Performance test method and system for IGBT (Insulated Gate Bipolar Translator) based on multi-source data

Abstract

The invention relates to the technical field of transistor performance testing, in particular to an IGBT performance testing method and system based on multi-source data, in the system, a performance testing analysis module obtains index change characteristics corresponding to elements in a performance index category adaptation set, calculates performance evaluation values of IGBT products based on application scenarios, and obtains the performance evaluation values of the IGBT products based on the application scenarios. And dynamically locking the performance test decay abnormal node of the obtained IGBT based on the application scene. In the process of testing the performance data of the IGBT product, differentiated testing of the performance of the IGBT product can be realized by combining the application scene information difference and the demand difference of the user on the IGBT product, so that the difference between the obtained performance test result and the performance obtaining data in the actual application scene is reduced; the locking of the decay abnormal node of the IGBT is tested based on the performance of an application scene, so that a data reference is provided for a user to identify a fault mode and defects of an IGBT product and for product quality control.

Description

Technical Field

[0001] The present invention relates to the technical field of transistor performance testing, and specifically to a method and system for testing the performance of an IGBT based on multi-source data. Background Art

[0002] As a core device in the field of power electronics, the IGBT (Insulated Gate Bipolar Transistor) has a wide range of application fields, and the quality of its performance directly affects the efficiency and stability of the entire application system. With the continuous improvement of power density, switching frequency, and reliability requirements, the performance testing of IGBT has become a key link in product R & D, quality control, and fault diagnosis. Traditional testing methods mainly rely on a single data source (such as electrical characteristics or temperature testing), and it is difficult to comprehensively evaluate the performance of IGBT under actual complex working conditions.

[0003] At the same time, existing IGBT performance testing systems based on multi-source data often only test the performance data of IGBT products under a single test condition, without combining the differences in application scenario information and demand differences of users for IGBT products to achieve differential testing of the performance of IGBT products. Therefore, the obtained performance test results often have a large deviation from the performance data obtained in the actual application scenario, resulting in a mismatch situation. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for testing the performance of an IGBT based on multi-source data to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: A method for testing the performance of an IGBT based on multi-source data, including: Step S100: Obtain the application scenario of the IGBT product to be tested, and extract the application feature information and performance requirement conditions of the obtained application scenario; Step S200: Dynamically generate aging test conditions according to the application feature information of the application scenario, and generate the change situation of each performance index of the IGBT product under the corresponding aging test conditions; Based on the performance requirement conditions of the obtained application scenario, dynamically intercept the performance adaptation segments in the obtained change situation of each performance index, and construct a performance index category adaptation set; Step S300: Obtain the index change characteristics corresponding to each element in the performance index category adaptation set, calculate the performance evaluation value of the IGBT product based on the application scenario, and dynamically lock the performance test decay abnormal node of the obtained IGBT based on the application scenario; Step S400: Generate a performance test report of the IGBT based on the performance evaluation value of the IGBT product based on the application scenario and the performance test decay abnormal node, and feedback it to the performance test management personnel.

[0006] Further, the step S100 includes: The application feature information includes the switching frequency, ambient temperature, and heat dissipation capacity coefficient of the IGBT; the heat dissipation capacity coefficient represents the coefficient value bound to the cooling duration within the preset cooling range of the IGBT product to be tested in the application scenario in the preset form of the database; the performance requirement conditions include the normal state ranges corresponding to each preset performance index type.

[0007] In the present invention, the performance requirement conditions include the working delay, maximum working temperature, and product working life threshold; at the same time, in the present invention, obtaining the application feature information of the IGBT product takes into account the differences in the application scenarios of the IGBT products to be tested. For the same product in different application scenarios, different performance data are often presented; therefore, the acquisition of the application feature information in the present invention is for extracting the aging test conditions for the IGBT product and building a product test scenario model adapted to the performance test of the IGBT product in the subsequent steps.

[0008] Further, the step S200 includes: Step S201: Using the application feature information of the application scenario as the aging test conditions, build an IGBT product test scenario model, and test the performance index data of the IGBT product at different time points. The types of performance indexes to be tested are preset in the database; Step S202: Extract the test data summary set {(ti 1 , Bi 1 ), (ti 2 , Bi 2 ),..., (ti ni , Bi ni ),..., (ti Ni-1 , Bi Ni-1 ), (ti Ni , Bi Ni )} of the IGBT product based on the i-th performance index under the aging test conditions, where ti 1 represents the starting test time point of the IGBT product based on the i-th performance index under the aging test conditions; ti ni represents the test time point corresponding to the ni-th test data obtained by the IGBT product based on the i-th performance index under the aging test conditions; Bi ni represents the ni-th test data obtained by the IGBT product based on the i-th performance index under the aging test conditions; ni ∈ [1, Ni], and Ni represents the total number of test data obtained by the IGBT product based on the i-th performance index under the aging test conditions; ti Ni represents the time point when the IGBT product is damaged under the aging test conditions; Step S203: Mark the coordinate points corresponding to each element in the summary set of test data of the IGBT product based on the i-th performance index under the aging test conditions in the i-th rectangular coordinate system, and sequentially connect the adjacent marked coordinate points corresponding to the time to obtain the fitting curve of the i-th performance index test data of the IGBT product changing with time under the corresponding aging test conditions, denoted as Fi; the i-th rectangular coordinate system is constructed with o as the origin, the test time point as the x-axis, and the test data of the i-th performance index as the y-axis; In the present invention, the fitting curves of the test data of each performance index of the IGBT product changing with time under the corresponding aging test conditions are all piecewise functions. Obtaining the fitting curves of the test data of each performance index of the IGBT product changing with time under the corresponding aging test conditions provides detailed and accurate data support for the performance adaptation segments intercepted dynamically in the subsequent steps; the parameters corresponding to the horizontal axes in each rectangular coordinate system constructed in the present invention are all the same, all being the test time; while the parameters corresponding to the vertical axes are all different, being the test data of the corresponding performance indexes respectively.

[0009] Step S204: Dynamically intercept the performance adaptation segment in the change situation of the i-th performance index, denoted as FPi; the FPi is the curve segment composed of the coordinate points in Fi whose corresponding function values do not belong to the normal state interval corresponding to the i-th preset performance index type in the performance requirement conditions. Step S205: Construct a performance index category adaptation set, which is a set of performance adaptation segments in the change situations of each dynamically intercepted performance index. Each element in the performance index category adaptation set corresponds to a performance adaptation segment in the change situation of one performance index.

[0010] Further, the step S300 includes: The index change characteristics include the time interval corresponding to the performance adaptation segment and the change rate of the test data of the performance index corresponding to each time point in the performance adaptation segment. The change rate of the test data of the performance index corresponding to each time point in the performance adaptation segment is equal to the value of the derivative function corresponding to the corresponding time point in the derivative function of the corresponding fitting function; Calculate the performance evaluation value of the IGBT product based on the application scenario, and the involved calculation formula is as follows: , where PR represents a performance evaluation value of a corresponding IGBT product under test based on the application scenario; TZ represents the interval length of the intersection interval between the time intervals corresponding to the performance adaptation segments respectively corresponding to each element in the performance index category adaptation set; T irepresents the interval length of the corresponding time interval of the performance adaptation segment corresponding to the i-th element in the performance index category adaptation set; m represents the preset number of performance index types; The performance evaluation value of the IGBT product based on the application scenario is equal to the average of the performance evaluation values of each tested IGBT product based on the application scenario.

[0011] Further, in the process of dynamically locking the performance test decay abnormal node of the obtained IGBT based on the application scenario in step S300, the change rate of the performance index test data corresponding to each time point in the index change characteristics corresponding to each element in the performance index category adaptation set is obtained; Obtain the time interval with the largest interval length formed by the time points with the largest change rate of the performance index test data in the index change characteristics corresponding to each element in the performance index category adaptation set corresponding to the same tested IGBT product, and record it as the performance decay abnormal interval of the corresponding tested IGBT product; Take any continuous interval in the union of the performance decay abnormal intervals of each tested IGBT product as the time mapping interval of a performance test decay abnormal node of the IGBT product based on the application scenario.

[0012] Further, the performance test report of the IGBT in step S400 is composed of the performance evaluation value of the IGBT product based on the application scenario, the performance test decay abnormal node, and the time mapping interval of each performance test decay abnormal node.

[0013] In the present invention, obtaining the performance test decay abnormal node and the time mapping interval of each performance test decay abnormal node is to facilitate the generation of inspection and maintenance decisions for the IGBT product by the management personnel when the IGBT product is put into the corresponding application scenario. Within the time mapping interval of each performance test decay abnormal node, it is necessary to increase the inspection and monitoring frequency of the IGBT product to achieve the purpose of timely discovering the risk of performance decay abnormality of the IGBT; At the same time, the acquisition of the performance test decay abnormal node of the IGBT product based on the application scenario and the time mapping interval of each performance test decay abnormal node also provides data references for users to identify the failure modes and defects of the IGBT product, as well as for product quality control and improvement.

[0014] A performance test system for IGBT based on multi-source data, the system includes a test condition information extraction module, a performance index test module, a performance test analysis module, and a performance test report feedback module, The test condition information extraction module obtains the application scenario of the IGBT product to be tested, and extracts the application feature information and performance requirement conditions of the obtained application scenario; The performance index test module dynamically generates aging test conditions according to the application characteristic information of the application scenario, and generates the change conditions of each performance index of the IGBT product under the corresponding aging test conditions; based on the obtained performance requirement conditions of the application scenario, it dynamically intercepts the performance adaptation segments in the obtained change conditions of each performance index, and constructs a performance index category adaptation set; The performance test analysis module obtains the index change characteristics corresponding to each element in the performance index category adaptation set, calculates the performance evaluation value of the IGBT product based on the application scenario, and dynamically locks the performance test decay abnormal nodes of the obtained IGBT based on the application scenario; The performance test report feedback module generates a performance test report of the IGBT based on the performance evaluation value of the IGBT product based on the application scenario and the performance test decay abnormal nodes, and feeds it back to the performance test management personnel.

[0015] Further, the performance index test module includes a performance index change relationship fitting unit and a performance adaptation analysis unit, The performance index change relationship fitting unit dynamically generates aging test conditions according to the application characteristic information of the application scenario, and generates the change conditions of each performance index of the IGBT product under the corresponding aging test conditions; The performance adaptation analysis unit dynamically intercepts the performance adaptation segments in the obtained change conditions of each performance index based on the obtained performance requirement conditions of the application scenario, and constructs a performance index category adaptation set.

[0016] Further, the performance test analysis module includes an index change characteristic extraction unit, a performance evaluation unit and a decay node analysis unit, The index change characteristic extraction unit obtains the index change characteristics corresponding to each element in the performance index category adaptation set; The performance evaluation unit calculates the performance evaluation value of the IGBT product based on the application scenario according to the extraction result of the index change characteristic extraction unit; The decay node analysis unit dynamically locks the performance test decay abnormal nodes of the obtained IGBT based on the application scenario.

[0017] Compared with the prior art, the beneficial effects achieved by the present invention are: (1) The present invention can comprehensively consider various parameters and data sources to more comprehensively and accurately test and evaluate the performance data of IGBT products, thereby overcoming the limitations of traditional single-data-source testing; (2)In the process of testing the performance data of IGBT products, the present invention can combine the differences in application scenario information and requirements of users for IGBT products to achieve differential testing of the performance of IGBT products, so as to reduce the difference between the obtained performance test results and the performance acquisition data in the actual application scenario, and increase the adaptability between the product performance test results and the application scenario; at the same time, the locking of the abnormal decay nodes of the performance test of IGBT based on the application scenario provides data reference for users to identify the failure modes and defects of IGBT products, as well as for product quality control and improvement. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings: Figure 1 is a schematic structural diagram of a performance test system for IGBT based on multi-source data of the present invention; Figure 2 is a schematic flow diagram of a performance test method for IGBT based on multi-source data of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0020] The present invention provides a technical solution: as Figure 1 shown, in this embodiment, a performance test system for IGBT based on multi-source data, the system includes a test condition information extraction module, a performance index test module, a performance test analysis module and a performance test report feedback module, The test condition information extraction module obtains the application scenario of the IGBT product to be tested, and extracts the application feature information and performance requirement conditions of the obtained application scenario; The performance index test module includes a performance index change relationship fitting unit and a performance adaptation analysis unit, The performance index change relationship fitting unit dynamically generates aging test conditions according to the application feature information of the application scenario, and generates the change conditions of each performance index of the IGBT product under the corresponding aging test conditions; The performance adaptation analysis unit dynamically intercepts the performance adaptation segments in the obtained change conditions of each performance index based on the performance requirement conditions of the obtained application scenario, and constructs a performance index category adaptation set; The performance test analysis module includes an index change feature extraction unit, a performance evaluation unit, and a decay node analysis unit. The index change feature extraction unit obtains the index change features corresponding to each element in the performance index category adaptation set. The performance evaluation unit calculates the performance evaluation value of the IGBT product based on the application scenario according to the extraction result of the index change feature extraction unit. The decay node analysis unit dynamically locks the performance test decay abnormal nodes of the obtained IGBT based on the application scenario. The performance test report feedback module generates a performance test report of the IGBT based on the performance evaluation value of the IGBT product based on the application scenario and the performance test decay abnormal nodes, and feeds it back to the performance test management personnel.

[0021] As Figure 2 shown, a performance test method for IGBT based on multi-source data in this embodiment includes: Step S100: Obtain the application scenario of the IGBT product to be tested, and extract the application feature information and performance requirement conditions of the obtained application scenario. In step S100, it includes: The application feature information includes the switching frequency, ambient temperature, and heat dissipation ability coefficient of the IGBT; the heat dissipation ability coefficient represents the coefficient value bound to the cooling duration within the preset cooling interval of the IGBT product to be tested in the application scenario in the preset form in the database; the performance requirement conditions include the normal state intervals corresponding to each preset performance index type.

[0022] In this embodiment, the performance requirement conditions include working delay, maximum working temperature, and product working life threshold.

[0023] Step S200: Dynamically generate aging test conditions according to the application feature information of the application scenario, and generate the change situations of each performance index of the IGBT product under the corresponding aging test conditions; based on the performance requirement conditions of the obtained application scenario, dynamically intercept the performance adaptation segments in the obtained change situations of each performance index, and construct a performance index category adaptation set. In step S200, it includes: Step S201: Use the application feature information of the application scenario as the aging test conditions, build a test scenario model for the IGBT product, and test the data of each performance index of the IGBT product at different time points. The types of performance indexes to be tested are preset in the database. Step S202: Extract the summary set of test data of the IGBT product based on the i-th performance index under the aging test conditions {(ti 1 , Bi 1 ), (ti2 ,Bi 2 ),..., (ti ni ,Bi ni ),..., (ti Ni-1 ,Bi Ni-1 ), (ti Ni ,Bi Ni ), where ti 1 represents the starting test time point of the IGBT product based on the i-th performance index under the aging test conditions; ti ni represents the test time point corresponding to the ni-th test data obtained by the IGBT product based on the i-th performance index under the aging test conditions; Bi ni represents the ni-th test data obtained by the IGBT product based on the i-th performance index under the aging test conditions; ni ∈ [1, Ni], and Ni represents the total number of test data obtained by the IGBT product based on the i-th performance index under the aging test conditions; ti Ni represents the time point when the IGBT product is damaged under the aging test conditions; Step S203: Mark the coordinate points corresponding to each element in the test data summary set of the IGBT product based on the i-th performance index in the i-th rectangular coordinate system, and connect the adjacent marked coordinate points in sequence to obtain the fitting curve of the i-th performance index test data of the IGBT product changing with time under the corresponding aging test conditions, denoted as Fi; the i-th rectangular coordinate system is constructed with o as the origin, the test time point as the x-axis, and the test data of the i-th performance index as the y-axis; Step S204: Dynamically intercept the performance adaptation segment in the obtained change of the i-th performance index, denoted as FPi; the FPi is the curve segment composed of the coordinate points corresponding to the function values in Fi that do not belong to the normal state interval corresponding to the i-th preset performance index type in the performance requirement conditions; Step S205: Construct a performance index category adaptation set, which is a set of performance adaptation segments in the changes of each performance index intercepted dynamically. Each element in the performance index category adaptation set corresponds to a performance adaptation segment in the change of a performance index.

[0024] Step S300: Obtain the index change characteristics corresponding to each element in the performance index category adaptation set, calculate the performance evaluation value of the IGBT product based on the application scenario, and dynamically lock the performance test decay abnormal nodes of the obtained IGBT based on the application scenario; The step S300 includes: The described index change characteristics include the time interval corresponding to the performance adaptation segment and the change rate of the performance index test data corresponding to each time point in the performance adaptation segment. The change rate of the performance index test data corresponding to each time point in the performance adaptation segment is equal to the value of the derivative function corresponding to the corresponding time point in the derivative function of the fitting function corresponding to the performance adaptation segment; Calculate the performance evaluation value of the IGBT product based on the application scenario. The involved calculation formula is as follows: , where PR represents a performance evaluation value of a corresponding IGBT product in the test based on the application scenario; TZ represents the interval length of the intersection interval between the corresponding time intervals of the performance adaptation segments corresponding to each element in the performance index category adaptation set; T i represents the interval length of the corresponding time interval of the performance adaptation segment corresponding to the i-th element in the performance index category adaptation set; m represents the preset number of performance index types; The performance evaluation value of the IGBT product based on the application scenario is equal to the average value of the performance evaluation values of each tested IGBT product based on the application scenario.

[0025] During the process of dynamically locking the performance test decay abnormal nodes of the obtained IGBT based on the application scenario in step S300, obtain the change rate of the performance index test data corresponding to each time point in the index change characteristics corresponding to each element in the performance index category adaptation set; Obtain the time interval with the largest interval length formed by the time points with the largest change rate of the performance index test data in the index change characteristics corresponding to each element in the performance index category adaptation set corresponding to the same tested IGBT product, and record it as the performance decay abnormal interval of the corresponding IGBT product in the test; Use any continuous interval in the union of the performance decay abnormal intervals of each tested IGBT product as the time mapping interval of a performance test decay abnormal node of the IGBT product based on the application scenario.

[0026] Step S400, generate a performance test report of the IGBT and feedback it to the performance test management personnel based on the performance evaluation value of the IGBT product based on the application scenario and the performance test decay abnormal nodes.

[0027] The performance test report of the IGBT in step S400 consists of the performance evaluation value of the IGBT product based on the application scenario, the performance test decay abnormal nodes, and the time mapping interval of each performance test decay abnormal node.

[0028] In this embodiment, obtaining the performance test decay abnormal nodes and the time mapping intervals of each performance test decay abnormal node is to facilitate the generation of inspection and maintenance decisions for the IGBT product by assisting the management personnel when the IGBT product is put into the corresponding application scenarios. Within the time mapping intervals of each performance test decay abnormal node, it is necessary to increase the inspection and monitoring frequency for the IGBT product to achieve the purpose of timely detecting the risk of abnormal performance decay of the IGBT. At the same time, the obtaining of the performance test decay abnormal nodes of the IGBT product based on the application scenarios and the time mapping intervals of each performance test decay abnormal node also provides data references for users to identify the failure modes and defects of the IGBT product, as well as for product quality control and improvement. In this embodiment, the IGBT product based on the application scenario may include one or more performance test decay abnormal nodes and their corresponding time mapping intervals.

[0029] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0030] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A performance test method for IGBT based on multi-source data, characterized in that: include: Step S100, obtaining an application scenario of the IGBT product to be tested, and extracting application feature information and performance requirement conditions of the obtained application scenario; Step S200: dynamically generate aging test conditions according to application feature information of the application scenario, and generate changes in various performance indicators of the IGBT product under the corresponding aging test conditions; based on the performance requirement conditions of the obtained application scenario, dynamically intercept the performance adaptation fragments in the obtained changes in various performance indicators, and construct a performance indicator category adaptation set; Step S300, obtaining the indicator change characteristics corresponding to each element in the performance indicator category adaptation set, calculating the performance evaluation value of the IGBT product based on the application scenario, and dynamically locking the obtained IGBT performance test decay abnormality node based on the application scenario; Step S400: Based on the performance evaluation value of the IGBT product based on the application scenario and the abnormal decay node of the performance test, a performance test report of the IGBT is generated and fed back to the performance test management personnel.

2. The performance test method of an IGBT based on multi-source data according to claim 1, characterized in that: The step S100 includes: The application characteristic information includes the switching frequency, ambient temperature and heat dissipation capacity coefficient of the IGBT; the heat dissipation capacity coefficient represents the coefficient value bound to the corresponding cooling time within the preset cooling range of the IGBT product to be tested in the application scenario in the preset form of the database; the performance requirement conditions include the normal state ranges corresponding to each preset performance indicator type.

3. The IGBT performance testing method based on multi-source data according to claim 1, characterized in that: The step S200 includes: Step S201: Using the application characteristic information of the application scenario as the aging test condition, building an IGBT product test scenario model, testing various performance indicator data of the IGBT product at different time points, wherein the performance indicator type of the test is preset in the database; Step S202: extract the test data summary set {(ti1, Bi1), (ti2, Bi2), ..., (ti ni ,Bi ni ),..., (ti Ni-1 ,Bi Ni-1 ), (ti Ni ,Bi Ni )}, where ti1 represents the starting test time point of the IGBT product based on the i-th performance indicator under aging test conditions; ti ni Indicates the test time point corresponding to the ni-th test data obtained based on the ith performance indicator of the IGBT product under aging test conditions; Bi ni represents the nith test data obtained based on the ith performance indicator of the IGBT product under aging test conditions; ni∈[1,Ni], Ni represents the total number of test data obtained based on the ith performance indicator of the IGBT product under aging test conditions; ti Ni Indicates the time point when the IGBT product is damaged under aging test conditions; Step S203, mark the corresponding coordinate points of each element in the test data summary set based on the i-th performance indicator of the IGBT product under the aging test condition at the i-th plane rectangular coordinate system, and connect the corresponding adjacent marked coordinate points in sequence to obtain a fitting curve of the i-th performance indicator test data of the IGBT product under the corresponding aging test condition over time, which is recorded as Fi; the i-th plane rectangular coordinate system is constructed with o as the origin, the test time point as the x-axis, and the i-th performance indicator test data as the y-axis; Step S204: dynamically intercept the performance adaptation segment in the change of the i-th performance indicator, recorded as FPi; the FPi is a curve segment composed of each coordinate point in the normal state interval corresponding to the i-th preset performance indicator type in the performance requirement condition in Fi where the corresponding function value does not belong to; Step S205: construct a performance indicator category adaptation set, where the performance indicator category adaptation set is a set of dynamically captured performance adaptation segments in various performance indicator change situations, and each element in the performance indicator category adaptation set corresponds to a performance adaptation segment in a performance indicator change situation.

4. The IGBT performance test method based on multi-source data according to claim 2, characterized in that: The step S300 includes: The indicator change characteristics include the time interval corresponding to the performance adaptation segment and the change rate of the performance indicator test data corresponding to each time point in the performance adaptation segment, and the change rate of the performance indicator test data corresponding to each time point in the performance adaptation segment is equal to the derivative function value corresponding to the corresponding time point in the derivative function of the fitting function corresponding to the corresponding performance adaptation segment; Calculate the performance evaluation value of IGBT products based on application scenarios. The calculation formula involved is as follows: , Wherein, PR represents a performance evaluation value based on an application scenario in the corresponding IGBT product under test; TZ represents the interval length of the intersection interval between the corresponding time intervals of the performance adaptation segments corresponding to each element in the performance indicator category adaptation set; T i represents the interval length of the corresponding time interval of the performance adaptation segment corresponding to the i-th element in the performance indicator category adaptation set; m represents the number of preset performance indicator types; The performance evaluation value of the IGBT product based on the application scenario is equal to the average value of the performance evaluation values ​​of each tested IGBT product based on the application scenario.

5. The IGBT performance test method based on multi-source data according to claim 4, characterized in that: In the process of dynamically locking the abnormal decay node of the performance test of the obtained IGBT based on the application scenario in step S300, the change rate of the performance indicator test data corresponding to each time point in the indicator change feature corresponding to each element in the performance indicator category adaptation set is obtained; Obtain the time interval with the largest interval length formed by the time points with the largest change rate of the performance indicator test data in the indicator change characteristics corresponding to each element in the performance indicator category adaptation set corresponding to the same IGBT product under test, and record it as the performance decay abnormality interval of the corresponding IGBT product under test; take any continuous interval in the union of the performance decay abnormality intervals of each IGBT product under test as the time mapping interval of a performance test decay abnormality node of the IGBT product based on the application scenario.

6. The performance test method of IGBT based on multi-source data according to claim 1, characterized in that: The performance test report of the IGBT in step S400 is composed of the performance evaluation value of the IGBT product based on the application scenario, the performance test decay abnormality node and the time mapping interval of each performance test decay abnormality node.

7. A performance test system for an IGBT based on multi-source data, using a performance test method for an IGBT based on multi-source data as claimed in any one of claims 1 to 6, characterized in that: The system includes a test condition information extraction module, a performance index test module, a performance test analysis module and a performance test report feedback module. The test condition information extraction module obtains the application scenario of the IGBT product to be tested, and extracts the application feature information and performance requirement conditions of the obtained application scenario; The performance indicator test module dynamically generates aging test conditions according to the application feature information of the application scenario, and generates the changes of various performance indicators of the IGBT product under the corresponding aging test conditions; based on the performance requirement conditions of the obtained application scenario, dynamically intercepts the performance adaptation fragments in the obtained changes of various performance indicators, and constructs a performance indicator category adaptation set; The performance test analysis module obtains the indicator change characteristics corresponding to each element in the performance indicator category adaptation set, calculates the performance evaluation value of the IGBT product based on the application scenario, and dynamically locks the obtained IGBT performance test decay abnormality node based on the application scenario; The performance test report feedback module generates a performance test report of the IGBT based on the performance evaluation value of the IGBT product based on the application scenario and the abnormal performance test decay node, and feeds it back to the performance test management personnel.

8. The IGBT performance test system based on multi-source data according to claim 7, characterized in that: The performance index test module includes a performance index change relationship fitting unit and a performance adaptation analysis unit. The performance indicator change relationship fitting unit dynamically generates aging test conditions according to application characteristic information of the application scenario, and generates changes in various performance indicators of the IGBT product under the corresponding aging test conditions; The performance adaptation analysis unit dynamically intercepts the performance adaptation segments in the obtained performance indicator changes based on the performance requirement conditions of the obtained application scenario, and constructs a performance indicator category adaptation set.

9. The IGBT performance test system based on multi-source data according to claim 7, characterized in that: The performance test analysis module includes an index change feature extraction unit, a performance evaluation unit and a decay node analysis unit. The indicator change feature extraction unit obtains the indicator change features corresponding to each element in the performance indicator category adaptation set; The performance evaluation unit calculates the performance evaluation value of the IGBT product based on the application scenario according to the extraction result of the indicator change feature extraction unit; The decay node analysis unit dynamically locks the abnormal decay node of the obtained IGBT performance test based on the application scenario.

Images