Automobile motor multi-working-condition performance comprehensive test method, system and equipment

Abstract

The invention discloses an automobile motor multi-working-condition performance comprehensive test method, system and device, and relates to the technical field of motor performance tests.The method comprises the steps that the motor model and the performance requirement index of a target test motor are obtained, and a working condition scene feature set is obtained; constructing a performance test scene prototype library; obtaining a multi-working-condition performance test scene prototype combination set, performing switching cost identification on the multi-working-condition performance test scene prototype combination set in combination with the concentrated working-condition scene features, and determining a target multi-working-condition performance test scene prototype combination and target multi-working-condition scene features; and carrying out comprehensive performance test on the target test motor. According to the invention, the technical problem of low test result reliability caused by insufficient coverage during the working condition performance test of the electric automobile motor in the prior art is solved, and the technical effects of improving the fitting degree between the multi-working condition test and the actual application condition of the automobile motor and improving the reliability of the test result are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of motor performance testing, and in particular to a multi-working-condition performance comprehensive testing method, system and device for an automobile motor. BACKGROUND

[0002] At present, as a core component of a new energy automobile driving system, the performance testing of an electric automobile motor is mainly carried out around a single or a small number of typical working conditions, such as constant speed running, high speed starting or slope climbing and the like fixed mode. Such a traditional testing method is difficult to comprehensively reflect the comprehensive performance of the motor under complex working conditions, especially in the evaluation facing the variable actual driving environment, there are problems of insufficient coverage and low testing precision. Part of the testing platform supports multi-scene switching testing, but often switches based on static preset scenes, without fully considering the dynamic nature of working condition combination and the cost problem in the switching process, resulting in low testing efficiency and high result distortion. SUMMARY

[0003] The present application provides a multi-working-condition performance comprehensive testing method, system and device for an automobile motor, which is used to solve the technical problem of low reliability of testing results caused by insufficient coverage in the performance testing of working conditions of an electric automobile motor in the prior art.

[0004] In view of the above problems, the present application provides a multi-working-condition performance comprehensive testing method, system and device for an automobile motor.

[0005] In a first aspect, the present application provides a multi-working-condition performance comprehensive testing method for an automobile motor, which comprises:

[0006] obtaining a motor model and performance requirement index of a target testing motor, and performing working condition scene mining based on the motor model and performance requirement index to obtain a working condition scene feature set;

[0007] performing multi-working-condition analysis and prototype extraction on the working condition scene feature set to construct a performance testing scene prototype library, wherein each performance testing scene prototype corresponds to a centralized working condition scene feature;

[0008] performing random multi-working-condition performance testing scene prototype combination on the performance testing scene prototype library to obtain a multi-working-condition performance testing scene prototype combination set, identifying switching cost of the multi-working-condition performance testing scene prototype combination set in combination with the centralized working condition scene feature, determining a target multi-working-condition performance testing scene prototype combination and a target multi-working-condition scene feature;

[0009] sending the target multi-working-condition performance testing scene prototype combination and the target multi-working-condition scene feature to a motor performance testing platform, and performing performance comprehensive testing on the target testing motor.

[0010] In an alternative embodiment, the performance requirement indicators include at least power requirement, efficiency requirement, temperature requirement and torque requirement.

[0011] In an alternative embodiment, the set of working condition scene features is subjected to multi-working condition analysis and prototype extraction to construct a performance test scene prototype library, wherein each performance test scene prototype corresponds to a centralized working condition scene feature, including:

[0012] The set of working condition scene features is clustered based on a preset working condition scene feature similarity constraint to determine M sets of clustered working condition scene features, wherein M is a positive integer.

[0013] The M sets of clustered working condition scene features are subjected to mean shift screening to determine M centralized working condition scene features.

[0014] The M performance test scene prototypes are obtained based on semantic analysis of the M centralized working condition scene features.

[0015] The M performance test scene prototypes are one-to-one mapped with the M centralized working condition scene features to construct the performance test scene prototype library.

[0016] In an alternative embodiment, the set of working condition scene features is clustered based on a preset working condition scene feature similarity constraint to determine M sets of clustered working condition scene features, including:

[0017] M working condition scene features are randomly extracted from the set of working condition scene features as M calibration working condition scene features.

[0018] Based on the M calibration working condition scene features, the set of working condition scene features is subjected to same-type aggregation based on the preset working condition scene feature similarity constraint to obtain M sets of clustered working condition scene features.

[0019] In an alternative embodiment, the method includes:

[0020] The M calibration working condition scene features are combined two by two to construct a calibration working condition scene feature combination set.

[0021] The proportion of combinations in the calibration working condition scene feature combination set with a combination similarity greater than or equal to a preset similarity threshold is counted, and if the counting result exceeds a preset proportion threshold, a calibration working condition scene feature reselection instruction is triggered, and the M calibration working condition scene features are randomly extracted again from the set of working condition scene features according to the calibration working condition scene feature reselection instruction.

[0022] In an alternative embodiment, the M performance test scene prototypes are obtained based on semantic analysis of the M centralized working condition scene features, including:

[0023] pre-building a semantic parser, wherein the semantic parser is trained based on the working condition scene features in the sample set and the sample performance test scene prototypes;

[0024] performing semantic analysis on the M working condition scene features by using the semantic parser to obtain the M performance test scene prototypes.

[0025] In an optional embodiment, the performance test scene prototype library is subjected to random multi-working condition performance test scene prototype combination to obtain a multi-working condition performance test scene prototype combination set, and the multi-working condition performance test scene prototype combination set is subjected to switching cost identification in combination with the working condition scene features to determine a target multi-working condition performance test scene prototype combination and a target multi-working condition scene feature combination, including:

[0026] traversing the multi-working condition performance test scene prototype combination set in combination with the working condition scene features corresponding to each performance test scene prototype to determine a scene test equipment combination set;

[0027] obtaining a scene test equipment position distribution map controlled by the motor performance test platform;

[0028] defining a working condition performance test scene switching cost item, and performing switching cost identification on the scene test equipment combination set based on the working condition performance test scene switching cost item and the scene test equipment position distribution map to obtain a switching cost set;

[0029] taking the multi-working condition performance test scene prototype combination corresponding to the maximum value in the switching cost set as the target multi-working condition performance test scene prototype combination, and performing aggregation on the working condition scene features corresponding to each performance test scene prototype in the target multi-working condition performance test scene prototype combination to obtain a target multi-working condition scene feature combination.

[0030] In an optional embodiment, the working condition performance test scene switching cost item at least includes a hardware switching cost, a switching time delay, an equipment position adjustment cost and a motor transfer cost.

[0031] A second aspect of the present application provides a multi-working condition performance comprehensive test system for an automobile motor, including:

[0032] a working condition scene feature set obtaining module configured to obtain a motor model and performance requirement indexes of a target test motor, and perform working condition scene mining based on the motor model and the performance requirement indexes to obtain a working condition scene feature set;

[0033] The test scene prototype library construction module is configured to analyze and extract prototypes from the set of working condition scene features, and construct a performance test scene prototype library, wherein each performance test scene prototype corresponds to a centralized working condition scene feature.

[0034] The multi-working condition scene feature determination module is configured to combine the set of multi-working condition performance test scene prototypes, identify switching costs in combination with the centralized working condition scene features, determine a target multi-working condition performance test scene prototype combination and a target multi-working condition scene feature.

[0035] The performance comprehensive test module is configured to send the target multi-working condition performance test scene prototype combination and the target multi-working condition scene feature to the motor performance test platform, and perform a performance comprehensive test on the target test motor.

[0036] In a third aspect, the present application provides an electronic device, comprising a memory configured to store executable instructions, and a processor configured to execute the executable instructions stored in the memory to implement the motor multi-working condition performance comprehensive test method for an automobile provided by the present application.

[0037] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0038] In the present application, the motor model and performance requirement index of a target test motor are acquired, working condition scenes are mined based on the motor model and performance requirement index, a set of working condition scene features is obtained, the set of working condition scene features is analyzed and extracted, a performance test scene prototype library is constructed, wherein each performance test scene prototype corresponds to a centralized working condition scene feature, then the performance test scene prototype library is combined for random multi-working condition performance test scene prototype combination, a set of multi-working condition performance test scene prototypes is obtained, switching costs are identified in combination with the centralized working condition scene features, a target multi-working condition performance test scene prototype combination and a target multi-working condition scene feature are determined, and then the target multi-working condition performance test scene prototype combination and the target multi-working condition scene feature are sent to a motor performance test platform to perform a performance comprehensive test on the target test motor. The technical effect of improving the fitting degree of multi-working condition test and actual application of an automobile motor and improving the reliability of test results is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A flow chart of a comprehensive test method for multi-operating-condition performance of an automotive motor provided in an embodiment of the present application;

[0041] Figure 2 A schematic diagram of the structure of a comprehensive test system for multi-operating-condition performance of an automotive motor provided in an embodiment of the present application;

[0042] Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of this application.

[0043] Explanation of the reference numerals: bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305, operating scenario feature set acquisition module 11, test scenario prototype library construction module 12, multi-operating scenario feature determination module 13, performance comprehensive test module 14. DETAILED DESCRIPTION

[0044] This application provides a comprehensive test method, system and equipment for the multi-operating performance of automobile motors, aiming to solve the technical problem in the prior art of insufficient coverage of operating performance tests on electric vehicle motors, resulting in low reliability of test results, thereby achieving the technical effect of improving the fit between multi-operating performance tests and the actual application conditions of automobile motors and enhancing the credibility of test results.

[0045] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0046] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0047] Example 1, as Figure 1 As shown, the present application provides a comprehensive test method for the multi-operating performance of an automobile motor, the method comprising:

[0048] Step S100: Obtain the motor model and performance requirement index of the target test motor, and perform working condition scene mining based on the motor model and performance requirement index to obtain a working condition scene feature set;

[0049] Further, the performance requirement index at least includes power requirement, efficiency requirement, temperature requirement, and torque requirement.

[0050] In one possible embodiment, the target test motor refers to an automobile driving motor to be subjected to performance evaluation and comprehensive testing, which has a unique model and structural parameters, such as an asynchronous motor or a permanent magnet synchronous motor. The performance requirement index is the working performance requirement of the target motor in a specific application environment, which at least includes four core dimensions: power requirement (such as peak power / continuous power, unit: kW), efficiency requirement (such as peak efficiency / efficiency at a certain speed, unit: %), temperature requirement (such as maximum winding temperature, shell stable temperature, unit: ℃), and torque requirement (such as maximum torque, stable torque, unit: N·m).

[0051] Preferably, according to the historical running data of the motor model, the industry test specification, or the simulated working condition library, the typical load and running state (such as starting, climbing, accelerating, and cruising) are analyzed and mined to extract multi-dimensional working condition parameter features reflecting the actual use environment of the motor, such as load-speed-temperature, to constitute the working condition scene feature set.

[0052] First, the motor model of the test object (for example: AM-1250, indicating a permanent magnet synchronous motor with a rated power of 125 kW) is input, and the performance requirement index thereof (for example: rated power 125 kW, peak power 250 kW, efficiency requirement ≥ 95%, maximum winding temperature not exceeding 150℃, and maximum torque reaching 450 N·m) is set.

[0053] According to these indexes, the typical working conditions with high matching degree are mined in the preset working condition library, including but not limited to high-speed cruising (low load, high speed), frequent start-stop (large load fluctuation), low-temperature cold start (temperature rise response), uphill full load (high power+high temperature), and the like. Each working condition is represented by a feature vector, for example: working condition 1 feature = [speed = 3000 rpm, load = 80%, temperature = 90℃, efficiency = 92%]. Finally, a working condition scene feature set is formed.

[0054] Step S200: Perform multi-working condition analysis and prototype extraction on the working condition scene feature set to construct a performance test scene prototype library, wherein each performance test scene prototype corresponds to a concentrated working condition scene feature;

[0055] Further, the multiple working condition scene feature set is analyzed and a prototype is extracted to construct a performance test scene prototype library, wherein each performance test scene prototype corresponds to a centralized working condition scene feature. The step S200 of the embodiment of the application further includes:

[0056] The multiple working condition scene feature set is clustered with a preset working condition scene feature similarity as a constraint to determine M clustered working condition scene feature sets, wherein M is a positive integer.

[0057] The M clustered working condition scene feature sets are screened by mean shift to determine M centralized working condition scene features.

[0058] The M centralized working condition scene features are semantically analyzed to obtain M performance test scene prototypes.

[0059] The M performance test scene prototypes are one-to-one mapped with the M centralized working condition scene features to construct the performance test scene prototype library.

[0060] In one possible embodiment, the performance test scene prototype is a representative expression of the result of clustering of multiple similar working condition features. A representative sample that can represent the mean or core mode of the working condition features is selected and referred to as a prototype. The multiple working condition scene feature set is distinguished according to a preset working condition scene feature similarity as a distinguishing basis to realize multiple working condition analysis. Then, the M clustered working condition scene feature sets obtained after the analysis are screened by a mean shift algorithm to determine representative samples to obtain the M centralized working condition features. Then, the M centralized working condition features are inversed to determine the represented scene description conditions to obtain the M performance test scene prototypes. The M centralized working condition features are correspondingly associated with the M performance test scene prototypes to obtain the performance test scene prototype library.

[0061] For example, the performance test scene prototype library is shown in Table 1.

[0062] Table 1: Performance test scene prototype library

[0063] Centralized feature numbering Rotational speed (rpm) Load (%) Temperature (°C) Efficiency (%) Semantic label c1 3200 85 95 92.4 High speed full load c2 800 20 50 96.8 Cold start low load c3 1500 70 110 91.1 Warm mid load cruise c4 3000 90 120 89.9 Warm shock high speed acceleration c5 2000 60 85 94.7 Daily urban driving

[0064] The application filters out the most representative centralized working condition scene features from a large number of working condition features to construct a standardized performance test prototype library as a basis for subsequent combination testing.

[0065] Further, the multiple working condition scene feature set is analyzed and a prototype is extracted to construct a performance test scene prototype library, wherein each performance test scene prototype corresponds to a centralized working condition scene feature. The step S200 of the embodiment of the application further includes:

[0066] randomly extracting M working condition scene features from the working condition scene feature set as M calibration working condition scene features;

[0067] based on the M calibration working condition scene features, performing same-class aggregation on the working condition scene feature set with the preset same working condition scene feature similarity as a constraint to obtain M clustered working condition scene feature sets.

[0068] Further, the step S200 of the embodiment of the present application further includes:

[0069] performing pairwise combination on the M calibration working condition scene features to construct a calibration working condition scene feature combination set;

[0070] statistically determining a proportion of combinations in the calibration working condition scene feature combination set with a combination similarity greater than or equal to a preset similarity threshold value, and if the statistical result exceeds a preset proportion threshold value, triggering a calibration working condition scene feature reselection instruction, and again performing random extraction of calibration working condition scene features from the working condition scene feature set according to the triggered calibration working condition scene feature reselection instruction.

[0071] Further, based on the M centralized working condition scene features, performing semantic analysis to obtain M performance test scene prototypes, the step S200 of the embodiment of the present application further includes:

[0072] preconstructing a semantic analyzer, wherein the semantic analyzer is trained based on sample centralized working condition scene features and sample performance test scene prototypes to obtain;

[0073] using the semantic analyzer to perform semantic analysis on the M centralized working condition scene features to obtain the M performance test scene prototypes.

[0074] In one possible embodiment, the calibration working condition scene feature refers to an initial cluster center candidate randomly extracted from the working condition feature set, used to guide the subsequent clustering process. The preset same working condition scene feature similarity is the minimum similarity of two features when the working condition scene features can be divided into the same set with the calibration working condition scene feature. The preset proportion threshold value is the maximum proportion preset by the person skilled in the art.

[0075] First, a number of features are randomly extracted from the working condition feature set as the initial calibration working condition features to guide subsequent similar aggregation operations. In the aggregation stage, all working condition features will be assigned to the corresponding cluster set based on the similarity between them and the calibration features. To ensure that there is sufficient difference between the calibration features, the system will combine all calibration features in pairs, calculate their similarity, and count the proportion of combinations that exceed the similarity threshold. If the ratio exceeds the preset standard, it means that the current calibration features are not different enough, which may cause overlapping or redundant clustering results. The system will trigger the reselection logic and randomly extract a new calibration feature set again until the combination similarity distribution meets the requirements. This mechanism ensures the rationality of the division of the working condition feature space and provides a more clearly distinguished and comprehensive working condition basis for the subsequent performance test prototype generation.

[0076] A semantic parser is a model component built using machine learning or expert rules. Its input is a structured operating condition feature vector, and its output is a test scenario prototype with semantic labels or classification characteristics. During training, the mapping relationship between operating condition features and prototype labels is learned, forming a generalizable semantic mapping model.

[0077] In one possible embodiment, by inputting the concentrated working condition features and the corresponding performance test prototypes in the historical samples, a mapping model between features and semantics is trained. The training method can adopt supervised learning methods, such as support vector machines, decision trees, deep neural networks, etc., or it can integrate expert experience to form a rule model. Subsequently, the M concentrated working condition features obtained from the current analysis are sequentially input into the parser, and the parser assigns a performance test prototype label to each concentrated working condition feature based on the learned mapping rules. For example, a certain feature combination may be parsed as a "medium-speed and medium-load steady-state cruising scenario" or a "high-temperature and high-power impact scenario". These semantic labels are used as the definition input of the standard test scenario and are uniformly included in the performance test scenario prototype library to provide a standard reference for subsequent combination testing and resource scheduling.

[0078] Step S300: performing random multi-condition performance test scenario prototype combination on the performance test scenario prototype library to obtain a multi-condition performance test scenario prototype combination set, performing switching cost identification on the multi-condition performance test scenario prototype combination set in combination with the centralized condition scenario characteristics, and determining a target multi-condition performance test scenario prototype combination and a target multi-condition scenario characteristic;

[0079] Step S400: sending the target multi-operating condition performance test scenario prototype combination and the target multi-operating condition scenario characteristics to a motor performance test platform, and performing a comprehensive performance test on the target test motor.

[0080] Further, the performance test scene prototype library is randomly combined with multi-working condition performance test scene prototypes to obtain a multi-working condition performance test scene prototype combination set. The multi-working condition performance test scene prototype combination set is combined with centralized working condition scene features to identify switching costs, determine a target multi-working condition performance test scene prototype combination and a target multi-working condition scene feature combination. The step S300 of the embodiment of the application further includes:

[0081] The multi-working condition performance test scene prototype combination set is traversed, and the centralized working condition scene features corresponding to each performance test scene prototype are determined to obtain a scene test device combination set.

[0082] A scene test device position distribution map controlled by the motor performance test platform is obtained.

[0083] A working condition performance test scene switching cost item is defined. The scene test device combination set is identified based on the working condition performance test scene switching cost item and the scene test device position distribution map to obtain a switching cost set.

[0084] The multi-working condition performance test scene prototype combination corresponding to the maximum value in the switching cost set is taken as the target multi-working condition performance test scene prototype combination. The centralized working condition scene features corresponding to each performance test scene prototype in the target multi-working condition performance test scene prototype combination are summarized to obtain a target multi-working condition scene feature combination.

[0085] Further, the working condition performance test scene switching cost item at least includes a hardware switching cost, a switching time delay, a device position adjustment cost and a motor transfer cost.

[0086] In one possible embodiment, a plurality of test scene prototypes are randomly or strategically selected from the performance test scene prototype library to form a combination for simulating a complete test flow of the motor running under continuous or changing working conditions, thereby obtaining the multi-working condition performance test scene prototype combination set. Further, the cost of switching different test scene prototypes is determined to obtain a target multi-working condition performance test scene prototype combination with minimum cost and corresponding target multi-working condition scene features.

[0087] In one embodiment, the device position distribution map is a spatial arrangement map and connection topology of all available test devices on the platform, which is used to analyze the physical conversion path between devices. The scene test device combination set refers to all test devices and their configurations required to be called to execute a certain combination. The working condition performance test scene switching cost item at least includes a hardware switching cost, a switching time delay, a device position adjustment cost and a motor transfer cost.

[0088] In one possible embodiment, the aforementioned randomly generated multi-condition performance test prototype combinations are traversed; in combination with the required centralized condition characteristics of each test prototype, the corresponding test equipment in the equipment list of the motor performance test platform is matched to form a corresponding scene test equipment combination set. The spatial layout information of the scene test equipment, i.e., the equipment position distribution map, is called to understand the physical arrangement and connection relationship of the equipment; a condition performance test scene switching cost item containing multiple dimensions is introduced, and for the switching of the equipment combination required between any two test prototypes, the required hardware replacement, arrangement change, time delay and transportation cost are calculated. For each test prototype combination, the switching cost involved in the overall execution process is calculated and stored in the switching cost set; the combination with the minimum switching cost is identified from the switching cost set, and is taken as the target multi-condition performance test scene prototype combination. The automation of the test path selection is realized, and the test representativeness and execution efficiency are considered through the multi-dimensional cost evaluation mechanism, so that the technical effects of avoiding repeated testing, equipment conflict and inefficient conversion, ensuring stable test process and minimizing system operation cost are achieved.

[0089] In one possible embodiment, the motor performance test platform integrates a motor loading device, a sensor module, a data acquisition and control system, supports multi-condition operation simulation and real-time performance index acquisition. The target multi-condition performance test scene prototype combination and the target multi-condition scene characteristics are sent to the motor performance test platform, and after the platform receives the information, the required operating conditions of each test prototype are loaded in turn, and the test device is controlled to perform simulation tasks under various conditions, such as loading different loads, controlling temperature rise curves, adjusting speed waveforms, etc.

[0090] During the test process, the platform synchronously acquires real-time response data of the target motor, such as output power, current waveform, efficiency curve, thermal stability time, etc., and compares the data with the preset performance indicators of each test prototype to generate a performance evaluation report under each condition. Through the continuous execution of the combined test path, the performance response trajectory of the motor under complex real conditions can be formed, and the comprehensive evaluation of the multi-dimensional performance of the motor, such as dynamic stability, peak performance, and condition adaptability, can be realized.

[0091] In the embodiments of the present application, as described above, the embodiments of the present application at least have the following technical effects:

[0092] This application obtains the motor model and performance requirement indicators of the target test motor, conducts working condition scenario mining based on the motor model and performance requirement indicators, obtains a working condition scenario feature set, then performs multi-working condition analysis and prototype extraction on the working condition scenario feature set, and constructs a performance test scenario prototype library, wherein each performance test scenario prototype corresponds to a centralized working condition scenario feature, and then performs random multi-working condition performance test scenario prototype combination on the performance test scenario prototype library to obtain a multi-working condition performance test scenario prototype combination set, and combines the centralized working condition scenario feature to identify the switching cost of the multi-working condition performance test scenario prototype combination set, determines the target multi-working condition performance test scenario prototype combination and the target multi-working condition scenario feature, and then sends the target multi-working condition performance test scenario prototype combination and the target multi-working condition scenario feature to the motor performance test platform to perform a comprehensive performance test on the target test motor. The technical effect of improving the fit between the multi-working condition test and the actual application of the automotive motor and enhancing the credibility of the test results is achieved.

[0093] The second embodiment is based on the same inventive concept as the comprehensive test method for multi-operating performance of automobile motors in the above embodiment. Figure 2 As shown, the present application provides a comprehensive test system for the multi-operating performance of an automobile motor. The system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0094] A working condition scenario feature set acquisition module 11 is used to obtain the motor model and performance requirement indicators of the target test motor, perform working condition scenario mining based on the motor model and performance requirement indicators, and obtain a working condition scenario feature set;

[0095] A test scenario prototype library construction module 12 is used to perform multi-operating condition analysis and prototype extraction on the operating condition scenario feature set to construct a performance test scenario prototype library, wherein each performance test scenario prototype corresponds to a centralized operating condition scenario feature;

[0096] A multi-operating-condition scenario feature determination module 13 is configured to perform random multi-operating-condition performance test scenario prototype combinations on the performance test scenario prototype library to obtain a multi-operating-condition performance test scenario prototype combination set, identify switching costs on the multi-operating-condition performance test scenario prototype combination set in combination with the centralized operating-condition scenario features, and determine a target multi-operating-condition performance test scenario prototype combination and a target multi-operating-condition scenario feature;

[0097] The comprehensive performance test module 14 is used to send the target multi-operating condition performance test scenario prototype combination and the target multi-operating condition scenario characteristics to the motor performance test platform to perform a comprehensive performance test on the target test motor.

[0098] Furthermore, the performance requirement indicators include at least power requirement, efficiency requirement, temperature requirement and torque requirement.

[0099] Further, the system is used to implement the following functions:

[0100] Clustering the working condition scene feature set with the preset same working condition scene feature similarity as a constraint to determine M clustered working condition scene feature sets, wherein M is a positive integer;

[0101] Performing mean shift filtering on the M clustered working condition scene feature sets to determine M centralized working condition scene features;

[0102] Performing semantic analysis based on the M centralized working condition scene features to obtain M performance test scene prototypes;

[0103] One-to-one mapping the M performance test scene prototypes and the M centralized working condition scene features to construct the performance test scene prototype library.

[0104] Further, the system is used to implement the following functions:

[0105] Randomly extracting M working condition scene features from the working condition scene feature set as M calibration working condition scene features;

[0106] Based on the M calibration working condition scene features, performing same type aggregation on the working condition scene feature set with the preset same working condition scene feature similarity as a constraint to obtain M clustered working condition scene feature sets.

[0107] Further, the system is used to implement the following functions:

[0108] Combining the M calibration working condition scene features in pairs to construct a calibration working condition scene feature combination set;

[0109] Statistically determining the proportion of combinations in the calibration working condition scene feature combination set with a combination similarity greater than or equal to a preset similarity threshold, and if the statistical result exceeds a preset proportion threshold, triggering a calibration working condition scene feature reselection instruction, and randomly extracting calibration working condition scene features from the working condition scene feature set again according to the triggered calibration working condition scene feature reselection instruction.

[0110] Further, the system is used to implement the following functions:

[0111] Preconstructing a semantic analyzer, wherein the semantic analyzer is trained based on sample centralized working condition scene features and sample performance test scene prototypes;

[0112] Performing semantic analysis on the M centralized working condition scene features using the semantic analyzer to obtain the M performance test scene prototypes.

[0113] Further, the system is used to implement the following functions:

[0114] Traverse the multi-working condition performance test scene prototype combination set, and determine a scene test equipment combination set in combination with the centralized working condition scene features corresponding to each performance test scene prototype;

[0115] Obtain a scene test equipment position distribution map controlled by the motor performance test platform;

[0116] Define a working condition performance test scene switching cost item, identify the switching cost of the scene test equipment combination set based on the working condition performance test scene switching cost item and the scene test equipment position distribution map, and obtain a switching cost set;

[0117] Take the multi-working condition performance test scene prototype combination corresponding to the maximum value in the switching cost set as a target multi-working condition performance test scene prototype combination, and aggregate the centralized working condition scene features corresponding to each performance test scene prototype in the target multi-working condition performance test scene prototype combination to obtain a target multi-working condition scene feature combination.

[0118] Further, the working condition performance test scene switching cost item at least includes a hardware switching cost, a switching time delay, an equipment position adjustment cost, and a motor transfer cost.

[0119] Embodiment three, based on the inventive concept of the automobile motor multi-working condition performance comprehensive test method in the foregoing embodiments, the present application further provides an electronic device, comprising: at least one processor; a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of any one of the method in the foregoing embodiment one.

[0120] Figure 3 The structure schematic diagram of the exemplary electronic device of the present application is shown in FIG. 1. Figure 3 In FIG. 1, the bus architecture is represented by a bus 300, which can include any number of interconnecting buses and bridges, the bus 300 connecting various circuitry including one or more processors represented by a processor 302 and memory represented by a memory 304. The bus 300 can also connect various other circuitry such as peripheral devices, voltage stabilizers, and power management circuitry, which are well known in the art, and thus, are not further described herein. A bus interface 305 provides an interface between the bus 300 and a receiver 301 and a transmitter 303. The receiver 301 and the transmitter 303 can be the same element, i.e., a transceiver, which provides a unit for communicating with various other devices on a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, while the memory 304 can be used for storing data used by the processor 302 in performing operations.

[0121] It should be noted that the above-mentioned order of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the above describes a specific embodiment of the present application. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0122] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0123] The present application and the drawings are only exemplary descriptions of the present application, and are considered to cover any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalent technology, the present application intends to include these modifications and changes.

Claims

1. A comprehensive test method for the multi-operating performance of an automobile motor, characterized in that: The method comprises: Obtaining the motor model and performance requirement indicators of the target test motor, performing operating scenario mining based on the motor model and performance requirement indicators, and obtaining an operating scenario feature set; Perform multi-operating condition analysis and prototype extraction on the operating condition scenario feature set to build a performance test scenario prototype library, wherein each performance test scenario prototype corresponds to a centralized operating condition scenario feature; Performing random multi-condition performance test scenario prototype combinations on the performance test scenario prototype library to obtain a multi-condition performance test scenario prototype combination set, performing switching cost identification on the multi-condition performance test scenario prototype combination set in combination with concentrated condition scenario features, and determining a target multi-condition performance test scenario prototype combination and a target multi-condition scenario feature; The target multi-operating condition performance test scenario prototype combination and the target multi-operating condition scenario characteristics are sent to the motor performance test platform to perform a comprehensive performance test on the target test motor.

2. The comprehensive test method for multi-operating-condition performance of an automobile motor according to claim 1, characterized in that: The performance requirement indicators include at least power requirement, efficiency requirement, temperature requirement and torque requirement.

3. The comprehensive test method for multi-operating-condition performance of an automobile motor according to claim 2, characterized in that: Perform multi-operating condition analysis and prototype extraction on the operating condition scenario feature set to build a performance test scenario prototype library, where each performance test scenario prototype corresponds to a centralized operating condition scenario feature, including: Clustering the working condition scene feature set based on the preset similarity of the same working condition scene features as a constraint to determine M clustered working condition scene feature sets, where M is a positive integer; Performing mean shift screening on the M clustered working condition scene feature sets to determine M concentrated working condition scene features; Perform semantic analysis based on the M centralized working condition scenario features to obtain M performance test scenario prototypes; The M performance test scenario prototypes are mapped one-to-one with the M centralized working condition scenario features to construct the performance test scenario prototype library.

4. The comprehensive test method for multi-operating-condition performance of an automobile motor according to claim 3, characterized in that: The working condition scene feature set is clustered based on the preset similarity of the same working condition scene features as a constraint to determine M clustered working condition scene feature sets, including: Randomly extracting M working condition scene features from the working condition scene feature set as M calibration working condition scene features; Based on the M calibrated working condition scene features, the working condition scene feature sets are clustered into the same type with the preset similarity of the same working condition scene features as a constraint to obtain M clustered working condition scene feature sets.

5. The comprehensive test method for multi-operating-condition performance of an automobile motor according to claim 4, characterized in that: include: Combining the M calibration working condition scene features in pairs to construct a calibration working condition scene feature combination set; The proportion of the combination similarities in the calibration working condition scene feature combination set that is greater than or equal to a preset similarity threshold is counted. If the statistical result exceeds the preset proportion threshold, the calibration working condition scene feature reselection instruction is triggered, and the calibration working condition scene feature is randomly extracted from the working condition scene feature set again according to the triggered calibration working condition scene feature reselection instruction.

6. The comprehensive test method for multi-operating-condition performance of an automobile motor according to claim 4, characterized in that: Based on the M centralized working condition scenario features, semantic analysis is performed to obtain M performance test scenario prototypes, including: Pre-building a semantic parser, wherein the semantic parser is trained based on the working scenario features in the sample set and the sample performance test scenario prototype; The semantic parser is used to perform semantic parsing on the M centralized working condition scenario features to obtain the M performance test scenario prototypes.

7. The comprehensive test method for multi-operating-condition performance of an automobile motor according to claim 1, characterized in that: The performance test scenario prototype library is randomly combined with multiple working condition performance test scenario prototypes to obtain a multi-working condition performance test scenario prototype combination set, and the multi-working condition performance test scenario prototype combination set is identified by combining the concentrated working condition scenario features to determine the target multi-working condition performance test scenario prototype combination and the target multi-working condition scenario feature combination, including: Traversing the multi-operating condition performance test scenario prototype combination set, and determining the scenario test equipment combination set in combination with the centralized operating condition scenario characteristics corresponding to each performance test scenario prototype; Obtaining a location distribution map of scene test equipment controlled by the motor performance test platform; Defining a working condition performance test scenario switching cost item, and based on the working condition performance test scenario switching cost item and the scenario test device location distribution map, performing switching cost identification on the scenario test device combination set to obtain a switching cost set; The multi-condition performance test scenario prototype combination corresponding to the maximum value in the switching cost set is used as the target multi-condition performance test scenario prototype combination, and the centralized condition scenario features corresponding to each performance test scenario prototype in the target multi-condition performance test scenario prototype combination are summarized to obtain the target multi-condition scenario feature combination.

8. The comprehensive test method for multi-operating-condition performance of an automobile motor according to claim 7, characterized in that: The switching cost items of the working condition performance test scenario include at least: hardware switching cost, switching time delay, equipment position adjustment cost and motor transportation cost.

9. The comprehensive test system for multi-operating performance of automobile motors is characterized by: The system is used to perform the comprehensive testing method for multi-operating-condition performance of an automobile motor according to any one of claims 1 to 8, and the system comprises: A working condition scenario feature set acquisition module is used to obtain the motor model and performance requirement indicators of the target test motor, perform working condition scenario mining based on the motor model and performance requirement indicators, and obtain a working condition scenario feature set; A test scenario prototype library construction module is used to perform multi-operating condition analysis and prototype extraction on the operating condition scenario feature set to construct a performance test scenario prototype library, wherein each performance test scenario prototype corresponds to a centralized operating condition scenario feature; a multi-operating-condition scenario feature determination module, configured to perform random multi-operating-condition performance test scenario prototype combinations on the performance test scenario prototype library to obtain a multi-operating-condition performance test scenario prototype combination set, identify switching costs on the multi-operating-condition performance test scenario prototype combination set in combination with the centralized operating-condition scenario features, and determine a target multi-operating-condition performance test scenario prototype combination and a target multi-operating-condition scenario feature; The performance comprehensive test module is used to send the target multi-operating condition performance test scenario prototype combination and the target multi-operating condition scenario characteristics to the motor performance test platform to perform a performance comprehensive test on the target test motor.

10. An electronic device, characterized in that: The electronic device comprises: a memory for storing executable instructions; The processor is configured to implement the comprehensive test method for multi-operating-condition performance of an automobile motor according to any one of claims 1 to 8 when executing the executable instructions stored in the memory.

Images