Motor matching method and device based on double drive system, equipment and storage medium

Abstract

This invention discloses a motor matching method, apparatus, device, and storage medium based on a dual-drive system. It generates a motor speed dataset by aggregating motor speed data from multiple motors. The motor speed data in this dataset are paired in pairs, and a distance correlation coefficient is calculated for each pair. Based on the calculation results, a correlation parameter matrix is ​​generated. The minimum value of the correlation parameter matrix and its corresponding two sets of motor speed data are obtained and saved. The two sets of motor speed data corresponding to the minimum value in the motor speed dataset are deleted, and a new motor speed dataset is generated. This process is repeated until no motor speed data exists in the original dataset, and the motor matching result dataset is output. Compared with existing technologies, this invention reduces the differences between paired motors by matching data from multiple motors.

Description

Technical Field

[0001] This invention relates to the technical field of intelligent vehicle drive, and in particular to a motor matching method, apparatus, device, and storage medium based on a dual-drive system. Background Technology

[0002] Current robotics research largely focuses on the innovative design of swarm control algorithms. However, if the overall performance of the drive system is limited, the practical effectiveness of the swarm algorithm is difficult to demonstrate. Furthermore, verifying swarm algorithms often requires a large number of verification platforms; if the cost of a single platform is relatively high, it increases the overall cost of the multi-agent physical system, which is unaffordable. Therefore, constructing a swarm algorithm verification system using numerous low-cost intelligent platforms is a widely adopted approach in universities and research institutions. However, the performance of low-cost platform drive systems is limited at the time of manufacture; for example, the left and right wheel drive systems of a low-cost intelligent vehicle differ significantly, resulting in limited performance matching. On the other hand, during repeated algorithm verification and use, drive systems often experience varying degrees of wear or damage, which can also lead to significant differences in drive systems and limited performance matching. Therefore, it is necessary to break down the drive systems of each subsystem in a low-cost swarm algorithm verification platform, perform homogeneity matching, and then re-pair and recombine them according to the matching results. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a motor matching method, device, equipment and storage medium based on a dual-drive system, which reduces the differences between paired motors by matching data of multiple motors.

[0004] To address the aforementioned technical problems, this invention provides a motor matching method based on a dual-drive system, comprising:

[0005] Obtain motor speed data corresponding to multiple motors under preset operating conditions, and preprocess the motor speed data to generate a motor speed dataset;

[0006] The motor speed data in the motor speed dataset are paired up in pairs, and the distance correlation coefficient between the two sets of motor speed data is calculated based on the pairing results. Based on the calculation results, a correlation parameter matrix is ​​generated.

[0007] Obtain the minimum value of the correlation parameter matrix, and save the minimum value and the corresponding two sets of motor speed data into the matching result dataset;

[0008] Delete the two sets of motor speed data corresponding to the minimum value in the motor speed dataset, generate a new motor speed dataset, and determine whether there is motor speed data in the motor speed dataset. If yes, return to the step "pair the motor speed data in the motor speed dataset in pairs". If no, output the matching result dataset.

[0009] Furthermore, the motor speed data is preprocessed to generate a motor speed dataset, specifically as follows:

[0010] The format of the motor speed data is adjusted to make the time step of all motor speed data the same. The adjusted motor speed data are then aggregated to generate a motor speed dataset.

[0011] Furthermore, after outputting the matching result dataset, the method further includes:

[0012] The multiple motors were re-paired and reassembled based on the matching result dataset, and the reassembled motors were experimentally verified.

[0013] Furthermore, the present invention also provides a motor matching device based on a dual-drive system, comprising: a data preprocessing module, a matching module, a data storage module, and a matching result output module;

[0014] The data preprocessing module is used to acquire motor speed data corresponding to multiple motors under preset operating conditions, and to preprocess the motor speed data to generate a motor speed dataset.

[0015] The pairing module is used to pair the motor speed data in the motor speed dataset in pairs, calculate the distance correlation coefficient between the two sets of motor speed data based on the pairing results, and generate a correlation parameter matrix based on the calculation results.

[0016] The data storage module is used to obtain the minimum value of the correlation parameter matrix and save the minimum value and the corresponding two sets of motor speed data into the matching result dataset.

[0017] The matching result output module is used to delete the two sets of motor speed data corresponding to the minimum value in the motor speed dataset, generate a new motor speed dataset, determine whether there is motor speed data in the motor speed dataset, if yes, return to the step "pairing the motor speed data in the motor speed dataset in pairs", if no, output the matching result dataset.

[0018] Furthermore, the data preprocessing module is used to preprocess the motor speed data to generate a motor speed dataset, specifically as follows:

[0019] The format of the motor speed data is adjusted to make the time step of all motor speed data the same. The adjusted motor speed data are then aggregated to generate a motor speed dataset.

[0020] Furthermore, the motor matching device based on a dual-drive system provided by the present invention also includes: an assembly module;

[0021] The assembly module is used to reassemble the multiple motors according to the matching result dataset, and to conduct experimental verification on the reassembled multiple motors.

[0022] Furthermore, the present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the motor matching method based on a dual-drive system as described in any of the preceding claims.

[0023] Furthermore, the present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the motor matching method based on a dual-drive system as described in any of the preceding claims.

[0024] The present invention provides a motor matching method, apparatus, device, and storage medium based on a dual-drive system, which, compared with the prior art, has the following advantages:

[0025] By aggregating the preprocessed motor speed data of multiple motors, a motor speed dataset is generated. Based on the motor speed data in this dataset, pairwise pairings are performed, and the distance correlation coefficient for each pair is calculated. A correlation parameter matrix is ​​generated based on the calculation results. Since a smaller correlation coefficient indicates a higher degree of matching, the minimum value of the correlation parameter matrix and its corresponding two sets of motor speed data are obtained and saved, achieving pairing of multiple motors at the data level. The two sets of motor speed data corresponding to the minimum value in the motor speed dataset are deleted, generating a new motor speed dataset. This process is repeated until no motor speed data remains in the original dataset, at which point the motor matching result dataset is output. Compared to existing technologies, this invention reduces the differences between paired motors by performing data matching on multiple motors and calculating the distance correlation coefficient for each pair to obtain the motor matching result. Attached Figure Description

[0026] Figure 1This is a flowchart illustrating an embodiment of the motor matching method based on a dual-drive system provided by the present invention.

[0027] Figure 2 This is a schematic diagram of the structure of an embodiment of the motor matching device based on a dual-drive system provided by the present invention;

[0028] Figure 3a This is a schematic diagram of the dynamic motor speed data of the left wheel motor of three intelligent cars according to an embodiment of the present invention;

[0029] Figure 3b This is a schematic diagram of the dynamic motor speed data of the right wheel motor of three intelligent cars according to an embodiment of the present invention;

[0030] Figure 4a This is a graph showing the motor speed data of the left and right wheel motors of the No. 2 intelligent vehicle according to an embodiment of the present invention.

[0031] Figure 4b This is a graph showing the motor speed data of the left and right wheel motors of the No. 3 intelligent vehicle according to an embodiment of the present invention.

[0032] Figure 4c This is a graph showing the motor speed data of the left and right wheel motors of the No. 4 intelligent vehicle according to an embodiment of the present invention.

[0033] Figure 5 This is a schematic diagram of the matching result dataset according to an embodiment of the present invention;

[0034] Figure 6 This is a motion trajectory diagram of an intelligent vehicle under constant working conditions according to one embodiment of the present invention;

[0035] Figure 7 This is a schematic diagram of the motion trajectory of an intelligent vehicle under varying working conditions according to an embodiment of the present invention. Detailed Implementation

[0036] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0037] Example 1

[0038] See Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the motor matching method based on a dual-drive system provided by the present invention, as shown below. Figure 1 As shown, the method includes steps 101-104, as detailed below:

[0039] Step 101: Obtain motor speed data corresponding to multiple motors under preset operating conditions, and preprocess the motor speed data to generate a motor speed dataset.

[0040] In this embodiment, multiple dual-drive system intelligent vehicles were selected for the experiment. Each intelligent vehicle contains two motors, used to control the left and right wheels of the vehicle respectively. The multiple dual-drive system intelligent vehicles were suspended in the air and subjected to an open-loop unloaded experiment. Based on sensors, the motor speed data of the left and right wheel motors of each intelligent vehicle were acquired. Figure 3a As shown, Figure 3a This is a schematic diagram showing the dynamic motor speed data of the left wheel motor of three smart cars; Figure 3b This is a schematic diagram showing the dynamic motor speed data of the right wheel motors of three intelligent vehicles; the dynamic motor speed data represents the change in motor speed over time under the same duty cycle signal; and... Figure 3a and Figure 3b All of these are dynamic speed data graphs when the input duty cycle signal is 0.3. It can be seen that the motor speed amplitude varies to different degrees in the dynamic data.

[0041] In this embodiment, before acquiring motor speed data of the intelligent vehicle, the preset working conditions required for the experiment must be set according to the test plan. The preset working conditions can be constant or variable. The relevant parameters under the preset working conditions can be set by the experimenters.

[0042] In this embodiment, if the preset working condition is a constant working condition, the same duty cycle signal is input to multiple dual-drive system smart cars within a preset time. Since the duty cycle signal input in the same motor corresponds to a set of motor speed data, when the same duty cycle input signal is input to each dual-drive system smart car, the drive motors corresponding to the left and right wheels will generate a set of motor speed data.

[0043] In a preferred embodiment, three dual-drive system intelligent vehicles are selected, and the motors of each vehicle are numbered. For example, the motors of the first dual-drive system intelligent vehicle are numbered 1 and 2, the motors of the second dual-drive system intelligent vehicle are numbered 3 and 4, and the motors of the third dual-drive system intelligent vehicle are numbered 5 and 6. The same duty cycle signal is input to all three dual-drive system intelligent vehicles to obtain the motor speed data of the drive motors corresponding to the left and right wheels of each intelligent vehicle. In a preferred embodiment, the input duty cycle signal is 0.3.

[0044] In this embodiment, if the preset operating condition is a variable operating condition, the difference between it and the constant operating condition lies only in that different duty cycle signals are input to multiple dual-drive system intelligent vehicles within a preset duration. As an example in this embodiment, within a preset duration of 6 seconds, the duty cycle input is 0.2 in the 1st and 2nd seconds, 0.3 in the 3rd and 4th seconds, and 0.4 in the 5th and 6th seconds. Within this preset duration, the drive motors corresponding to the left and right wheels in each dual-drive system intelligent vehicle will also generate a set of motor speed data.

[0045] In this embodiment, all motor speed data generated by multiple intelligent vehicles with dual-drive systems under preset working conditions will be acquired as experimental data, and the experimental data will be preprocessed. Specifically, the data format of the motor speed data used as experimental data will be adjusted to ensure that the time step of all motor speed data is the same. The corresponding motor speed data of the left and right wheel motors of all intelligent vehicles after the data format adjustment will be integrated to generate a motor speed dataset.

[0046] Step 102: Calculate the distance correlation coefficient for each pair of motor speed data in the motor speed dataset, and generate a correlation parameter matrix based on the calculation results.

[0047] In this embodiment, based on the motor speed data corresponding to the left and right wheels of each smart car, the degree of difference in the motor speeds of the left and right wheels under the current pairing can be determined, such as... Figure 4a As shown, Figure 4a This is a graph showing the motor speed data for the left and right wheel motors of the No. 2 intelligent car; for example... Figure 4b As shown, Figure 4b This is a graph showing the motor speed data for the left and right wheel motors of the No. 3 intelligent car; for example... Figure 4c As shown, Figure 4c This is a graph showing the motor speed data for the left and right wheel motors of the No. 4 intelligent car; Figure 4a , Figure 4b and Figure 4c The comparison shows that the motor speed data curves of the left and right wheel motors of the No. 2 intelligent vehicle have the largest difference, therefore the difference between the left and right wheel motors of the No. 2 intelligent vehicle is considered to be the greatest, followed by the No. 3 intelligent vehicle, and the difference between the No. 4 intelligent vehicle is the smallest. In this embodiment, the degree of difference between the left and right wheel motors of the intelligent vehicle also affects the actual trajectory of the intelligent vehicle. When the degree of difference between the left and right wheel motors of the intelligent vehicle is large, the actual trajectory deviation is greater.

[0048] In this embodiment, since each motor speed data in the motor speed dataset corresponds to the left and right wheel motors of different smart cars, all motor speed data in the motor speed dataset are paired up in pairs. That is, at the data level, the operation of splitting and pairing the left and right wheels of all smart cars in the experiment is realized, all pairing possibilities are obtained, and the motor speed data corresponding to all pairs are obtained based on the pairing results.

[0049] In this embodiment, the distance value between the two sets of motor speed data in each pair is obtained, that is, the difference between the two sets of motor speed data is obtained, and the difference between the two sets of motor speed data in each pair is used as the distance correlation coefficient corresponding to the pair. The distance correlation coefficients corresponding to each pair are collected to generate a correlation parameter matrix.

[0050] Step 103: Obtain the minimum value of the correlation parameter matrix, and save the minimum value and the corresponding two sets of motor speed data into the matching result dataset.

[0051] In this embodiment, since the smaller the distance between two sets of motor speed data, the better their correlation, i.e., the higher the degree of matching, all distance correlation coefficients in the correlation parameter matrix are traversed to obtain the minimum value of the correlation parameter matrix. Based on the minimum value, the two sets of motor speed data in the corresponding pair are obtained. At the same time, based on the two sets of motor speed data, the numbers of the left and right wheel motors of the corresponding smart car are obtained. The numbers of the left and right wheel motors of the smart car corresponding to the two sets of motor speed data are used as the pairing result, and the obtained minimum value is saved as a distance parameter in the matching result dataset.

[0052] Step 104: Delete the two sets of motor speed data corresponding to the minimum value in the motor speed dataset, generate a new motor speed dataset, and determine whether there is motor speed data in the motor speed dataset. If yes, return to step "pair the motor speed data in the motor speed dataset in pairs". If no, output the matching result dataset.

[0053] In this embodiment, based on the two sets of motor speed data corresponding to the minimum value in the obtained correlation parameter matrix, the two sets of motor speed data in the corresponding motor speed dataset are deleted, and a new motor speed dataset is generated. It is determined whether motor speed data exists in the newly generated motor speed dataset. If so, the motor speed data in the newly generated motor speed dataset is continuously updated in a loop according to steps 102-104 above, so as to continuously generate a new correlation parameter matrix. The minimum value is obtained from the continuously generated new correlation parameter matrix, and the numbers of the left and right wheel motors of the smart car corresponding to the two sets of motor speed data with the minimum value, along with the obtained minimum value, are saved to the matching result dataset. If it is determined that there is no motor speed data in the newly generated motor speed dataset, the matching result dataset is output. The matching result dataset is as follows: Figure 5 As shown.

[0054] In this embodiment, after outputting the matching result dataset, the multiple motors are re-paired and reassembled at the hardware level based on the matching result dataset, so as to reduce the differences between the left and right wheel motors of the smart car at the hardware level.

[0055] In this embodiment, the intelligent vehicle with reassembled and matched motors is experimentally verified under unchanged operating conditions. Specifically, the same duty cycle signal is input to each of the three intelligent vehicles, making their yaw angle 0. Starting from the origin, the verification is performed based on the motion trajectory of the three vehicles. Figure 6 As shown, Figure 6 This is a motion trajectory diagram of the intelligent vehicle under constant working conditions. The dashed lines in the diagram represent the trajectory results of random assembly before matching, while the solid lines represent the trajectory of reassembly after matching the motors according to the matching results. It can be clearly seen from the diagram that the matched vehicle can complete the specified task more stably, faster, and more accurately. That is, the homogeneous matching method has a significant effect on improving the performance of the vehicle itself.

[0056] In this embodiment, the intelligent vehicle after reassembling and matching the motor is also experimentally verified under varying operating conditions. Specifically, based on the varying operating condition data, different duty cycle signals are input to the three intelligent vehicles to make their yaw angle 0. Starting from the origin of the coordinate system, the verification is performed based on the motion trajectory of the three vehicles. Figure 7 As shown, Figure 7 This is a motion trajectory diagram of the intelligent vehicle under varying working conditions. The solid line represents the motion trajectory of the intelligent vehicle after being reinstalled based on the matching results, while the dashed line represents the trajectory of the vehicle combined with any other drive system. It can be seen that the matched drive system is more consistent and can complete the task more accurately compared to other combinations.

[0057] In this embodiment, by matching the motors based on the differences in the motors in the drive system, the car is re-paired and reassembled, thereby optimizing the drive system of the intelligent car, ensuring the maximum stability of the drive system, and obtaining the matching results based on a simple algorithm, reducing the burden on the control layer.

[0058] See Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of the motor matching device based on a dual-drive system provided by the present invention, as shown below. Figure 2 As shown, the device includes a data preprocessing module 201, a pairing module 202, a data storage module 203, and a matching result output module 204, as detailed below:

[0059] The data preprocessing module 201 is used to acquire motor speed data corresponding to multiple motors under preset operating conditions, and to preprocess the motor speed data to generate a motor speed dataset.

[0060] The pairing module 202 is used to pair the motor speed data in the motor speed dataset in pairs, calculate the distance correlation coefficient between the two sets of motor speed data based on the pairing results, and generate a correlation parameter matrix based on the calculation results.

[0061] The data storage module 203 is used to obtain the minimum value of the correlation parameter matrix and save the minimum value and the corresponding two sets of motor speed data into the matching result dataset.

[0062] The matching result output module 204 is used to delete the two sets of motor speed data corresponding to the minimum value in the motor speed dataset, generate a new motor speed dataset, determine whether there is motor speed data in the motor speed dataset, if yes, return to the step "pairing the motor speed data in the motor speed dataset in pairs", if no, output the matching result dataset.

[0063] In this embodiment, the motor matching device based on the dual-drive system further includes an assembly module; wherein the assembly module is used to reassemble the multiple motors according to the matching result dataset, and to conduct experimental verification on the reassembled multiple motors.

[0064] In this embodiment, the data preprocessing module 201 is used to preprocess the motor speed data to generate a motor speed dataset. Specifically, the format of the motor speed data is adjusted so that the time step of all motor speed data is the same. The format-adjusted motor speed data is then collected to generate a motor speed dataset.

[0065] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0066] It should be noted that the above-described embodiment of the motor matching device based on a dual-drive system is merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0067] Based on the above embodiments of the motor matching method based on a dual-drive system, another embodiment of the present invention provides a motor matching terminal device based on a dual-drive system. The motor matching terminal device based on a dual-drive system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the motor matching method based on a dual-drive system according to any embodiment of the present invention.

[0068] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the motor matching terminal device based on the dual-drive system.

[0069] The motor matching terminal device based on the dual-drive system can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The motor matching terminal device based on the dual-drive system may include, but is not limited to, a processor and a memory.

[0070] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the motor matching terminal equipment based on the dual-drive system, connecting all parts of the equipment via various interfaces and lines.

[0071] The memory can be used to store the computer programs and / or modules. The processor, by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory, realizes various functions of the motor matching terminal device based on the dual-drive system. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0072] Based on the above embodiments of the motor matching method based on a dual-drive system, another embodiment of the present invention provides a storage medium, the storage medium including a stored computer program, wherein, when the computer program is running, the device where the storage medium is located controls the execution of the motor matching method based on a dual-drive system according to any embodiment of the present invention.

[0073] In this embodiment, the storage medium is a computer-readable storage medium, and the computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0074] In summary, this invention, based on a motor matching method, apparatus, device, and storage medium for a dual-drive system, generates a motor speed dataset by aggregating motor speed data from multiple motors. It then pairs the motor speed data in the dataset, calculates the distance correlation coefficient for each pair, and generates a correlation parameter matrix based on the calculation results. The minimum value of the correlation parameter matrix and its corresponding two sets of motor speed data are obtained and saved. The two sets of motor speed data corresponding to the minimum value in the dataset are then deleted, generating a new motor speed dataset. This process is repeated until no motor speed data remains in the dataset, at which point the motor matching result dataset is output. Compared to existing technologies, this invention reduces the differences between paired motors by matching data from multiple motors.

[0075] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present invention.

Claims

1. A motor matching method based on a dual-drive system, characterized in that, include: Obtain motor speed data corresponding to multiple motors under preset operating conditions, and preprocess the motor speed data to generate a motor speed dataset; The motor speed data in the motor speed dataset are paired up in pairs, and the distance correlation coefficient between the two sets of motor speed data is calculated based on the pairing results. Based on the calculation results, a correlation parameter matrix is ​​generated. Obtain the minimum value of the correlation parameter matrix, and save the minimum value and the corresponding two sets of motor speed data into the matching result dataset; Delete the two sets of motor speed data corresponding to the minimum value in the motor speed dataset, generate a new motor speed dataset, determine whether there is motor speed data in the motor speed dataset, if yes, return to the step "pair up the motor speed data in the motor speed dataset", if no, output the matching result dataset; The step of pairing the motor speed data in the motor speed dataset includes: For each motor speed data in the motor speed dataset, perform a split and pairing operation on the left and right wheel motors of different smart cars to obtain all pairing possibilities and get the pairing results; The calculation of the distance correlation coefficient between the two sets of motor speed data based on the pairing results includes: Obtain the difference between the two sets of motor speed data in each pair, and use the difference between the two sets of motor speed data as the distance correlation coefficient corresponding to the pair; The step of deleting the two sets of motor speed data corresponding to the minimum value in the motor speed dataset to generate a new motor speed dataset, determining whether motor speed data exists in the motor speed dataset, and if so, returning to the step "pairing the motor speed data in the motor speed dataset", includes: Based on the two sets of motor speed data corresponding to the minimum value in the obtained correlation parameter matrix, the two sets of motor speed data in the corresponding motor speed dataset are deleted, and a new motor speed dataset is generated. It is determined whether there is motor speed data in the newly generated motor speed dataset. If so, the process returns to the step "pairing the motor speed data in the motor speed dataset" and continuously updates the motor speed data in the motor speed dataset to continuously generate a new correlation parameter matrix. The minimum value is obtained from the continuously generated new correlation parameter matrix, and the left and right wheel motor numbers of the smart car corresponding to the two sets of motor speed data with the minimum value and the obtained minimum value are saved to the matching result dataset.

2. The motor matching method based on a dual-drive system as described in claim 1, characterized in that, The motor speed data is preprocessed to generate a motor speed dataset, specifically as follows: The format of the motor speed data is adjusted to make the time step of all motor speed data the same. The adjusted motor speed data are then aggregated to generate a motor speed dataset.

3. The motor matching method based on a dual-drive system as described in claim 1, characterized in that, After outputting the matching result dataset, the method further includes: The multiple motors were re-paired and reassembled based on the matching result dataset, and the reassembled motors were experimentally verified.

4. A motor matching device based on a dual-drive system, characterized in that, include: The system includes a data preprocessing module, a matching module, a data saving module, and a matching result output module. The data preprocessing module is used to acquire motor speed data corresponding to multiple motors under preset operating conditions, and to preprocess the motor speed data to generate a motor speed dataset. The pairing module is used to pair the motor speed data in the motor speed dataset in pairs, calculate the distance correlation coefficient between the two sets of motor speed data based on the pairing results, and generate a correlation parameter matrix based on the calculation results. The data storage module is used to obtain the minimum value of the correlation parameter matrix and save the minimum value and the corresponding two sets of motor speed data into the matching result dataset. The matching result output module is used to delete the two sets of motor speed data corresponding to the minimum value in the motor speed dataset, generate a new motor speed dataset, determine whether there is motor speed data in the motor speed dataset, if yes, return to the step "pair the motor speed data in the motor speed dataset", if no, output the matching result dataset; The pairing module performs pairwise pairing of motor speed data in the motor speed dataset, including: The pairing module performs a splitting and pairing operation on each motor speed data in the motor speed dataset, corresponding to the left and right wheel motors of different smart cars, to obtain all pairing possibilities and obtain the pairing result. The pairing module calculates the distance correlation coefficient between the two sets of motor speed data based on the pairing results, including: The pairing module obtains the difference between the two sets of motor speed data in each pairing, and uses the difference between the two sets of motor speed data as the distance correlation coefficient corresponding to the pairing; The matching result output module deletes the two sets of motor speed data corresponding to the minimum value in the motor speed dataset, generates a new motor speed dataset, and determines whether motor speed data exists in the motor speed dataset. If so, it returns to the step "pairing the motor speed data in the motor speed dataset," which includes: The matching result output module, based on the minimum value in the obtained correlation parameter matrix, deletes the corresponding two sets of motor speed data in the motor speed dataset and generates a new motor speed dataset. It then determines whether motor speed data exists in the newly generated motor speed dataset. If so, it returns to the step "pairing the motor speed data in the motor speed dataset" and continuously updates the motor speed data in the motor speed dataset to continuously generate a new correlation parameter matrix. The module then obtains the minimum value of the continuously generated correlation parameter matrix and saves the left and right wheel motor numbers of the smart car corresponding to the two sets of motor speed data with the minimum value and the obtained minimum value to the matching result dataset.

5. The motor matching device based on a dual-drive system as described in claim 4, characterized in that, The data preprocessing module is used to preprocess the motor speed data to generate a motor speed dataset, specifically as follows: The format of the motor speed data is adjusted to make the time step of all motor speed data the same. The adjusted motor speed data are then aggregated to generate a motor speed dataset.

6. The motor matching device based on a dual-drive system as described in claim 4, characterized in that, Also includes: Assembly modules; The assembly module is used to reassemble the multiple motors according to the matching result dataset, and to conduct experimental verification on the reassembled multiple motors.

7. A terminal device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the motor matching method based on a dual-drive system as described in any one of claims 1 to 3.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the motor matching method based on a dual-drive system as described in any one of claims 1 to 3.

Images