Rack performance test script generation method and device, electronic equipment and storage medium

Abstract

The application discloses a kind of test rig performance test script generation method, device, electronic equipment and storage medium.Therein, the method comprises: determining the vehicle start-stop parameter corresponding to the target test road condition of the vehicle to be tested according to the road profile data corresponding to the target test road condition of the vehicle to be tested;Determine at least one candidate characteristic working condition corresponding to the vehicle to be tested according to the road profile data;Determine at least one target characteristic working condition according to at least one candidate characteristic working condition and road profile data;According to the vehicle start-stop parameter and at least one target characteristic working condition, generate the test rig performance test script corresponding to the vehicle to be tested.The technical scheme of the embodiment of the present application realizes the optimization of the vehicle test rig durability performance test process, shortens the development cycle, and reduces the research and development cost.

Description

Technical Field

[0001] This invention relates to the field of engine performance testing technology, and in particular to a method, apparatus, electronic device, and storage medium for generating bench performance test scripts. Background Technology

[0002] To improve fuel efficiency and fuel economy, hybrid vehicles employ significantly different engine control strategies compared to traditional gasoline vehicles. For example, they typically incorporate an automatic start-stop function to achieve fuel savings. Therefore, hybrid vehicles in urban driving generally experience frequent start-stop operations, placing higher demands on the wear resistance of engine bearings, bushings, and other friction pairs.

[0003] In related technologies, traditional engine durability testing specifications mainly target medium-to-high load conditions such as torque points and rated points, rarely conducting specific tests on engine start-stop systems. Furthermore, traditional engine durability testing only addresses the engine itself, failing to consider the impact of electric motor coupling. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for generating bench performance test scripts, thereby optimizing the vehicle bench durability performance testing process, shortening the development cycle, reducing R&D costs, and achieving the effect of bench durability performance testing applicable to different hybrid vehicle models, thus having universality.

[0005] According to one aspect of the present invention, a method for generating bench performance test scripts is provided, the method comprising:

[0006] The vehicle start-stop parameters of the vehicle under test under the target test road conditions are determined based on the road spectrum data corresponding to the vehicle under test under the target test road conditions.

[0007] Based on the road spectrum data, at least one candidate characteristic condition corresponding to the vehicle under test is determined;

[0008] Based on the at least one candidate characteristic condition and the road spectrum data, at least one target characteristic condition is determined;

[0009] Based on the vehicle start-stop parameters and the at least one target characteristic condition, a bench performance test script corresponding to the vehicle under test is generated.

[0010] According to another aspect of the present invention, a bench performance test script generation apparatus is provided, the apparatus comprising:

[0011] The parameter determination module is used to determine the vehicle start-stop parameters of the vehicle under test under the target test road condition based on the road spectrum data corresponding to the vehicle under test under the target test road condition.

[0012] The candidate feature condition determination module is used to determine at least one candidate feature condition corresponding to the vehicle under test based on the road spectrum data.

[0013] The target feature condition determination module is used to determine at least one type of target feature condition based on the at least one type of candidate feature condition and the road spectrum data.

[0014] The test script generation module is used to generate a bench performance test script corresponding to the vehicle under test based on the vehicle start-stop parameters and the at least one type of target characteristic working condition.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute the bench performance test script generation method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the bench performance test script generation method according to any embodiment of the present invention.

[0020] The technical solution of this invention determines the vehicle start-stop parameters corresponding to the target test road conditions based on the road spectrum data of the vehicle under test. Then, it determines at least one candidate characteristic condition corresponding to the vehicle under test based on the road spectrum data. Further, it determines at least one target characteristic condition based on the at least one candidate characteristic condition and the road spectrum data. Finally, it generates a bench performance test script corresponding to the vehicle under test based on the vehicle start-stop parameters and the at least one target characteristic condition. This solves the problems in related technologies where engine durability testing mainly focuses on medium-to-high loads such as torque points and rated points, with little targeted assessment of engine start-stop. Furthermore, durability testing only targets the engine itself and does not consider the impact of motor coupling. This optimizes the vehicle bench durability testing process, shortens the development cycle, reduces R&D costs, and achieves universal applicability to vehicle bench durability testing for different hybrid models.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a bench performance test script generation method according to Embodiment 1 of the present invention;

[0024] Figure 2 This is a schematic diagram of the working condition transition probability matrix provided in Embodiment 1 of the present invention;

[0025] Figure 3 This is a flowchart of a bench performance test script generation method according to Embodiment 2 of the present invention;

[0026] Figure 4 This is a schematic diagram of a bench performance test script generation device according to Embodiment 3 of the present invention;

[0027] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the bench performance test script generation method of this invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Example 1

[0031] Figure 1 This is a flowchart of a test script generation method provided in Embodiment 1 of the present invention. This embodiment is applicable to the construction of test scripts for bench performance testing of any vehicle model. The method can be executed by a test script generation device, which can be implemented in hardware and / or software and can be configured in a terminal and / or server. Figure 1 As shown, the method includes:

[0032] S110. Determine the vehicle start-stop parameters corresponding to the target test road conditions based on the road spectrum data corresponding to the vehicle under the target test road conditions.

[0033] The vehicle to be tested can be any type of vehicle, optionally including hybrid vehicles. The target test road condition can be a road condition that meets the requirements of bench performance testing, or it can be understood as a road condition that presents performance requirements for the vehicle's start-stop durability during vehicle operation. The target test road condition can be any road condition used for vehicle testing; optionally, it can be urban road conditions. In practical applications, vehicles may encounter various start-stop conditions while driving on urban roads, such as pedestrians, other vehicles, traffic lights, or other obstacles. Compared to other types of roads, urban roads include a relatively large number of vehicle start-stop conditions; therefore, urban road conditions can be used as the target test road condition. Road spectrum data can be data generated during vehicle operation. Optionally, road spectrum data can include road spectrum mileage, vehicle engine speed, vehicle engine torque (or throttle opening), vehicle coolant temperature, and electric motor torque. Vehicle start-stop parameters can be parameters related to vehicle start-stop performance. Optionally, vehicle start-stop parameters may include average starting speed, average start duration, average stop duration, average start-stop time interval, and preset number of start-stop cycles during the engine's service life.

[0034] In practical applications, to test a vehicle's start-stop performance under test road conditions, the vehicle to be tested and the target test road conditions with higher requirements for start-stop performance can be determined first. Then, the vehicle to be tested can be controlled to drive on the road surface corresponding to the target test road conditions according to preset test requirements, and vehicle driving data can be collected during the driving process according to a preset data sampling frequency to obtain road spectrum data. Furthermore, the collected road spectrum data can be processed according to a preset vehicle start-stop parameter determination method. Thus, the vehicle start-stop parameters corresponding to the vehicle to be tested under the target test road conditions can be obtained. The preset data sampling frequency can be any frequency, optionally greater than or equal to 10 Hz.

[0035] It should be noted that different vehicle start-stop parameters require different methods of parameter determination. The following will explain the process of determining different vehicle start-stop parameters.

[0036] The first type of vehicle start-stop parameter can be the average starting speed. Optionally, the vehicle start-stop parameters corresponding to the test vehicle under the target test road conditions are determined based on the road spectrum data corresponding to the test vehicle under the target test road conditions, including: determining the number of starts of the test vehicle under the target test road conditions, the starting speed and start duration corresponding to each start process, and the stop interval for each start process based on the engine speed in the road spectrum data; and determining the average starting speed based on the starting speed and number of starts corresponding to each start process.

[0037] In this embodiment, during the test vehicle's operation, the engine speed can be collected, and a vehicle driving curve is generated based on the vehicle's driving time and the engine speed at each time point. The number of starts, the starting speed and duration of each start, and the stopping interval can be determined from the vehicle driving curve in the target test road condition. The number of starts can be understood as the number of times the test vehicle starts and stops in the target test road condition, that is, the number of times the test vehicle stops and restarts within a preset time period in the target test road condition. The starting speed corresponding to the starting process can be the starting end speed, that is, the speed at which the current starting process ends. The starting duration corresponding to the starting process can be the time from the start to the end of the current starting process. The stopping interval can be the time from when the vehicle's engine speed is 0 to when the engine speed is greater than 0.

[0038] In practical applications, when the vehicle under test is driving on the target test road condition, a vehicle driving curve can be generated based on the vehicle's driving time and the corresponding engine speed at each time point. This driving curve can include multiple starting curves, each representing one starting process. Furthermore, the number of starting curves included in the driving curve can be used as the number of starts the vehicle under test has made on the target test road condition. Further, for each starting curve segment in the driving curve, the engine speed in that segment is determined from the last point greater than or equal to 0 until the next extreme point (i.e., the slope of the speed curve is 0 or negative, and the speed is greater than the idle speed), and this segment is used as the vehicle starting curve. The time span of this segment can be used as the starting duration corresponding to the current starting process, and the speed corresponding to the extreme point in this segment can be used as the starting speed corresponding to the current starting process. Therefore, the starting duration and starting speed corresponding to each starting process can be determined using the above method. The time interval between each pair of adjacent starting curves in the driving curve is also determined to obtain multiple time intervals, each of which can be used as a parking interval.

[0039] Furthermore, the starting speeds corresponding to each starting process can be accumulated sequentially to obtain the accumulated starting speed value of the vehicle under test during the entire driving process. Then, the ratio between the accumulated starting speed value and the number of starts can be determined, and this ratio can be used as the average starting speed.

[0040] For example, the average starting speed can be determined based on the following formula:

[0041]

[0042] in, Indicates the average starting speed; n si N represents the starting speed corresponding to each starting process; st Indicates the number of times it has been started.

[0043] The second type of vehicle start-stop parameter can be the average start-up time. Accordingly, the average start-up time is determined based on the start-up time corresponding to each start-up process and the number of starts.

[0044] In practical applications, the starting time corresponding to each starting process can be accumulated sequentially to obtain the cumulative starting time value of the vehicle under test during the entire driving process. Then, the ratio between the cumulative starting time value and the number of starts can be determined, and this ratio can be used as the average starting time.

[0045] For example, the average start-up time can be determined based on the following formula:

[0046]

[0047] in, t represents the average start-up time. si N represents the start-up duration for each start-up process; st Indicates the number of times it has been started.

[0048] The third vehicle start-stop parameter can be the average stopping time. Accordingly, the average stopping time is determined based on the interval between each stop and the number of starts.

[0049] In practical applications, the parking intervals can be accumulated sequentially to obtain the accumulated parking interval value. Then, the ratio between the accumulated parking interval value and the number of starts can be determined, and this ratio can be used as the average parking time.

[0050] For example, the average parking time can be determined based on the following formula:

[0051]

[0052] in, t represents the average parking time; ti Indicates the interval between each stop; N st Indicates the number of times it has been started.

[0053] The fourth vehicle start-stop parameter can be the average start-stop time interval. Accordingly, the average start-stop mileage interval is determined based on the road spectrum mileage and number of starts in the road spectrum data; the average start-stop time interval is determined based on the average vehicle speed and average start-stop mileage interval in the road spectrum data.

[0054] The road spectrum mileage can be the total mileage of the target test road conditions. The road spectrum mileage can be any value, optional, and can be greater than or equal to 200 kilometers. The average start-stop mileage interval can be understood as the mileage interval corresponding to each start-stop process. The average vehicle speed can be the ratio between the road spectrum mileage and the total vehicle travel time.

[0055] In practical applications, the ratio between the road mileage and the number of starts can be used as the average start-stop mileage interval. Furthermore, the ratio between the average start-stop mileage interval and the average vehicle speed can be determined and used as the average start-stop time interval.

[0056] For example, the average start-stop mileage interval can be determined based on the following formula:

[0057]

[0058] in, S0 represents the average start-stop interval; N represents the route spectrum mileage; st Indicates the number of times it has been started.

[0059] Furthermore, the average start-stop time interval can be determined based on the following formula:

[0060]

[0061] Among them, t st Indicates the average start-stop time interval; This indicates the average vehicle speed.

[0062] The fifth type of vehicle start-stop parameter can be a preset number of start-stop cycles during the engine's service life. Accordingly, the preset number of start-stop cycles during the engine's service life is determined based on the preset service life and average start-stop mileage interval corresponding to the vehicle under test.

[0063] The preset service life can be pre-set and is used to characterize the reliability of the vehicle engine. The preset service life can be any value, and can be optional, such as the B10 life. Generally, if the preset service life of the vehicle under test is B10, the engine's service life is 1 million kilometers.

[0064] In practical applications, the preset service life of the vehicle under test can be obtained. Then, the ratio between the preset service life and the average start-stop mileage interval can be determined, and this ratio can be used as the preset number of start-stop cycles during the engine's service life.

[0065] For example, the preset number of start-stop cycles during the engine's service life can be determined based on the following formula:

[0066]

[0067] Where, N B10 Indicates the preset number of start-stop cycles during the engine's service life; S B10 Indicates the preset service life; This indicates the average start-stop mileage interval.

[0068] S120. Determine at least one candidate feature condition corresponding to the vehicle under test based on the road spectrum data.

[0069] Here, candidate feature conditions can be any conditions with distinct start-stop performance characteristics that may be included in the target test road conditions. Correspondingly, the candidate feature condition dataset can be a set of data points that conform to the corresponding candidate feature conditions.

[0070] In practical applications, after obtaining the road spectrum data corresponding to the vehicle under the target test road condition, the road spectrum data can be clustered according to a pre-set clustering algorithm to bring together similar data in the road spectrum data to obtain at least one dataset. Then, at least one type of candidate feature condition included in the target test road condition can be determined based on at least one dataset.

[0071] Optionally, determine at least one candidate feature condition corresponding to the vehicle under test based on the road spectrum data, including: filtering and / or normalizing the road spectrum data to obtain road spectrum data to be processed; clustering each data point in the road spectrum data to be processed according to a preset clustering algorithm to obtain road spectrum data to be applied; classifying the road spectrum data to be applied according to the working condition to obtain a dataset corresponding to at least one candidate feature condition; and determining at least one candidate feature condition based on the dataset corresponding to at least one candidate feature condition.

[0072] In this embodiment, the road spectrum data may include multiple data points, each of which may correspond to multi-dimensional data; that is, each data point may correspond to multiple types of road spectrum data at each time point during vehicle operation. Optionally, each data point may be 4-dimensional data, namely, engine speed, engine torque, motor torque, and engine coolant temperature. For example, for each data point included in the road spectrum data, the corresponding 4-dimensional data can be represented by the following expression:

[0073]

[0074] Where, x i This represents the data points in the road spectrum data; n i Indicates engine speed; M i Indicates engine torque; M i ′ Indicates motor torque; This indicates the engine coolant outlet temperature.

[0075] In practical applications, during the test vehicle's journey on the road surface corresponding to the target test road conditions, vehicle driving parameters at corresponding time points can be collected according to a preset data sampling frequency to obtain multiple data points. Each data point can include multiple types of vehicle driving parameters. Furthermore, road spectrum data can be constructed based on the sampled data points.

[0076] Furthermore, to reduce the impact of transitional operating conditions on clustering, the data corresponding to the engine starting portion of the road spectrum data can be removed to obtain the road spectrum data after removal. Furthermore, since the dimensions of each vehicle driving parameter in the road spectrum data are different—for example, engine speed, engine torque, electric motor torque, and engine coolant temperature have different dimensions—the road spectrum data including these vehicle driving parameters can be normalized to eliminate the influence of dimensions. The normalized road spectrum data can then be used as the road spectrum data to be processed.

[0077] For example, the road spectrum data normalization process can be represented by the following formula:

[0078]

[0079] in, It can represent the smallest data point in the road spectrum data; X can represent the largest data point in the road spectrum data; X can represent the road spectrum data to be processed.

[0080] In this embodiment, after obtaining the road spectrum data to be processed, each data point in the road spectrum data to be processed can be clustered according to a preset clustering algorithm to obtain the road spectrum data to be applied.

[0081] The preset clustering algorithm can be a pre-defined algorithm that performs clustering processing on the road spectrum data to divide the data points included in the road spectrum data into at least one dataset. The preset clustering algorithm can be any algorithm capable of performing data clustering processing. Optionally, the preset clustering algorithm can be the Mean Shift (MS) clustering algorithm.

[0082] Those skilled in the art will understand that the MS clustering algorithm is a mature clustering algorithm, and its basic form can be:

[0083]

[0084] Where, x i Given a d-dimensional Euclidean space R d The formula represents the average of the vectors connecting the data point x to all points within a range of Euclidean radius h. M represents the sum of the values ​​of the vectors connecting the data point x to all points within a range of h. h The endpoint is used as the new center data point x to continue the iteration, which shows that the final M is obtained. h Vectors will converge to the region of highest data density. Therefore, the MS algorithm can group similar data together in a data sample, thus achieving clustering. Considering R... d Within a spatial dimension, points closer to x have a greater influence on the estimated statistical properties around x, while those farther away have a smaller influence. Furthermore, the importance of each sample data point may not be equal; therefore, a kernel function g(x) and weighting coefficients are introduced here. The final form of the extended MS algorithm is as follows:

[0085]

[0086] Where g(x) is the kernel function; h is the bandwidth, i.e., the Euclidean radius of the cluster; ω(x) i ) represents the weighting coefficient; m represents the number of sample data points; x ′ That is, after one MS operation, we obtain M starting from x. h The endpoint of a vector is also the starting point of the next MS operation.

[0087] In practical applications, after obtaining the road spectrum data to be processed, each data point in the road spectrum data can be clustered and converged according to a pre-set clustering algorithm. Then, after each data point in the road spectrum data has been clustered and converged, a new dataset can be formed based on the clustered data points, and this dataset can be used as the road spectrum data to be applied.

[0088] For example, if the preset clustering algorithm is the MS algorithm, after obtaining the road spectrum data X to be processed, MS clustering calculation can be performed on X. First, the first step: the kernel function used is the unit Gaussian kernel function, and the formula can be: The Euclidean radius can be taken as a constant of 0.05, and the weighting coefficient ω(x) i The constant value can be 1. These values ​​can be substituted into the above formula to calculate x. ′ Step 2: Calculate ||x ′ -x‖, obtain the first value. If the first value is less than the preset convergence threshold ε, it can be considered converged. ′ This is the final point after clustering x points, and the loop ends; if the first value is greater than the preset convergence threshold ε, proceed to the next step; third step: [The text abruptly ends here, likely due to an incomplete sentence or a formatting error.] ′ The value is assigned to x, and the first step is executed again. The preset convergence threshold ε can be a constant 0.001. Furthermore, when each point X in X... i After all the clustering calculation results converged, a series of new 4-dimensional data X→X were obtained. ms X can be ms As road spectrum data to be applied.

[0089] Furthermore, after obtaining the road spectrum data to be applied, the road spectrum data can be classified to divide each data point in the road spectrum data into at least one pre-built working condition category, thereby obtaining a dataset corresponding to at least one candidate feature working condition.

[0090] Optionally, the road spectrum data to be applied is classified according to working conditions to obtain a dataset corresponding to at least one type of candidate feature working condition. This includes: for each data point in the road spectrum data to be applied, performing probability density estimation processing on the current data point based on the current data point and a preset Euclidean radius to obtain the probability density distribution corresponding to the current data point; determining the set of data points corresponding to the target data point based on the target probability density in the probability density distribution; if the set of data points meets the preset classification conditions, using the set of data points as the dataset corresponding to the candidate feature working condition, and removing the set of data points from the road spectrum data to be applied; if the road spectrum data to be applied after removal is not an empty set, repeating the steps of probability density estimation for the current data point, determining the set of data points, and removing the set of data points until the road spectrum data to be applied after removal is an empty set, thus obtaining a dataset corresponding to at least one type of candidate feature working condition.

[0091] The preset Euclidean radius can be any value, optionally 0.05. Those skilled in the art will understand that the probability density estimation method is used to estimate the probability density distribution of each data point in a dataset. In practical applications, for each data point in the road spectrum data to be applied, a data point filtering region can be constructed with the current data point as the center and the preset Euclidean radius as the radius. Then, all data points included within this filtering region can be determined in the road spectrum data to be applied, and the probability density distribution corresponding to the current data point can be taken as the total probability density distribution. Furthermore, based on the target data point corresponding to the target probability density in the probability density distribution, the set of data points corresponding to the target data point can be determined.

[0092] Here, the target probability density can be the maximum probability density in the probability density distribution. Correspondingly, the target data point can be the data point corresponding to the target probability density. In practical applications, after determining the target data point, a pre-defined classification Euclidean radius can be obtained. Then, a data point classification region can be constructed with the target data point as the center and the classification Euclidean radius as the radius. Furthermore, all data points included within this classification region can be determined in the road spectrum data to be applied, and these all data points can be used as the data point set corresponding to the target data point. Further, if the data point set meets the preset classification conditions, the data point set is used as the dataset corresponding to the candidate feature condition, and the data point set is removed from the road spectrum data to be applied.

[0093] The preset classification condition can be a pre-set data point condition classification condition. Optionally, the preset classification condition can be that the ratio between the number of data points in the data point set and the number of data points in the road spectrum data to be applied is greater than a preset threshold. The preset threshold can be any value, optionally 0.01. In practical applications, after obtaining the data point set, it can be determined whether the ratio between the number of data points in the data point set and the number of data points in the road spectrum data to be applied is greater than the preset threshold. If the ratio is greater than the preset threshold, it can be determined that the data point set meets the preset classification condition. Therefore, the data point set can be used as the dataset corresponding to the candidate feature condition, and the data point set can be removed from the road spectrum data to be applied. It should be noted that if the data point set does not meet the preset classification condition, it can be considered as discrete points or singular points generated by some transitional conditions and cannot be used as the dataset corresponding to the candidate feature condition. In this case, only the data point set can be removed from the road spectrum data to be applied.

[0094] Furthermore, if the road spectrum data to be applied after elimination is not an empty set, the steps of estimating the probability density of the current data point, determining the data point set, and eliminating the data point set are repeated until the road spectrum data to be applied after elimination is an empty set, thus obtaining a dataset corresponding to at least one type of candidate feature condition.

[0095] Furthermore, at least one type of candidate feature condition can be determined based on the dataset corresponding to at least one type of candidate feature condition.

[0096] Optionally, based on the dataset corresponding to at least one type of candidate feature condition, determine at least one type of candidate feature condition, including: for each type of candidate feature condition, determine the set of mean data points corresponding to the current dataset, and determine the candidate feature condition based on the set of mean data points, so as to obtain at least one type of candidate feature condition.

[0097] In this embodiment, the data included in the dataset corresponding to the candidate feature conditions are normalized data. Therefore, after obtaining at least one dataset, inverse normalization can be performed on each dataset to restore the data points in each dataset to the data points in the road spectrum data. Furthermore, for each restored dataset corresponding to the candidate feature conditions, the current dataset can be averaged to obtain the set of mean data points corresponding to the current dataset. The set of mean data points includes average engine speed, average engine torque, average motor torque, and average engine coolant temperature.

[0098] In practical applications, for each candidate characteristic operating condition, the dataset can be averaged to obtain a set of mean data points. This set can include average engine speed, average engine torque, average motor torque, and average engine outlet water temperature. Furthermore, after obtaining the set of mean data points for each candidate characteristic operating condition, the corresponding candidate characteristic operating condition can be determined based on each set of mean data points; that is, the data included in the set of mean data points is used as the data corresponding to the corresponding candidate characteristic operating condition.

[0099] For example, continuing with the previous example, the process of determining candidate characteristic conditions may include the following steps:

[0100] 1. With X ms Each point in Centered on a point, calculate the data points contained within the Euclidean radius h = 0.05, denoted as . probability density estimation

[0101] 2. Estimation from probability density The largest The classification begins at point Y, with a Euclidean radius of μ = 0.1. Data points within 0.1 of this point are considered to belong to the same class. If the proportion of data points in this class to the total data exceeds a threshold θ = 0.01, this is denoted as Y. i Otherwise, it is denoted as Y0, where Y0 is usually a discrete point or singular point generated by a partial transitional condition in the road spectrum. Here, i represents the i-th classification, and Y... i This represents the dataset corresponding to the i-th type of data, i.e., the candidate feature condition in the i-th category.

[0102] 3. Place Y0 or Y i From X ms After removing the data from the middle, the remaining data is denoted as X. ′ ms If X ′ ms If not empty, then X ′ ms Assign X ms Go back to step 1; otherwise, go to step 4.

[0103] 4. Obtain the array set Y = {Y0, Y1, Y2…Y} k That is, the road spectrum is divided into a total of k+1 classes. Among them, class Y0 is considered as other classes composed of transition points and singular points, which are not considered in subsequent calculations and need to be removed. Therefore, the dataset corresponding to the candidate feature conditions of k classes can be obtained.

[0104] 5. Since the array set Y (after removing Y0) is normalized data, it needs to be restored to the data in the road spectrum by reversing the normalization rules in step four, as shown in the following formula: Y∈[0,1]→y={y1,y2…y k}∈[x min ,x max ]; where y i This represents the dataset after restoring the working conditions of the i-th candidate feature class, where i = 1, 2, ..., k;

[0105] 6. Calculate the mean for each dataset in y, as shown in the following formula: To obtain the set of mean data points for each dataset, the formula is as follows: K = [k1, k2, ..., k k ]; where k i The values ​​represent the average engine speed, average engine torque, average motor torque, and average engine outlet water temperature for the i-th candidate characteristic operating condition.

[0106] At this point, the road spectrum data, after MS clustering and classification, yields K containing k feature data centers, meaning that k candidate feature conditions have been identified from the road spectrum data.

[0107] It should be noted that, specifically, because the computational cost of the MS algorithm is exponentially related to the amount of data, its consumption of computational resources is far greater than that of the K-means algorithm. Therefore, under the same computer hardware level and data volume, the MS algorithm takes much longer to compute than the K-means algorithm, but its clustering accuracy is higher. When the amount of road spectrum data is large, if both improved computational efficiency and good clustering results are required, a compromise method is proposed here, with the following steps: 1. Resample the road spectrum data at a lower sampling frequency, for example, reducing 10Hz to 1Hz; 2. Cluster the resampled road spectrum data using the MS algorithm described above, obtaining k cluster centers; 3. Use these k cluster centers as initial points and substitute them into the K-means algorithm to perform cluster analysis on the original road spectrum data, obtaining k cluster centers again. This compromise algorithm can improve the running efficiency of the clustering algorithm while reducing the error caused by the selection of initial points in the K-means algorithm.

[0108] S130. Based on at least one type of candidate characteristic working condition and road spectrum data, determine at least one type of target characteristic working condition.

[0109] The target characteristic operating condition can be an operating condition related to the vehicle's start-stop durability performance on the test bench. Optionally, the target characteristic operating condition can be an operating condition that occurs immediately after the engine starts during vehicle operation.

[0110] In practical applications, at least one type of candidate feature condition is determined based on road spectrum data generated by the vehicle under test during its journey on the target test road condition. Therefore, there is a temporal order among the at least one type of candidate feature condition. Statistics can be performed based on the temporal order between the road spectrum data and the candidate feature conditions to determine the conversion probability between one type of candidate feature condition and another. Furthermore, at least one target feature condition can be determined from the at least one type of candidate feature condition based on the determined conversion probability.

[0111] Optionally, determining at least one target feature condition based on the at least one type of candidate feature condition and the road spectrum data includes: determining a parking condition from at least one candidate feature condition based on the dataset corresponding to at least one candidate feature condition; constructing a condition transition probability matrix based on at least one candidate feature condition and the road spectrum data; determining at least one pending transition probability corresponding to the parking condition based on the condition transition probability matrix; and, if the pending transition probability meets a preset feature condition standard, using the candidate feature condition corresponding to the transition probability as the target feature condition.

[0112] The parking condition can be understood as the condition where the engine speed and / or engine torque are zero. The condition transition probability matrix can be understood as a matrix storing the transition probabilities between one type of condition and another. The transition probability can be understood as the percentage of times one type of condition transitions to another. The transition probability to be processed is the probability of the parking condition transitioning to a candidate feature condition. The preset feature condition standard can be a pre-set standard used to filter feature conditions. Optionally, the preset feature condition standard can be a transition probability greater than a preset threshold. The preset threshold can be 0.

[0113] In practical applications, at least one type of candidate feature condition can be understood as the feature conditions encountered by the test vehicle during its journey through the target test road condition. Therefore, the dataset corresponding to at least one type of candidate feature condition can be understood as the dataset obtained by classifying the road spectrum data corresponding to the test vehicle under the target test road condition. Furthermore, the data in the dataset corresponding to the candidate feature condition has a one-to-one mapping relationship with the road spectrum data. Therefore, in the road spectrum data, statistics can be performed according to the time series to determine the proportion of candidate feature conditions that convert from the earlier to the later candidate feature condition between two adjacent time-series candidate feature conditions, i.e., the conversion probability. For example, as shown... Figure 2 The diagram shown is a schematic representation of the operating condition transition probability matrix. Figure 2 It can be seen that the target test road conditions include k candidate feature conditions, namely k1, k2, ..., k i ,k j …,k k , of which Sij It can represent the k-th i Candidate feature conditions are converted to the kth class. j The proportion of candidate feature conditions, i.e., the conversion probability.

[0114] Furthermore, a parking condition can be determined from at least one candidate feature condition based on the engine speed and / or engine torque in the dataset corresponding to at least one candidate feature condition. Then, after obtaining the condition transition probability matrix, the transition probability of the parking condition transforming into other candidate feature conditions can be determined based on the condition transition probability matrix, resulting in at least one transition probability to be processed. Then, each transition probability to be processed can be judged according to a preset feature condition standard to determine whether the transition probability to be processed meets the preset feature condition standard. Finally, if it is determined that the transition probability to be processed meets the preset feature condition standard, the candidate feature condition corresponding to that transition probability can be determined as the target feature condition.

[0115] For example, continue to refer to Figure 2 Assume k i The candidate feature condition is the parking condition, which can be determined by k. i The conversion probability of a candidate feature condition transforming into another candidate feature condition is extracted, that is, the probability of transforming a candidate feature condition into another candidate feature condition is extracted. Figure 2 Chinese K i Extracting the row element corresponding to the candidate feature case of class k will yield the result. i The k unprocessed transformation probabilities corresponding to the candidate feature conditions are S, respectively. i1 ,S i2 ,…,S ij ,…,S ik Furthermore, it can be determined whether the probability of each transformation to be processed is greater than 0. If S ib >0, then k b Candidate characteristic working conditions are used as target characteristic working conditions. Assuming that q target characteristic working conditions are selected from k candidate characteristic working conditions, the target characteristic working condition set P = [p1, p2, ..., p...] can be obtained. q ], where p i It can represent the target characteristic working condition.

[0116] S140. Generate a bench performance test script for the vehicle under test based on the vehicle start-stop parameters and at least one target characteristic condition.

[0117] The bench performance test script can be a script for testing the bench performance of the vehicle under test under start-stop conditions. In this embodiment, the bench performance test script may include a start-stop durability cycle framework.

[0118] In practical applications, in order to reproduce the actual road conditions of the vehicle as much as possible, bench performance test scripts can be compiled based on the vehicle's start-stop parameters and at least one target characteristic condition to test the bench performance of the vehicle under start-stop conditions.

[0119] Optionally, based on the vehicle start-stop parameters and the at least one type of target characteristic operating condition, a bench performance test script corresponding to the vehicle under test is generated, including: determining the number of bench test start-stops and the total bench performance test duration based on the average start-stop time interval in the vehicle start-stop parameters, the preset number of start-stops during the engine's service life, and the pre-set bench start-stop interval; constructing a bench performance test loop framework based on the vehicle start-stop parameters and the at least one type of target characteristic operating condition, and generating a bench performance test script based on the bench performance test loop framework, the number of bench test start-stops, and the total bench performance test duration.

[0120] In this embodiment, the start-stop interval of the test bench can be any value, optionally ranging from 60 seconds to 90 seconds.

[0121] It should be noted that, although the preset number of start-stop cycles N during the engine's service life has been determined... B10 However, considering bench resources and time factors, it is difficult to fully verify N. B10 Since there are multiple start-stop cycles, an acceleration factor can be introduced to reduce the number of start-stop tests on the bench.

[0122] In practical applications, the ratio between the average start-stop time interval in the vehicle start-stop parameters and the preset bench start-stop interval can be determined, and this ratio can be used as an acceleration factor. Then, the ratio between the preset number of start-stop cycles during the engine's lifespan and the acceleration factor can be determined, and this ratio can be used as the number of bench test start-stop cycles. Finally, the product of the number of bench test start-stop cycles and the bench start-stop interval can be determined, and this product can be used as the total bench performance test duration.

[0123] For example, the number of start-stop cycles and the total duration of bench performance testing can be determined based on the following formula:

[0124]

[0125] Where β can represent the acceleration factor; t st It can represent the average start-stop time interval; t can represent the start-stop interval of the test bench.

[0126]

[0127] Where N can represent the number of start-stop cycles during bench testing; N B10 It can indicate the preset number of start-stop cycles during the engine's service life.

[0128] T = N × t

[0129] Where T can represent the total duration of bench performance testing.

[0130] Furthermore, a bench performance test cycle framework can be constructed based on vehicle start-stop parameters and at least one target characteristic condition. The entire bench performance test cycle can include multiple sub-cycles, each of which includes three parts: starting condition, target characteristic condition, and stopping condition. For the starting condition, it can be constructed based on the vehicle start-stop parameters. Specifically, the engine's final starting speed in the starting condition can be kept consistent with or as close as possible to the average starting speed in the vehicle start-stop parameters, and the starting time can be kept consistent with or as close as possible to the average starting time in the vehicle start-stop parameters. For the stopping condition, the larger value between the average stopping time in the vehicle start-stop parameters and the preset stopping time can be determined, and this value can be used as the stopping time for the stopping condition. The preset stopping time can be any value, optionally 30 seconds. The advantage of this setting is that it ensures that the engine oil in the main oil passage can essentially return to the oil pan. Furthermore, for each sub-cycle, excluding the starting and stopping conditions, all other times within the sub-cycle constitute the target characteristic condition. That is, at the time corresponding to the target characteristic condition, the vehicle's driving parameters can be set according to the data in the set of average data points corresponding to the target characteristic condition. In other words, when in the target characteristic condition, the vehicle's driving parameters can be set according to the average engine speed, average engine torque, average electric motor torque, and average engine coolant temperature corresponding to the target characteristic condition. It should be noted that each sub-cycle includes only one target characteristic condition. The target characteristic conditions appearing in the sub-cycles throughout the entire bench performance test cycle should traverse all determined target characteristic conditions.

[0131] Furthermore, after obtaining the bench performance test cycle framework, a bench performance test script can be generated based on the number of bench test start-stop cycles, the total bench performance test duration, and the bench performance test cycle framework. Thus, a bench start-stop durability test can be performed on the vehicle according to the bench performance test script. If the test result is good, the test can be terminated; if the test result is not good, the bench performance test script can be further optimized until the test result corresponding to the optimized bench performance test script is good. Durability testing is conducted according to the bench performance test script provided in this embodiment of the invention. Based on the analysis of the durability operation process and engine disassembly and inspection, the hybrid engine vehicle strategy can be optimized and adjusted, such as optimizing the start-up time and start-up speed, and the charging and discharging logic of the electric motor after engine start-up. This also provides guidance for the optimization and improvement of the engine friction pairs. After the hybrid strategy and friction pair optimization are completed, road tests and road spectrum collection need to be conducted again. The road spectrum data is then re-analyzed, and a new bench start-stop durability cycle is formulated to verify the effectiveness of the optimization and improvement.

[0132] The technical solution of this invention determines the vehicle start-stop parameters corresponding to the target test road conditions based on the road spectrum data of the vehicle under test. Then, it determines at least one candidate characteristic condition corresponding to the vehicle under test based on the road spectrum data. Further, it determines at least one target characteristic condition based on the at least one candidate characteristic condition and the road spectrum data. Finally, it generates a bench performance test script corresponding to the vehicle under test based on the vehicle start-stop parameters and the at least one target characteristic condition. This solves the problems in related technologies where engine durability testing mainly focuses on medium-to-high loads such as torque points and rated points, with little targeted assessment of engine start-stop. Furthermore, durability testing only targets the engine itself and does not consider the impact of motor coupling. This optimizes the vehicle bench durability testing process, shortens the development cycle, reduces R&D costs, and achieves universal applicability to vehicle bench durability testing for different hybrid models.

[0133] Example 2

[0134] Figure 3 This is a flowchart of a bench performance test script generation method provided in Embodiment 2 of the present invention. This embodiment is an optional embodiment of the above embodiments. Figure 3 As shown, the method of this embodiment of the invention may include the following steps:

[0135] 1. Determine the object to be tested (the vehicle or engine to be tested);

[0136] 2. Obtain the road spectrum data of the object to be tested under the target test road conditions;

[0137] 3. Calculate the starting time and starting speed;

[0138] 4. Remove the starting portion of the road spectrum data to obtain the road spectrum data to be processed;

[0139] 5. Determine if the amount of road spectrum data to be processed is too large. If yes, proceed to step 6; otherwise, proceed to step 9.

[0140] 6. Reduce the frequency of the road spectrum data to be processed and resample it;

[0141] 7. Perform MS clustering calculations on the processed data;

[0142] 8. Substitute the calculation results into the K-means to re-cluster the road spectrum data to be processed, and obtain k candidate feature conditions;

[0143] 9. Perform MS clustering calculation on the road spectrum data to be processed to obtain k candidate feature conditions;

[0144] 10. Calculate the probability matrix of mutual transformation between k candidate characteristic working conditions;

[0145] 11. Obtain the target characteristic operating conditions after the engine starts;

[0146] 12. Based on road spectrum data, determine the average stopping time, the preset number of start-stop cycles during the engine's service life, introduce an acceleration factor, and determine the number of start-stop cycles in bench testing and the total duration of bench performance testing;

[0147] 13. Develop a bench start-stop durability cycle framework to obtain a bench performance test script;

[0148] 14. Conduct a durability test to determine if the test results are satisfactory. If yes, the process ends; otherwise, proceed to step 15.

[0149] 15. Optimize hybrid strategy and friction pair to optimize bench performance test scripts.

[0150] The technical solution of this invention determines the vehicle start-stop parameters corresponding to the target test road conditions based on the road spectrum data of the vehicle under test. Then, it determines at least one candidate characteristic condition corresponding to the vehicle under test based on the road spectrum data. Further, it determines at least one target characteristic condition based on the at least one candidate characteristic condition and the road spectrum data. Finally, it generates a bench performance test script corresponding to the vehicle under test based on the vehicle start-stop parameters and the at least one target characteristic condition. This solves the problems in related technologies where engine durability testing mainly focuses on medium-to-high loads such as torque points and rated points, with little targeted assessment of engine start-stop. Furthermore, durability testing only targets the engine itself and does not consider the impact of motor coupling. This optimizes the vehicle bench durability testing process, shortens the development cycle, reduces R&D costs, and achieves universal applicability to vehicle bench durability testing for different hybrid models.

[0151] Example 3

[0152] Figure 4 This is a schematic diagram of a bench performance test script generation device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: a parameter determination module 310, a candidate feature condition determination module 320, a target feature condition determination module 330, and a test script generation module 340.

[0153] The parameter determination module 310 is used to determine the vehicle start-stop parameters of the vehicle under the target test road condition based on the road spectrum data corresponding to the vehicle under the target test road condition; the candidate feature condition determination module 320 is used to determine at least one candidate feature condition corresponding to the vehicle under the test based on the road spectrum data; the target feature condition determination module 330 is used to determine at least one target feature condition based on the at least one candidate feature condition and the road spectrum data; and the test script generation module 340 is used to generate a bench performance test script corresponding to the vehicle under the test based on the vehicle start-stop parameters and the at least one target feature condition.

[0154] The technical solution of this invention determines the vehicle start-stop parameters corresponding to the target test road conditions based on the road spectrum data of the vehicle under test. Then, it determines at least one candidate characteristic condition corresponding to the vehicle under test based on the road spectrum data. Further, it determines at least one target characteristic condition based on the at least one candidate characteristic condition and the road spectrum data. Finally, it generates a bench performance test script corresponding to the vehicle under test based on the vehicle start-stop parameters and the at least one target characteristic condition. This solves the problems in related technologies where engine durability testing mainly focuses on medium-to-high loads such as torque points and rated points, with little targeted assessment of engine start-stop. Furthermore, durability testing only targets the engine itself and does not consider the impact of motor coupling. This optimizes the vehicle bench durability testing process, shortens the development cycle, reduces R&D costs, and achieves universal applicability to vehicle bench durability testing for different hybrid models.

[0155] Optionally, the vehicle start-stop parameters include average starting speed, average starting time, and average stopping time;

[0156] Accordingly, the parameter determination module 310 includes: a start count determination unit, an average start speed determination unit, an average start time determination unit, and an average stop time determination unit.

[0157] The start count determination unit is used to determine the number of starts of the vehicle under test in the target test road condition, the starting speed and start time corresponding to each start process, and the stopping interval for each start process based on the engine speed in the road spectrum data.

[0158] An average starting speed determination unit is used to determine the average starting speed based on the starting speed corresponding to each starting process and the number of starts; and...

[0159] An average start-up time determination unit is configured to determine the average start-up time based on the start-up time corresponding to each start-up process and the number of start-ups; and...

[0160] An average parking time determination unit is used to determine the average parking time based on the parking interval and the number of starts.

[0161] Optionally, the vehicle start-stop parameters may also include the average start-stop time interval and the preset number of start-stop cycles during the engine's service life;

[0162] Correspondingly, the parameter determination module 310 includes: an average start-stop mileage interval determination unit, an average start-stop time interval determination unit, and a start-stop count determination unit.

[0163] The average start-stop mileage interval determination unit is used to determine the average start-stop mileage interval based on the road spectrum mileage in the road spectrum data and the number of starts;

[0164] An average start-stop time interval determination unit is used to determine the average start-stop time interval based on the average vehicle speed and the average start-stop mileage interval in the road spectrum data.

[0165] The start-stop count determination unit is used to determine the preset number of start-stop cycles during the engine's service life based on the preset service life corresponding to the vehicle under test and the average start-stop mileage interval.

[0166] Optionally, the candidate feature condition determination module 320 includes: a data filtering processing unit, a data clustering processing unit, a data classification processing unit, and a candidate feature condition determination unit.

[0167] A data filtering and processing unit is used to filter and / or normalize the road spectrum data to obtain road spectrum data to be processed; wherein, the road spectrum data includes multiple data points, and the data corresponding to the data points is a multivariate set, which includes engine speed, engine torque, motor torque and engine outlet water temperature.

[0168] The data clustering processing unit is used to cluster each data point in the road spectrum data to be processed according to a preset clustering algorithm to obtain the road spectrum data to be applied.

[0169] A data classification and processing unit is used to classify the road spectrum data to be applied according to the working conditions to obtain a dataset corresponding to the at least one type of candidate feature working condition.

[0170] The candidate feature condition determination unit is used to determine at least one type of candidate feature condition based on the dataset corresponding to at least one type of candidate feature condition.

[0171] Optionally, the data classification processing unit includes: a probability density estimation processing subunit, a data point set determination subunit, a dataset determination subunit, and a step repetition execution subunit.

[0172] The probability density estimation processing subunit is used to perform probability density estimation processing on each data point in the road spectrum data to be applied, based on the current data point and a preset Euclidean radius, to obtain the probability density estimation distribution corresponding to the current data point.

[0173] The data point set determination subunit is used to determine the data point set corresponding to the target data point based on the target data point corresponding to the target probability density in the probability density estimation distribution.

[0174] The dataset determination subunit is used to, when the set of data points meets the preset classification conditions, use the set of data points as the dataset corresponding to the candidate feature condition, and remove the set of data points from the road spectrum data to be applied;

[0175] The step repeat execution subunit is used to repeatedly execute the steps of probability density estimation of the data points, determination of the data point set, and data point set removal when the road spectrum data to be applied after removal is not an empty set, until the road spectrum data to be applied after removal is an empty set, thereby obtaining the dataset corresponding to the at least one type of candidate feature condition.

[0176] Optionally, the candidate feature condition determination unit is specifically used to determine the set of mean data points corresponding to the current dataset for each type of candidate feature condition, and to determine the candidate feature condition based on the set of mean data points, so as to obtain the at least one type of candidate feature condition; wherein, the set of mean data points includes average engine speed, average engine torque, average motor torque and average engine outlet water temperature.

[0177] Optionally, the target characteristic working condition determination module 330 includes: a working condition transformation probability matrix construction unit and a target characteristic working condition determination unit.

[0178] The working condition transition probability matrix construction unit is used to determine the parking condition from the at least one type of candidate feature working condition based on the dataset corresponding to the at least one type of candidate feature working condition, and to construct the working condition transition probability matrix based on the at least one type of candidate feature working condition and the road spectrum data.

[0179] The target feature condition determination unit is used to determine at least one pending conversion probability corresponding to the parking condition based on the condition conversion probability matrix, and to take the candidate feature condition corresponding to the conversion probability as the target feature condition if the pending conversion probability meets the preset feature condition standard; wherein, the pending conversion probability is the conversion probability of the parking condition being converted into the candidate feature condition.

[0180] Optionally, the test script generation module 340 includes: a bench test start / stop count determination unit and a bench performance test script generation unit.

[0181] The bench test start-stop number determination unit is used to determine the bench test start-stop number and the total bench performance test duration based on the average start-stop time interval in the vehicle start-stop parameters, the preset start-stop number during the engine service life, and the pre-set bench start-stop interval.

[0182] The bench performance test script generation unit is used to construct a bench performance test loop framework based on the vehicle start-stop parameters and at least one type of target characteristic working condition, and to generate the bench performance test script based on the bench performance test loop framework, the number of bench test start-stops, and the total bench performance test duration.

[0183] The bench performance test script generation device provided in this embodiment of the invention can execute the bench performance test script generation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0184] Example 4

[0185] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0186] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0187] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0188] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as bench performance test script generation methods.

[0189] In some embodiments, the bench performance test script generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the bench performance test script generation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the bench performance test script generation method by any other suitable means (e.g., by means of firmware).

[0190] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0191] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0192] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0193] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0194] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0195] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0196] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0197] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for generating bench performance test scripts, characterized in that, include: The vehicle start-stop parameters of the vehicle under test under the target test road conditions are determined based on the road spectrum data corresponding to the vehicle under test under the target test road conditions. Based on the road spectrum data, at least one candidate characteristic condition corresponding to the vehicle under test is determined; Based on the at least one candidate characteristic condition and the road spectrum data, at least one target characteristic condition is determined; Based on the vehicle start-stop parameters and the at least one target characteristic operating condition, generate the bench performance test script corresponding to the vehicle to be tested; The step of determining at least one candidate feature condition corresponding to the vehicle under test based on the road spectrum data includes: filtering and / or normalizing the road spectrum data to obtain road spectrum data to be processed; wherein, the road spectrum data includes multiple data points, and the data corresponding to each data point is a tuple, the tuple including engine speed, engine torque, motor torque, and engine coolant temperature; clustering each data point in the road spectrum data to be processed according to a preset clustering algorithm to obtain road spectrum data to be applied; classifying the road spectrum data to be applied according to the operating conditions to obtain a dataset corresponding to the at least one candidate feature condition; and determining at least one candidate feature condition based on the dataset corresponding to the at least one candidate feature condition. The step of determining at least one target feature condition based on the at least one candidate feature condition and the road spectrum data includes: determining a parking condition from the at least one candidate feature condition based on the dataset corresponding to the at least one candidate feature condition; constructing a condition conversion probability matrix based on the at least one candidate feature condition and the road spectrum data; determining at least one pending conversion probability corresponding to the parking condition based on the condition conversion probability matrix; and, if the pending conversion probability meets a preset feature condition standard, using the candidate feature condition corresponding to the conversion probability as the target feature condition; wherein, the pending conversion probability is the conversion probability of the parking condition being converted into a candidate feature condition.

2. The method according to claim 1, characterized in that, The vehicle start-stop parameters include average starting speed, average start-up time, and average stopping time; Accordingly, determining the vehicle start-stop parameters of the vehicle under test under the target test road condition based on the road spectrum data of the vehicle under test under the target test road condition includes: The number of starts of the vehicle under test in the target test road condition, the starting speed and start time corresponding to each start process, and the stop interval are determined based on the engine speed in the road spectrum data. The average starting speed is determined based on the starting speed corresponding to each starting process and the number of starts; and... The average start-up time is determined based on the start-up time corresponding to each start-up process and the number of starts; and... The average parking time is determined based on the parking interval and the number of starts.

3. The method according to claim 2, characterized in that, The vehicle start-stop parameters also include the average start-stop time interval and the preset number of start-stop cycles during the engine's service life; Accordingly, determining the vehicle start-stop parameters of the vehicle under test under the target test road condition based on the road spectrum data of the vehicle under test under the target test road condition includes: The average start-stop mileage interval is determined based on the road spectrum mileage in the road spectrum data and the number of starts. The average start-stop time interval is determined based on the average vehicle speed in the road spectrum data and the average start-stop mileage interval. The preset number of start-stop cycles during the engine's service life is determined based on the preset service life corresponding to the vehicle under test and the average start-stop mileage interval.

4. The method according to claim 1, characterized in that, The step of classifying the road spectrum data to be applied to obtain the dataset corresponding to the at least one candidate feature condition includes: For each data point in the road spectrum data to be applied, the probability density estimation process is performed on the current data point based on the current data point and the preset Euclidean radius to obtain the probability density estimation distribution corresponding to the current data point. Based on the target data points corresponding to the target probability density in the probability density estimation distribution, determine the set of data points corresponding to the target data points; If the set of data points meets the preset classification conditions, the set of data points is used as the dataset corresponding to the candidate feature condition, and the set of data points is removed from the road spectrum data to be applied. If the road spectrum data to be applied after elimination is not an empty set, repeat the steps of probability density estimation of the data points, determination of the data point set, and elimination of the data point set until the road spectrum data to be applied after elimination is an empty set, and obtain the dataset corresponding to the at least one candidate feature condition.

5. The method according to claim 1, characterized in that, The step of determining at least one candidate feature condition based on the dataset corresponding to at least one candidate feature condition includes: For each candidate characteristic operating condition, a set of mean data points corresponding to the current dataset is determined, and candidate characteristic operating conditions are determined based on the set of mean data points to obtain the at least one candidate characteristic operating condition; wherein, the set of mean data points includes average engine speed, average engine torque, average motor torque, and average engine outlet water temperature.

6. The method according to claim 1, characterized in that, The step of generating a bench performance test script for the vehicle under test based on the vehicle start-stop parameters and the at least one target characteristic condition includes: Based on the average start-stop time interval in the vehicle start-stop parameters, the preset number of start-stops during the engine's service life, and the pre-set bench start-stop interval, determine the number of bench test start-stops and the total bench performance test duration. Based on the vehicle start-stop parameters and at least one target characteristic condition, a bench performance test loop framework is constructed, and a bench performance test script is generated based on the bench performance test loop framework, the number of bench test start-stops, and the total bench performance test duration.

7. A bench performance test script generation device, characterized in that, include: The parameter determination module is used to determine the vehicle start-stop parameters of the vehicle under test under the target test road condition based on the road spectrum data corresponding to the vehicle under test under the target test road condition. The candidate feature condition determination module is used to determine at least one candidate feature condition corresponding to the vehicle under test based on the road spectrum data. The target feature condition determination module is used to determine at least one target feature condition based on the at least one candidate feature condition and the road spectrum data. The test script generation module is used to generate a bench performance test script for the vehicle under test based on the vehicle start-stop parameters and the at least one target characteristic condition. The candidate feature condition determination module includes: a data filtering processing unit, a data clustering processing unit, a data classification processing unit, and a candidate feature condition determination unit. The data filtering processing unit is used to filter and / or normalize the road spectrum data to obtain road spectrum data to be processed. The road spectrum data includes multiple data points, and the data corresponding to each data point is a tuple, which includes engine speed, engine torque, motor torque, and engine coolant temperature. The data clustering processing unit is used to cluster each data point in the road spectrum data to be processed according to a preset clustering algorithm to obtain road spectrum data to be applied. The data classification processing unit is used to classify the road spectrum data to be applied according to operating conditions to obtain a dataset corresponding to the at least one candidate feature condition. The candidate feature condition determination unit is used to determine at least one candidate feature condition based on the dataset corresponding to the at least one candidate feature condition. The target feature condition determination module includes: a condition transition probability matrix construction unit and a target feature condition determination unit; the condition transition probability matrix construction unit is used to determine the parking condition from the at least one candidate feature condition based on the dataset corresponding to the at least one candidate feature condition, and to construct a condition transition probability matrix based on the at least one candidate feature condition and the road spectrum data; the target feature condition determination unit is used to determine at least one pending conversion probability corresponding to the parking condition based on the condition transition probability matrix, and to take the candidate feature condition corresponding to the conversion probability as the target feature condition if the pending conversion probability meets the preset feature condition standard; wherein, the pending conversion probability is the conversion probability of the parking condition being converted into the candidate feature condition.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the bench performance test script generation method according to any one of claims 1-6.

Images