Parameter identification method and device, electronic equipment and storage medium

Abstract

The invention provides a parameter identification method and device, electronic equipment and a storage medium, and relates to the technical field of vehicles, and the method comprises the steps: obtaining the real vehicle data of a to-be-tested vehicle, and extracting the input data meeting a preset test condition from the real vehicle data; according to the input data, parameter identification processing is carried out through an optimization algorithm and a vehicle sliding resistance algorithm, and sliding resistance parameters are obtained; performing parameter identification processing through an optimization algorithm and a motor torsional vibration algorithm according to the sliding resistance parameter and the input data to obtain a motor torsional vibration parameter; and determining a motor torsional vibration parameter and the sliding resistance parameter as input parameters corresponding to the to-be-tested vehicle. Compared with the prior art, the input parameters corresponding to the to-be-tested vehicle are acquired, so that the input parameters can accurately reflect the state of the to-be-tested vehicle, the consistency between the HIL test result and the to-be-tested vehicle is improved, and the test accuracy and effectiveness of the to-be-tested vehicle are improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, and particularly relates to a parameter identification method and device, electronic equipment and storage medium. BACKGROUND

[0002] At present, the mainstream software test of the vehicle industry is hardware-in-the-loop (HIL) test. The HIL test combines real vehicle controllers and sensors with virtual vehicle models to simulate real driving scenarios and test the performance of the vehicle control system. Meanwhile, when performing the HIL test, the input parameters of the vehicle need to be determined through a controlled object model and input into the simulation model in the controlled object model to perform simulation test of the vehicle. Since the controlled object model used in the current stage of HIL test is a vehicle dynamics physical model, the response followability of the vehicle dynamics physical model and the steady-state error compared with the real vehicle have a great influence on the accuracy and effectiveness of the vehicle test process.

[0003] However, the existing controlled object model mostly adopts a simplified vehicle dynamics physical model scheme. Since there are differences between individual vehicles, the existing controlled object model cannot cover all individual vehicles and cannot ensure whether the input parameters of the vehicle can truly reflect the vehicle state, resulting in a large error between the HIL test result and the running condition of the real vehicle, and the simulation of the real vehicle running condition cannot be completed, which reduces the accuracy and effectiveness of the vehicle test process. SUMMARY

[0004] The present disclosure provides a parameter identification method and device, electronic equipment and storage medium. The main purpose is to solve the problem that the existing controlled object model cannot cover all individual vehicles, cannot ensure whether the input parameters of the simulation model can truly reflect the vehicle state, results in a large error between the HIL test result and the running condition of the real vehicle, and the simulation of the real vehicle running condition cannot be completed, which reduces the accuracy and effectiveness of the vehicle test process.

[0005] According to a first aspect of the present disclosure, a parameter identification method is provided, which comprises:

[0006] obtaining real vehicle data of a vehicle to be tested, and extracting input data satisfying a preset test condition from the real vehicle data, wherein the real vehicle data at least contains vehicle speed and motor speed of the vehicle to be tested;

[0007] According to the input data, parameter identification processing is performed by an optimization algorithm and a vehicle sliding resistance algorithm to obtain a sliding resistance parameter, and according to the sliding resistance parameter and the input data, a simulation vehicle speed of the vehicle to be tested is calculated by a preset speed algorithm; wherein the parameter identification processing at least includes parameter calculation and parameter optimization, and the optimization algorithm is used for parameter optimization processing of the sliding resistance parameter;

[0008] In the case that the difference between the simulation vehicle speed and the vehicle speed is less than a first preset difference threshold, parameter identification processing is performed by the optimization algorithm and a motor torsional vibration algorithm according to the sliding resistance parameter and the input data to obtain a motor torsional vibration parameter, and according to the motor torsional vibration parameter and the input data, a simulation rotational speed of the vehicle to be tested is calculated by a preset rotational speed algorithm; wherein the optimization algorithm is used for parameter optimization processing of the motor torsional vibration parameter;

[0009] In the case that the difference between the simulation rotational speed and the motor rotational speed is less than a second preset difference threshold, the motor torsional vibration parameter and the sliding resistance parameter are determined as the input parameters corresponding to the vehicle to be tested.

[0010] Optionally, the obtaining of the real vehicle data of the vehicle to be tested comprises:

[0011] The vehicle data of the vehicle to be tested in different driving scenes is screened through a shadow mode, and the vehicle data is determined as the real vehicle data.

[0012] Optionally, the screening of the vehicle data of the vehicle to be tested in different driving scenes through the shadow mode and the determination of the vehicle data as the real vehicle data comprises:

[0013] The driving information corresponding to each driving scene of the vehicle to be tested is obtained;

[0014] The simulation driving information corresponding to each driving scene of the vehicle to be tested is calculated by a preset simulation algorithm;

[0015] The driving information and the simulation driving information are compared, and whether the driving information and the simulation driving information corresponding to the same driving scene are the same is determined according to the comparison result;

[0016] In the case that the driving information and the simulation driving information corresponding to the same driving scene are not the same, the vehicle data of the vehicle to be tested in the driving scene corresponding to the simulation driving information is obtained, and the vehicle data is determined as the real vehicle data.

[0017] Optionally, after calculating the simulation vehicle speed of the vehicle to be tested according to the input data and the sliding resistance parameter through a preset speed algorithm, the method further comprises:

[0018] calculating the difference between the simulation vehicle speed and the vehicle speed;

[0019] in the case that the difference between the simulation vehicle speed and the vehicle speed is greater than or equal to the first preset difference threshold, re-performing the parameter identification processing according to the input data through the optimization algorithm and the vehicle sliding resistance algorithm.

[0020] Optionally, after calculating the simulation motor speed of the vehicle to be tested according to the input data and the motor torsional vibration parameter through a preset speed algorithm, the method further comprises:

[0021] calculating the difference between the simulation motor speed and the motor speed;

[0022] in the case that the difference between the simulation motor speed and the motor speed is greater than or equal to the second preset difference threshold, re-performing the parameter identification processing according to the input data through the optimization algorithm and the motor torsional vibration algorithm.

[0023] Optionally, after determining the motor torsional vibration parameter and the sliding resistance parameter as the input parameter corresponding to the vehicle to be tested, the method further comprises:

[0024] inputting the input parameter and the input data into a preset simulation model, performing simulation test on the vehicle to be tested, and obtaining a test result.

[0025] According to a second aspect of the present disclosure, a parameter identification device is provided, comprising:

[0026] an acquisition unit configured to acquire real vehicle data of a vehicle to be tested;

[0027] an extraction unit configured to extract input data satisfying a preset test condition from the real vehicle data, the real vehicle data at least containing vehicle speed and motor speed of the vehicle to be tested;

[0028] an identification unit configured to perform parameter identification processing according to the input data through an optimization algorithm and a vehicle sliding resistance algorithm, and obtain a sliding resistance parameter;

[0029] a calculation unit configured to calculate simulation vehicle speed of the vehicle to be tested according to the input data and the sliding resistance parameter through a preset speed algorithm; wherein the parameter identification processing at least contains parameter calculation and parameter optimization, and the optimization algorithm is used for parameter optimization processing of the sliding resistance parameter;

[0030] The identification unit is further configured to, in a case where a difference between the simulated vehicle speed and the vehicle speed is less than a first preset difference threshold, perform parameter identification processing on the input data by using the optimization algorithm and a motor torsional vibration algorithm to obtain a motor torsional vibration parameter.

[0031] The calculation unit is further configured to calculate a simulated rotational speed of the vehicle to be tested by using a preset rotational speed algorithm according to the motor torsional vibration parameter and the input data, wherein the optimization algorithm is configured to perform parameter optimization processing on the motor torsional vibration parameter.

[0032] The determination unit is configured to, in a case where a difference between the simulated rotational speed and the motor rotational speed is less than a second preset difference threshold, determine the motor torsional vibration parameter and the coasting resistance parameter as the input parameters corresponding to the vehicle to be tested.

[0033] Optionally, the acquisition unit is further configured to filter vehicle data of the vehicle to be tested in different driving scenes by using a shadow mode, and determine the vehicle data as the real vehicle data.

[0034] Optionally, the acquisition unit comprises:

[0035] The acquisition module is configured to acquire driving information corresponding to each driving scene of the vehicle to be tested.

[0036] The calculation module is configured to calculate simulated driving information corresponding to each driving scene of the vehicle to be tested by using a preset simulation algorithm.

[0037] The comparison module is configured to compare the driving information with the simulated driving information, and determine whether the driving information and the simulated driving information corresponding to a same driving scene are the same according to a comparison result.

[0038] The acquisition module is further configured to, in a case where the driving information and the simulated driving information corresponding to a same driving scene are not the same, acquire the vehicle data of the vehicle to be tested in the driving scene corresponding to the simulated driving information, and determine the vehicle data as the real vehicle data.

[0039] Optionally, the calculation unit is further configured to calculate a difference between the simulated vehicle speed and the vehicle speed.

[0040] The identification unit is further configured to, in a case where the difference between the simulated vehicle speed and the vehicle speed is greater than or equal to the first preset difference threshold, perform parameter identification processing on the input data by using the optimization algorithm and the vehicle coasting resistance algorithm again.

[0041] Optionally, the computing unit is further configured to calculate a difference between the simulated rotating speed and the motor rotating speed.

[0042] The identification unit is further configured to, in a case that the difference between the simulated rotating speed and the motor rotating speed is greater than or equal to the second preset difference threshold, perform parameter identification processing according to the coasting resistance parameter and the input data by the optimization algorithm and the motor torsional vibration algorithm again.

[0043] Optionally, the device further comprises:

[0044] The input unit is configured to input the input parameter and the input data into a preset simulation model, perform simulation testing on the vehicle to be tested, and obtain a test result.

[0045] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0046] at least one processor; and

[0047] a memory connected with the at least one processor; wherein

[0048] 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 perform the method of the first aspect.

[0049] According to a fourth aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to perform the method of the first aspect.

[0050] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of the first aspect.

[0051] The method and device for parameter identification, the electronic device and the storage medium provided by the present disclosure obtain real vehicle data of a vehicle to be tested, and extract input data satisfying a preset test condition from the real vehicle data, wherein the real vehicle data at least includes vehicle speed and motor speed of the vehicle to be tested; parameter identification processing is performed on the input data by using an optimization algorithm and a vehicle coasting resistance algorithm to obtain a coasting resistance parameter, and a simulated vehicle speed of the vehicle to be tested is calculated by using a preset speed algorithm according to the coasting resistance parameter and the input data; wherein the parameter identification processing at least includes parameter calculation and parameter optimization, and the optimization algorithm is used to perform parameter optimization processing on the coasting resistance parameter; in a case where a difference between the simulated vehicle speed and the vehicle speed is less than a first preset difference threshold, parameter identification processing is performed on the input data by using the optimization algorithm and a motor torsional vibration algorithm to obtain a motor torsional vibration parameter, and a simulated motor speed of the vehicle to be tested is calculated by using a preset speed algorithm according to the motor torsional vibration parameter and the input data; wherein the optimization algorithm is used to perform parameter optimization processing on the motor torsional vibration parameter; in a case where a difference between the simulated motor speed and the motor speed is less than a second preset difference threshold, the motor torsional vibration parameter and the coasting resistance parameter are determined as input parameters corresponding to the vehicle to be tested. Compared with related technologies, the present disclosure performs parameter identification processing on the real vehicle data of the vehicle to be tested by using the optimization algorithm, the vehicle coasting resistance algorithm and the motor torsional vibration algorithm, and obtains the input parameters corresponding to the vehicle to be tested, which can ensure that the input parameters accurately reflect the vehicle state of the vehicle to be tested, thereby improving the consistency between the HIL test result and the vehicle to be tested, and improving the accuracy and effectiveness of vehicle testing.

[0052] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0053] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0054] Figure 1 A flowchart of a method for parameter identification provided by the embodiments of the present disclosure;

[0055] Figure 2 A principle diagram of a method for parameter identification provided by the embodiments of the present disclosure;

[0056] Figure 3 A flowchart of a vehicle test provided by the embodiments of the present disclosure;

[0057] Figure 4A structural schematic diagram of a parameter identification device provided by an embodiment of the present disclosure.

[0058] Figure 5 A structural schematic diagram of another parameter identification device provided by an embodiment of the present disclosure.

[0059] Figure 6 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0060] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, which should be considered in a descriptive sense only. Thus, it will be apparent to one of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0061] The parameter identification method and device, the electronic device and the storage medium of the embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0062] Figure 1 A flowchart of a parameter identification method provided by an embodiment of the present disclosure.

[0063] As shown in the method includes the following steps: Figure 1

[0064] Step 101, obtaining real vehicle data of a vehicle to be tested, and extracting input data satisfying a preset test condition in the real vehicle data, wherein the real vehicle data at least includes vehicle speed of the vehicle to be tested and motor speed of the vehicle to be tested.

[0065] The parameter identification method described in the present disclosure can be applied to any type of vehicle test, such as vehicle power test, vehicle hardware test, etc. Specifically, the application scenarios of the present disclosure are not limited by the embodiments of the present disclosure.

[0066] In order to facilitate the understanding of the embodiments of the present disclosure, the vehicle power test is taken as an example for description hereinafter.

[0067] In the embodiments of the present disclosure, the real vehicle data includes but is not limited to vehicle speed of the vehicle to be tested, motor speed of the vehicle to be tested, motor torque of the vehicle to be tested, steering angle of the vehicle to be tested, etc. Specifically, the content of the real vehicle data is not limited by the embodiments of the present disclosure.

[0068] ​The preset test condition is a data screening condition set by the user, which is used to screen data for testing the corresponding function of the vehicle to be tested, for example, screening data for testing the power of the vehicle, screening data for testing the hardware of the vehicle, etc. The content of the input data is different according to the different preset conditions, for example, when the preset test condition is to screen data for testing the power of the vehicle, the input data includes but is not limited to the driving torque of the vehicle to be tested, the vehicle speed of the vehicle to be tested, the vehicle steering angle of the vehicle to be tested, the slope information of the vehicle to be tested, and other data related to the power of the vehicle. When the preset test condition is to screen data for testing the hardware of the vehicle, the input data includes but is not limited to sensor data of the vehicle to be tested, control unit data of the vehicle to be tested, hardware fault information of the vehicle to be tested, and other data related to the hardware. Specifically, the preset test condition and the preset input data are not limited in the embodiment of the present disclosure.

[0069] In step 102, the input data is processed by an optimization algorithm and a vehicle coasting resistance algorithm to obtain a coasting resistance parameter, and a simulated vehicle speed of the vehicle to be tested is calculated according to the coasting resistance parameter and the input data by a preset speed algorithm. The parameter identification process includes at least parameter calculation and parameter optimization, and the optimization algorithm is used for parameter optimization processing of the coasting resistance parameter.

[0070] In the embodiment of the present disclosure, the vehicle coasting resistance algorithm is a self-defined algorithm, for example, an algorithm in a vehicle coasting resistance model. The vehicle coasting resistance model is a mathematical model used to describe the resistance experienced by a vehicle during coasting. The vehicle coasting resistance model is of great significance for fuel economy analysis, vehicle control system design, and development of driving assistance systems. It can predict the coasting behavior of the vehicle under certain conditions, so that the control system can adjust the engine output or the brake system to optimize fuel economy or improve driving safety.

[0071] The optimization algorithm is a self-defined algorithm, for example, an algorithm in a particle swarm optimization (PSO) parameter identification model. The PSO identification model is a swarm intelligence-based optimization algorithm that solves problems by simulating the social behavior of animal groups such as bird flocks and fish flocks. Each potential solution to an optimization problem is regarded as a particle, which seeks the optimal solution by flying in a multi-dimensional space. The particles update their positions by tracking two optimal values: the best position of the particle itself (pbest) and the best position of the entire group (gbest). When PSO is used for parameter identification, the goal is to find a set of parameters that minimize a certain function (for example, the prediction error of a model). In the parameter identification of the vehicle coasting resistance model, PSO can be used to optimize the parameters of the model to more accurately predict the resistance of the vehicle during coasting. In the initial configuration of the PSO parameter identification model, the initial particle group size, individual learning factor (C1), social learning factor (C2), and maximum number of iterations can be self-defined to complete the identification of the coasting resistance parameters.

[0072] The coasting resistance parameters include but are not limited to A, the reference vehicle coasting resistance constant term coefficient; B, the reference vehicle coasting resistance linear term coefficient; C, the reference vehicle coasting resistance quadratic term coefficient, etc. The preset speed algorithm is a self-defined algorithm that can calculate the corresponding vehicle speed based on the coasting resistance parameters. Specifically, the disclosure embodiments do not limit the coasting resistance parameters and the preset speed algorithm.

[0073] It should be noted that the parameter identification process is a term in the field of mathematics and signal processing, which refers to the process of determining the parameter values of a system or model from a set of observed data.

[0074] In step 103, if the difference between the simulated vehicle speed and the vehicle speed is less than a first preset difference threshold, parameter identification processing is performed on the coasting resistance parameters and the input data by the optimization algorithm and the motor torsional vibration algorithm to obtain motor torsional vibration parameters, and the simulated speed of the vehicle to be tested is calculated by a preset speed algorithm based on the motor torsional vibration parameters and the input data. The optimization algorithm is used for parameter optimization processing of the motor torsional vibration parameters.

[0075] In the embodiments of the present disclosure, when the difference between the simulated vehicle speed calculated by the coasting resistance parameter and the actual vehicle speed of the vehicle to be tested is less than a first preset difference threshold, it is determined that the coasting resistance parameter meets the vehicle test condition and can reflect the true situation of the vehicle to be tested, wherein the first preset difference threshold is a threshold set by the user, for example, 1 km / h, 0.5 km / h, etc. Specifically, the first preset difference threshold is not limited in the embodiments of the present disclosure.

[0076] The motor torsional vibration algorithm is an algorithm selected by the user, for example, an algorithm in a motor torsional vibration model. The motor torsional vibration model is a mathematical model used to describe the torque and vibration behavior of the motor during operation. This model is crucial for understanding and analyzing the dynamic characteristics of the motor, as well as designing and optimizing the operation control system of the motor. It usually involves the rotor, stator, and their interaction of the motor. The rotor generates torque under the action of the rotating magnetic field of the motor and may cause vibration due to uneven mass distribution, bearing friction, wind resistance, etc. The role of the stator is to generate a rotating magnetic field and interact with the rotor to generate torque.

[0077] The motor torsional vibration parameters include but are not limited to Jm1 front motor rotor-inertia, Jm2 rear motor rotor-inertia, Jg1 front motor equivalent load-inertia, Jg2 rear motor equivalent load-inertia, C1 front motor connecting shaft-equivalent damping coefficient, C2 rear motor connecting shaft-equivalent damping coefficient, k1 front motor connecting shaft-equivalent torsional stiffness, k2 rear motor connecting shaft-equivalent torsional stiffness, etc. The preset speed algorithm is an algorithm set by the user, which can calculate the corresponding motor speed according to the motor torsional vibration parameters. Specifically, the motor torsional vibration parameters and the preset speed algorithm are not limited in the embodiments of the present disclosure.

[0078] For the optimization algorithm, please refer to the description in step 102 above, which will not be repeated here.

[0079] It should be noted that when calculating the motor torsional vibration parameters, the initial particle swarm number, individual learning factor (C1), social learning factor (C2), and maximum iteration number of the optimization algorithm are different from those when calculating the coasting resistance parameter.

[0080] Step 104, in the case where the difference between the simulated speed and the motor speed is less than a second preset difference threshold, the motor torsional vibration parameters and the coasting resistance parameters are determined as the input parameters corresponding to the vehicle to be tested.

[0081] In the embodiments of the present disclosure, when the difference between the simulated rotating speed calculated by the motor torsional vibration parameter and the actual motor rotating speed of the vehicle to be tested is less than a second preset difference threshold, i.e., the motor torsional vibration parameter is determined to meet the vehicle test condition, which can reflect the real situation of the vehicle to be tested, wherein the second preset difference threshold is a threshold set by the user, for example: 5 r / min, 10 r / min, etc. Specifically, the second preset difference threshold is not limited in the embodiments of the present disclosure.

[0082] In order to facilitate the understanding of the acquisition process of each parameter, the present disclosure provides a schematic diagram of the principle of parameter identification, as shown in Figure 2 The vehicle rolling resistance model includes a vehicle rolling resistance algorithm, and the torsional vibration model includes a motor torsional vibration algorithm.

[0083] Regarding the working principle of the vehicle rolling resistance model, the embodiments of the present disclosure provide a program for explanation, for example: program 1:

[0084] def vehicle_Rolling_Resistance_Model (FrTq_Nm_t0, Veh_Spd_kph_t0, ReTq_Nm_t0, x1, x2, x3, Rr=0.374, pi=A, B, C

[0085] A=X1

[0086] B=X2

[0087] C=X3

[0088] #FrSpd_rpm_t0=w1_radps_t0_Fr*(30 / pi)

[0089] #Motor rotating speed rpm->vehicle speed kph

[0090] #VehSpd_kph=FrSpd_rpm_t0*((2*pi*Rr) / n_fr) / 60*3.6

[0091] #Total wheel edge resistance fitting formula

[0092] Fx_total=(veh_Spd_kph_t0*Veh_Spd_kph_t0*c)+(Veh_Spd_kph_t0*B)+A

[0093] #Total wheel edge driving force fitting formula

[0094] Drv_trq=FrTq_Nm_t0*n_fr+ReTq_Nm_tθ*n_re

[0095] Wherein, the program 1 and Figure 2 Corresponding to function 1.

[0096] Regarding the working principle of the motor torsional vibration model, the embodiment of the present disclosure provides a program for illustration, for example: Program 2 and Program 3,

[0097] Program 2:

[0098] def mot_spd_pred_2dof(FrTq_Nm_te,w1_radps

[0099] ReTq_Nm_te,w1 radps_t0,

[0100] C1_Fr, K1_Fr, J1_Fr, J2_F

[0101] n fr=11.529,n_re=11.701,

[0102] Program 3:

[0103] def obj_func(p):

[0104] x1, x2, x3, x4, x5, x6, x7, x8 = p # parameters to be identified

[0105] e_list = []

[0106] Wherein, the program 2 and Figure 2 Function 2 corresponds to program 3. Figure 2 Corresponding to function 3.

[0107] Regarding the working principle of the optimization, the embodiment of the present disclosure provides a program for illustration, for example: Program 4:

[0108] from sko.Pso import PSO

[0109] pso=pso(func=obj_func,dim=8,pop=50,max_iter=100,1b=

[0110] pso.run()

[0111] print('best_x is',pso.gbest x,'best_y is',pso.gbest y)

[0112] Among them, the program 4 and Figure 2 Corresponding to function 4.

[0113] The method for parameter identification provided in the present disclosure obtains real vehicle data of a vehicle to be tested, and extracts input data satisfying a preset test condition in the real vehicle data, wherein the real vehicle data at least includes vehicle speed and motor speed of the vehicle to be tested; parameter identification processing is performed on the input data by using an optimization algorithm and a vehicle coasting resistance algorithm to obtain a coasting resistance parameter, and a simulated vehicle speed of the vehicle to be tested is calculated by using a preset speed algorithm according to the coasting resistance parameter and the input data; wherein the parameter identification processing at least includes parameter calculation and parameter optimization, and the optimization algorithm is used to perform parameter optimization processing on the coasting resistance parameter; in a case where a difference between the simulated vehicle speed and the vehicle speed is less than a first preset difference threshold, parameter identification processing is performed on the input data by using the optimization algorithm and a motor torsional vibration algorithm to obtain a motor torsional vibration parameter, and a simulated motor speed of the vehicle to be tested is calculated by using a preset speed algorithm according to the motor torsional vibration parameter and the input data; wherein the optimization algorithm is used to perform parameter optimization processing on the motor torsional vibration parameter; in a case where a difference between the simulated motor speed and the motor speed is less than a second preset difference threshold, the motor torsional vibration parameter and the coasting resistance parameter are determined as input parameters corresponding to the vehicle to be tested. Compared with related technologies, the present disclosure can obtain input parameters corresponding to the vehicle by performing parameter identification, so as to ensure that the input parameters accurately reflect the state of the vehicle, thereby improving consistency between HIL test results and the vehicle, and improving accuracy and effectiveness of vehicle testing.

[0114] In an implementable manner of the present disclosure, when the real vehicle data is obtained, data with a high correlation degree to vehicle testing needs to be screened out to improve the accuracy of vehicle testing. Therefore, in order to accurately perform vehicle testing, the following manner can be used, but is not limited to: vehicle data of the vehicle to be tested in different driving scenarios is screened out by using a shadow mode, and the vehicle data is determined as the real vehicle data.

[0115] In the present disclosure, the shadow mode can be understood as follows: in a manned driving state, the system includes sensors that are still running but do not participate in vehicle control, and only verifies the decision algorithm - the algorithm of the system continuously simulates decision-making in the "shadow mode", and compares the decision-making with the behavior of the driver. Once the two are inconsistent, the scene is determined as an "extreme working condition", and data back transmission is triggered.

[0116] In an implementable manner of the embodiment of the present disclosure, in relation to the above-mentioned embodiment, the implementation process of screening real vehicle data through a shadow mode can be implemented by, but is not limited to, the following manner: obtaining driving information corresponding to each driving scene of the to-be-tested vehicle; calculating simulation driving information corresponding to each driving scene of the to-be-tested vehicle through a preset simulation algorithm; comparing and processing the driving information and the simulation driving information, and determining whether the driving information and the simulation driving information corresponding to the same driving scene are the same according to a comparison result; in a case where the driving information and the simulation driving information corresponding to the same driving scene are not the same, obtaining vehicle data of the to-be-tested vehicle in the driving scene corresponding to the simulation driving information, and determining the vehicle data as the real vehicle data.

[0117] In the embodiment of the present disclosure, the preset simulation algorithm is the algorithm used in simulation decision-making. The autonomous vehicle compares the data such as the environment information, decision-making process and vehicle control instruction perceived during actual driving with the ideal output of the system. This comparison is like a "shadow" of the system, which can reflect the difference between the actual performance and the expectation of the system in actual operation. The autonomous driving system records all the decisions and operations it should make, even if these decisions and operations are not actually executed. It can evaluate the response of the autonomous driving system in different situations and record any deviation, so that developers can identify problems in subsequent analysis and optimize the algorithm.

[0118] In an implementable manner of the embodiment of the present disclosure, when it is determined whether the parameter is a parameter that can reflect the real situation of the to-be-tested vehicle and meets the vehicle test condition, if the parameter does not meet the requirement, further parameter identification needs to be performed until a parameter meeting the requirement is obtained. Therefore, in order to obtain a parameter accurately reflecting the vehicle condition, the following method can also be used, but is not limited to: calculating a difference between the simulation vehicle speed and the vehicle speed; in a case where the difference between the simulation vehicle speed and the vehicle speed is greater than or equal to the first preset difference threshold, re-performing parameter identification processing according to the input data through the optimization algorithm and the vehicle sliding resistance algorithm.

[0119] In an implementable manner of the embodiment of the present disclosure, the above-mentioned embodiment illustrates the process of obtaining the coasting resistance parameter accurately reflecting the vehicle condition, and the process of obtaining the motor torsional vibration parameter accurately reflecting the vehicle condition is illustrated next. As for the obtaining of the motor torsional vibration parameter, the following methods can be used but are not limited thereto: calculating the difference between the simulated speed and the motor speed; and in the case that the difference between the simulated speed and the motor speed is greater than or equal to the second preset difference threshold, re-performing the parameter identification processing according to the coasting resistance parameter and the input data by the optimization algorithm and the motor torsional vibration algorithm.

[0120] In an implementable manner of the embodiment of the present disclosure, after obtaining the input parameter accurately reflecting the vehicle condition, the input parameter needs to be input into the simulation model for HIL testing. Therefore, in order to complete the testing of the vehicle, the following methods can be used but are not limited thereto: inputting the input parameter and the input data into a preset simulation model, performing simulation testing on the vehicle to be tested, and obtaining the testing result.

[0121] In order to understand the whole implementation process of the embodiment of the present disclosure, as shown in Figure 3 Figure 3 a flowchart of vehicle testing provided by the embodiment of the present disclosure is provided.

[0122] In summary, the embodiment of the present disclosure can achieve the following effects:

[0123] 1. The embodiment of the present disclosure can obtain the input parameter of the vehicle by performing parameter identification, which can ensure that the input parameter accurately reflects the vehicle state, thereby improving the consistency between the HIL testing result and the vehicle and improving the accuracy and effectiveness of vehicle testing.

[0124] 2. The embodiment of the present disclosure can calibrate model parameters by learning the behavior data of real vehicles, and the model can better adapt to various driving environments and conditions, including complex scenarios that are difficult to directly derive from physical principles.

[0125] 3. The embodiment of the present disclosure can improve the performance of the model in simulating the transient response of the vehicle, such as acceleration, braking or emergency control, by combining the physical model and the data-driven method, which is particularly important for the testing of safety-critical systems.

[0126] 4. The embodiment of the present disclosure can reduce the need for accurate engineering data and long development cycles of traditional physical models through parameter identification. The data-driven model can reduce the dependence on professional knowledge to a certain extent due to its adaptive learning ability, thereby reducing the overall cost of model development and maintenance.

[0127] ​5.The parameter optimization process of the embodiments of the present disclosure can be automatically performed, reducing the time for manual parameter adjustment, while the data-driven model generally has faster execution speed, which can significantly accelerate the overall simulation test process. And the data-driven model can be continuously updated and optimized, realizing continuous improvement of model performance, and ensuring that the test environment evolves with the development of vehicle technology.

[0128] Corresponding to the parameter identification method described above, the present application also provides a parameter identification device. Since the device embodiments of the present application correspond to the method embodiments described above, for details not disclosed in the device embodiments, please refer to the method embodiments described above, which will not be described in detail in the present application.

[0129] Figure 4 A structural schematic diagram of a parameter identification device provided by the embodiments of the present disclosure is shown in Figure 4 As shown in the figure, it includes:

[0130] The acquisition unit 41 is configured to acquire real vehicle data of a vehicle to be tested.

[0131] The extraction unit 42 is configured to extract input data satisfying a preset test condition from the real vehicle data, wherein the real vehicle data at least includes vehicle speed and motor speed of the vehicle to be tested.

[0132] The identification unit 43 is configured to perform parameter identification processing according to the input data through an optimization algorithm and a vehicle coasting resistance algorithm, to obtain a coasting resistance parameter.

[0133] The calculation unit 44 is configured to calculate a simulated vehicle speed of the vehicle to be tested according to the coasting resistance parameter and the input data through a preset speed algorithm, wherein the parameter identification processing at least includes parameter calculation and parameter optimization, and the optimization algorithm is used for parameter optimization processing of the coasting resistance parameter.

[0134] The identification unit 43 is further configured to, in a case where a difference between the simulated vehicle speed and the vehicle speed is less than a first preset difference threshold, perform parameter identification processing according to the coasting resistance parameter and the input data through the optimization algorithm and a motor torsional vibration algorithm, to obtain a motor torsional vibration parameter.

[0135] The calculation unit 44 is further configured to calculate a simulated motor speed of the vehicle to be tested according to the motor torsional vibration parameter and the input data through a preset speed algorithm, wherein the optimization algorithm is used for parameter optimization processing of the motor torsional vibration parameter.

[0136] The determining unit 45 is configured to determine the motor torsional vibration parameter and the coasting resistance parameter as the input parameter corresponding to the to-be-tested vehicle in a case where the difference between the simulation rotating speed and the motor rotating speed is less than a second preset difference threshold.

[0137] Further, in a possible implementation of the embodiment of the present disclosure, the obtaining unit 41 is further configured to filter vehicle data of the to-be-tested vehicle in different driving scenes through a shadow mode, and determine the vehicle data as the real vehicle data.

[0138] Further, in a possible implementation of the embodiment of the present disclosure, as shown in Figure 5 The obtaining unit 41 comprises:

[0139] The obtaining module 411 is configured to obtain driving information corresponding to each driving scene of the to-be-tested vehicle.

[0140] The calculation module 412 is configured to calculate simulation driving information corresponding to each driving scene of the to-be-tested vehicle through a preset simulation algorithm.

[0141] The comparison module 413 is configured to compare and process the driving information and the simulation driving information, and determine whether the driving information and the simulation driving information corresponding to the same driving scene are the same according to a comparison processing result.

[0142] The obtaining module 411 is further configured to, in a case where the driving information and the simulation driving information corresponding to the same driving scene are not the same, obtain vehicle data of the to-be-tested vehicle in the driving scene corresponding to the simulation driving information, and determine the vehicle data as the real vehicle data.

[0143] Further, in a possible implementation of the embodiment of the present disclosure, the calculation unit 44 is further configured to calculate a difference between the simulation vehicle speed and the vehicle speed.

[0144] The identification unit 43 is further configured to, in a case where the difference between the simulation vehicle speed and the vehicle speed is greater than or equal to the first preset difference threshold, perform parameter identification processing again according to the input data through the optimization algorithm and the vehicle coasting resistance algorithm.

[0145] Further, in a possible implementation of the embodiment of the present disclosure, the calculation unit 44 is further configured to calculate a difference between the simulation rotating speed and the motor rotating speed.

[0146] The identification unit 43 is further configured to, in a case where the difference between the simulation rotating speed and the motor rotating speed is greater than or equal to the second preset difference threshold, re-perform parameter identification processing according to the coasting resistance parameter and the input data by the optimization algorithm and the motor torsional vibration algorithm.

[0147] Further, in a possible implementation manner of the embodiment of the present disclosure, as shown in Figure 5 The apparatus further includes:

[0148] The input unit 46 is configured to input the input parameter and the input data into a preset simulation model, perform simulation testing on the vehicle to be tested, and obtain a testing result.

[0149] It should be noted that the foregoing explanation and description of the method embodiment are also applicable to the apparatus of the embodiment of the present disclosure, and the principle is the same, which is not limited in the embodiment of the present disclosure.

[0150] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0151] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0152] As shown in Figure 6 The device 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 602 or a computer program loaded from a storage unit 608 into a RAM (Random Access Memory) 603. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An I / O (Input / Output) interface 605 is also connected to the bus 604.

[0153] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through computer networks, such as the Internet, and / or various telecommunication networks.

[0154] The computing unit 601 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 601 performs various methods and processes described above, such as the method of parameter identification. For example, in some embodiments, the method of parameter identification can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the aforementioned method of parameter identification by other any appropriate means, such as by means of firmware.

[0155] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a Field Programmable Gate Array (FPGA), an Application-Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a System on a Chip (SOC), a Complex Programmable Logic Device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0156] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general or special purpose computer, such that the program code, when executed by the processor or controller, causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0157] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include a linearly-programmed electrical connection, a portable computer diskette, a hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory), or flash memory, an optical fiber, a CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0158] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; 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 acoustic, speech, or tactile input.

[0159] The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, and a blockchain network.

[0160] The computer system can include clients and servers. This relationship can be between a client and a server that are typically remote from each other and typically interact through a communication network. The relationship between client and server exists by virtue of computer programs running on the respective computer systems and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS (Virtual Private Server, or VPS for short) services. The server can also be a server of a distributed system, or a server combined with a blockchain.

[0161] It should be noted that artificial intelligence is a discipline that studies enabling computers to simulate some thinking processes and intelligent behaviors of people (such as learning, reasoning, thinking, planning, etc.), both hardware and software technologies. Artificial intelligence hardware technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing, etc.; artificial intelligence software technology mainly includes computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, knowledge graph technology, etc. several major directions.

[0162] It should be understood that the various forms of the flow shown above can be used to reorder, add or delete steps. For example, each step described in the present disclosure can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, which is not limited herein.

[0163] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. 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 replacements and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for parameter identification, characterized in that: include: Acquire real vehicle data of the vehicle to be tested, and extract input data that meets preset test conditions from the real vehicle data, wherein the real vehicle data at least includes the vehicle speed and motor speed of the vehicle to be tested; performing parameter identification processing based on the input data using an optimization algorithm and a vehicle coasting resistance algorithm to obtain a coasting resistance parameter, and calculating a simulated vehicle speed of the vehicle to be tested based on the coasting resistance parameter and the input data using a preset speed algorithm; wherein the parameter identification processing includes at least parameter calculation and parameter optimization, and the optimization algorithm is used to perform parameter optimization processing on the coasting resistance parameter; When the difference between the simulated vehicle speed and the vehicle speed is less than a first difference threshold, performing parameter identification processing using the optimization algorithm and the motor torsional vibration algorithm based on the coasting resistance parameter and the input data to obtain motor torsional vibration parameters, and calculating the simulated speed of the vehicle to be tested using a preset speed algorithm based on the motor torsional vibration parameters and the input data; wherein the optimization algorithm is used to perform parameter optimization processing on the motor torsional vibration parameters; When the difference between the simulated rotational speed and the motor rotational speed is less than a second difference threshold, the motor torsional vibration parameter and the sliding resistance parameter are determined as input parameters corresponding to the vehicle to be tested.

2. The method according to claim 1, characterized in that The step of obtaining the actual vehicle data of the vehicle to be tested includes: The vehicle data of the vehicle to be tested in different driving scenarios is screened through the shadow mode, and the vehicle data is determined as the real vehicle data.

3. The method according to claim 2, characterized in that The step of screening the vehicle data of the vehicle to be tested in different driving scenarios by using the shadow mode and determining the vehicle data as the real vehicle data includes: Obtaining driving information corresponding to each driving scenario of the vehicle to be tested; Calculating simulated driving information corresponding to each driving scenario of the vehicle to be tested by a preset simulation algorithm; Comparing the driving information with the simulated driving information, and determining whether the driving information and the simulated driving information corresponding to the same driving scene are the same based on the comparison result; In a case where the driving information corresponding to the same driving scene is different from the simulated driving information, the vehicle data of the vehicle to be tested in the driving scene corresponding to the simulated driving information is obtained, and the vehicle data is determined as the real vehicle data.

4. The method according to claim 1, wherein After calculating the simulated vehicle speed of the vehicle to be tested by a preset speed algorithm according to the sliding resistance parameter and the input data, the method further includes: calculating a difference between the simulated vehicle speed and the vehicle speed; When the difference between the simulated vehicle speed and the vehicle speed is greater than or equal to the first preset difference threshold, parameter identification processing is performed again according to the input data using the optimization algorithm and the vehicle sliding resistance algorithm.

5. The method according to claim 1, wherein After calculating the simulated speed of the vehicle to be tested by a preset speed algorithm according to the motor torsional vibration parameters and the input data, the method further includes: Calculating the difference between the simulated speed and the motor speed; When the difference between the simulated speed and the motor speed is greater than or equal to the second preset difference threshold, parameter identification processing is performed again according to the sliding resistance parameter and the input data using the optimization algorithm and the motor torsional vibration algorithm.

6. The method according to claim 1, characterized in that After determining the motor torsional vibration parameter and the sliding resistance parameter as input parameters corresponding to the vehicle to be tested, the method further includes: The input parameters and the input data are input into a preset simulation model, a simulation test is performed on the vehicle to be tested, and a test result is obtained.

7. A parameter identification device, characterized in that: include: An acquisition unit, used to acquire real vehicle data of the vehicle to be tested; an extraction unit, configured to extract input data satisfying a preset test condition from the real vehicle data, wherein the real vehicle data at least includes a vehicle speed and a motor speed of the vehicle to be tested; an identification unit, configured to perform parameter identification processing based on the input data using an optimization algorithm and a vehicle sliding resistance algorithm to obtain sliding resistance parameters; a calculation unit, configured to calculate a simulated vehicle speed of the vehicle to be tested based on the coasting resistance parameter and the input data using a preset speed algorithm; wherein the parameter identification process includes at least parameter calculation and parameter optimization, and the optimization algorithm is configured to perform parameter optimization processing on the coasting resistance parameter; The identification unit is further configured to, when a difference between the simulated vehicle speed and the vehicle speed is less than a first preset difference threshold, perform parameter identification processing using the optimization algorithm and the motor torsional vibration algorithm according to the coasting resistance parameter and the input data to obtain a motor torsional vibration parameter; The calculation unit is further configured to calculate the simulated speed of the vehicle to be tested using a preset speed algorithm according to the motor torsional vibration parameters and the input data; wherein the optimization algorithm is configured to perform parameter optimization processing on the motor torsional vibration parameters; A determination unit is configured to determine the motor torsional vibration parameter and the sliding resistance parameter as input parameters corresponding to the vehicle to be tested when a difference between the simulated speed and the motor speed is less than a second preset difference threshold.

8. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed 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 perform the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images