Complex parameter atlas-based crimping type IGBT junction temperature measurement method and device

Abstract

The embodiment of the invention provides a crimping type IGBT junction temperature measurement method and device based on a complex parameter atlas. The method comprises the steps that temperature-sensitive electrical parameters generated in the current operation process of a crimping type IGBT device are collected; according to the current operation condition, a corresponding map is determined from a plurality of pre-trained complex parameter action maps, and the complex parameter action maps are obtained by sampling current and voltage signals under multiple working conditions at a high speed, extracting dynamic temperature-sensitive electrical parameters, modeling by utilizing multiple regression or machine learning, and obtaining the dynamic temperature-sensitive electrical parameters. The mapping function is converted based on a fitting algorithm; inputting the temperature-sensitive electrical parameters into the complex parameter action atlas based on an interpolation method so as to obtain a junction temperature calculation result of the current crimping type IGBT; according to the method, the map of the influence of the complex parameters on the temperature-sensitive electrical parameters can be generated through multi-dimensional fitting, and accurate prediction of the junction temperature under different working conditions is realized.

Description

Technical Field

[0001] The present application relates to the field of temperature detection, and specifically to a method and device for measuring the junction temperature of a crimped IGBT based on a complex parameter map. Background Art

[0002] Insulated Gate Bipolar Transistor (IGBT) is a semiconductor device widely used in modern power electronic systems, especially suitable for high voltage and high current applications, such as frequency converters, inverters, high voltage direct current transmission equipment, etc. As the core component of power conversion equipment, the performance and reliability of IGBT during operation directly affect the stability and service life of the entire system. In actual operation, the junction temperature (Junction Temperature) inside the IGBT will fluctuate with the changes in current and voltage, and excessively high junction temperature may cause performance degradation or even failure of the device. Therefore, real-time and accurate monitoring and control of the junction temperature of the IGBT is crucial to ensure the normal operation of the system and extend the service life of the device.

[0003] Traditional IGBT junction temperature measurement methods mainly rely on temperature sensors, including thermistors (NTCs), thermocouples, and built-in temperature sensors. These methods can measure the junction temperature of the device more accurately in a static environment or under specific working conditions. However, in practical applications, such as scenarios where current and voltage change frequently, IGBTs usually need to work under complex dynamic conditions. At this time, the response speed and measurement accuracy of traditional measurement methods are not enough to track the rapid fluctuations in junction temperature. In addition, most traditional methods rely on steady-state temperature-sensitive electrical parameters (TSEP), such as the measurement of saturation voltage drop Vce(sat). Such parameters can only reflect the junction temperature changes of the device in a stable state, and cannot accurately capture the temperature characteristics during dynamic operation.

[0004] Under complex working conditions, changes in current, voltage, drive resistance, gate drive voltage and other factors will significantly affect the junction temperature state of the IGBT. Due to the hysteresis and limitations of traditional junction temperature measurement methods, such methods cannot meet the high-precision requirements for real-time monitoring of junction temperature in dynamic environments. Therefore, how to achieve online real-time measurement of IGBT junction temperature under various working conditions has become a technical problem that needs to be solved urgently in modern power electronic systems. Summary of the invention

[0005] In response to the problems in the prior art, the present application provides a method and device for measuring the junction temperature of a crimped IGBT based on a complex parameter map, which can generate a map of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting, thereby achieving accurate prediction of the junction temperature under different working conditions.

[0006] To solve at least one of the above problems, the present application provides the following technical solutions:

[0007] According to the first aspect of the embodiments of the present application, the present application provides a method for measuring the junction temperature of a press-pack IGBT based on a complex parameter map, including:

[0008] Collecting the temperature-sensitive electrical parameters generated during the current operation of the press-pack IGBT device;

[0009] Determining a corresponding map from multiple pre-trained complex parameter effect maps according to the current operating conditions, where the complex parameter effect map is obtained by high-speed sampling of current and voltage signals under multiple conditions, extracting dynamic temperature-sensitive electrical parameters, and using multiple regression or machine learning to model, and then converting and mapping functions based on a fitting algorithm;

[0010] Inputting the temperature-sensitive electrical parameters into the complex parameter effect map based on the interpolation method to obtain the calculation result of the junction temperature of the current press-pack IGBT.

[0011] According to any implementation manner of the present application, the construction process of the multiple pre-trained complex parameter effect maps includes:

[0012] High-frequency sampling of the current and voltage signals of the press-pack IGBT device under multiple conditions through a high-speed data acquisition device;

[0013] Extracting the dynamic temperature-sensitive electrical parameters of the press-pack IGBT device under multiple conditions according to the current and voltage signals, and performing standardization processing on the dynamic temperature-sensitive electrical parameters;

[0014] Modeling the dynamic temperature-sensitive electrical parameters collected under multiple conditions according to multiple regression or machine learning methods to obtain a complex parameter mapping function under multiple conditions;

[0015] Based on the fitting algorithm, respectively converting the complex parameter mapping functions under multiple conditions to obtain the multiple complex parameter effect maps.

[0016] According to any implementation manner of the present application, after modeling the dynamic temperature-sensitive electrical parameters collected under multiple conditions according to multiple regression or machine learning methods to obtain a complex parameter mapping function under multiple conditions, it further includes:

[0017] Assigning weight coefficients to each parameter in the complex parameter mapping function based on a preset rule;

[0018] After inputting the temperature-sensitive electrical parameters into the complex parameter effect map based on the interpolation method to obtain the calculation result of the junction temperature of the current press-pack IGBT, it further includes:

[0019] Obtain the current junction temperature measurement result of the press-fit IGBT;

[0020] Compare the junction temperature measurement result and the junction temperature calculation result through an error optimization algorithm to determine the current first calculation error;

[0021] Adjust the weight coefficient based on the backpropagation algorithm to reduce the first calculation error.

[0022] According to any embodiment of the present application, the inputting the temperature-sensitive electrical parameter into the complex parameter effect map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit IGBT includes:

[0023] Input the temperature-sensitive electrical parameter into the complex parameter effect map based on the interpolation method;

[0024] During the process of calculating the junction temperature in the complex parameter effect map, in response to the change of working conditions, dynamically correct the current junction temperature calculation result according to the complex parameter effect map corresponding to the changed working conditions.

[0025] According to any embodiment of the present application, after inputting the temperature-sensitive electrical parameter into the complex parameter effect map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit IGBT, it further includes:

[0026] Conduct a calibration experiment on the junction temperature of the press-fit IGBT devices of the same batch under laboratory conditions to obtain the corresponding calibration measurement results;

[0027] Determine the current second calculation error according to the calibration measurement result and the junction temperature calculation result;

[0028] Determine the current error source according to the second calculation error, and the error source includes device aging and / or working condition change;

[0029] Optimize the complex parameter mapping function based on the error compensation algorithm to reduce the second calculation error.

[0030] According to any embodiment of the present application, after inputting the temperature-sensitive electrical parameter into the complex parameter effect map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit IGBT, it further includes:

[0031] Repeatedly calculate the junction temperature of the press-fit IGBT under preset working conditions, and optimize the complex parameter mapping function according to the multiple calculation results to enhance the robustness of the current junction temperature calculation result.

[0032] According to the second aspect of the embodiments of the present application, the present application provides a press-fit IGBT junction temperature measurement device based on a complex parameter map, including:

[0033] A parameter acquisition module, configured to: acquire the temperature-sensitive electrical parameters generated during the current operation of the press-fit IGBT device;

[0034] A map determination module, configured to: determine a corresponding map from multiple pre-trained complex parameter effect maps according to the current operating conditions, wherein the complex parameter effect maps are obtained by high-speed sampling of current and voltage signals under multiple conditions, extracting dynamic temperature-sensitive electrical parameters, and using multiple regression or machine learning to model, and then obtaining the conversion mapping function based on the fitting algorithm;

[0035] A junction temperature calculation module, configured to: input the temperature-sensitive electrical parameters into the complex parameter effect map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit IGBT.

[0036] According to any implementation manner of the present application, the construction process of the multiple pre-trained complex parameter effect maps includes:

[0037] A signal sampling module, configured to: perform high-frequency sampling on the current and voltage signals of the press-fit IGBT device under multiple conditions through a high-speed data acquisition device;

[0038] A parameter calculation module, configured to: extract the dynamic temperature-sensitive electrical parameters of the press-fit IGBT device under multiple conditions according to the current and voltage signals, and perform standardization processing on the dynamic temperature-sensitive electrical parameters;

[0039] A function determination module, configured to: perform modeling on the dynamic temperature-sensitive electrical parameters collected under multiple conditions according to a multiple regression or machine learning device to obtain a complex parameter mapping function under multiple conditions;

[0040] A map determination module, configured to: respectively perform conversion on the complex parameter mapping functions under multiple conditions based on the fitting algorithm to obtain the multiple complex parameter effect maps.

[0041] According to any implementation manner of the present application, it further includes: a coefficient distribution module and a coefficient adjustment module;

[0042] The coefficient distribution module is configured to: perform weight coefficient distribution on each parameter in the complex parameter mapping function based on a preset rule;

[0043] The coefficient adjustment module includes:

[0044] A junction temperature measurement unit, configured to: obtain the junction temperature measurement result of the current press-fit IGBT;

[0045] A first error determination unit, configured to: compare the junction temperature measurement result and the junction temperature calculation result through an error optimization algorithm to determine the current first calculation error;

[0046] A coefficient adjustment unit, configured to: adjust the weight coefficient based on the backpropagation algorithm to reduce the first calculation error.

[0047] According to any embodiment of the present application, the junction temperature calculation module includes:

[0048] A parameter input unit, configured to: input the temperature-sensitive electrical parameter into the complex parameter action map based on the interpolation method;

[0049] A dynamic correction unit, configured to: during the process of calculating the junction temperature by the complex parameter action map, in response to a change in the working condition, dynamically correct the current junction temperature calculation result according to the complex parameter action map corresponding to the changed working condition.

[0050] According to any embodiment of the present application, it further includes a verification and optimization module, including:

[0051] An experimental calibration unit, configured to: perform a calibration experiment on the junction temperature of the same batch of press-pack IGBT devices under laboratory conditions to obtain corresponding calibration measurement results;

[0052] A second error determination unit, configured to: determine the current second calculation error according to the calibration measurement result and the junction temperature calculation result;

[0053] An error source determination unit, configured to: determine the current error source according to the second calculation error, where the error source includes device aging and / or working condition change;

[0054] A first function optimization unit, configured to: optimize the complex parameter mapping function based on the error compensation algorithm to reduce the second calculation error.

[0055] According to any embodiment of the present application, it further includes a multi-condition test module, configured to:

[0056] Repeatedly calculate the junction temperature of the press-pack IGBT under different preset working conditions, and optimize the complex parameter mapping function according to the multiple calculation results to enhance the robustness of the current junction temperature calculation result.

[0057] According to the third aspect of the embodiments of the present application, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the steps of the method for measuring the junction temperature of a press-pack IGBT based on a complex parameter map.

[0058] According to the fourth aspect of the embodiments of the present application, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned method for measuring the junction temperature of a press-pack IGBT based on a complex parameter map are implemented.

[0059] According to the fifth aspect of the embodiments of the present application, the present application provides a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps of the above-mentioned method for measuring the junction temperature of a press-pack IGBT based on a complex parameter map are implemented.

[0060] As can be seen from the above technical solutions, the present application provides a method and device for measuring the junction temperature of a press-pack IGBT based on a complex parameter map. By collecting the temperature-sensitive electrical parameters generated during the current operation of the press-pack IGBT device; determining a corresponding map from multiple pre-trained complex parameter effect maps according to the current operating conditions, wherein the complex parameter effect map is obtained by high-speed sampling of current and voltage signals under multiple operating conditions, extracting dynamic temperature-sensitive electrical parameters, and using multiple regression or machine learning to model, and then obtaining a conversion mapping function based on a fitting algorithm; inputting the temperature-sensitive electrical parameters into the complex parameter effect map based on interpolation to obtain the calculation result of the junction temperature of the current press-pack IGBT, which can generate a map of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting, and realize accurate prediction of the junction temperature under different operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0062] Figure 1 It is a schematic flow chart of the method for measuring the junction temperature of a press-pack IGBT based on a complex parameter map in an embodiment of the present application;

[0063] Figure 2 It is a schematic flow chart of the method for measuring the junction temperature of a press-pack IGBT based on a complex parameter map in an embodiment of the present application;

[0064] Figure 3 It is a schematic flow chart of the method for measuring the junction temperature of a press-pack IGBT based on a complex parameter map in an embodiment of the present application;

[0065] Figure 4 It is a schematic flow chart of the method for measuring the junction temperature of a press-pack IGBT based on a complex parameter map in an embodiment of the present application;

[0066] Figure 5 It is the fifth flow schematic diagram of the crimp-type IGBT junction temperature measurement method based on a complex parameter map in the embodiments of the present application;

[0067] Figure 6 It is one of the structural diagrams of the crimp-type IGBT junction temperature measurement device based on a complex parameter map in the embodiments of the present application;

[0068] Figure 7 It is the second structural diagram of the crimp-type IGBT junction temperature measurement device based on a complex parameter map in the embodiments of the present application;

[0069] Figure 8 It is the structural schematic diagram of the electronic device in the embodiments of the present application. Specific embodiments

[0070] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0071] In the technical solutions of the present application, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations.

[0072] Considering the lag and limitations of traditional junction temperature measurement methods, and the problem that such methods cannot meet the high-precision requirements for real-time monitoring of junction temperature in a dynamic environment, the present application provides a crimp-type IGBT junction temperature measurement method and device based on a complex parameter map, and generates a map of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting to achieve accurate prediction of junction temperature under different working conditions.

[0073] In order to be able to generate a map of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting and achieve accurate prediction of junction temperature under different working conditions, the present application provides an embodiment of a crimp-type IGBT junction temperature measurement method based on a complex parameter map. Refer to Figure 1 , the crimp-type IGBT junction temperature measurement method based on a complex parameter map specifically includes the following content:

[0074] Step S101: Collect the temperature-sensitive electrical parameters generated during the current operation of the crimp-type IGBT device.

[0075] Under high-voltage and high-current operating conditions, temperature variations in IGBT devices can cause fluctuations in these electrical parameters. Therefore, accurately collecting these parameters is crucial for subsequent junction temperature calculations. Exemplarily, to ensure the timeliness and accuracy of data, this application uses a high-speed sampling device at the MHz level to capture the instantaneous changes in temperature-sensitive electrical parameters, thereby comprehensively reflecting the state of IGBT devices under different dynamic operating conditions.

[0076] This application uses a high-speed data acquisition device to collect in real time the temperature-sensitive electrical parameters generated during the operation of the press-pack IGBT device. Among them, the dynamic temperature-sensitive electrical parameters (Dynamic Temperature-Sensitive Electrical Parameters, D-TSEP) refer to the electrical characteristic parameters directly related to temperature during the dynamic operation of the IGBT device, such as turn-on time (ton), turn-off time (toff), turn-on voltage drop (Vce(on)), turn-off current fluctuations, etc. These parameters are not only affected by the device temperature but also closely related to the current level, voltage level, and driving conditions (driving resistance and driving voltage) in which the device is located.

[0077] Step S102: Determine a corresponding map from multiple pre-trained complex parameter effect maps according to the current operating conditions, where the complex parameter effect map is obtained by high-speed sampling current and voltage signals under multiple conditions, extracting dynamic temperature-sensitive electrical parameters, and using multiple regression or machine learning to model and then converting the mapping function based on a fitting algorithm.

[0078] In a specific embodiment of this application, the junction temperature measurement of the press-pack IGBT device needs to accurately select a most matching map from multiple pre-trained complex parameter effect maps according to the current operating conditions. This process is achieved by real-time monitoring of key operating condition parameters such as the current, voltage, driving resistance, and gate voltage of the IGBT device and matching these parameters with the data in the pre-trained map library. Each map covers the mapping relationship between temperature-sensitive electrical parameters and junction temperature under different operating conditions. Therefore, selecting the map closest to the current operating conditions is the key to ensuring the accuracy of junction temperature calculation.

[0079] For example, in practical applications, in a motor system controlled by a certain frequency converter, the IGBT device operates under the conditions of a current of 80 A and a voltage of 600 V. The system first collects the current operating condition parameters and compares these parameters with the pre-trained data in the atlas library. The atlas library contains multiple mapping relationship atlases constructed in a laboratory environment, such as combinations of different current levels (50 A, 100 A), different voltage levels (400 V, 800 V), etc. The system uses a similarity matching algorithm (such as Euclidean distance or cosine similarity) to calculate the similarity between the current operating condition parameters and each atlas data, and finally selects the atlas that is closest to a current of 80 A and a voltage of 600 V.

[0080] Preferably, after matching the atlas, it is possible to further check whether multi-atlas fusion is required. For example, in some complex operating conditions, such as when the current and voltage fluctuate frequently, the matching of a single atlas may not fully meet the accuracy requirements. At this time, according to the changing trend of the current operating conditions, adjacent atlases can be dynamically selected for fusion, and a more accurate mapping relationship can be calculated between the multi-atlases through an interpolation algorithm. In this way, even when the current increases from 80 A to 90 A, the present application can ensure that the atlas used always remains consistent with the current operating conditions.

[0081] Step S103: Input the temperature-sensitive electrical parameter into the complex parameter effect atlas based on the interpolation method to obtain the junction temperature calculation result of the current press-pack IGBT.

[0082] After the present application selects the complex parameter effect atlas that matches the current operating conditions, the collected temperature-sensitive electrical parameters are input into the atlas for junction temperature calculation. Since the parameters in actual operation may not exactly correspond to the discrete data points in the atlas, the present application uses an interpolation algorithm to process the temperature-sensitive electrical parameters and estimate the junction temperature value that meets the current conditions. Among them, the interpolation method can calculate the function relationship between adjacent data points, making the calculation result more accurate. Even if the operating conditions change slightly, it can provide accurate junction temperature measurement. In addition, the present application also performs dynamic correction according to the ambient temperature and changes in operating conditions to ensure that the measurement results have high reliability and accuracy under complex and changeable operating conditions.

[0083] As can be seen from the above description, the method for measuring the junction temperature of a press-pack IGBT based on a complex parameter atlas provided by the embodiment of the present application can generate an atlas of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting, and achieve accurate prediction of the junction temperature under different operating conditions.

[0084] In an embodiment of the method for measuring the junction temperature of a press-pack IGBT based on a complex parameter atlas of the present application, refer to Figure 2 , the construction process of the multiple pre-trained complex parameter effect atlases includes:

[0085] Step S01: High-frequency sampling of the current and voltage signals of the press-pack IGBT device under multiple working conditions is performed by a high-speed data acquisition device.

[0086] Under different working conditions (such as different current levels, voltage levels, and drive resistance conditions), high-frequency sampling of the current and voltage signals of the IGBT device is performed by a high-speed data acquisition device. The sampling rate is usually at the MHz level to ensure capturing the transient changes during the dynamic operation of the device. The collected data will be used to extract dynamic temperature-sensitive electrical parameters, such as turn-on time (ton), turn-off time (toff), turn-on voltage drop (Vce(on)), etc.

[0087] In an optional embodiment, in a laboratory environment, a press-pack IGBT device with a rated voltage of 1200V and a rated current of 200A is tested. During the experiment, different current and voltage conditions are simulated by a frequency converter. A high-speed data acquisition card with a sampling rate of 5MHz is used to record the current and voltage signals to ensure capturing the instantaneous changes. The sampling process can be to run the IGBT for 10 seconds under each working condition, during which the fluctuation curves of the current and voltage are recorded. Through the above tests under multiple working conditions, a large amount of instantaneous data is collected to ensure covering the operating characteristics of the IGBT under different scenarios such as high load and low load.

[0088] Step S02: Extract the dynamic temperature-sensitive electrical parameters of the press-pack IGBT device under multiple working conditions according to the current and voltage signals, and perform standardization processing on the dynamic temperature-sensitive electrical parameters.

[0089] According to the collected current and voltage signals, this application extracts the dynamic temperature-sensitive electrical parameters, which are closely related to the junction temperature of the IGBT. The extracted parameters will be subjected to standardization processing, that is, they are converted into a unified dimension format to eliminate the scale differences between different data. The processed data can be more conveniently modeled and analyzed, improving the generalization ability and accuracy of the model.

[0090] In an optional embodiment, multiple dynamic temperature-sensitive electrical parameters can be extracted from the current and voltage signals collected in Step 1, such as:

[0091] Turn-on time (ton): Calculate the time from the rising edge of the current.

[0092] Turn-off time (toff): Calculate the time from the falling edge of the current.

[0093] Turn-on voltage drop (Vce(on)): Measure the transient voltage drop when the IGBT is in the on state.

[0094] Standardize these parameters. For example, unify the time of ton and toff into milliseconds, and convert the voltage and current values into dimensionless values to ensure that all data is within the same numerical range (e.g., normalized to between 0 and 1) for more accurate subsequent modeling.

[0095] Step S03 models the dynamic temperature-sensitive electrical parameters under the multi-condition situation collected according to the multiple regression or machine learning method to obtain a complex parameter mapping function under the multi-condition situation.

[0096] To better describe the relationship between the dynamic temperature-sensitive electrical parameters and the junction temperature under multi-condition conditions, this application uses multiple regression analysis or machine learning algorithms for modeling. For example, using methods such as neural networks and support vector machines (SVM), multiple sets of dynamic temperature-sensitive electrical parameters (D) and condition parameters (such as current I, voltage V, drive resistance Rg, and gate voltage Vgs) are used as input variables to establish a complex mapping function:

[0097] Tj = F(D, I, V, Rg, Vgs)

[0098] Among them, Tj is the junction temperature, D represents the set of dynamic temperature-sensitive electrical parameters, I is the current, V is the voltage, Rg is the drive resistance, and Vgs is the gate drive voltage.

[0099] In an optional embodiment, based on the dynamic temperature-sensitive electrical parameters extracted and standardized in the above steps, a mapping model of the IGBT is constructed using a neural network. The training data set contains input data under different conditions (such as 50A / 600V, 100A / 800V). Among them, the dynamic temperature-sensitive electrical parameters D (such as ton, toff, Vce(on)) and the condition parameters (I, V, Rg, Vgs) can be used as inputs, and a three-layer neural network (input layer, hidden layer, output layer) is used to train the model until it can output the predicted value of the junction temperature Tj, and the error range is controlled within ±1°C. After training, a mapping function for different conditions is obtained, such as:

[0100] Tj = F(D, I, V, Rg, Vgs)

[0101] Step S04: Based on the fitting algorithm, convert the complex parameter mapping function under the multi-condition situation respectively to obtain the multiple complex parameter action diagrams.

[0102] After obtaining the complex parameter mapping function, this application uses a multi-dimensional fitting algorithm to further convert the mapping function into a complex parameter action diagram applicable to different condition conditions. The diagram is stored in the form of a high-dimensional matrix or a look-up table, and covers the junction temperature changes under various operating conditions, not only describing the relationship between the temperature-sensitive electrical parameters and the junction temperature, but also reflecting the complex influence of current, voltage, and drive conditions on the parameters.

[0103] In an optional embodiment, a polynomial fitting algorithm can be used to convert the mapping function under different working conditions into a high-dimensional complex parameter action map:

[0104] In the voltage range of 600V to 1200V and the current range of 50A to 200A, the predicted values of the junction temperature under all combined working conditions are calculated and stored in the form of a two-dimensional matrix, so that each row of the matrix corresponds to a current value and each column corresponds to a voltage value.

[0105] In an embodiment of the method for measuring the junction temperature of a press-fit IGBT based on a complex parameter map in the present application, after modeling the dynamic temperature-sensitive electrical parameters under the multi-working conditions collected according to the multiple regression or machine learning method to obtain a complex parameter mapping function under the multi-working conditions, it further includes:

[0106] Assigning weight coefficients to each parameter in the complex parameter mapping function based on a preset rule;

[0107] After inputting the temperature-sensitive electrical parameters into the complex parameter action map based on the interpolation method to obtain the calculation result of the junction temperature of the current press-fit IGBT, see Figure 3 , it further includes:

[0108] Step S104: Obtain the measurement result of the junction temperature of the current press-fit IGBT;

[0109] Step S105: Compare the junction temperature measurement result and the junction temperature calculation result through an error optimization algorithm to determine the current first calculation error;

[0110] Step S106: Adjust the weight coefficient based on the backpropagation algorithm to reduce the first calculation error.

[0111] After completing the multiple regression or machine learning modeling and obtaining the complex parameter mapping function under multi-working conditions, the present application further improves the accuracy and reliability of the junction temperature calculation through weight coefficient assignment and error optimization algorithms. The reasonable assignment of weight coefficients is a crucial step, aiming to reflect the importance of each parameter (such as current, voltage, driving resistance, etc.) in the junction temperature calculation under different working conditions. In the initial stage, the present application assigns preset weights to each parameter based on experimental data analysis and engineering experience. For example, the weight of current I is 0.4, the weight of voltage V is 0.3, the weight of driving resistance Rg is 0.2, and the weight of gate driving voltage Vgs is 0.1, ensuring that the model has a certain accuracy in the initial calculation stage and laying a foundation for subsequent dynamic optimization.

[0112] During the actual operation, this application will input the temperature-sensitive electrical parameters into the mapping function and the complex parameter effect map, calculate the current junction temperature result, and compare it with the actually measured junction temperature value to determine the first calculation error. For example, if the calculated junction temperature is 90 °C, but the actual measured value is 85 °C, the preliminary error is 5 °C. Through this error comparison, this application can promptly detect the deviation in the model, identify the deficiencies in weight allocation, and make necessary optimization adjustments.

[0113] Preferably, to reduce the calculation error, this application uses the Backpropagation algorithm to dynamically optimize the weight coefficients in the model. The Backpropagation algorithm passes the error from the output layer back to the input layer, continuously updating the weight of each parameter to ensure that the calculation result is closer to the actual situation.

[0114] For the error in the above example, the algorithm of this application detects that the weights of current and voltage may be too high. Therefore, the weight of current is adjusted from 0.4 to 0.35, the weight of voltage is adjusted from 0.3 to 0.25, the weight of the driving resistance is increased to 0.25, and the weight of the gate driving voltage is adjusted to 0.15. This optimization process enables the model to more accurately reflect the actual impact of current, voltage, and driving resistance on the junction temperature. After the weight adjustment, the recalculated junction temperature value is 86 °C, and the new error is reduced to 1 °C, indicating that the accuracy of the model has been significantly improved.

[0115] Through this dynamic optimization method, the junction temperature measurement of this application can not only adapt to the working condition changes during real-time operation, but also continuously reduce errors and improve the reliability of measurement. The combination of the automatic optimization of weight coefficients and the Backpropagation algorithm makes the application of the complex parameter effect map under multiple working conditions more accurate and efficient, ensuring high accuracy and stability of the temperature monitoring of the press-pack IGBT device under different operating conditions.

[0116] In an embodiment of the method for measuring the junction temperature of a press-pack IGBT based on a complex parameter map of this application, refer to Figure 4 , inputting the temperature-sensitive electrical parameters into the complex parameter effect map based on the interpolation method to obtain the junction temperature calculation result of the current press-pack IGBT, including:

[0117] Step S103A: Input the temperature-sensitive electrical parameters into the complex parameter effect map based on the interpolation method;

[0118] Step S103B: During the process of calculating the junction temperature in the complex parameter effect map, in response to the change of the working condition, dynamically correct the current junction temperature calculation result according to the complex parameter effect map corresponding to the changed working condition.

[0119] In practical applications, the complex parameter effect map stores the mapping relationship between the temperature-sensitive electrical parameters and the junction temperature under different operating conditions. However, due to the diversity and instantaneous changes of operating conditions, direct lookup table calculation sometimes cannot provide sufficient accuracy. Therefore, interpolation methods are used to process the data. During the measurement process, if the collected temperature-sensitive electrical parameters are between specific data points in the map, the system will use interpolation algorithms to calculate the approximate values between these data points, thereby obtaining a more accurate junction temperature result. The interpolation method can adopt polynomial interpolation or spline interpolation, and the optimal interpolation strategy can be flexibly selected according to the requirements of calculation speed and accuracy.

[0120] In actual operation, the operating condition parameters such as the current and voltage of the IGBT may fluctuate over time, resulting in the need to continuously update the predicted value of the junction temperature. To cope with this change, this application designs a real-time dynamic correction mechanism based on the change of operating conditions. When it is detected that parameters such as current, voltage, or drive resistance change, the system will automatically switch to the complex parameter effect map corresponding to the new operating condition and recalculate the current junction temperature. At the same time, the system adjusts the parameter weights through an adaptive algorithm to ensure that the model can automatically adapt to the new external conditions. In this way, even during long-term operation or when the ambient temperature changes, the system can still reduce error accumulation and maintain the accuracy and reliability of junction temperature monitoring.

[0121] In a specific embodiment, for example, under the initial operating condition with a rated current of 100A and a rated voltage of 800V, the system calculates the current junction temperature of the IGBT to be 85°C through interpolation. Subsequently, if the current increases to 120A while the voltage remains unchanged, the system will automatically switch to the new operating condition map and calculate a new junction temperature value based on the new map, such as 87°C. If it is detected that the ambient temperature has also risen, the system will further perform correction by adjusting the parameter weight coefficient in the mapping function to reduce errors and control the deviation between the junction temperature measurement result and the actual value within ±1°C. This measurement process combining interpolation and dynamic correction not only ensures the accuracy of real-time calculation but also improves the system's ability to handle complex operating conditions, providing a reliable guarantee for the stable operation of the press-pack IGBT device.

[0122] In an embodiment of the method for measuring the junction temperature of a press-pack IGBT based on a complex parameter map in this application, refer to Figure 5 , after inputting the temperature-sensitive electrical parameters into the complex parameter effect map based on the interpolation method to obtain the calculation result of the current junction temperature of the press-pack IGBT, it further includes:

[0123] Step S107: Conduct a calibration experiment on the junction temperature of the press-pack IGBT devices of the same batch under laboratory conditions to obtain the corresponding calibration measurement results;

[0124] Step S108: Determine the current second calculation error based on the calibration measurement result and the junction temperature calculation result;

[0125] Step S109: Determine the current error source according to the second calculation error, where the error source includes device aging and / or working condition change;

[0126] Step S110: Optimize the complex parameter mapping function based on the error compensation algorithm to reduce the second calculation error.

[0127] During the implementation of this application, to ensure the accuracy and long-term stability of the crimped IGBT junction temperature calculation model, an error analysis and compensation mechanism based on laboratory calibration is adopted. After completing the interpolation method to calculate the junction temperature and obtaining the preliminary result, multiple groups of calibration experiments are carried out on the IGBT devices of the same batch under laboratory conditions. These experiments simulate different current, voltage, and environmental conditions to obtain real reference measurement data as the calibration measurement result. Through the process of calibration experiments, basic data can be provided for the accuracy of the model and used for subsequent optimization and adjustment of the model.

[0128] After the calibration experiment is completed, compare the calibration measurement result with the junction temperature calculation result of the model to determine the current second calculation error. This error can not only reveal the deviation of the model under specific working conditions but also provide a basis for judging the error source. If the calculated error exceeds the preset accuracy range, the error source will be analyzed in depth. For example, as the usage time of the device increases, the internal materials may degenerate, resulting in the deviation of the temperature-sensitive electrical parameters from the initial parameters; or, due to the change of the operating environment temperature or the increase of the device load, there may be a large error between the prediction of the model and the actual situation.

[0129] Once the error source is determined, the complex parameter mapping function can continue to be optimized based on the error compensation algorithm, including adjusting the weight coefficients in the model through backpropagation or correcting the calculation error by updating the data points in the parameter map.

[0130] In a specific embodiment, if the calibration experiment finds that the calculated junction temperature is 5°C higher, and the error source is identified as the aging of the device, then the system will reduce the current and voltage weights under the corresponding working conditions to reflect the behavioral characteristics after the device degradation. At the same time, in future calculations, the system will dynamically adjust the mapping function according to the new calibration result to reduce error accumulation and improve the accuracy of the model.

[0131] Through the above error analysis and compensation process, the present application realizes the dynamic optimization of the complex parameter mapping function, enabling the model to maintain long-term stability and high precision under various working conditions. This not only improves the reliability of the junction temperature measurement results but also ensures the efficient operation and accurate temperature monitoring of the press-pack IGBT device in practical applications.

[0132] In an optional embodiment, after inputting the temperature-sensitive electrical parameter into the complex parameter action map based on the interpolation method to obtain the junction temperature calculation result of the current press-pack IGBT, it further includes:

[0133] Repeatedly calculate the junction temperature of the press-pack IGBT under preset working conditions, and optimize the complex parameter mapping function according to the multiple calculation results to enhance the robustness of the current junction temperature calculation result.

[0134] Among them, in the specific implementation of the present application, in order to ensure that the junction temperature calculation result of the press-pack IGBT device has high precision and robustness under various working conditions, a model optimization method based on multiple calculation results is designed. After obtaining the initial junction temperature calculation result, the system will repeatedly calculate the IGBT device under a variety of preset working conditions to verify its stability under different conditions. These preset working conditions can cover different current levels, voltage levels, and temperature environments, such as high-voltage power supply application scenarios, frequency converter operating environments, etc. Through multiple calculations under these conditions, the present application can verify the adaptability and robustness of the model in real applications.

[0135] After each calculation, the system will compare the current calculation result with the multiple calculation results to determine whether the output of the model is within a reasonable error range. If there is a large deviation between the calculation results, it indicates that the model may have insufficient response to certain parameters under specific working conditions, and the complex parameter mapping function needs to be further optimized. Specifically, the system determines whether to adjust the weight coefficient in the mapping function or re-fit some data points according to the trend of the calculation results through error analysis to ensure the sensitivity of the model to working condition changes and the stability of the calculation results.

[0136] In actual implementation, for example, in the operating environment of an inverter, the system measures the temperature-sensitive electrical parameters of the press-fit IGBT device multiple times, and records the change in the junction temperature during the process of gradually increasing the current from 50A to 200A. The results after each calculation may have slight deviations. For example, the junction temperature calculated in the first round is 85°C, the second round is 84.5°C, and the third round is 85.3°C. The system optimizes the final junction temperature value to 85°C through cluster analysis and error correction of these calculation results. At the same time, if it is found that the error deviation under a certain working condition is relatively large, for example, the junction temperature measured at a current of 200A is significantly higher than expected in a certain measurement, the system will automatically trigger the optimization of the mapping function and adjust the parameter weights of this working condition to reduce the error in future calculations.

[0137] In order to be able to generate a map of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting and achieve accurate prediction of the junction temperature under different working conditions, this application provides an embodiment of a press-fit IGBT junction temperature measurement device for implementing all or part of the content of the press-fit IGBT junction temperature measurement method based on the complex parameter map. See Figure 6 The press-fit IGBT junction temperature measurement device based on the complex parameter map specifically includes the following content:

[0138] The parameter acquisition module 1101 is used to: acquire the temperature-sensitive electrical parameters generated by the press-fit IGBT device during the current operation process;

[0139] The map determination module 1102 is used to: determine a corresponding map from multiple pre-trained complex parameter effect maps according to the current operating condition, where the complex parameter effect map is obtained by high-speed sampling of current and voltage signals under multiple working conditions, extracting dynamic temperature-sensitive electrical parameters, and using multiple regression or machine learning to build a model and then converting the mapping function based on the fitting algorithm.

[0140] The junction temperature calculation module 1103 is used to: input the temperature-sensitive electrical parameters into the complex parameter effect map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit IGBT.

[0141] According to any implementation manner of this application, see Figure 7 The construction process of the multiple pre-trained complex parameter effect maps includes:

[0142] The signal sampling module 001 is used to: perform high-frequency sampling on the current and voltage signals of the press-fit IGBT device under multiple working conditions through a high-speed data acquisition device;

[0143] The parameter calculation module 002 is used to: extract the dynamic temperature-sensitive electrical parameters of the press-fit IGBT device under multiple working conditions according to the current and voltage signals, and perform standardization processing on the dynamic temperature-sensitive electrical parameters;

[0144] A function determination module 003, configured to: model the dynamically temperature-sensitive electrical parameters collected under the multi-condition by a multiple regression or machine learning device to obtain a complex parameter mapping function under the multi-condition;

[0145] A map determination module 004, configured to: respectively convert the complex parameter mapping function under the multi-condition based on a fitting algorithm to obtain the multiple complex parameter effect maps.

[0146] According to any embodiment of the present application, it further includes: a coefficient allocation module and a coefficient adjustment module;

[0147] The coefficient allocation module is configured to: allocate weight coefficients to each parameter in the complex parameter mapping function based on a preset rule;

[0148] The coefficient adjustment module includes:

[0149] A junction temperature measurement unit, configured to: obtain a junction temperature measurement result of the current press-fit IGBT;

[0150] A first error determination unit, configured to: compare the junction temperature measurement result and the junction temperature calculation result through an error optimization algorithm to determine the current first calculation error;

[0151] A coefficient adjustment unit, configured to: adjust the weight coefficient based on a backpropagation algorithm to reduce the first calculation error.

[0152] According to any embodiment of the present application, the junction temperature calculation module includes:

[0153] A parameter input unit, configured to: input the temperature-sensitive electrical parameters into the complex parameter effect map based on an interpolation method;

[0154] A dynamic correction unit, configured to: during the process of calculating the junction temperature by the complex parameter effect map, in response to a change in the working condition, dynamically correct the current junction temperature calculation result according to the complex parameter effect map corresponding to the changed working condition.

[0155] According to any embodiment of the present application, it further includes a verification and optimization module, including:

[0156] An experimental calibration unit, configured to: perform a calibration experiment on the junction temperature of the press-fit IGBT devices of the same batch under laboratory conditions to obtain corresponding calibration measurement results;

[0157] A second error determination unit, configured to: determine the current second calculation error according to the calibration measurement result and the junction temperature calculation result;

[0158] An error source determination unit, configured to: determine a current error source according to the second calculation error, where the error source includes device aging and / or operating condition change;

[0159] A first function optimization unit, configured to: optimize the complex parameter mapping function based on an error compensation algorithm to reduce the second calculation error.

[0160] According to any implementation manner of the present application, it further includes a multi-condition test module, configured to:

[0161] Repeatedly calculate the junction temperature of the press-pack IGBT under different preset operating conditions, and optimize the complex parameter mapping function according to the multiple calculation results to enhance the robustness of the current junction temperature calculation result.

[0162] As can be seen from the above description, the press-pack IGBT junction temperature measurement device based on a complex parameter map provided by the embodiments of the present application can generate a map of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting, and achieve accurate prediction of the junction temperature under different operating conditions.

[0163] From a hardware perspective, in order to be able to generate a map of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting and achieve accurate prediction of the junction temperature under different operating conditions, the present application provides an embodiment of an electronic device for implementing all or part of the content in the press-pack IGBT junction temperature measurement method based on a complex parameter map. The electronic device specifically includes the following content:

[0164] A processor, a memory, a communication interface, and a bus; wherein, the processor, the memory, and the communication interface complete communication with each other through the bus; the communication interface is used to implement information transmission between the press-pack IGBT junction temperature measurement device based on a complex parameter map and related devices such as a core business system, a user terminal, and a related database, etc. The logic controller can be a desktop computer, a tablet computer, a mobile terminal, etc., and this embodiment is not limited thereto. In this embodiment, the logic controller can be implemented with reference to the embodiments of the press-pack IGBT junction temperature measurement method based on a complex parameter map and the embodiments of the press-pack IGBT junction temperature measurement device based on a complex parameter map, and the content is incorporated herein, and the repeated parts will not be elaborated.

[0165] It can be understood that the user terminal may include a smart phone, a tablet electronic device, an Internet set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0166] In practical applications, part of the crimped IGBT junction temperature measurement method based on the complex parameter map can be executed on the electronic device side as described above, or all operations can be completed in the client device. Specifically, it can be selected according to the processing capacity of the client device and the limitations of the user usage scenario, etc. This application does not make any limitations in this regard. If all operations are completed in the client device, the client device may further include a processor.

[0167] The above-mentioned client device may have a communication module (i.e., a communication unit), which can be communicatively connected to a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, it may also include a server of an intermediate platform, such as a server of a third-party server platform communicatively linked to the task scheduling center server. The server may include a single computer device, or a server cluster composed of multiple servers, or a server structure of a distributed device.

[0168] Figure 8 It is a schematic block diagram of the system composition of the electronic device 9600 according to an embodiment of the present application. As Figure 8 shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It should be noted that this Figure 8 is exemplary; other types of structures may also be used to supplement or replace this structure to achieve telecommunication functions or other functions.

[0169] In one embodiment, the function of the crimped IGBT junction temperature measurement method based on the complex parameter map can be integrated into the central processing unit 9100. Among them, the central processing unit 9100 may be configured to perform the following controls:

[0170] Step S101: Collect the temperature-sensitive electrical parameters generated during the current operation of the crimped IGBT device;

[0171] Step S102: Determine a corresponding map from multiple pre-trained complex parameter effect maps according to the current operating conditions, where the complex parameter effect map is obtained by high-speed sampling of current and voltage signals under multiple operating conditions, extracting dynamic temperature-sensitive electrical parameters, and using multiple regression or machine learning to model, and then obtaining a conversion mapping function based on a fitting algorithm;

[0172] Step S103: Input the temperature-sensitive electrical parameters into the complex parameter effect map based on the interpolation method to obtain the junction temperature calculation result of the current crimped IGBT.

[0173] As can be seen from the above description, the electronic device provided by the embodiments of the present application generates a map of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting, and realizes accurate prediction of the junction temperature under different working conditions.

[0174] In another embodiment, the crimp-type IGBT junction temperature measurement device based on the complex parameter map can be separately configured from the central processor 9100. For example, the crimp-type IGBT junction temperature measurement device based on the complex parameter map can be configured as a chip connected to the central processor 9100, and the function of the crimp-type IGBT junction temperature measurement method based on the complex parameter map is realized through the control of the central processor.

[0175] As Figure 8 shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It should be noted that the electronic device 9600 does not necessarily have to include Figure 8 all the components shown in Figure 8 ; in addition, the electronic device 9600 may further include

[0176] components not shown in Figure 8 ; reference may be made to the prior art.

[0177] Among them, the memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices. The above information related to failures can be stored, and in addition, programs for executing relevant information can also be stored. And the central processor 9100 can execute the program stored in the memory 9140 to realize information storage or processing, etc.

[0178] The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to supply power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display can be, for example, an LCD display, but is not limited thereto.

[0179] The memory 9140 may be a solid-state memory, such as, for example, a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that stores information even when power is off, can be selectively erased and has more data, and examples of such a memory are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 that is used to store application programs and function programs or the processes for operating the electronic device 9600 by the central processing unit 9100.

[0180] The memory 9140 may also include a data storage unit 9143 that is used to store data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers of the electronic device for communication functions and / or for performing other functions of the electronic device (such as a messaging application, an address book application, etc.).

[0181] The communication module 9110 is a transmitter / receiver 9110 that transmits and receives signals via the antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processing unit 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.

[0182] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module, etc. The communication module (transmitter / receiver) 9110 is also coupled to the speaker 9131 and the microphone 9132 via the audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby implementing normal telecommunication functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 9130 is also coupled to the central processing unit 9100, so that recording can be performed on the local device via the microphone 9132 and the sound stored on the local device can be played via the speaker 9131.

[0183] An embodiment of the present application further provides a computer-readable storage medium that can implement all steps of the crimped IGBT junction temperature measurement method based on a complex parameter map with the execution subject being a server or a client in the above embodiment. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, all steps of the crimped IGBT junction temperature measurement method based on a complex parameter map with the execution subject being a server or a client in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0184] Step S101: Collect the temperature-sensitive electrical parameters generated by the crimped IGBT device during the current operation;

[0185] Step S102: Determine a corresponding map from multiple pre-trained complex parameter effect maps according to the current operating conditions, where the complex parameter effect map is obtained by high-speed sampling of current and voltage signals under multiple operating conditions, extracting dynamic temperature-sensitive electrical parameters, and using multiple regression or machine learning to model and then converting the mapping function based on a fitting algorithm;

[0186] Step S103: Input the temperature-sensitive electrical parameters into the complex parameter effect map based on the interpolation method to obtain the junction temperature calculation result of the current crimped IGBT.

[0187] As can be seen from the above description, the computer-readable storage medium provided by the embodiment of the present application generates a map of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting, realizing accurate prediction of the junction temperature under different operating conditions.

[0188] An embodiment of the present application further provides a computer program product that can implement all steps of the crimped IGBT junction temperature measurement method based on a complex parameter map with the execution subject being a server or a client in the above embodiment. When the computer program / instructions are executed by a processor, the steps of the crimped IGBT junction temperature measurement method based on a complex parameter map are implemented. For example, the computer program / instructions implement the following steps:

[0189] Step S101: Collect the temperature-sensitive electrical parameters generated by the crimped IGBT device during the current operation;

[0190] Step S102: Determine a corresponding map from multiple pre-trained complex parameter effect maps according to the current operating conditions, where the complex parameter effect map is obtained by high-speed sampling of current and voltage signals under multiple operating conditions, extracting dynamic temperature-sensitive electrical parameters, and using multiple regression or machine learning to model and then converting the mapping function based on a fitting algorithm;

[0191] Step S103: Input the temperature-sensitive electrical parameter into the complex parameter effect map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit IGBT.

[0192] As can be seen from the above description, the computer program product provided by the embodiments of the present application generates a map of the influence of complex parameters on temperature-sensitive electrical parameters through multi-dimensional fitting, realizing accurate prediction of junction temperature under different working conditions.

[0193] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, devices, or computer program products. Therefore, the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0194] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0195] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0196] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0197] In the present invention, specific embodiments are used to illustrate the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for measuring junction temperature of a crimped IGBT based on a complex parameter map, characterized in that: The method comprises: Collect the temperature-sensitive electrical parameters generated by the crimped IGBT device during the current operation; Determine a corresponding map from a plurality of pre-trained complex parameter action maps according to the current operating condition, wherein the complex parameter action map is obtained by extracting dynamic temperature-sensitive electrical parameters by high-speed sampling of current and voltage signals under multiple operating conditions, and converting the mapping function based on a fitting algorithm after multivariate regression or machine learning modeling; The temperature-sensitive electrical parameters are input into the complex parameter action map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit type IGBT.

2. The method for measuring junction temperature of a press-fit IGBT based on a complex parameter map according to claim 1, characterized in that: The construction process of the plurality of pre-trained complex parameter action maps includes: The current and voltage signals of the crimped IGBT devices under multiple working conditions are sampled at high frequency through high-speed data acquisition equipment; Extracting dynamic temperature-sensitive electrical parameters of the crimped IGBT device under multiple operating conditions according to the current and voltage signals, and performing standardization processing on the dynamic temperature-sensitive electrical parameters; Modeling the collected dynamic temperature-sensitive electrical parameters under the multiple working conditions according to a multivariate regression or machine learning method to obtain a complex parameter mapping function under the multiple working conditions; Based on the fitting algorithm, the complex parameter mapping functions under the multiple working conditions are converted respectively to obtain the multiple complex parameter action maps.

3. The method for measuring junction temperature of a crimped IGBT based on a complex parameter map according to claim 2, characterized in that: After the dynamic temperature-sensitive electrical parameters collected under the multiple working conditions are modeled according to a multivariate regression or machine learning method to obtain a complex parameter mapping function under the multiple working conditions, the method further includes: Allocating weight coefficients to various parameters in the complex parameter mapping function based on preset rules; After the temperature-sensitive electrical parameters are input into the complex parameter action map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit IGBT, the method further includes: Get the junction temperature measurement result of the current press-fit IGBT; Comparing the junction temperature measurement result with the junction temperature calculation result through an error optimization algorithm to determine a current first calculation error; The weight coefficient is adjusted based on a back propagation algorithm to reduce the first calculation error.

4. The method for measuring junction temperature of a crimped IGBT based on a complex parameter map according to claim 2, characterized in that: The step of inputting the temperature-sensitive electrical parameter into the complex parameter action map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit IGBT includes: Inputting the temperature-sensitive electrical parameters into the complex parameter action map based on an interpolation method; In the process of calculating the junction temperature by the complex parameter action map, in response to a change in operating conditions, a current junction temperature calculation result is dynamically corrected according to the complex parameter action map corresponding to the changed operating conditions.

5. The method for measuring junction temperature of a press-fit IGBT based on a complex parameter map according to claim 2, characterized in that: After the temperature-sensitive electrical parameters are input into the complex parameter action map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit IGBT, the method further includes: Conduct a calibration experiment on the junction temperature of the same batch of press-fit IGBT devices under laboratory conditions to obtain the corresponding calibration measurement results; Determine a current second calculation error according to the calibration measurement result and the junction temperature calculation result; Determining a current error source according to the second calculated error, wherein the error source includes device aging and / or operating condition changes; The complex parameter mapping function is optimized based on an error compensation algorithm to reduce the second calculation error.

6. The method for measuring junction temperature of a press-fit IGBT based on a complex parameter map according to claim 2, characterized in that: After the temperature-sensitive electrical parameters are input into the complex parameter action map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit IGBT, the method further includes: The junction temperature of the press-fit IGBT is repeatedly calculated under preset working conditions, and the complex parameter mapping function is optimized according to the multiple calculation results to enhance the robustness of the current junction temperature calculation result.

7. A device for measuring junction temperature of a crimped IGBT based on a complex parameter map, characterized in that: The device comprises: The parameter acquisition module is used to: collect the temperature-sensitive electrical parameters generated by the crimped IGBT device during the current operation; A map determination module is used to determine a corresponding map from a plurality of pre-trained complex parameter action maps according to the current operating condition, wherein the complex parameter action map is obtained by extracting dynamic temperature-sensitive electrical parameters by high-speed sampling of current and voltage signals under multiple operating conditions, and converting the mapping function based on a fitting algorithm after modeling using multiple regression or machine learning; The junction temperature calculation module is used to: input the temperature-sensitive electrical parameters into the complex parameter action map based on the interpolation method to obtain the junction temperature calculation result of the current press-fit type IGBT.

8. The device for measuring junction temperature of a compression-type IGBT based on a complex parameter map according to claim 7, characterized in that: The construction process of the plurality of pre-trained complex parameter action maps includes: The signal sampling module is used to: perform high-frequency sampling of current and voltage signals of crimp-type IGBT devices under multiple working conditions through high-speed data acquisition equipment; A parameter calculation module, used to extract the dynamic temperature-sensitive electrical parameters of the crimped IGBT device under multiple working conditions according to the current and voltage signals, and perform standardization processing on the dynamic temperature-sensitive electrical parameters; A function determination module is used to: model the dynamic temperature-sensitive electrical parameters collected under the multiple working conditions according to a multivariate regression or machine learning device to obtain a complex parameter mapping function under the multiple working conditions; The spectrum determination module is used to: convert the complex parameter mapping functions under the multiple working conditions respectively based on the fitting algorithm to obtain the multiple complex parameter action spectra.

9. The device for measuring junction temperature of a compression-type IGBT based on a complex parameter map according to claim 8, characterized in that: Also includes: Coefficient allocation module and coefficient adjustment module; The coefficient allocation module is used to: allocate weight coefficients to various parameters in the complex parameter mapping function based on preset rules; The coefficient adjustment module comprises: The junction temperature measurement unit is used to obtain the junction temperature measurement result of the current press-fit IGBT; A first error determination unit is used to compare the junction temperature measurement result and the junction temperature calculation result through an error optimization algorithm to determine a current first calculation error; A coefficient adjustment unit is used to adjust the weight coefficient based on a back propagation algorithm to reduce the first calculation error.

10. The device for measuring junction temperature of a compression-type IGBT based on a complex parameter map according to claim 8, characterized in that: The junction temperature calculation module includes: A parameter input unit, used to: input the temperature-sensitive electrical parameter into the complex parameter action map based on an interpolation method; The dynamic correction unit is used to: in the process of calculating the junction temperature by the complex parameter action map, in response to the change of the working condition, dynamically correct the current junction temperature calculation result according to the complex parameter action map corresponding to the changed working condition.

11. The device for measuring junction temperature of a compression-type IGBT based on a complex parameter map according to claim 8, characterized in that: Also included are validation optimization modules, including: The experimental calibration unit is used to: perform a calibration experiment on the junction temperature of the same batch of press-fit IGBT devices under laboratory conditions to obtain corresponding calibration measurement results; A second error determination unit, configured to: determine a current second calculation error according to the calibration measurement result and the junction temperature calculation result; an error source determination unit, configured to: determine a current error source according to the second calculated error, wherein the error source includes device aging and / or operating condition changes; The first function optimization unit is used to optimize the complex parameter mapping function based on an error compensation algorithm to reduce the second calculation error.

12. The device for measuring junction temperature of a compression-type IGBT based on a complex parameter map according to claim 8, characterized in that: Also includes multi-condition test modules for: The junction temperature of the press-fit IGBT is repeatedly calculated under different preset working conditions, and the complex parameter mapping function is optimized according to the multiple calculation results to enhance the robustness of the current junction temperature calculation result.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for measuring the junction temperature of a press-fit IGBT based on a complex parameter map as described in any one of claims 1 to 6 are implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for measuring the junction temperature of a press-fit IGBT based on a complex parameter map as described in any one of claims 1 to 6 are implemented.

15. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the method for measuring the junction temperature of a press-fit IGBT based on a complex parameter map as described in any one of claims 1 to 6 are implemented.

Images