Method, device, equipment and medium for constructing a proxy model of motor temperature stress field

Abstract

The present application relates to a method, device, equipment and medium for constructing a proxy model of a motor temperature stress field. The method comprises: obtaining a sample space range, the sample space range comprising a load sample space range, a stator base temperature operating range and an upper frame temperature operating range, the load sample space range being determined based on load inversion data obtained based on load inversion, the stator base temperature operating range and the upper frame temperature operating range being respectively determined based on corresponding historical acquisition data; sampling the sample space range using a uniform sampling algorithm to obtain a plurality of sample points; simulating the plurality of sample points based on a finite element model of a stator base-upper frame to obtain response values ​​respectively corresponding to the plurality of sample points; constructing a converged target stator base-upper frame proxy model based on the plurality of sample points and a target data set determined based on the plurality of sample points and the response values ​​respectively corresponding to the plurality of sample points.

Description

Technical Field

[0001] The present application relates to the technical field of generator simulation, and in particular to a method, device, equipment and medium for constructing a proxy model of a motor temperature stress field. Background Art

[0002] The construction of a multi-physics proxy model for a motor can greatly improve the simulation speed, and real-time visualization simulation of the multi-physics field of a motor can be achieved by relying on digital twins and visualization technology. The performance of the proxy model is closely related to the distribution of sample points in the modeling space and the number of sample points. An appropriate number of evenly distributed sample points can well reflect the changing trends and information of the real model in space, thereby ensuring that the information provided by the proxy model has high accuracy and credibility when used. On the contrary, if the sample points are not selected properly, the construction cost of the proxy model will be too high and the fitting accuracy will be poor, resulting in providing erroneous information, or even the proxy model cannot be successfully established.

[0003] However, the current proxy model sample point range is determined more based on empirical values, the sample range cannot be controlled, the number of sample points cannot be controlled, and there is no accurate mechanism constraint, which leads to poor performance of the proxy model. Therefore, there is an urgent need for a method that can improve the performance of the motor temperature stress field proxy model based on the selection of precise sample point range. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a method, device, equipment, medium and product for constructing a motor temperature stress field proxy model.

[0005] In a first aspect of an embodiment of the present application, a method for constructing a proxy model of a motor temperature stress field is provided, the method comprising: obtaining a sample space range, the sample space range comprising a load sample space range, a stator base temperature operating range and an upper frame temperature operating range, the load sample space range being determined based on load inversion data obtained based on load inversion, the stator base temperature operating range and the upper frame temperature operating range being respectively determined based on corresponding historical acquisition data; sampling the sample space range using a uniform sampling algorithm to obtain a plurality of sample points; simulating the plurality of sample points based on a finite element model of a stator base-upper frame to obtain response values ​​respectively corresponding to the plurality of sample points; constructing a converged target stator base-upper frame proxy model based on the plurality of sample points and a target data set determined based on the plurality of sample points and the response values ​​respectively corresponding to the plurality of sample points.

[0006] In some embodiments of the present application, the target data set determined based on the multiple sample points and the response values ​​respectively corresponding to the multiple sample points is used to construct a converged target stator base-upper frame proxy model, including: constructing an initial stator base-upper frame proxy model based on the target data set; inputting an actual load value, an actual stator base temperature value, and an actual frame temperature value in actual operating condition data into the initial stator base-upper frame proxy model to obtain a test response value, wherein the actual operating condition data also includes an actual response value corresponding to the actual load value, the actual stator base temperature value, and the actual frame temperature value; determining whether the initial stator base-upper frame proxy model is converged according to a relationship between the test response value and the actual response value; and when the initial stator base-upper frame proxy model is converged, determining the initial stator base-upper frame proxy model as the target stator base-upper frame proxy model.

[0007] In some embodiments of the present application, after determining whether the proxy model of the initial stator base-upper frame has converged based on the relationship between the test response value and the actual response value, the method further includes: when it is determined that the proxy model of the initial stator base-upper frame has not converged, determining at least one new sample point based on the target data set and a sequence sampling method; simulating the at least one new sample point based on the finite element model of the stator base-upper frame to obtain response values ​​corresponding to the at least one new sample point; updating the target data set based on the at least one new sample point and the response values ​​corresponding to the at least one new sample point to obtain an updated data set; using the updated data set as the target data set, returning to execute the construction of the proxy model of the initial stator base-upper frame based on the target data set until a converged proxy model of the target stator base-upper frame is obtained.

[0008] In some embodiments of the present application, the method based on the target data set and the sequence sampling method determines at least one new sample point, including: based on the target data set, dividing the spatial range corresponding to the target variable into multiple Thiessen polygon areas by the Thiessen diagram method, and the target variable is any one of the load, the stator base temperature and the upper frame temperature; based on the errors of the sample points respectively corresponding to the multiple Thiessen polygon areas, the Thiessen polygon areas corresponding to the n sample points with the largest errors are determined as n sensitive polygon areas, where n is a positive integer; and a sampling point is determined from each of the n sensitive polygon areas to obtain the at least one new sample point.

[0009] In some embodiments of the present application, a sampling point is determined from each of the n sensitive polygonal areas to obtain the at least one new sample point, including: performing random sampling on the target sensitive polygonal area to obtain multiple random sampling points; and determining the point among the multiple random sampling points that is farthest from the sample point corresponding to the sensitive polygonal area as a new sample point corresponding to the target sensitive polygonal area.

[0010] In some embodiments of the present application, the determining whether the proxy model of the initial stator base-upper frame has converged is based on the relationship between the test response value and the actual response value, including: when the absolute value of the ratio of a target difference value to the actual response value is less than or equal to a ratio threshold, determining that the proxy model of the initial stator base-upper frame has converged, and the target difference value is the difference between the test response value and the actual response value; when the absolute value of the ratio of the target difference value to the actual response value is greater than the ratio threshold, determining that the proxy model of the initial stator base-upper frame has not converged.

[0011] In some embodiments of the present application, the determining whether the proxy model of the initial stator base-upper frame has converged is based on the relationship between the test response value and the actual response value, including: when the absolute value of the difference between the test response value and the actual response value is less than or equal to a difference threshold, determining that the proxy model of the initial stator base-upper frame has converged; when the absolute value of the difference between the test response value and the actual response value is greater than the difference threshold, determining that the proxy model of the initial stator base-upper frame has not converged.

[0012] In some embodiments of the present application, the uniform sampling algorithm is used to sample the sample space range to obtain multiple sample points, including: using the optimal super Latin method to sample the sample space range to obtain the multiple sample points.

[0013] According to a second aspect of an embodiment of the present application, there is provided a device for constructing a proxy model of a motor temperature stress field, comprising: an acquisition module for acquiring a sample space range, the sample space range comprising a load sample space range, a stator base temperature operating range and an upper frame temperature operating range, the load sample space range being determined based on load inversion data obtained based on load inversion, the stator base temperature operating range and the upper frame temperature operating range being respectively determined based on corresponding historical acquisition data; a sampling module for sampling the sample space range using a uniform sampling algorithm to obtain a plurality of sample points; a simulation module for simulating the plurality of sample points based on a finite element model of a stator base-upper frame to obtain response values ​​respectively corresponding to the plurality of sample points; and a construction module for constructing a converged target stator base-upper frame proxy model based on the plurality of sample points and a target data set determined by the response values ​​respectively corresponding to the plurality of sample points.

[0014] In some embodiments of the present application, the construction module is specifically used to construct an initial stator base-upper frame proxy model based on the target data set; input the actual load value, the actual stator base temperature value and the actual frame temperature value in the actual operating condition data into the initial stator base-upper frame proxy model to obtain a test response value, and the actual operating condition data also includes an actual response value corresponding to the actual load value, the actual stator base temperature value and the actual frame temperature value; determine whether the initial stator base-upper frame proxy model converges according to the relationship between the test response value and the actual response value; if the initial stator base-upper frame proxy model converges, determine the initial stator base-upper frame proxy model as the target stator base-upper frame proxy model.

[0015] In some embodiments of the present application, the construction module is further used to determine whether the proxy model of the initial stator base-upper frame has converged according to the relationship between the test response value and the actual response value. When it is determined that the proxy model of the initial stator base-upper frame has not converged, determine at least one new sample point based on the target data set and based on a sequence sampling method; simulate the at least one new sample point based on the finite element model of the stator base-upper frame to obtain the response values ​​corresponding to the at least one new sample point; update the target data set based on the at least one new sample point and the response values ​​corresponding to the at least one new sample point to obtain an updated data set; use the updated data set as the target data set, and return to execute the construction of the proxy model of the initial stator base-upper frame based on the target data set until a converged proxy model of the target stator base-upper frame is obtained.

[0016] In some embodiments of the present application, the construction module is specifically used to divide the spatial range corresponding to the target variable into multiple Thiessen polygon areas based on the target data set by the Thiessen diagram method, and the target variable is any one of the load, the stator base temperature and the upper frame temperature; based on the errors of the sample points corresponding to the multiple Thiessen polygon areas, the Thiessen polygon areas corresponding to the n sample points with the largest errors are determined as n sensitive polygon areas, where n is a positive integer; a sampling point is determined from each of the n sensitive polygon areas to obtain the at least one newly added sample point.

[0017] In some embodiments of the present application, the construction module is specifically used to perform random sampling on the target sensitive polygonal area to obtain multiple random sampling points; the point among the multiple random sampling points that is farthest from the sample point corresponding to the sensitive polygonal area is determined as a new sample point corresponding to the target sensitive polygonal area.

[0018] In some embodiments of the present application, the construction module is specifically used to determine that the proxy model of the initial stator base-upper frame has converged when the absolute value of the ratio of the target difference to the actual response value is less than or equal to the ratio threshold, and the target difference is the difference between the test response value and the actual response value; when the absolute value of the ratio of the target difference to the actual response value is greater than the ratio threshold, determine that the proxy model of the initial stator base-upper frame has not converged.

[0019] In some embodiments of the present application, the construction module is specifically used to determine that the proxy model of the initial stator base-upper frame has converged when the absolute value of the difference between the test response value and the actual response value is less than or equal to the difference threshold; and to determine that the proxy model of the initial stator base-upper frame has not converged when the absolute value of the difference between the test response value and the actual response value is greater than the difference threshold.

[0020] In some embodiments of the present application, the sampling module is specifically used to sample the sample space range using the optimal super Latin cube method to obtain the multiple sample points.

[0021] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the method for constructing a proxy model of a motor temperature stress field as described in the first aspect is implemented.

[0022] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for constructing a motor temperature stress field proxy model as described in the first aspect is implemented.

[0023] According to a fifth aspect of an embodiment of the present application, a computer program product is provided, wherein the computer program product includes a computer program. When the computer program product runs on a processor, the processor executes the computer program to implement the method for constructing a motor temperature stress field proxy model as described in the first aspect.

[0024] In a sixth aspect of an embodiment of the present application, a chip is provided, which includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run program instructions to implement the method for constructing a motor temperature stress field proxy model as described in the first aspect.

[0025] The technical solution provided by the embodiment of the present application has the following advantages compared with the prior art: by obtaining a sample space range, the sample space range includes a load sample space range, a stator base temperature operating range and an upper frame temperature operating range, the load sample space range is determined based on load inversion data obtained based on load inversion, and the stator base temperature operating range and the upper frame temperature operating range are respectively determined based on corresponding historical acquisition data; the sample space range is sampled using a uniform sampling algorithm to obtain a plurality of sample points; the plurality of sample points are simulated based on a finite element model of the stator base-upper frame to obtain response values ​​corresponding to the plurality of sample points respectively; a converged target stator base-upper frame proxy model is constructed based on the plurality of sample points and a target data set determined based on the plurality of sample points and the response values ​​corresponding to the plurality of sample points respectively. In this way, with the help of load inversion, the constraints on the experimental design range of load sample points are realized, the effectiveness of the sample points is improved, and the sample space range is sampled by a uniform sampling algorithm to obtain a suitable number of uniformly distributed sample points. The multiple sample points obtained in this way can well reflect the changing trends and information of the real model in space, and can ensure that the information provided by the proxy model when using it has high accuracy and credibility, thereby improving the performance of the motor temperature stress field proxy model. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0028] Figure 1 One of the flow charts of the method for constructing a motor temperature stress field proxy model provided in an embodiment of the present application;

[0029] Figure 2 A second flow chart of a method for constructing a motor temperature stress field proxy model provided in an embodiment of the present application;

[0030] Figure 3 A third flow chart of a method for constructing a motor temperature stress field proxy model provided in an embodiment of the present application;

[0031] Figure 4 A structural block diagram of a motor temperature stress field proxy model construction device provided in an embodiment of the present application;

[0032] Figure 5A structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0034] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.

[0035] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0036] The electronic device in the embodiment of the present application may be a mobile electronic device or a non-mobile electronic device. The mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA); the non-mobile electronic device may be a personal computer (PC), a television (TV), a teller machine, or a self-service machine; the embodiment of the present application does not specifically limit the above.

[0037] The executor of the method for constructing a motor temperature stress field proxy model provided in the embodiment of the present application can be the above-mentioned electronic device (including mobile electronic devices and non-mobile electronic devices), or it can be a functional module and / or functional entity in the electronic device that can implement the method for constructing a motor temperature stress field proxy model. The specific execution can be determined based on actual usage requirements and is not limited by the embodiment of the present application.

[0038] The method for constructing a motor temperature stress field proxy model provided by the embodiment of the present application is described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0039] like Figure 1 As shown, an embodiment of the present application provides a method for constructing a motor temperature stress field proxy model, which may include the following steps 101 to 104.

[0040] 101. Get the sample space range.

[0041] Among them, the sample space range includes the load sample space range, the stator base temperature operating range and the upper frame temperature operating range. The load sample space range is determined based on the load inversion data obtained by load inversion, and the stator base temperature operating range and the upper frame temperature operating range are respectively determined based on the corresponding historical collection data.

[0042] Among them, load inversion refers to the pre-test analysis based on the unit load finite element analysis (FEA) result file combined with the load identification software (True-Load), giving the specific position of the test strain gauge, and then conducting accurate physical strain precision testing to obtain test data, and finally inversely calculating the different load values ​​applied at each position.

[0043] The specific load inversion process includes:

[0044] Step 1. Obtain unit load FEA result file

[0045] Construct the correct finite element model of the stator frame and upper frame, apply unit load on the prepared FEA model to obtain the solution result, and obtain the unit load FEA result file.

[0046] Step 2. Test pre-analysis

[0047] Import the unit load results into True-Load, and perform pre-test analysis through the Pre-Test module to provide the specific location of the test strain gauge.

[0048] Step 3. Physical test

[0049] According to the strain gauge position provided by True-Load, the correct physical strain precision test is carried out to obtain the test data of the physical test.

[0050] Step 4. Load identification

[0051] The Post-Test module inversely calculates the different load values ​​applied at each position based on the strain data of the test.

[0052] In the embodiment of the present application, the load inversion data obtained in the load inversion process is extracted to form the load space range [Load min , Load max 】.

[0053] In some embodiments of the present application, the load space range [Load min , Load max 】 is the load sample space range.

[0054] In some embodiments of the present application, in order to ensure that the sample used to construct the stator frame-upper frame proxy model is more accurate, the load space range [Load min , Load max 】, the corresponding spatial range can be appropriately expanded. For example, the load sample spatial range can be [0.9Load min , 1.1 Load max 】, or 【0.95Load min ,1.05Load max ], and can also be other feasible load space ranges, which can be determined according to actual conditions and are not limited here.

[0055] According to the temperature sensor data arranged at the corresponding positions on the stator frame and the upper frame, the historically collected stator frame temperature and upper frame temperature, the corresponding stator frame temperature operating range [T 1min , T 1max 】 and upper rack temperature operating range

T 2min , T 2max

[0056] In some embodiments of the present application, the stator base temperature operating range constituting the sample space range may be the stator base temperature operating range described above.

[0057] In some embodiments of the present application, in order to ensure that the sample used to construct the stator frame-upper frame proxy model is more accurate, the stator frame temperature operating range [T 1min , T 1max 】, the corresponding spatial range can be appropriately expanded. For example, the stator frame temperature operating range that constitutes the sample spatial range can be 【0.9T 1min , 1.1T 1max 】, or 【0.95T 1min , 1.05T 1max ], and may also be other feasible stator frame temperature operating ranges, which may be specifically determined based on actual conditions and are not limited here.

[0058] In some embodiments of the present application, the upper rack temperature operating range constituting the sample space range may be the upper rack temperature operating range [T 2min , T 2max 】.

[0059] In some embodiments of the present application, in order to ensure that the sample used to construct the stator frame-upper frame proxy model is more accurate, the upper frame temperature operating range [T 2min , T 2max 】, the corresponding spatial range can be appropriately expanded. For example, the upper rack temperature operating range that constitutes the sample spatial range can be 【0.9T 2min , 1.1T 2max 】, or 【0.95T 2min , 1.05T 2max ], and may also be other feasible upper rack temperature operating ranges, which may be determined based on actual conditions and are not limited here.

[0060] 102. Use a uniform sampling algorithm to sample the sample space range to obtain multiple sample points.

[0061] In the embodiment of the present application, the sample space range is sampled using a uniform sampling algorithm, so that multiple sample points can be evenly distributed.

[0062] Among them, the uniform sampling algorithm can be a super Latin method, an optimal super Latin method, or other sampling algorithms. The specific method can be determined according to actual conditions and is not limited here.

[0063] In some embodiments of the present application, the above step 102 can be specifically implemented through the following step 102a.

[0064] 102a. Sample the sample space range using the optimal super Latin method to obtain the multiple sample points.

[0065] In the embodiment of the present application, since the optimal super Latin cube method samples relatively evenly, multiple sample points can be evenly distributed. Such multiple sample points can well reflect the changing trend and information of the real model in space, and can ensure that the information provided by the proxy model when using it has high accuracy and credibility, thereby improving the performance of the motor temperature stress field proxy model.

[0066] 103. Simulate the multiple sample points based on the finite element model of the stator base-upper frame to obtain response values ​​corresponding to the multiple sample points.

[0067] Based on multiple sample points, combined with the correct (accurate) finite element model of the stator base and the upper frame (i.e., the temperature-stress field finite element model of the stator base-upper frame), the response values ​​[W1, W2, ..., Wn] corresponding to the multiple sample points are obtained.

[0068] In the embodiment of the present application, the response value can be determined according to actual usage requirements. For example, the response value can be the real-time stress value, average stress value, maximum stress value, temperature extreme value, body average temperature, surface average temperature, etc. of a certain point, which is not limited here.

[0069] In the embodiment of the present application, different finite element models of the stator base and the upper frame can be constructed according to the different response values ​​that need to be obtained, and then based on multiple sample points, combined with the finite element models of the stator base and the upper frame, the response values ​​corresponding to the multiple sample points can be calculated.

[0070] 104. Based on the multiple sample points and the target data set determined by the response values ​​corresponding to the multiple sample points, a converged target stator base-upper frame proxy model is constructed.

[0071] Among them, the target data set is [T 1m , T 2m 、Load m 】~

W1, W2,..., Wn

[0072] In the embodiment of the present application, a corresponding target stator base-upper frame proxy model can be constructed based on the target data set using a data fitting method.

[0073] The data fitting method may be based on a neural network data fitting method, a support vector machine data fitting method, or other data fitting methods, which are not limited here.

[0074] In the embodiment of the present application, with the help of load inversion, the constraints on the experimental design range of load sample points are implemented, thereby improving the effectiveness of the sample points. By sampling the sample space range through a uniform sampling algorithm, a suitable number of uniformly distributed sample points can be obtained. The multiple sample points obtained in this way can well reflect the changing trends and information of the real model in space, and can ensure that the information provided by the proxy model when using it has high accuracy and credibility, thereby improving the performance of the motor temperature stress field proxy model.

[0075] In some embodiments of the present application, Figure 1 ,like Figure 2 As shown, the above step 104 can be specifically implemented through the following steps 104a to 104d.

[0076] 104a. Based on the target data set, construct an initial stator frame-upper frame proxy model.

[0077] The initial stator frame-upper frame proxy model is a proxy model constructed based on the multiple sample points and the response values ​​corresponding to the multiple sample points.

[0078] 104b. Input the actual load value, the actual stator base temperature value and the actual frame temperature value in the actual operating condition data into the initial stator base-upper frame proxy model to obtain a test response value.

[0079] The actual operating condition data also includes actual response values ​​corresponding to the actual load value, the actual stator base temperature value and the actual frame temperature value.

[0080] 104c. Determine whether the initial stator frame-upper frame proxy model is converged according to the relationship between the test response value and the actual response value.

[0081] In the embodiment of the present application, whether the initial stator base-upper frame proxy model is converged is determined based on the magnitude relationship between the error of the test response value relative to the actual response value and the error threshold.

[0082] In the embodiment of the present application, whether the proxy model of the initial stator base-upper frame has converged can be determined based on the relationship between the absolute value of the difference between the test response value and the actual response value and the difference threshold; whether the proxy model of the initial stator base-upper frame has converged can also be determined based on the absolute value of the difference between the test response value and the actual response value, and then the relationship between the ratio of the actual response value and the ratio threshold; whether the proxy model of the initial stator base-upper frame has converged can also be determined based on other feasibility relationships between the test response value and the actual response value; the specific determination can be based on actual conditions and is not limited here.

[0083] It can be understood that, when it is determined that the proxy model of the initial stator base-upper frame has converged according to the relationship between the test response value and the actual response value, the following step 104d is performed to output the proxy model of the initial stator base-upper frame as the proxy model of the target stator base-upper frame; when it is determined that the proxy model of the initial stator base-upper frame has converged according to the relationship between the test response value and the actual response value, the proxy model of the initial stator base-upper frame can be reconstructed by updating the data set and then based on the updated data set, and when the reconstructed proxy model of the initial stator base-upper frame has converged, the reconstructed proxy model of the initial stator base-upper frame can be output as the proxy model of the target stator base-upper frame.

[0084] In some embodiments of the present application, the error can be determined based on the absolute value of the difference between the test response value and the actual response value and the ratio to the actual response value. The above step 104c can be specifically implemented by the following steps 104c1 to 104c2.

[0085] 104c1. When the absolute value of the ratio of the target difference value to the actual response value is less than or equal to the ratio threshold, determine that the proxy model of the initial stator base-upper frame converges, and the target difference value is the difference between the test response value and the actual response value.

[0086] 104c2. When the absolute value of the ratio of the target difference value to the actual response value is greater than the ratio threshold, it is determined that the initial stator base-upper frame proxy model does not converge.

[0087] The ratio threshold can be determined according to actual conditions and is not limited here.

[0088] Among them, according to the actual operating conditions on site, the test response W output by the proxy model of the initial stator frame-upper frame is calculated x , based on the actual response W0 obtained from the sensor data, calculate the error and determine whether the initial stator frame-upper frame proxy model converges. The error can be The ratio threshold may be 10%, that is, if ρ is greater than 10%, the initial stator frame-upper frame proxy model does not converge; conversely, if ρ is less than or equal to 10%, the initial stator frame-upper frame proxy model converges.

[0089] In the embodiment of the present application, the ratio of the target difference to the actual response value is used as an error to determine whether the initial stator base-upper frame proxy model has converged, which can accurately determine whether the initial stator base-upper frame proxy model has converged.

[0090] In some embodiments of the present application, the error can be determined based on the absolute value of the difference between the test response value and the actual response value. The above step 104c can be specifically implemented by the following steps 104c3 to 104c4.

[0091] 104c3. When the absolute value of the difference between the test response value and the actual response value is less than or equal to the difference threshold, determine that the proxy model of the initial stator base-upper frame is converged.

[0092] 104c4. When the absolute value of the difference between the test response value and the actual response value is greater than the difference threshold, it is determined that the initial stator base-upper frame proxy model does not converge.

[0093] The difference threshold can be determined according to actual conditions and is not limited here.

[0094] Among them, according to the actual operating conditions on site, the test response W output by the proxy model of the initial stator frame-upper frame is calculated x , based on the actual response W0 obtained from the sensor data, calculate the error and determine whether the initial stator frame-upper frame proxy model converges. The error can be ρ = |W X -W0|, that is, if ρ is greater than the difference threshold, the proxy model of the initial stator frame-upper frame does not converge; conversely, if ρ is less than or equal to the difference threshold, the proxy model of the initial stator frame-upper frame converges.

[0095] In the embodiment of the present application, the absolute value of the difference between the test response value and the actual response value is used as an error to determine whether the proxy model of the initial stator base-upper frame has converged, so as to accurately determine whether the proxy model of the initial stator base-upper frame has converged.

[0096] 104d. When the proxy model of the initial stator base-upper frame converges, determine the proxy model of the initial stator base-upper frame as the proxy model of the target stator base-upper frame.

[0097] In the embodiment of the present application, after constructing the proxy model of the initial stator base-upper frame based on the target data set, the relationship between the test response value and the actual response value is used to verify whether the proxy model of the initial stator base-upper frame converges, and then when the proxy model of the initial stator base-upper frame converges, the proxy model of the initial stator base-upper frame is used as output. In this way, the precision and accuracy of the output target stator base-upper frame proxy model can be guaranteed.

[0098] In some embodiments of the present application, the method for updating the data set may be to resample the sample space range so that the sample point data obtained by sampling includes more sample points, and then return to re-execute the above step 103 to update the target data set, and update the initial stator base-upper frame proxy model by re-executing the above step 104a, and then re-execute the above steps 104b to 104d to output a converged target stator base-upper frame proxy model, or if the updated initial stator base-upper frame proxy model still does not converge, update the data set again, and repeat the above steps until a converged target stator base-upper frame proxy model is output.

[0099] In some embodiments of the present application, the data set may be updated by a sequence sampling method.

[0100] Sequential sampling means taking a part of the sample points to build the proxy model and then adaptively determining the next sampling point based on the information provided by the proxy model until the predetermined iteration end requirements are met. Sequential sampling can solve the problem of insufficient one-time sampling accuracy and improve global accuracy.

[0101] For example, in combination Figure 2 ,like Figure 3 As shown, after the above step 104c, the above step 104 may further include the following steps 104e to 104h.

[0102] 104e. When it is determined that the initial stator base-upper frame proxy model does not converge, determine at least one new sample point based on the target data set and a sequence sampling method.

[0103] The at least one newly added sample point may be one or more newly added sample points, which may be specifically determined according to actual conditions and is not limited here.

[0104] 104f. Simulate the at least one newly added sample point based on the finite element model of the stator base-upper frame to obtain response values ​​corresponding to the at least one newly added sample point.

[0105] 104g. Based on the at least one newly added sample point and the response values ​​respectively corresponding to the at least one newly added sample point, update the target data set to obtain an updated data set.

[0106] It can be understood that the updated data set includes multiple sample points, response values ​​corresponding to the multiple sample points, and the at least one newly added sample point, and response values ​​corresponding to the at least one newly added sample point.

[0107] 104h. Use the updated data set as the target data set, and return to execute the process of constructing an initial stator base-upper frame proxy model based on the target data set until a converged target stator base-upper frame proxy model is obtained.

[0108] It can be understood that, when the initial stator base-upper frame proxy model constructed based on the updated data set converges, the initial stator base-upper frame proxy model constructed based on the updated data set is output as the target stator base-upper frame proxy model, and when the initial stator base-upper frame proxy model constructed based on the updated data set does not converge, the target data set is updated again by the sequence sampling method, and then the initial stator base-upper frame proxy model is reconstructed based on the updated data set, and so on, until the target stator base-upper frame proxy model is output.

[0109] In the embodiment of the present application, the data set is updated by the sequence sampling method, and then the proxy model of the initial stator frame-upper frame is updated, which can improve the update rate of the data set and the update rate of the proxy model of the initial stator frame-upper frame, and then the efficiency of outputting the proxy model of the target stator frame-upper frame can be improved. Based on the sequence sampling method, the update of the data set and the self-update of the proxy model are realized, and the precision and accuracy of the proxy model are improved.

[0110] In an embodiment of the present application, the sequence sampling method can be an adaptive sequence block sampling algorithm based on radial basis functions, or it can be a sampling method that combines the Thiessen diagram method to determine sensitive polygon areas and increase the number of sample points according to actual conditions. The specific method can be determined based on actual conditions and is not limited here.

[0111] In some embodiments of the present application, the above step 104g can be specifically implemented through the following steps 104g1 to 104g3.

[0112] 104g1. Based on the target data set, the spatial range corresponding to the target variable is divided into multiple Thiessen polygon areas by using the Thiessen diagram method.

[0113] The target variable is any one of the load, the stator frame temperature and the upper frame temperature.

[0114] 104g2. Based on the errors of the sample points respectively corresponding to the multiple Thiessen polygon areas, determine the Thiessen polygon areas respectively corresponding to the n sample points with the largest errors as n sensitive polygon areas.

[0115] Wherein, n is a positive integer.

[0116] Exemplarily, n can be 1, 2, 3, ..., which can be determined according to actual conditions and is not limited here.

[0117] In some embodiments of the present application, n is 3, which can ensure both the accuracy of the sample points and the number of the sample points, and can improve the efficiency of obtaining the target stator base-upper frame proxy model based on sequence sampling.

[0118] The error of the sample point may be the absolute value of the difference between the predicted response value and the actual response value corresponding to the sample point, and the ratio thereof to the actual response value, or the absolute value of the difference between the predicted response value and the actual response value corresponding to the sample point. The specific error may be determined according to actual conditions and is not limited here.

[0119] 104g3. Determine a sampling point from each of the n sensitive polygonal areas to obtain the at least one newly added sample point.

[0120] In some embodiments of the present application, a sampling point can be randomly determined from each sensitive polygon area as a new sampling point, or a random sampling point that is farthest from the sampling point corresponding to the sensitive polygon area can be determined from each sensitive polygon area as a new sampling point. The specific sampling point can be determined based on actual conditions and is not limited here.

[0121] In some embodiments of the present application, multiple sample points may be determined respectively from the n sensitive polygonal areas to obtain the at least one newly added sample point.

[0122] In the embodiment of the present application, the sensitive polygon area is determined by combining the Thiessen diagram method and the sequence sampling method that increases the number of sample points according to the actual situation, which can quickly find suitable new sample points and improve the sampling accuracy of the new sample points.

[0123] In some embodiments of the present application, the above step 104g3 can be specifically implemented through the following steps 104g3a to 104g3b.

[0124] 104g3a. Random sampling is performed on the target sensitive polygon area to obtain multiple random sampling points.

[0125] In the embodiment of the present application, random sampling can be performed by a Monte Carlo-based random sampling method, or by a Monte Carlo-based random beam search method, or by a Gumbel-Top-K-based random beam search method. The specific method can be determined based on actual conditions and is not limited here.

[0126] 104g3b. Determine the point among the multiple random sampling points that is farthest from the sample point corresponding to the sensitive polygonal area as a newly added sample point corresponding to the target sensitive polygonal area.

[0127] In the embodiment of the present application, the above steps 104g3a to 104g3b can make the newly added sample points more accurate, thereby improving the precision and accuracy of the stator base-upper frame proxy model constructed based on the newly added sample points, and improving the efficiency of obtaining a converged stator base-upper frame proxy model.

[0128] For example, n=3, and the initial data set [T 1m , T 2m 、Load m 】~

W1, W2, ..., Wn

[0129] Step 1: Construct Thiessen polygons. Based on the existing initial data set, select one of the three variables as the standard, with the stator frame temperature T1m For example, based on the Thiessen diagram method, the spatial range is divided into a set of Thiessen polygon areas A = [A1, A2, ..., A m-1 , A m 】, where each sample point in the initial data set corresponds to a Thiessen multi-deformation region.

[0130] Step 2: Identify sensitive polygonal areas. Calculate the error [ρ1, ρ2, ..., ρ m-1 , m 】As the error of the corresponding Thiessen polygon area, the sensitive polygon area is the three Thiessen polygon areas with the largest error.

[0131] By A sensitive = arg maxρ i , (i=1, 2, ..., m), select the three Thiessen polygon areas with the largest errors, which are the top three sensitive polygon areas (recorded as id1, id2, id3); or idx=sort(A,'descend') (indicating that A is sorted in descending order), rank the errors of each Thiessen polygon area, and then take the Thiessen polygon areas corresponding to the top three maximum error values ​​of id1, id2, and id3, which are the top three sensitive polygon areas.

[0132] Step 3: Select new sample points in three sensitive polygonal areas.

[0133] By randomly sampling id1, id2, and id3 respectively through a Monte Carlo-based random sampling method, a plurality of random sampling points corresponding to id1, id2, and id3 are obtained.

[0134] Select a random sampling point from each of the three areas corresponding to id1, id2, and id3, with a distance T i-sensitive The farthest random sampling point is used as the new sample point.

[0135] T id1 = arg max|T 1y -T 1-sensitive |

[0136] Among them, T id1 T is the new sample point of the sensitive polygon area of ​​id1. 1y (where y=, 2, 3, ...) are multiple random sampling points corresponding to id1, T 1-sensitive is the sample point corresponding to id1.

[0137] T id2 = arg max|T 2y -T 2-sensitive |

[0138] Among them, T id2 T is the new sample point of the id2 sensitive polygon area. 2y (where y=, 2, 3, ...) are multiple random sampling points corresponding to id2, T 2-sensitive is the sample point corresponding to id2.

[0139] T id3 = arg max|T 3y -T 3-sensitive |

[0140] Among them, T id3 T is the new sample point of ID3 sensitive polygon area. 3y (where y=, 2, 3, ...) are multiple random sampling points corresponding to id3, T 3-sensitive is the sample point corresponding to id3.

[0141] Step 4: Calculate the response of the newly added sample points, update the target data set, use the updated data set to build the stator frame-upper frame proxy model, and re-perform convergence judgment.

[0142] In the embodiment of the present application, based on the sequence sampling method, a self-updating method for the proxy model under multiple input variables is proposed, and a method of adding three sample points at one time is proposed to quickly eliminate interference in areas with large errors.

[0143] Figure 4 This is a structural block diagram of a motor temperature stress field proxy model construction device shown in an embodiment of the present application, such as Figure 4 As shown, it includes: an acquisition module 401, which is used to acquire a sample space range, and the sample space range includes a load sample space range, a stator base temperature operating range, and an upper frame temperature operating range. The load sample space range is determined based on load inversion data obtained based on load inversion, and the stator base temperature operating range and the upper frame temperature operating range are respectively determined based on corresponding historical acquisition data; a sampling module 402, which is used to sample the sample space range using a uniform sampling algorithm to obtain a plurality of sample points; a simulation module 403, which is used to simulate the plurality of sample points based on a finite element model of a stator base-upper frame to obtain response values ​​corresponding to the plurality of sample points; and a construction module 404, which is used to construct a converged target stator base-upper frame proxy model based on the plurality of sample points and a target data set determined by the response values ​​corresponding to the plurality of sample points.

[0144] In some embodiments of the present application, the construction module 404 is specifically used to construct an initial stator base-upper frame proxy model based on the target data set; input the actual load value, the actual stator base temperature value and the actual frame temperature value in the actual operating condition data into the initial stator base-upper frame proxy model to obtain a test response value, and the actual operating condition data also includes an actual response value corresponding to the actual load value, the actual stator base temperature value and the actual frame temperature value; determine whether the initial stator base-upper frame proxy model converges according to the relationship between the test response value and the actual response value; if the initial stator base-upper frame proxy model converges, determine the initial stator base-upper frame proxy model as the target stator base-upper frame proxy model.

[0145] In some embodiments of the present application, the construction module 404 is further used to determine whether the proxy model of the initial stator base-upper frame has converged according to the relationship between the test response value and the actual response value. If it is determined that the proxy model of the initial stator base-upper frame has not converged, determine at least one new sample point based on the target data set and based on a sequence sampling method; simulate the at least one new sample point based on the finite element model of the stator base-upper frame to obtain the response values ​​corresponding to the at least one new sample point; update the target data set based on the at least one new sample point and the response values ​​corresponding to the at least one new sample point to obtain an updated data set; use the updated data set as the target data set, and return to execute the construction of the proxy model of the initial stator base-upper frame based on the target data set until a converged proxy model of the target stator base-upper frame is obtained.

[0146] In some embodiments of the present application, the construction module 404 is specifically used to divide the spatial range corresponding to the target variable into multiple Thiessen polygon areas based on the target data set by using the Thiessen diagram method, and the target variable is any one of the load, the stator base temperature and the upper frame temperature; based on the errors of the sample points corresponding to the multiple Thiessen polygon areas, the Thiessen polygon areas corresponding to the n sample points with the largest errors are determined as n sensitive polygon areas, where n is a positive integer; and a sampling point is determined from each of the n sensitive polygon areas to obtain the at least one newly added sample point.

[0147] In some embodiments of the present application, the construction module 404 is specifically used to perform random sampling on the target sensitive polygon area to obtain multiple random sampling points; and determine the point among the multiple random sampling points that is farthest from the sample point corresponding to the sensitive polygon area as a new sample point corresponding to the target sensitive polygon area.

[0148] In some embodiments of the present application, the construction module 404 is specifically used to determine that the proxy model of the initial stator base-upper frame has converged when the absolute value of the ratio of the target difference value to the actual response value is less than or equal to the ratio threshold, and the target difference value is the difference between the test response value and the actual response value; when the absolute value of the ratio of the target difference value to the actual response value is greater than the ratio threshold, determine that the proxy model of the initial stator base-upper frame has not converged.

[0149] In some embodiments of the present application, the construction module 404 is specifically used to determine that the proxy model of the initial stator base-upper frame has converged when the absolute value of the difference between the test response value and the actual response value is less than or equal to the difference threshold; and to determine that the proxy model of the initial stator base-upper frame has not converged when the absolute value of the difference between the test response value and the actual response value is greater than the difference threshold.

[0150] In some embodiments of the present application, the sampling module 402 is specifically used to sample the sample space range using the optimal super Latin cube method to obtain the multiple sample points.

[0151] In the embodiment of the present application, each module can implement the motor temperature stress field proxy model construction method provided in the above method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0152] Figure 5 The structural schematic diagram of an electronic device provided in the embodiment of the present application is used to exemplify the electronic device that implements the method for constructing an agent model of temperature stress field of any motor in the embodiment of the present application, and should not be understood as a specific limitation on the embodiment of the present application.

[0153] like Figure 5 As shown, the electronic device 500 may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processor 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0154] Typically, the following devices may be connected to the I / O interface 505: input devices 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication devices 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although the electronic device 500 is shown with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have instead.

[0155] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processor 501, the functions defined in any motor temperature stress field proxy model construction method provided in the embodiment of the present application can be executed.

[0156] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0157] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0158] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0159] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a sample space range, the sample space range includes a load sample space range, a stator base temperature operating range and an upper frame temperature operating range, the load sample space range is determined based on load inversion data obtained based on load inversion, and the stator base temperature operating range and the upper frame temperature operating range are respectively determined based on corresponding historical acquisition data; samples the sample space range using a uniform sampling algorithm to obtain a plurality of sample points; simulates the plurality of sample points based on a finite element model of the stator base-upper frame to obtain response values ​​corresponding to the plurality of sample points respectively; and constructs a converged target stator base-upper frame proxy model based on the plurality of sample points and a target data set determined based on the plurality of sample points and the response values ​​corresponding to the plurality of sample points respectively.

[0160] In an embodiment of the present application, a computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, and the above-mentioned programming languages ​​include but are not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and also include conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed completely on the computer, partially on the computer, as an independent software package, partially on the computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0161] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0162] The units involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of a unit does not, in some cases, constitute a limitation on the unit itself.

[0163] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0164] In the context of the present application, a computer-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a computer-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0165] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

[0166] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0167] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for constructing a proxy model of motor temperature stress field, characterized in that: The method comprises: Obtaining a sample space range, wherein the sample space range includes a load sample space range, a stator base temperature operating range, and an upper frame temperature operating range, wherein the load sample space range is determined based on load inversion data obtained based on load inversion, and the stator base temperature operating range and the upper frame temperature operating range are respectively determined based on corresponding historical acquisition data; The sample space range is sampled using a uniform sampling algorithm to obtain a plurality of sample points; Simulating the plurality of sample points based on a finite element model of a stator base-upper frame to obtain response values ​​corresponding to the plurality of sample points respectively; Based on the multiple sample points and the target data set determined by the response values ​​respectively corresponding to the multiple sample points, construct an initial stator frame-upper frame proxy model; Inputting the actual load value, the actual stator base temperature value and the actual frame temperature value in the actual operating condition data into the initial stator base-upper frame proxy model to obtain a test response value, wherein the actual operating condition data also includes an actual response value corresponding to the actual load value, the actual stator base temperature value and the actual frame temperature value; Determining whether the initial stator base-upper frame proxy model converges according to the relationship between the test response value and the actual response value; When the proxy model of the initial stator base-upper frame converges, determining the proxy model of the initial stator base-upper frame as the proxy model of the target stator base-upper frame; In the case where the initial stator base-upper frame proxy model does not converge, determining at least one new sample point based on the target data set and a sequence sampling method; Simulating the at least one newly added sample point based on the finite element model of the stator base-upper frame to obtain response values ​​corresponding to the at least one newly added sample point; Based on the at least one newly added sample point and the response values ​​respectively corresponding to the at least one newly added sample point, updating the target data set to obtain an updated data set; The updated data set is used as the target data set, and the process of constructing an initial stator base-upper frame proxy model based on the target data set is returned to execute until a converged target stator base-upper frame proxy model is obtained.

2. The method according to claim 1, characterized in that The determining at least one new sample point based on the target data set and a sequence sampling method includes: Based on the target data set, the spatial range corresponding to the target variable is divided into a plurality of Thiessen polygon regions by using Thiessen diagram method, wherein the target variable is any one of the load, the stator frame temperature and the upper frame temperature; Based on the errors of the sample points respectively corresponding to the multiple Thiessen polygon areas, the Thiessen polygon areas respectively corresponding to the n sample points with the largest errors are determined as n sensitive polygon areas, where n is a positive integer; A sampling point is determined from each of the n sensitive polygonal areas to obtain the at least one newly added sample point.

3. The method according to claim 2, characterized in that The step of determining a sampling point from each of the n sensitive polygonal areas to obtain the at least one newly added sampling point includes: Random sampling is performed on the target sensitive polygon area to obtain multiple random sampling points; A point among the multiple random sampling points that is farthest from the sample point corresponding to the sensitive polygonal area is determined as a newly added sample point corresponding to the target sensitive polygonal area.

4. The method according to claim 1, characterized in that: The determining, based on the relationship between the test response value and the actual response value, whether the initial stator base-upper frame proxy model is converged includes: When an absolute value of a ratio of a target difference value to the actual response value is less than or equal to a ratio threshold, determining that the proxy model of the initial stator base-upper frame has converged, the target difference value being a difference between the test response value and the actual response value; When the absolute value of the ratio of the target difference value to the actual response value is greater than the ratio threshold, it is determined that the initial stator frame-upper frame proxy model does not converge.

5. The method according to claim 1, characterized in that The determining, based on the relationship between the test response value and the actual response value, whether the initial stator base-upper frame proxy model is converged includes: When the absolute value of the difference between the test response value and the actual response value is less than or equal to the difference threshold, determining that the proxy model of the initial stator base-upper frame converges; When the absolute value of the difference between the test response value and the actual response value is greater than the difference threshold, it is determined that the initial stator frame-upper frame proxy model does not converge.

6. The method according to any one of claims 1 to 5, characterized in that The uniform sampling algorithm is used to sample the sample space range to obtain multiple sample points, including: The sample space range is sampled using an optimal super-Latin method to obtain the multiple sample points.

7. A device for constructing a proxy model of a motor temperature stress field, characterized in that: include: An acquisition module, used for acquiring a sample space range, wherein the sample space range includes a load sample space range, a stator base temperature operating range, and an upper frame temperature operating range, wherein the load sample space range is determined based on load inversion data obtained based on load inversion, and the stator base temperature operating range and the upper frame temperature operating range are respectively determined based on corresponding historical acquisition data; A sampling module, used to sample the sample space range using a uniform sampling algorithm to obtain multiple sample points; A simulation module, used to simulate the multiple sample points based on a finite element model of the stator base-upper frame to obtain response values ​​corresponding to the multiple sample points respectively; A construction module, configured to construct an initial stator frame-upper frame proxy model based on the plurality of sample points and a target data set determined by response values ​​corresponding to the plurality of sample points; Inputting the actual load value, the actual stator base temperature value and the actual frame temperature value in the actual operating condition data into the initial stator base-upper frame proxy model to obtain a test response value, wherein the actual operating condition data also includes an actual response value corresponding to the actual load value, the actual stator base temperature value and the actual frame temperature value; Determining whether the initial stator base-upper frame proxy model converges according to the relationship between the test response value and the actual response value; When the proxy model of the initial stator base-upper frame converges, determining the proxy model of the initial stator base-upper frame as the proxy model of the target stator base-upper frame; In the case where the initial stator base-upper frame proxy model does not converge, determining at least one new sample point based on the target data set and a sequence sampling method; Simulating the at least one newly added sample point based on the finite element model of the stator base-upper frame to obtain response values ​​corresponding to the at least one newly added sample point; Based on the at least one newly added sample point and the response values ​​respectively corresponding to the at least one newly added sample point, updating the target data set to obtain an updated data set; The updated data set is used as the target data set, and the process of constructing an initial stator base-upper frame proxy model based on the target data set is returned to execute until a converged target stator base-upper frame proxy model is obtained.

8. An electronic device, characterized in that: include: A memory and a processor, the memory is used to store a computer program; the processor is used to execute the motor temperature stress field proxy model construction method described in any one of claims 1 to 6 when calling the computer program.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for constructing a motor temperature stress field proxy model according to any one of claims 1 to 6 is implemented.

Images