the power cycle times N under each group of stress conditions cyc And the number of power cycles to failure N under the stress condition f And the ratio is added to obtain a fatigue damage cumulative value D so as to calculate the actual residual life. The actual remaining life is calculated as follows:
wherein c 2 For the actual residual life, D is the cumulative value of fatigue damage, N cyc For the number of power cycles, N f Is the number of power cycles to failure.
In one embodiment of the present application, if the life attenuation degree reaches the preset threshold, the power module junction temperature estimation method further includes: and 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.
In this embodiment, since the IGBT module varies in thermal resistance value with the accumulation of fatigue damage of the IGBT module even when the IGBT module is operated under the same operating condition, the calculated IGBT module junction temperature varies. Considering the influence of the life decay of the target power module on the thermal impedance value of the target power module, when the life decay degree reaches a preset threshold value, the thermal impedance value in the electrothermal network model is updated, so that the reliability and the accuracy of junction temperature estimation of the electrothermal network model can be ensured in the process of continuously decaying the life of the target power module. The specific updating mode is that average or weighted average calculation is carried out based on average junction temperature in each group of thermal stress, average value of all average junction temperature is obtained and is taken as average junction temperature of the current period, a new thermal impedance value is obtained according to calculation of a formula (2) according to average junction temperature of the current period, current loss power and shell temperature in current working condition data, and the thermal impedance value in the electric heating network model is updated to the new thermal impedance value, so that updating of the electric heating network model is completed. The current loss power can be calculated according to the formula (1) according to the switching frequency, the voltage data and the current data in the current working condition data. The current shell temperature can be estimated based on the linear relation among the cooling water temperature, the shell temperature and the cooling water temperature in the current working condition data, and a new thermal impedance value is calculated according to the formula (2) according to the average junction temperature of the current period, the current loss power and the estimated current shell temperature.
In another embodiment of the present application, if the life degradation degree reaches a preset threshold, the power module junction temperature estimation method further includes: 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.
In this embodiment, the input power in the current operating mode data may also be used as the current loss power to calculate the new thermal impedance value according to the method in the above embodiment.
In another embodiment of the present application, if the life degradation degree does not reach the preset threshold, neither the junction temperature estimation neural network model of the vehicle end nor the thermal impedance value is updated.
According to the technical scheme provided by the embodiment of the application, the service life attenuation degree of the target power module is newly added as the dimension of junction temperature settlement of the target power module, and the accuracy of junction temperature calculation is improved. And secondly, the junction temperature of the target power module is calculated off-line at the vehicle end by adopting the neural network, so that the calculation load of the vehicle-mounted chip is greatly reduced. Meanwhile, the actual residual life of the target power module is calculated, the current junction temperature estimation neural network model is updated and trained in real time on line, and then a new junction temperature estimation neural network model is pushed to a vehicle end through OTA to perform a new round of power module junction temperature calculation.
Referring to fig. 7, fig. 7 is a flowchart illustrating a server side estimating an IGBT module junction temperature and neural network training according to an embodiment of the application. As shown in fig. 7, the service side obtains the switching frequency f under the real-time working condition of the vehicle side sw Collector current I c Load current I m Bus voltage U dc Conduction voltage drop U ce The motor rotation speed n and the cooling water temperature T cool Temperature T of the outer shell c And IGBT module current lifetime c 1 . Establishing a high-precision power loss model and a high-precision thermal network model of a digital twin IGBT module corresponding to the IGBT module at the vehicle end, and coupling the two models to obtain an electrothermal network model so as to calculate the junction temperature T of the IGBT module according to the electrothermal network model j . Will f sw 、I c 、U dc 、n、T cool And c 1 As an input value, c 1 As output value, carrying out neural network iterative training on the current junction temperature estimation neural network model to obtain a new trained junction temperature estimation neural network model so as to updateAnd estimating a neural network model by the junction temperature of the server. And calculating the actual residual life of the IGBT module according to the junction temperature output by the electrothermal network model, thereby obtaining the life attenuation degree of the IGBT module. When the service life attenuation degree reaches 2%, uploading the new junction temperature estimation neural network model to the OTA platform so that the OTA platform pushes an OTA upgrade package comprising the new junction temperature estimation neural network model to the vehicle end, updates the junction temperature estimation neural network model of the vehicle end, and updates the thermal impedance value to update a thermal network model (high-precision thermal network model) in the electric heating network model. When the service life attenuation degree is not up to 2%, the junction temperature estimation neural network model of the vehicle end is not updated, and the thermal impedance value is not updated. Please refer to the descriptions in the foregoing embodiments for the detailed process in the flow chart of fig. 7, which will not be repeated here. According to the technical scheme, a neural network model considering service life attenuation is adopted in junction temperature estimation, so that on one hand, the on-line calculation amount of a vehicle end is reduced, and the calculation load of a vehicle-mounted chip is reduced. On the other hand, the service life attenuation is considered in the process of calculating the junction temperature, and the junction temperature estimation neural network can be more accurately trained by combining real-time working condition data of the automobile, wherein the data sample size is large and has variability. Meanwhile, the vehicle end data is uploaded to the large data platform end and iterated with the service life evaluation, so that safety, health and fault early warning can be better carried out on the vehicle.
It should be noted that, in each specific embodiment of the present application, the current lifetime c of the IGBT module and the IGBT module under the real-time working condition 1 Switching frequency f sw Collector current I c Load current I m Bus voltage U dc Conduction voltage drop U ce The motor rotation speed n and the cooling water temperature T cool Temperature T of the outer shell c The method is sequentially equivalent to a target power module, the current period residual life, the switching frequency, the collector current, the load current, the bus voltage, the conduction voltage drop, the water pump rotating speed, the cooling water temperature and the shell temperature in the current working condition data in each embodiment of the application.
Referring to fig. 8, fig. 8 is a block diagram of a junction temperature estimation device for a power module according to an exemplary embodiment of the application. The device may be applied to the implementation environment shown in fig. 1, and is specifically configured in the server 102. The apparatus may also be adapted to other exemplary implementation environments and may be specifically configured in other devices, and the present embodiment is not limited to the implementation environments to which the apparatus is adapted.
As shown in fig. 8, the exemplary power module junction temperature estimation apparatus includes:
the acquiring module 810 is configured to acquire current working condition data and current cycle remaining life of the target power module, where the working condition data includes switching frequency, voltage data, current data and temperature data; the calculation module 820 is configured to input 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, and the electrothermal network model is built based on the thermal impedance value of the target power module, wherein the thermal impedance value is changed; the training module 830 is configured to perform iterative training on the current junction temperature estimated neural network model based on the current working condition data, the current cycle residual life and the current junction temperature, so as to obtain a new trained junction temperature estimated neural network model; the updating module 840 is configured to update the junction temperature estimation neural network model of the corresponding vehicle end of the target power module, so as to perform power module junction temperature estimation.
It should be noted that, the power module junction temperature estimation device provided in the foregoing embodiment and the power module junction temperature estimation method provided in the foregoing embodiment belong to the same concept, and specific manners in which each module and each unit perform operations have been described in detail in the method embodiment, which is not repeated herein. In practical application, the power module junction temperature estimation device provided in the above embodiment may distribute the functions to be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above, which is not limited herein.
The embodiment of the application also provides electronic equipment, which comprises: one or more processors; and a storage device for storing one or more programs, which when executed by the one or more processors, cause the electronic device to implement the power module junction temperature estimation method provided in the foregoing embodiments.
Referring to fig. 9, fig. 9 is a schematic diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present application. It should be noted that, the computer system 900 of the electronic device shown in fig. 9 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.
As shown in fig. 9, the computer system 900 includes a central processing unit (Central Processing Unit, CPU) 901 which can perform various appropriate actions and processes according to a program stored in a Read-Only Memory (ROM) 902 or a program loaded from a storage portion 908 into a random access Memory (Random Access Memory, RAM) 903, for example, performing the method described in the above embodiment. In the RAM 903, various programs and data required for system operation are also stored. The CPU 901, ROM 902, and RAM 903 are connected to each other through a bus 904. An Input/Output (I/O) interface 905 is also connected to bus 904.
The following components are connected to the I/O interface 905: an input section 906 including a keyboard, a mouse, and the like; an output section 907 including a speaker and the like, such as a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and the like; a storage portion 908 including a hard disk or the like; and a communication section 909 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. The drive 910 is also connected to the I/O interface 905 as needed. Removable media 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on the drive 910 so that a computer program read out therefrom is installed as needed into the storage section 908.
In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 909 and/or installed from the removable medium 911. When the computer program is executed by a Central Processing Unit (CPU) 901, various functions defined in the system of the present application are performed.
It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
Another aspect of the application also provides 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 as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment or may exist alone without being incorporated in the electronic device.
Another aspect of the application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the power module junction temperature estimation method provided in the above embodiments.
The above embodiments are merely illustrative of the principles of the present application and its effectiveness, and are not intended to limit the application. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the application. It is therefore intended that all equivalent modifications and changes made by those skilled in the art without departing from the spirit and technical spirit of the present application shall be covered by the appended claims.

Claims (10)

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;
and 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 junction temperature estimation neural network model after training, and updating the junction temperature estimation neural network model of the corresponding vehicle end of the target power module to carry out power module junction temperature estimation.
2. The power module junction temperature estimation method according to claim 1, wherein after switching frequency, voltage data, current data and temperature data in the current operating condition data are input to a preset electrothermal network model so that the electrothermal network model outputs the current junction temperature, the power module junction temperature estimation method comprises:
Determining the actual residual life of the target power module based on the historical junction temperature and the current junction temperature output by the electrothermal network model;
calculating the life attenuation degree of the target power module based on the current period residual life and the actual residual life;
and if the life attenuation degree reaches a preset threshold, transmitting the actual remaining life and the new junction temperature estimation neural network model to a vehicle end so that the vehicle end can determine 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.
3. The power module junction temperature estimation method of claim 2, wherein determining an actual remaining life of the target power module based on the current junction temperature and the 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.
4. The power module junction temperature estimation method according to claim 3, wherein if the lifetime degradation degree reaches a preset threshold, 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.
5. The method for estimating a junction temperature of a power module according to any one of claims 1 to 4, wherein the method for establishing the electrothermal network model includes:
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.
6. The power module junction temperature estimation method according to any one of claims 1 to 4, wherein performing iterative training on a current junction temperature estimation 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 estimation neural network model, includes:
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.
7. The power module junction temperature estimation method according to any one of claims 1 to 4, 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.
8. 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;
and the updating module is used for updating the junction temperature estimation neural network model of the corresponding vehicle end of the target power module so as to estimate the junction temperature of the power module.
9. 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 1-7.
10. 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 1-7.
CN202310635986.9A 2023-05-31 2023-05-31 Power module junction temperature estimation method and device, electronic equipment and storage medium Pending CN116702675A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310635986.9A CN116702675A (en) 2023-05-31 2023-05-31 Power module junction temperature estimation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310635986.9A CN116702675A (en) 2023-05-31 2023-05-31 Power module junction temperature estimation method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116702675A true CN116702675A (en) 2023-09-05

Family

ID=87827075

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310635986.9A Pending CN116702675A (en) 2023-05-31 2023-05-31 Power module junction temperature estimation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116702675A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116930729A (en) * 2023-09-18 2023-10-24 法特迪精密科技（苏州）有限公司 Multi-chip aging test system and method

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116930729A (en) * 2023-09-18 2023-10-24 法特迪精密科技（苏州）有限公司 Multi-chip aging test system and method

Similar Documents

Publication Publication Date Title
CN116702675A (en) Power module junction temperature estimation method and device, electronic equipment and storage medium
CN107037370B (en) Electric vehicle remaining power calculation method based on monitoring data
JP2021503086A (en) How to estimate deterioration
US11709112B2 (en) System, apparatus and method of determining remaining life of a bearing
KR102648764B1 (en) Battery performance evaluation method and battery performance evaluation device
CN112818535B (en) Method and device for establishing electrothermal simulation model and obtaining electrothermal simulation value
CN111460639B (en) Method and device for dynamically calculating temperature of cable conductor, electronic equipment and storage medium
CN114910756A (en) Insulation performance evaluation method and system for low-voltage bus duct
CN115186592A (en) Method for predicting life of power semiconductor module, terminal device, and storage medium
CN114329337A (en) Method and system for predicting insulation resistance of electric vehicle and storage medium
CN116070302A (en) Cable insulation state prediction method and device
CN113119796B (en) Electric vehicle residual charging time prediction method and system based on cloud sparse charging data
CN115128986A (en) Industrial internet yield real-time monitoring system and method based on SaaS (software as a service) level
CN115358104A (en) IGBT module health monitoring method using digital twinning method
CN109581125B (en) Method and device for detecting service life of power module of wind power converter and storage medium
CN112926259A (en) Method for predicting junction temperature of semiconductor device based on RBF neural network model
CN115659572A (en) Vehicle-mounted cooling liquid flow estimation method
CN111103319A (en) Health state monitoring method for heat-conducting silicone grease and cooling fan
CN111666729B (en) Insulator silicon rubber surface temperature calculation method based on thermodynamics and related device
CN116068413B (en) Battery voltage prediction method, device, equipment and storage medium
TWI645341B (en) Method for estimating temperature of rotating machine
Kaleli et al. Recursive ARMAX-Based Global Battery SOC Estimation Model Design using Kalman Filter with Optimized Parameters by Radial Movement Optimization Method
CN115077740B (en) Gearbox temperature testing method and system
US20240044989A1 (en) Manufacturing method, generation device, estimation device, identification information imparting method, and imparting device
CN115689005A (en) Method, device, equipment and medium for predicting driving range based on actual road resistance degradation coefficient

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination