Vehicle power module junction temperature estimation methods, devices, electronic equipment, and storage media

Abstract

This invention provides a method, apparatus, electronic device, and storage medium for estimating the junction temperature of a vehicle power module. The method includes acquiring operating data of the vehicle power module, including switching frequency, bus voltage, water pump pulse width modulation signal, inlet temperature, current in different phases, and thermistor temperature in different phases. The method calculates the power loss of each phase based on the switching frequency, bus voltage, and current in each phase. The operating data is input into a water temperature estimation model to obtain the water temperature of different phases. The junction temperature of each phase is estimated based on thermal impedance, power loss in each phase, and water temperature in each phase, and the junction temperature of the vehicle power module is determined. This method improves the accuracy of junction temperature estimation for each phase of the IGBT chips in the vehicle power module, thereby improving the accuracy of the vehicle power module junction temperature estimation, ensuring the normal operation of the vehicle power module, delaying the degradation of the vehicle power module's lifespan, and eliminating the need for modification of the vehicle power module, thus reducing costs.

Description

Technical Field

[0001] This application relates to the field of vehicle power module technology, specifically to a method, apparatus, electronic device, and storage medium for estimating the junction temperature of a vehicle power module. Background Technology

[0002] In recent years, the global new energy vehicle market has developed rapidly. The motor controller is a key unit in new energy vehicles responsible for energy conversion, and semiconductor power devices are the core components of the motor controller's power conversion device. In electric vehicle applications, IGBT (Insulated Gate Bipolar Transistor) modules, also known as power modules, have been widely used due to their strong current load capacity, simple driving method, and relatively low cost. Therefore, the reliability of IGBT modules has received significant attention in industrial applications. The junction temperature of the IGBT module refers to the highest operating temperature of the IGBT chip and is an important condition for determining whether the IGBT module is operating safely. The operating junction temperature of the IGBT module limits the maximum output capacity of the controller. If real-time junction temperature information of the IGBT module can be obtained without affecting the normal operation of the electric vehicle, and decisions can be made to change the motor's operating state or heat dissipation conditions to implement thermal management of the motor controller. This can reduce the current and thermal stress on the power module, playing a crucial role in improving the lifespan of the IGBT module and enhancing the overall vehicle reliability.

[0003] Chinese patent CN114910765A discloses an IGBT junction temperature estimation device and method for motor controllers. This method involves controlling one IGBT among multiple IGBT chips to be off while the others are on. The device calculates the junction temperatures of the off IGBT chip and the diode chip, taking into account thermal coupling, based on the junction temperature of the off IGBT chip, the junction temperature of the diode chip connected in parallel with the off IGBT chip, and the coolant temperature. However, because the cooling water (coolant) temperature varies at different IGBT chips, the junction temperature of each chip in the IGBT module differs. This solution does not consider these influencing factors, resulting in low accuracy in calculating the IGBT chip junction temperature. This, in turn, affects the accuracy of the power module junction temperature calculation and may accelerate the degradation of the power module's lifespan. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, this application provides a method, apparatus, electronic device and storage medium for estimating the junction temperature of a vehicle power module, in order to solve the technical problem that the accuracy of IGBT junction temperature estimation is not high due to the failure to consider the differences in water temperature at different IGBT chips.

[0005] This application provides a method for estimating the junction temperature of a vehicle power module. The method includes: acquiring operating data of the vehicle power module, including switching frequency, bus voltage, water pump pulse width modulation signal, inlet temperature, current of different phases, and thermistor temperature of different phases; calculating the power loss of each phase based on the switching frequency, bus voltage, and current of each phase; inputting the operating data into a pre-trained water temperature estimation model to obtain the water temperature of different phases, wherein the water temperature estimation model is trained based on a sample dataset, the sample dataset including historical switching frequency, historical bus voltage, historical water pump pulse width modulation signal, historical inlet temperature, historical current of different phases, historical thermistor temperature of different phases, and historical water temperature of different phases at different times; estimating the junction temperature of each phase based on the thermal impedance of the vehicle power module, the power loss of each phase, and the water temperature of each phase, and determining the junction temperature of the vehicle power module.

[0006] In one embodiment of this application, the loss power of each phase is calculated based on the switching frequency, the bus voltage, and the current of each phase, including: calculating the conduction loss power of each phase based on the bus voltage and the current of each phase; calculating the switching loss power of each phase based on the switching frequency, the bus voltage, and the current of each phase; and determining the sum of the conduction loss power of the same phase and the switching loss power of the same phase as the loss power of the same phase, thereby obtaining the loss power of each phase.

[0007] In one embodiment of this application, the water temperature estimation model is obtained through the following training process: acquiring historical switching frequencies, historical bus voltages, historical pump pulse width modulation signals, historical inlet temperatures, historical currents of different phases, historical thermistor temperatures of different phases, and historical water temperatures of different phases at different times; generating the sample dataset; dividing the sample dataset into a training set and a validation set; and acquiring the historical water temperatures of different phases based on water temperature sensors installed at the radiator in the sample power module; training a preset neural network model using the training set; and validating the trained neural network model using the validation set to obtain the water temperature estimation model.

[0008] In one embodiment of this application, a preset neural network model is trained using the training set, and the trained neural network model is validated using the validation set to obtain the water temperature estimation model. This includes: training the preset neural network model using historical switching frequencies, historical bus voltages, historical pump pulse width modulation signals, historical inlet temperatures, historical currents of different phases, and historical thermistor temperatures of different phases from the training set as input values, and using the historical water temperatures of different phases from the training set as output values, to obtain the trained neural network model; inputting the historical switching frequencies, historical bus voltages, historical pump pulse width modulation signals, historical inlet temperatures, historical currents of different phases, and historical thermistor temperatures of different phases from the validation set into the trained neural network model to obtain the validation water temperatures of different phases output by the trained neural network model; calculating the error between the validation water temperature of the same phase and the historical water temperature of the same phase in the validation set, obtaining the error for each phase, and adjusting the trained neural network model based on the error for each phase to obtain the water temperature estimation model.

[0009] In one embodiment of this application, the loss power of each phase is calculated based on the switching frequency, the bus voltage, and the current of each phase, and further includes: establishing a power module loss model based on the switching frequency parameters, the bus voltage parameters, and the current parameters. The power module loss model includes a first sub-model for calculating conduction loss power, a second sub-model for calculating switching loss power, and a third sub-model for calculating loss power. The conduction loss power of each phase is obtained using the bus voltage, the current of each phase, and the first sub-model; the switching loss power of each phase is obtained using the switching frequency, the bus voltage, the current of each phase, and the second sub-model; and the loss power of each phase is obtained using the conduction loss power of each phase, the switching loss power of each phase, and the third sub-model.

[0010] In one embodiment of this application, the junction temperature of each phase is estimated based on the thermal impedance of the vehicle power module, the power loss of each phase, and the water temperature of each phase, and the junction temperature of the vehicle power module is determined, including: calculating the temperature difference of each phase based on the thermal impedance and the power loss of each phase; calculating the junction temperature of the same phase based on the temperature difference of the same phase and the water temperature of the same phase, obtaining the junction temperature of each phase, and determining the maximum junction temperature as the junction temperature of the vehicle power module.

[0011] In one embodiment of this application, before estimating the junction temperature of each phase based on the thermal impedance of the vehicle power module, the power loss of each phase, and the water temperature of each phase, the junction temperature estimation method of the vehicle power module includes: presetting the thermal impedance; or, obtaining the equivalent thermal resistance and thermal time constant of the vehicle power module, determining the thermal impedance based on the equivalent thermal resistance, the thermal time constant, and the operating time of the vehicle power module, wherein the operating data also includes the operating time of the vehicle power module.

[0012] In one embodiment of this application, a vehicle power module junction temperature estimation device is also provided. The vehicle power module junction temperature estimation device includes: a data acquisition module for acquiring operating data of the vehicle power module, the operating data including switching frequency, bus voltage, water pump pulse width modulation signal, inlet temperature, current of different phases, and thermistor temperature of different phases; a power loss calculation module for calculating the power loss of each phase based on the switching frequency, the bus voltage, and the current of each phase; a water temperature estimation module for inputting the operating data into a pre-trained water temperature estimation model to obtain the water temperature of different phases, the water temperature estimation model being trained based on a sample dataset, the sample dataset including historical switching frequency, historical bus voltage, historical water pump pulse width modulation signal, historical inlet temperature, historical current of different phases, historical thermistor temperature of different phases, and historical water temperature of different phases at different times; and a junction temperature determination module for estimating the junction temperature of each phase based on the thermal impedance of the vehicle power module, the power loss of each phase, and the water temperature of each phase, and determining the vehicle power module junction temperature.

[0013] In one embodiment of this application, an electronic device is also provided, the electronic device comprising: 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 vehicle power module junction temperature estimation method as described above.

[0014] In one embodiment of this application, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a computer's processor, causes the computer to execute the vehicle power module junction temperature estimation method as described above.

[0015] The beneficial effects of this invention are as follows: This invention provides a method, apparatus, electronic device, and storage medium for estimating the junction temperature of a vehicle power module. The method estimates the cooling water temperature at each phase of the IGBT chip in the vehicle power module using a water temperature estimation module, obtaining the water temperature of each phase and calculating the power loss of each phase. Based on the power loss, thermal impedance, and water temperature of each phase, the junction temperature of each phase is estimated to determine the junction temperature of the vehicle power module. This improves the accuracy of junction temperature estimation for each phase of the IGBT chip in the vehicle power module, thereby enhancing the accuracy of the vehicle power module junction temperature estimation, ensuring the normal operation of the vehicle power module, delaying the degradation of the vehicle power module's lifespan, and eliminating the need for modification of the vehicle power module, thus reducing costs.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0018] Figure 1 This is a schematic diagram showing the thermal imaging results of an IGBT black module test, according to a specific embodiment of this application.

[0019] Figure 2 This is a schematic diagram illustrating the implementation environment of a vehicle power module junction temperature estimation method, as shown in an exemplary embodiment of this application.

[0020] Figure 3 This is a flowchart illustrating a method for estimating the junction temperature of a vehicle power module, as shown in an exemplary embodiment of this application.

[0021] Figure 4 This is a schematic diagram showing the internal IGBT chip layout of a power module according to a specific embodiment of this application;

[0022] Figure 5 This is a schematic diagram showing the installation position of the water temperature sensor according to a specific embodiment of this application;

[0023] Figure 6 This is a schematic diagram illustrating the training of a water temperature estimation model according to a specific embodiment of this application;

[0024] Figure 7 This is a flowchart illustrating a method for estimating the junction temperature of a three-phase vehicle power module, as shown in a specific embodiment of this application;

[0025] Figure 8 yes Figure 7 A flowchart of the neural network training method in the specific embodiment shown;

[0026] Figure 9 This is a block diagram illustrating a vehicle power module junction temperature estimation device according to an exemplary embodiment of this application;

[0027] Figure 10 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0028] The embodiments of this application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be understood that the preferred embodiments are only for illustrating this application and are not intended to limit the scope of protection of this application.

[0029] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0030] It should be noted that in this application, terms such as "first" and "second" are merely for distinguishing similar objects, and do not limit the order or sequence of similar objects. The variations of "including" and "having" indicate that the scope covered by the subject of the word is not exclusive, except for the examples shown by the word.

[0031] It is understood that the various numerical designations, step numbers, and other identifiers recorded in this application are for descriptive convenience and are not intended to limit the scope of this application. The size of the identifiers in this application does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0032] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the present application. However, it will be apparent to those 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 to avoid obscuring embodiments of the present application.

[0033] It should be noted that in electric vehicles, the vehicle power module is also called a power module or IGBT module. Generally, a vehicle power module includes multi-phase IGBT chips, such as three-phase IGBT chips. Due to differences in cooling channel structure and cooling water flow rate, the water temperature at each phase IGBT chip within the vehicle power module varies, resulting in different junction temperatures for each phase IGBT chip. Please refer to [link / reference]. Figure 1 , Figure 1 This is a schematic diagram illustrating the thermal imaging results of an IGBT black module test, as shown in a specific embodiment of this application. Figure 1 As shown, the leftmost IGBT chip has the highest temperature, and the rightmost IGBT chip has the lowest temperature. Therefore, if the difference in water temperature is ignored, the accuracy of the estimated IGBT chip junction temperature will inevitably be low.

[0034] To address the aforementioned problems, embodiments of this application propose a method for estimating the junction temperature of a vehicle power module, a device for estimating the junction temperature of a vehicle power module, an electronic device, a computer-readable storage medium, and a computer program product, which will be described in detail below.

[0035] Please see Figure 2 , Figure 2 This is a schematic diagram illustrating the implementation environment of a vehicle power module junction temperature estimation method, as shown in an exemplary embodiment of this application.

[0036] like Figure 2 As shown, the implementation environment may include an intelligent electric vehicle 201 and a computer device 202. The computer device 202 can be at least one of a microcomputer, an embedded computer, or a neural network computer. The computer device 202 can be configured within the intelligent electric vehicle 201, or it can be a standalone computer device; no limitation is made here. The intelligent electric vehicle 201 collects operating data from its vehicle power module and sends it to the computer device 202. This operating data includes switching frequency, bus voltage, water pump pulse width modulation signal, inlet temperature, current in different phases, and thermistor temperatures in different phases. The computer device 202 estimates the junction temperature of the vehicle power module based on this operating data.

[0037] For example, the power loss of each phase is calculated based on the switching frequency, bus voltage, and current of each phase. The operating data is then input into a pre-trained water temperature estimation model to obtain the water temperature of different phases. This model is trained on a sample dataset, which includes historical switching frequencies, historical bus voltages, historical pump pulse width modulation signals, historical inlet temperatures, historical currents of different phases, historical thermistor temperatures of different phases, and historical water temperatures of different phases. Based on the thermal impedance of the vehicle power module, the power loss of each phase, and the water temperature of each phase, the junction temperature of each phase is estimated, and the junction temperature of the vehicle power module is determined. Therefore, the technical solution of this application uses a water temperature estimation model to estimate the water temperature of different phases, and then calculates the junction temperature of different phases to determine the junction temperature of the vehicle power module. This improves the accuracy of the IGBT chip junction temperature estimation for each phase in the vehicle power module, thereby ensuring the normal operation of the vehicle power module, delaying the degradation of the vehicle power module's lifespan, and eliminating the need for modification of the vehicle power module, thus reducing costs.

[0038] It should be noted that the vehicle power module junction temperature estimation method provided in this application embodiment is generally executed by computer device 202, and the corresponding vehicle power module junction temperature estimation device is generally set in computer device 202.

[0039] Please see Figure 3 , Figure 3 This is a flowchart illustrating a method for estimating the junction temperature of a vehicle power module, as shown in an exemplary embodiment of this application. This method can be applied to... Figure 2 The implementation environment is shown, and the method is specifically executed by computer device 202 within that implementation environment. It should be understood that the method can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments; this embodiment does not limit the implementation environment to which the method is applicable.

[0040] like Figure 3 As shown, in an exemplary embodiment, the vehicle power module junction temperature estimation method includes at least steps S310 to S340, which are described in detail below:

[0041] Step S310: Obtain the operating data of the vehicle power module.

[0042] In one embodiment of this application, the operating data of the vehicle power module can be acquired in real time or periodically based on sensor sampling or internal signal transmission of the electric drive. This operating data includes the switching frequency of the vehicle power module, bus voltage (DC bus voltage), water pump pulse width modulation signal, inlet temperature, current in different phases, and thermistor temperature in different phases. The water pump pulse width modulation signal refers to the PWM (Pulse Width Modulation) signal of the pump controlling the coolant flow in the vehicle power module. The inlet temperature refers to the temperature of the coolant at the inlet. Coolant, also called coolant fluid, can be pure water, oil, ethylene glycol, or other liquid media; no limitation is made here. The current in different phases refers to the current corresponding to each phase of the IGBT chip within the vehicle power module. The thermistor temperature in different phases refers to the temperature of the thermistor of each phase of the IGBT chip within the vehicle power module. The thermistor can be a negative temperature coefficient (NTC) thermistor or a positive temperature coefficient (PTC) thermistor; no limitation is made here.

[0043] Please see Figure 4 , Figure 4 This is a schematic diagram illustrating the internal IGBT chip layout of a power module according to a specific embodiment of this application. Figure 4 As shown, the power module includes three-phase IGBT chips, and each phase IGBT chip is equipped with an NTC thermistor. The temperature can be collected through the NTC thermistor, i.e., the thermistor temperature.

[0044] Step S320: Calculate the power loss of each phase based on the switching frequency, bus voltage, and current of each phase in the operating data.

[0045] Taking a three-phase vehicle power module as an example, the three phases are named phase A, phase B, and phase C respectively. The power loss of phase A is calculated using the switching frequency, bus voltage, and phase A current. The power loss of phase B is calculated using the switching frequency, bus voltage, and phase B current. The power loss of phase C is calculated using the switching frequency, bus voltage, and phase C current.

[0046] In one embodiment of this application, step S320 includes: calculating the conduction loss power of each phase based on the bus voltage and the current of each phase; calculating the switching loss power of each phase based on the switching frequency, the bus voltage and the current of each phase; determining the loss power of the same phase as the sum of the conduction loss power of the same phase and the switching loss power of the same phase, and obtaining the loss power of each phase respectively.

[0047] In this embodiment, the power loss consists of conduction loss power and switching loss power. The conduction loss power of each phase is mainly related to the bus voltage and the current of that phase, while the switching loss power of each phase is mainly related to the switching frequency, the bus voltage, and the current of that phase. The calculation method for conduction loss power is as follows:

[0048] P cond =f(U dc ,I) Formula (1),

[0049] Among them, P cond U is the conduction loss power of a certain phase. dc I is the bus voltage, and I is the current in that phase.

[0050] The calculation method for switching power loss is as follows:

[0051] P switch =f(f sw U dc ,I) Formula (2),

[0052] Among them, P switch f is the switching loss power of a certain phase. sw U is the switching frequency. dc I is the bus voltage, and I is the current in that phase.

[0053] The power loss is calculated as follows:

[0054] P loss =P cond +P switch Equation (3),

[0055] Among them, P loss P represents the power loss of a certain phase. cond P is the conduction loss power of this phase. switch This represents the switching loss power of this phase.

[0056] In one specific embodiment of this application, the conduction loss power of phase A is calculated based on the bus voltage, phase A current and equation (1), the switching loss power of phase A is calculated based on the switching frequency, bus voltage, phase A current and equation (2), and the loss power of phase A is calculated based on the conduction loss power of phase A, the switching loss power of phase A and equation (3); the conduction loss power of phase B is calculated based on the bus voltage, phase B current and equation (1), the switching loss power of phase B is calculated based on the switching frequency, bus voltage, phase B current and equation (2), and the loss power of phase B is calculated based on the conduction loss power of phase B, the switching loss power of phase B and equation (3); the conduction loss power of phase C is calculated based on the bus voltage, phase C current and equation (1), the switching loss power of phase C is calculated based on the switching frequency, bus voltage, phase C current and equation (2), and the loss power of phase C is calculated based on the conduction loss power of phase C, the switching loss power of phase C and equation (3).

[0057] In another embodiment of this application, step S320 includes: establishing a power module loss model based on switching frequency parameters, bus voltage parameters, and current parameters. The power module loss model includes a first sub-model for calculating conduction loss power, a second sub-model for calculating switching loss power, and a third sub-model for calculating loss power. The conduction loss power of each phase is obtained using the bus voltage, the current of each phase, and the first sub-model. The switching loss power of each phase is obtained using the switching frequency, the bus voltage, the current of each phase, and the second sub-model. The loss power of each phase is obtained using the conduction loss power of each phase, the switching loss power of each phase, and the third sub-model.

[0058] In this embodiment, a power module loss model is established using equations (1), (2), and (3). Specifically, a first sub-model is established based on equation (1), a second sub-model is established based on equation (2), and a third sub-model is established based on equation (3). The switching frequency, bus voltage, and current of each phase are input into the established power module loss model to obtain the power loss of each phase.

[0059] Step S330: Input the running data into the pre-trained water temperature estimation model to obtain the water temperature of different phases.

[0060] In one embodiment of this application, considering the influence of cooling water on the junction temperature of each phase of the IGBT chip, the junction temperature of each phase is calculated using the water temperature of different phases of the IGBT module as a reference point, and the maximum value is taken as the final junction temperature of the IGBT module. Water temperature acquisition can be achieved by adding a temperature sensor, but this requires modification of the IGBT module, increasing costs. To avoid increasing costs, the temperature (thermistor temperature), switching frequency, current of each phase, DC bus voltage, PWM signal (pump pulse width modulation signal) of the water pump control, and inlet temperature of each phase of the IGBT chip inside the IGBT module can be used as input values ​​for the water temperature estimation model. The water temperature estimation model outputs the water temperature of each phase. The water temperature estimation model is trained based on a sample dataset, which includes historical switching frequencies, historical bus voltages, historical pump pulse width modulation signals, historical inlet temperatures, historical currents of different phases, historical thermistor temperatures of different phases, and historical water temperatures of different phases at different times.

[0061] It should be noted that steps S320 and S330 can be performed simultaneously, or step S330 can be performed before step S320.

[0062] In one embodiment of this application, the water temperature estimation model is obtained through the following training process: acquiring historical switching frequencies, historical bus voltages, historical pump pulse width modulation signals, historical inlet temperatures, historical currents of different phases, historical thermistor temperatures of different phases, and historical water temperatures of different phases at different times; generating a sample dataset; and dividing the sample dataset into a training set and a validation set; the historical water temperatures of different phases are collected based on water temperature sensors installed at the radiator in the sample power module; training a preset neural network model using the training set; and validating the trained neural network model using the validation set to obtain the water temperature estimation model.

[0063] In this embodiment, a sample power module with the same model as the vehicle power module is selected, and a water temperature sensor is installed at the bottom of the radiator of the sample power module to collect the historical water temperature of each phase at different times.

[0064] Taking a three-phase sample power module as an example: Please refer to Figure 5 , Figure 5 This is a schematic diagram showing the installation position of the water temperature sensor according to a specific embodiment of this application. Figure 5As shown, temperature sensors are installed at positions corresponding to the bottom of the heat sink on the A-phase, B-phase, and C-phase IGBT chips to collect the water temperature at these locations. These temperature sensors can be surface-mounted. The sample power module is used to simulate vehicle operation under different conditions. Historical switching frequency, historical bus voltage, historical water pump pulse width modulation signal, historical inlet temperature, historical three-phase current, historical three-phase thermistor temperature, and historical three-phase water temperature of the sample power module at different times are obtained under different operating conditions, generating a sample dataset. This dataset is divided into two parts: a training set and a validation set, with each time point corresponding to a specific value. Based on the sample dataset, the historical switching frequency, historical bus voltage, historical water pump pulse width modulation signal, historical inlet temperature, historical three-phase current, and historical three-phase thermistor temperature are used as input values ​​to a neural network model, and the historical three-phase water temperature is used as the output value. The neural network model is trained and validated using this data, resulting in a water temperature estimation model that improves its maturity and robustness. Therefore, the water temperature estimation model can output the three-phase reference point temperature corresponding to each working condition and time, which is the three-phase water temperature.

[0065] In one embodiment of this application, a water temperature estimation model is obtained by training a preset neural network model using a training set and validating the trained neural network model using a validation set. This includes: training the preset neural network model with historical switching frequencies, historical bus voltages, historical pump pulse width modulation signals, historical inlet temperatures, historical currents of different phases, and historical thermistor temperatures of different phases from the training set as input values, and using the historical water temperatures of different phases from the training set as output values; inputting the historical switching frequencies, historical bus voltages, historical pump pulse width modulation signals, historical inlet temperatures, historical currents of different phases, and historical thermistor temperatures of different phases from the validation set into the trained neural network model to obtain the validation water temperatures of different phases output by the trained neural network model; calculating the error between the validation water temperature of the same phase and the historical water temperature of the same phase in the validation set, obtaining the error for each phase, and adjusting the trained neural network model based on the error of each phase to obtain the water temperature estimation model.

[0066] Similarly, taking the above three-phase sample power module as an example: Please refer to... Figure 6 , Figure 6 This is a schematic diagram illustrating the training of a water temperature estimation model according to a specific embodiment of this application. Figure 6 As shown, f sw_ex For historical switching frequencies, I A_ex For the historical current of phase A, I B_ex For the historical current of phase B, I C_ex For the historical current of phase C, Udc_ex For historical bus voltage, T NTCA_ex T represents the historical thermistor temperature of phase A. NTCB_ex T represents the historical thermistor temperature of phase B. NTCC_ex The historical thermistor temperature of phase C, the historical water pump PWM signal (i.e., the historical water pump pulse width modulation signal), T IN_ex T represents the historical inlet temperature. refA_ex T represents the historical water temperature of phase A. refB_ex For the historical water temperature of phase B, T refC_ex The historical water temperature of phase C.

[0067] During the training phase, f in the training set sw_ex I A_ex I B_ex I C_ex U dc_ex T NTCA_ex T NTCB_ex T NTCC_ex Historical water pump PWM signal and T IN_ex As the input value of the neural network model, T refA_ex T refB_ex and T refC_ex The neural network model is trained using the output values ​​of the neural network model.

[0068] During the verification phase, f in the verification set sw_ex I A_ex I B_ex I C_ex U dc_ex T NTCA_ex T NTCB_ex T NTCC_ex Historical water pump PWM signal and T IN_ex The input is fed into the trained neural network model, and the output is used as the verification water temperature for the three phases. Errors are calculated based on the verification water temperature and the corresponding historical water temperatures in the verification set to obtain the errors for the three phases. Weights are learned based on these errors to adjust the trained neural network model, verifying its generalization ability and preventing overfitting. When the errors meet preset conditions, the water temperature estimation model is obtained.

[0069] Step S340: Based on the thermal impedance of the vehicle power module, the power loss of each phase and the water temperature of each phase, the junction temperature of each phase is estimated and the junction temperature of the vehicle power module is determined.

[0070] In one embodiment of this application, the junction temperature of each phase is the junction temperature of each phase IGBT chip. Since there is a temperature difference between the junction temperature of each phase IGBT chip and the water temperature of that phase, and this temperature difference is mainly related to the power loss of that phase and the thermal impedance of the vehicle power module, the junction temperature of that phase can be calculated based on the thermal impedance, the power loss of a certain phase, and the water temperature of that phase. For example: the junction temperature of phase A is calculated based on the thermal impedance, the power loss of phase A, and the water temperature of phase A; the junction temperature of phase B is calculated based on the thermal impedance, the power loss of phase B, and the water temperature of phase B; and the junction temperature of phase C is calculated based on the thermal impedance, the power loss of phase C, and the water temperature of phase C. Since the IGBT junction temperature refers to the highest operating temperature of the IGBT chip, the maximum value among the junction temperatures of different phases can be taken as the final junction temperature of the IGBT module, i.e., the junction temperature of the vehicle power module. Exemplarily, the thermal impedance can be preset or calculated.

[0071] In one embodiment of this application, before step S340, the vehicle power module junction temperature estimation method includes: presetting the thermal impedance; or, obtaining the equivalent thermal resistance and thermal time constant of the vehicle power module, determining the thermal impedance based on the equivalent thermal resistance, thermal time constant and vehicle power module operating time, and the operating data also includes the vehicle power module operating time.

[0072] In this embodiment, since the thermal impedance of the IGBT module reaches a stable state within a short time, such as 10 seconds, the thermal impedance can be preset directly using the stabilized value. Alternatively, a thermal network model can be established to calculate the thermal impedance, for example, by establishing a Foster thermal network model (a local network thermal path model, one type of thermal network model) in the following way:

[0073]

[0074] Among them, Z th Let R be the thermal resistance, n be the order of the Foster network to be fitted, R be the fitted equivalent thermal resistance, and τ be the product of the fitted equivalent thermal resistance R and the fitted equivalent heat capacity C. R and τ can be obtained by consulting the IGBT datasheet, and thus the thermal resistance of the IGBT module can be calculated using the established Foster thermal network model.

[0075] In one embodiment of this application, step S340 includes: calculating the temperature difference of each phase based on the thermal impedance and the power loss of each phase; calculating the junction temperature of the same phase based on the temperature difference of the same phase and the water temperature of the same phase, obtaining the junction temperature of each phase, and determining the maximum junction temperature as the junction temperature of the vehicle power module.

[0076] In this embodiment, the junction temperature of each phase is estimated. Specifically, the product of the thermal resistance and the power loss of a certain phase is used as the temperature difference of that phase to obtain the temperature difference of each phase. The sum of the temperature difference of a certain phase and the water temperature of that phase is used as the junction temperature of that phase to obtain the junction temperature of each phase. Alternatively, the junction temperature of each phase can be estimated using the following calculation method:

[0077] T = P loss *Z th +T ref Equation (5),

[0078] Where T is the junction temperature of a certain phase, and P loss Z represents the power loss of this phase. th For thermal resistance, T ref P represents the water temperature of this phase. loss *Z th This represents the temperature difference of the phase.

[0079] The maximum value among the estimated junction temperatures of each phase in the IGBT module is selected as the junction temperature of the vehicle power module. By calculating the junction temperature of each IGBT chip using the water temperature of each phase, the accuracy of the junction temperature estimation for each phase is improved. Furthermore, using the maximum value among these junction temperatures as the vehicle power module junction temperature further enhances the accuracy of the estimated junction temperature. This ensures the normal operation of the vehicle power module and slows down its lifespan degradation.

[0080] Please see Figure 7 , Figure 7 This is a flowchart illustrating a method for estimating the junction temperature of a three-phase vehicle power module, as shown in a specific embodiment of this application. Figure 7 As shown, the flowchart of the three-phase vehicle power module junction temperature estimation method is as follows:

[0081] 1. Determine the input operating conditions, including the switching frequency f. sw Phase A current I A Phase B current I B C-phase current I C and bus voltage U dc .

[0082] 2. Establish a power module loss model based on equations (1), (2), and (3), and use f sw I A I B I C U dc The power loss P of phase A is calculated using the power module loss model. lossA The power loss P of phase B lossB The power loss P of phase C lossC .

[0083] 3. Establish a thermal network model based on equation (4) and the IGBT datasheet, and calculate the thermal impedance Z. th .

[0084] 4. Acquire the temperature of the three-phase NTC sensor (thermistor temperature), and acquire the water pump PWM (pulse width modulation signal) and inlet temperature, and set f sw I A I B I C U dc The three-phase NTC sensor temperature, water pump PWM, and inlet water temperature are used as input values ​​for the neural network, i.e., the water temperature estimation model. The three-phase reference water temperature (three-phase water temperature) T is calculated based on the neural network. refA T refB and T refC .

[0085] 5. Calculate the three-phase junction temperature T according to formula (5). A T B and T C The maximum value among the three-phase junction temperatures is taken as the junction temperature T of the IGBT module. j .

[0086] Please see Figure 8 , Figure 8 yes Figure 7 The flowchart illustrates the neural network training method in a specific embodiment. For example... Figure 8 As shown, the process of neural network training is as follows:

[0087] 1. Install a water temperature sensor at the bottom of the sample power module heat sink, such as... Figure 5 As shown.

[0088] 2. Determine historical input conditions, including historical switching frequency f. sw_ex Phase A historical current I A_ex Phase B historical current I B_ex C-phase historical current I C_ex and historical bus voltage U dc_ex It also collects historical temperatures of the three-phase NTC sensors of the power module (historical thermistor temperatures of different phases), historical water pump PWM (historical water pump pulse width modulation signal), historical inlet water temperature, and historical temperatures of the three-phase water temperature sensors (historical water temperatures of different phases).

[0089] 3. f sw_ex I A_ex I B_ex I C_ex U dc_exThe historical temperature of the three-phase NTC sensor, the historical PWM of the water pump, and the historical inlet temperature are used as input nodes (input values) of the neural network. The historical temperature of the three-phase water temperature sensor is used as the output node (output value) of the neural network. The neural network is built using the input and output nodes to complete data training and validation. The output neural network is used as a water temperature estimation model to calculate the corresponding water temperature T. refA T refB and T refC .

[0090] Figure 7 and Figure 8 For detailed information on the process, please refer to the descriptions in the aforementioned embodiments; they will not be repeated here.

[0091] Please see Figure 9 , Figure 9 This is a block diagram illustrating a vehicle power module junction temperature estimation device according to an exemplary embodiment of this application. The device can be applied to... Figure 2 The implementation environment shown is specifically configured in computer device 202. This device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0092] like Figure 9 As shown, this exemplary vehicle power module junction temperature estimation device includes:

[0093] The data acquisition module 910 is configured to acquire the operating data of the vehicle power module, including switching frequency, bus voltage, water pump pulse width modulation signal, inlet temperature, current of different phases, and thermistor temperature of different phases. The power loss calculation module 920 is configured to calculate the power loss of each phase based on the switching frequency, bus voltage, and current of each phase. The water temperature estimation module 930 is configured to input the operating data into a pre-trained water temperature estimation model to obtain the water temperature of different phases. The water temperature estimation model is trained based on a sample dataset, which includes historical switching frequency, historical bus voltage, historical water pump pulse width modulation signal, historical inlet temperature, historical current of different phases, historical thermistor temperature of different phases, and historical water temperature of different phases at different times. The junction temperature determination module 940 is configured to estimate the junction temperature of each phase based on the thermal impedance of the vehicle power module, the power loss of each phase, and the water temperature of each phase, and determine the junction temperature of the vehicle power module.

[0094] It should be noted that the vehicle power module junction temperature estimation device and the vehicle power module junction temperature estimation method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the vehicle power module junction temperature estimation device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0095] Embodiments of this application also provide an electronic device, including: 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 vehicle power module junction temperature estimation method provided in the above embodiments.

[0096] Please see Figure 10 , Figure 10 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 10 The computer system 1000 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0097] like Figure 10 As shown, the computer system 1000 includes a Central Processing Unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1002 or programs loaded from storage portion 1008 into Random Access Memory (RAM) 1003, such as performing the methods described in the above embodiments. The RAM 1003 also stores various programs and data required for system operation. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An Input / Output (I / O) interface 1005 is also connected to the bus 1004.

[0098] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. Removable media 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1010 as needed so that computer programs read from them can be installed into storage section 1008 as needed.

[0099] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit (CPU) 1001, it performs various functions defined in the system of this application.

[0100] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0102] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0103] Another aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a computer's processor, causes the computer to perform the vehicle power module junction temperature estimation method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0104] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the vehicle power module junction temperature estimation method provided in the various embodiments described above.

[0105] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method of estimating junction temperature of a vehicle power module, the method comprising: The vehicle power module junction temperature estimation method comprises: obtaining operation data of a vehicle power module, the operation data comprising a switching frequency, a bus voltage, a water pump pulse width modulation signal, an inlet water temperature, currents of different phases, and thermistor temperatures of different phases; calculating loss power of each phase based on the switching frequency, the bus voltage, and the current of each phase; inputting the operation data into a pre-trained water temperature estimation model to obtain water temperatures of different phases, the water temperature estimation model being trained based on a sample data set, the sample data set comprising historical switching frequencies, historical bus voltages, historical water pump pulse width modulation signals, historical inlet water temperatures, historical currents of different phases, historical thermistor temperatures of different phases, and historical water temperatures of different phases; estimating junction temperatures of each phase based on thermal impedance of the vehicle power module, loss power of each phase, and water temperatures of each phase, and determining a vehicle power module junction temperature of the vehicle power module.

2. The vehicle power module junction temperature estimation method of claim 1, wherein, The calculating of loss power of each phase based on the switching frequency, the bus voltage, and the current of each phase comprises: calculating conduction loss power of each phase based on the bus voltage and the current of each phase; calculating switching loss power of each phase based on the switching frequency, the bus voltage, and the current of each phase; determining the sum of the conduction loss power of the same phase and the switching loss power of the same phase as the loss power of the same phase to obtain loss power of each phase.

3. The vehicle power module junction temperature estimation method of claim 1, wherein, The water temperature estimation model is obtained through the following training process: obtaining historical switching frequencies, historical bus voltages, historical water pump pulse width modulation signals, historical inlet water temperatures, historical currents of different phases, historical thermistor temperatures of different phases, and historical water temperatures of different phases at different times, generating the sample data set, and dividing the sample data set into a training set and a validation set, the historical water temperatures of different phases being collected based on water temperature sensors arranged at radiators of a sample power module; training a preset neural network model through the training set and verifying the trained neural network model through the validation set to obtain the water temperature estimation model.

4. The vehicle power module junction temperature estimation method of claim 3, wherein, The training of the preset neural network model through the training set and the verification of the trained neural network model through the validation set to obtain the water temperature estimation model comprises: training the preset neural network model by taking the historical switching frequencies, the historical bus voltages, the historical water pump pulse width modulation signals, the historical inlet water temperatures, the historical currents of different phases, and the historical thermistor temperatures of different phases in the training set as input values and taking the historical water temperatures of different phases in the training set as output values to obtain the trained neural network model; inputting the historical switching frequencies, the historical bus voltages, the historical water pump pulse width modulation signals, the historical inlet water temperatures, the historical currents of different phases, and the historical thermistor temperatures of different phases in the validation set into the trained neural network model to obtain validation water temperatures of different phases output by the trained neural network model. Calculate the error between the verification water temperature of the same phase and the historical water temperature of the same phase in the verification set to obtain the error of each phase respectively, and adjust the trained neural network model according to the error of each phase to obtain the water temperature estimation model.

5. The vehicle power module junction temperature estimation method of claim 1, wherein, The loss power of each phase is calculated based on the switching frequency, the bus voltage and the current of each phase, and the method further comprises: A power module loss model is established based on the switching frequency parameter, the bus voltage parameter and the current parameter, and the power module loss model comprises a first sub-model for calculating conduction loss power, a second sub-model for calculating switching loss power and a third sub-model for calculating loss power; The conduction loss power of each phase is obtained through the bus voltage, the current of each phase and the first sub-model; The switching loss power of each phase is obtained through the switching frequency, the bus voltage, the current of each phase and the second sub-model; The loss power of each phase is obtained through the conduction loss power of each phase, the switching loss power of each phase and the third sub-model.

6. The vehicle power module junction temperature estimation method of any one of claims 1-5, wherein, The junction temperature of each phase is estimated based on the thermal impedance of the vehicle power module, the loss power of each phase and the water temperature of each phase, and the vehicle power module junction temperature is determined, comprising: The temperature difference of each phase is calculated based on the thermal impedance and the loss power of each phase; The junction temperature of each phase is calculated based on the temperature difference of the same phase and the water temperature of the same phase, and the maximum junction temperature is determined as the vehicle power module junction temperature.

7. The vehicle power module junction temperature estimation method of any one of claims 1-5, wherein, Before the junction temperature of each phase is estimated based on the thermal impedance of the vehicle power module, the loss power of each phase and the water temperature of each phase, the vehicle power module junction temperature estimation method comprises: The thermal impedance is pre-set; Or, The equivalent thermal resistance and the thermal time constant of the vehicle power module are obtained, and the thermal impedance is determined based on the equivalent thermal resistance, the thermal time constant and the vehicle power module operation time, and the operation data further comprises the vehicle power module operation time.

8. A vehicle power module junction temperature estimation apparatus characterized by comprising: The vehicle power module junction temperature estimation device comprises: A data acquisition module is configured to acquire operation data of a vehicle power module, and the operation data comprises switching frequency, bus voltage, water pump pulse width modulation signal, water inlet temperature, current of different phases and thermistor temperature of different phases. A loss power calculation module is configured to calculate the loss power of each phase based on the switching frequency, the bus voltage and the current of each phase. A water temperature estimation module is configured to input the operation data into a pre-trained water temperature estimation model to obtain the water temperature of different phases, and the water temperature estimation model is trained based on a sample data set, and the sample data set comprises historical switching frequency, historical bus voltage, historical water pump pulse width modulation signal, historical water inlet temperature, historical current of different phases, historical thermistor temperature of different phases and historical water temperature of different phases. A junction temperature determination module is configured to estimate the junction temperature of each phase based on the thermal impedance of the vehicle power module, the loss power of each phase and the water temperature of each phase, and determine the vehicle power module junction temperature of the vehicle power module.

9. An electronic device, comprising: The electronic device includes: one or more processors; 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 vehicle power module junction temperature estimation method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, a computer program stored thereon, which, when executed by a processor of a computer, causes the computer to perform the vehicle power module junction temperature estimation method of any one of claims 1-7.

Images