Model training method, clutch control method and related equipment

Abstract

The present application provides a model training method and a clutch control method. The method can obtain a first position value of a clutch and parameters corresponding to the first position value when a first preset condition is satisfied, and use the first position value and parameters as training data to train a clutch control model, thereby obtaining a clutch control model trained based on clutch position data during normal vehicle operation. The clutch control method obtains vehicle parameters and then inputs the parameters into the clutch control model to obtain a reference position value, thereby controlling the clutch based on the reference position value, thereby achieving high-precision clutch control.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a model training method, a gear selection control method, a device, a equipment, a computer-readable storage medium, a computer program product, and a clutch control method, a device, a device, a computer-readable storage medium, and a computer program product. Background Art

[0002] The clutch provides a flexible connection between shafts. When controlling the clutch through an automated manual transmission (AMT), the clutch's slip point is crucial. This point refers to the clutch's position when the clutch is engaged and the engine speed is within a certain range.

[0003] Therefore, a machine learning method can be used to determine the reference position of the clutch slip point, and the clutch can be controlled according to the reference position.

[0004] However, in general, the data source for the position value of the clutch slip point is static data, which may have a certain deviation from the actual working conditions. Since the training data is not real, the output results of machine learning may be unrealistic. Summary of the Invention

[0005] This application provides a model training method and a clutch control method. This method can train and obtain a clutch control model with high accuracy, and the clutch control method can achieve high-precision clutch control using this clutch control model. This application also provides corresponding devices, equipment, computer-readable storage media, and computer program products.

[0006] In a first aspect, the present application provides a model training method, the method comprising:

[0007] obtaining a first position value of the clutch when a first preset condition is satisfied, wherein the first preset condition includes clutch engagement;

[0008] Obtaining a parameter corresponding to the first position value, the parameter including at least one of a gear position, a load, and a slope;

[0009] The first position value and the parameter are used as training data, and a clutch control model is trained using the training data. The clutch control model is used to output a reference position value to control the clutch.

[0010] In some possible implementations, the first preset condition includes that the engine speed satisfies a preset speed condition, and the first position value of the clutch is a slip point position value of the clutch.

[0011] In some possible implementations, the method further includes:

[0012] Acquiring a fully disengaged position value of the clutch and a fully engaged position value of the clutch;

[0013] The step of using the first position value and the parameter as training data and training the clutch control model using the training data includes:

[0014] The first position value, the parameter, the completely disengaged position value, and the completely engaged position value are used as training data, and a clutch control model is trained using the training data.

[0015] In some possible implementations, obtaining the fully disengaged position value of the clutch and the fully engaged position value of the clutch includes:

[0016] comparing the position value of the clutch with the position value of the last acquisition point;

[0017] The larger value is determined as the complete separation position value, and the smaller value is determined as the complete binding position value.

[0018] In some possible implementations, the first preset condition includes air pressure satisfying a preset air pressure condition.

[0019] In a second aspect, the present application provides a clutch control method, the method comprising:

[0020] Acquiring vehicle parameters, the parameters including at least one of a gear position, a load, and a slope;

[0021] Inputting the parameters into a clutch control model, and obtaining a reference position value of the clutch according to the parameters through the clutch control model;

[0022] The clutch is controlled according to the reference position value.

[0023] In a third aspect, the present application provides a model training device, comprising:

[0024] a position value acquisition module, configured to acquire a first position value of the clutch when a first preset condition is satisfied, wherein the first preset condition includes clutch engagement;

[0025] a parameter acquisition module, configured to acquire a parameter corresponding to the first position value, the parameter comprising at least one of a gear position, a load, and a slope;

[0026] A training module is used to use the first position value and the parameter as training data to train a clutch control model through the training data, and the clutch control model is used to output a reference position value to control the clutch.

[0027] In some possible implementations, the first preset condition includes that the engine speed satisfies a preset speed condition, and the first position value of the clutch is a slip point position value of the clutch.

[0028] In some possible implementations, the position value acquisition module is further configured to:

[0029] Acquiring a fully disengaged position value of the clutch and a fully engaged position value of the clutch;

[0030] The training module is also used to:

[0031] The first position value, the parameter, the completely disengaged position value, and the completely engaged position value are used as training data, and a clutch control model is trained using the training data.

[0032] In some possible implementations, the position value acquisition module is specifically used to:

[0033] comparing the position value of the clutch with the position value of the last acquisition point;

[0034] The larger value is determined as the complete separation position value, and the smaller value is determined as the complete binding position value.

[0035] In some possible implementations, the first preset condition includes air pressure satisfying a preset air pressure condition.

[0036] In a fourth aspect, the present application provides a clutch control device, comprising:

[0037] a parameter acquisition module, configured to acquire vehicle parameters, wherein the parameters include at least one of a gear position, a load, and a slope;

[0038] a target position value acquisition module, configured to input the parameters into a clutch control model, and acquire a reference position value of the clutch according to the parameters through the clutch control model;

[0039] A control module is configured to control the clutch according to the reference position value.

[0040] In a fifth aspect, the present application provides a device comprising a processor and a memory. The processor and the memory communicate with each other. The processor is configured to execute instructions stored in the memory, causing the device to perform the method of any implementation of the first or second aspect.

[0041] In a sixth aspect, the present application provides a computer-readable storage medium, in which instructions are stored, and the instructions instruct a device to execute the method described in any implementation of the first aspect or the second aspect above.

[0042] In a seventh aspect, the present application provides a computer program product comprising instructions, which, when executed on a device, enables the device to execute the method described in any one of the implementations of the first or second aspect above.

[0043] Based on the implementation methods provided in the above aspects, this application can also be further combined to provide more implementation methods.

[0044] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0045] An embodiment of the present application provides a model training method that obtains a first position value of a clutch when a first preset condition, including clutch engagement, is satisfied, then obtains parameters corresponding to the first position value, and uses the first position value and the parameters as training data to train a clutch control model, thereby enabling the clutch control model to output a reference position value. The clutch control method can obtain parameter data of a vehicle, including at least one of gear position, load, and slope, and then input the parameter data into the clutch control model to obtain a reference position value of the clutch, and then control the clutch based on the reference position value.

[0046] In this way, the position value of the clutch in normal operation is used as training data for machine learning, thereby obtaining a clutch control model with high accuracy. The clutch is controlled by the parameter data output by the model, thereby achieving high-precision control of the clutch.

[0047] Based on the implementation methods provided in the above aspects, this application can also be further combined to provide more implementation methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical methods of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0049] Figure 1 A flowchart of a model training method provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of determining a clutch disengagement position and an engagement position provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of verifying the disengaged position and engaged position of a clutch provided in an embodiment of the present application;

[0052] Figure 4A schematic diagram of determining a clutch slip point provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of a clutch control process provided in an embodiment of the present application;

[0054] Figure 6 A schematic diagram of the results of a model training device provided in an embodiment of the present application;

[0055] Figure 7 A schematic structural diagram of a clutch control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following will describe the solutions in the embodiments provided in this application in conjunction with the drawings in this application.

[0057] The terms "first" and "second" in the embodiments of this application are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Therefore, features specified as "first" or "second" may explicitly or implicitly include one or more of the features.

[0058] First, some technical terms involved in the embodiments of this application are introduced.

[0059] An automated mechanical transmission (AMT) is an automatic transmission with an electronic unit installed while the basic structure of the original mechanical manual transmission remains unchanged. It replaces the manual operations of the driver, such as clutch disengagement and engagement, shifting and engaging gears, and adjusting the engine speed and torque, thus automating the shifting process and bringing convenience to the driver.

[0060] Clutches are used to connect shafts. In automotive applications, friction clutches are typically used. They can be used to create a connection with a speed difference between the engine and the transmission input shaft.

[0061] When controlling the clutch through an AMT, the clutch slip point is very important. The slip point refers to the position of the clutch when the clutch is engaged and the engine speed is within a certain range.

[0062] Therefore, a machine learning method can be used to determine the reference position of the slip point of the clutch, so that the clutch can be controlled according to the reference position.

[0063] However, the data source for the clutch slip point position value is usually static data, which may deviate from the actual working conditions, resulting in unrealistic training data. Unrealistic training data may also lead to unrealistic machine learning output results.

[0064] In view of this, the present application provides a clutch control method and a model training method, which uses the position value of the clutch in normal operation as training data for machine learning, thereby obtaining a clutch control model with high accuracy, and controls the clutch through the reference data output by the model, thereby achieving higher-precision control of the clutch.

[0065] The control method can be executed by an automatic transmission control unit (TCU). Specifically, the TCU obtains vehicle parameter data, including at least one of gear position, load, and slope, and then inputs the parameter data into a clutch control model to obtain a reference position value for the clutch. The clutch is then controlled based on the reference position value.

[0066] The clutch control model can be trained using training data. Specifically, the processing device can obtain a first position value of the clutch when a first preset condition, including clutch engagement, is satisfied, and then obtain parameters corresponding to the first position value. The first position value and parameters are used as training data to train the clutch control model, thereby enabling the clutch control model to output a reference position value.

[0067] The processing device can be a device with data processing capabilities. In this embodiment, since the first position value and parameters are obtained during normal operation of the vehicle, the processing device can be a device with data processing capabilities during normal operation of the vehicle, such as an electronic control unit (ECU) or a TCU.

[0068] In order to make the technical solution of the present disclosure clearer and easier to understand, the following takes TCU as an example. Figure 1 As shown, the model training method provided by the embodiment of the present disclosure is introduced.

[0069] S102: The TCU obtains a first position value of the clutch when a first preset condition is met.

[0070] The first preset condition includes clutch engagement. When the clutch is engaged and the engine speed meets the preset speed condition, the current clutch position value is the clutch slip point position value. The first clutch position value refers to the current clutch position value, i.e., the first clutch position is the clutch slip point position value. Meeting the first preset condition indicates that the vehicle is operating normally.

[0071] For example, the preset speed condition may be that the engine speed ranges from 50 to 100 r / s. When the clutch is engaged and the engine speed ranges from 50 to 100 r / s, the slip point position of the clutch is acquired.

[0072] In some possible implementations, to avoid errors, the clutch slip point position may be the average of the clutch position at the current moment, the clutch position at the previous acquisition point (step length), and the clutch position at the previous acquisition point (step length), where both the previous acquisition point and the previous acquisition point satisfy the first preset condition.

[0073] Furthermore, the first preset condition also includes an air pressure condition, that is, the air pressure satisfies the preset air pressure condition. Satisfying the preset air pressure condition indicates that the air pressure in the gas tank is sufficient. For example, the air pressure condition may be that the air pressure value is greater than 6 Pa (par).

[0074] The first preset condition may also include the position value range, such as Figure 2 As shown, when the clutch is engaged and the engine speed meets the preset speed condition (for example, the engine speed is between 50-100 rpm), the actual clutch position at that time is determined as the slip point position value. The slip point position values ​​under the same parameter conditions are then continuously recorded, and a moving average is taken as the final slip point position value, or the first position value. If the number of slip points under the same parameter conditions is less than the step size of the moving average, the positions of the first few slip points are determined as the first position value, and recording continues for the next driving cycle. If the default slip point position value is 54 mm, the position value range can be 50 mm to 55 mm.

[0075] S104: The TCU obtains parameters corresponding to the first position value.

[0076] Parameters include one or more of gear position, load, and slope. Parameters may also include engine water temperature, vehicle speed, and air pipe pressure. The following uses the gear position, load, and slope as an example.

[0077] Specifically, the TCU determines various parameters corresponding to the first position value. In some possible implementations, the TCU obtains the corresponding parameters when obtaining the first position value of the clutch.

[0078] S106: The TCU uses the first position value and the parameters as training data to train the clutch control model.

[0079] The clutch control model is used to output a reference position value so as to control the clutch according to the reference position value.

[0080] Specifically, the TCU may use the first position value and the corresponding parameters as training data to train the clutch control model. The clutch control model may be implemented through machine learning, such as a neural network model.

[0081] In some possible implementations, the TCU may save the correspondence between the parameter and the first position value in the form of a MAP.

[0082] The TCU also obtains the fully disengaged position value and the fully engaged position value of the clutch. The TCU can then use the first position value, the parameter, the fully disengaged position value, and the fully engaged position value as training data to train the clutch control model.

[0083] In some possible implementations, the recording of completely separate position values ​​and completely combined position values ​​can be as follows: Figure 3 As shown. The TCU can verify the current position value with the original data, and determine whether to use the current position value as training data based on the verification result. For example, if the current position value is significantly different from the original data, the position value will not be used as training data. If the separation position is the maximum value and the engagement position is the minimum value, then the position value of the current acquisition point can be compared with the position value saved at the previous acquisition point (previous step length), and the larger value is taken as the clutch completely separation position value, and the smaller value is taken as the fully engaged position value. At the next moment, the current position value will continue to be compared with the saved position value, and the larger value will be taken as the clutch completely separation position value, and the smaller value will be taken as the fully engaged position value.

[0084] For example, in chronological order, the position values ​​are: x1, x2, x3, x4, x5, where the interval is one step, and the position value size is: x1>x2>x4>x5>x3. Then, at the time x2, the completely separated position value is x1, and the completely joined position value is x2. At the time x3, the completely separated position value is x1, and the completely joined position value is x3. At the time x4, the completely separated position value is x1, and the completely joined position value is x3. At the time x5, the completely separated position value is x1, and the completely joined position value is x3.

[0085] Similarly, the values ​​for the fully separated position and the fully joined position can also be verified. If they differ significantly from the default values, they are not used as training data. Taking into account loss, for example, if the default value for the fully separated position is 72mm, then the range of the fully separated position value can be set to 70mm to 74mm. If the default value for the fully joined position is 42mm, then the range of the fully joined position value can be set to 40mm to 44mm.

[0086] In some possible implementations, the engine has two modes: hybrid starting and motor reverse engine starting. Different clutch control models can be obtained according to different starting modes to achieve accurate control of different starting modes.

[0087] like Figure 4 As shown, when the clutch is engaged and the engine speed range meets preset conditions (e.g., 50-100 rpm), the clutch position at that moment is recorded as the slip point. The slip point positions within the same gear, load, slope, and air pressure ranges are continuously recorded, and a moving average (e.g., the average of three steps) is taken as the slip point position value. If the number of slip points within the same gear, load, slope, and air pressure range is less than the step length of the moving average, the moving average of the first few times is recorded as training data.

[0088] As described above, this application provides a model training method. Specifically, a TCU obtains a first clutch position value when a first preset condition is satisfied, where the first preset condition includes clutch engagement. Parameters corresponding to the first position value, including gear position, load, and slope, are then obtained. The first position value and parameters are used as training data to train a clutch control model, thereby obtaining a clutch control model capable of outputting accurate reference position values. Because the training data is based on values ​​that satisfy the first preset condition, it is real data collected under actual operating conditions. Therefore, the parameters output by the clutch control model trained based on this real training data are highly accurate.

[0089] The clutch control model obtained by training in the above manner can output a reference position value for realizing clutch control.

[0090] Take TCU as an example below. Figure 5 As shown, the clutch control method of the embodiment of the present disclosure is introduced.

[0091] S502: The TCU obtains vehicle parameters.

[0092] The vehicle parameters include gear position, load, slope, etc. The TCU can obtain various parameters of the vehicle including gear position, load, and slope through the ECU.

[0093] S504: The TCU inputs the vehicle parameters into the clutch control model, and outputs a reference position value of the clutch according to the parameters through the clutch control model.

[0094] The clutch control model may be a clutch control model trained through S102 to S106 , or a clutch control model obtained through training in other ways.

[0095] The input data of the clutch control model are the relevant parameters of the vehicle, and the output is the reference position value of the clutch.

[0096] S506: The TCU controls the clutch according to the reference position value.

[0097] TCU can control the clutch according to the reference position value to achieve automatic shifting and improve the automation of shifting operations.

[0098] In this way, during the control process of the clutch, the TCU can obtain the vehicle's parameters including at least one of the gear, load and slope, and then obtain the reference position value through the clutch control model based on these parameters, and control the clutch according to the reference position value, thereby achieving high-precision control of the clutch.

[0099] Corresponding to the above method embodiment, this application also provides a model training device, see Figure 6 The device 600 includes: a position value acquisition module 602, a parameter acquisition module 604 and a training module 606.

[0100] a position value acquisition module, configured to acquire a first position value of the clutch when a first preset condition is satisfied, wherein the first preset condition includes clutch engagement;

[0101] a parameter acquisition module, configured to acquire a parameter corresponding to the first position value, the parameter comprising at least one of a gear position, a load, and a slope;

[0102] A training module is used to use the first position value and the parameter as training data to train a clutch control model through the training data, and the clutch control model is used to output a reference position value to control the clutch.

[0103] In some possible implementations, the first preset condition includes that the engine speed satisfies a preset speed condition, and the first position value of the clutch is a slip point position value of the clutch.

[0104] In some possible implementations, the position value acquisition module is further configured to:

[0105] Acquiring a fully disengaged position value of the clutch and a fully engaged position value of the clutch;

[0106] The training module is also used to:

[0107] The first position value, the parameter, the completely disengaged position value, and the completely engaged position value are used as training data, and a clutch control model is trained using the training data.

[0108] In some possible implementations, the position value acquisition module is specifically used to:

[0109] comparing the position value of the clutch with the position value of the last acquisition point;

[0110] The larger value is determined as the complete separation position value, and the smaller value is determined as the complete binding position value.

[0111] In some possible implementations, the first preset condition includes air pressure satisfying a preset air pressure condition.

[0112] Corresponding to the above method embodiment, the present application also provides a clutch control device, see Figure 7 The device 700 includes: a parameter acquisition module 702, a target position value acquisition module 704 and a control module 706.

[0113] a parameter acquisition module, configured to acquire vehicle parameters, wherein the parameters include at least one of a gear position, a load, and a slope;

[0114] a target position value acquisition module, configured to input the parameters into a clutch control model, and acquire a reference position value of the clutch according to the parameters through the clutch control model;

[0115] A control module is configured to control the clutch according to the reference position value.

[0116] The present application provides a device for implementing a model training method. The device includes a processor and a memory. The processor and the memory communicate with each other. The processor is configured to execute instructions stored in the memory to cause the device to perform the model training method.

[0117] The present application provides a device for implementing a clutch control method. The device includes a processor and a memory. The processor and the memory communicate with each other. The processor is configured to execute instructions stored in the memory to cause the device to perform the clutch control method.

[0118] The present application provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a device, the device executes the above-mentioned model training method.

[0119] The present application provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a device, the device executes the above-mentioned clutch control method.

[0120] The present application provides a computer program product containing instructions, which, when executed on a device, enables the device to perform the above-mentioned model training method.

[0121] The present application provides a computer program product comprising instructions, which, when executed on a device, enables the device to perform the above clutch control method.

[0122] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.

[0123] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memories, special components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits, etc. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.

[0124] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0125] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website, a computer, a training device or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

Claims

1. A model training method, characterized in that: The method comprises: Acquiring a first position value of the clutch when a first preset condition is satisfied, wherein the first preset condition includes clutch engagement, and the first position value of the clutch is a slip point position value of the clutch; Obtaining a parameter corresponding to the first position value, the parameter including at least one of a gear position, a load, and a slope; Using the first position value and the parameter as training data, a clutch control model is trained using the training data, wherein the clutch control model is used to output a reference position value to control the clutch; Acquiring a fully disengaged position value of the clutch and a fully engaged position value of the clutch; The step of using the first position value and the parameter as training data and training the clutch control model using the training data includes: using the first position value, the parameter, the fully disengaged position value, and the fully engaged position value as training data, and training a clutch control model using the training data; The obtaining of the fully disengaged position value of the clutch and the fully engaged position value of the clutch includes: comparing the position value of the clutch with the position value of the last acquisition point; The larger value is determined as the complete separation position value, and the smaller value is determined as the complete binding position value.

2. The method according to claim 1, characterized in that The first preset condition includes that the engine speed meets a preset speed condition.

3. The method according to claim 1, characterized in that The first preset condition includes that the air pressure meets a preset air pressure condition.

4. A clutch control method, characterized in that: The method comprises: Acquiring vehicle parameters, the parameters including at least one of a gear position, a load, and a slope; Inputting the parameters into a clutch control model, and obtaining a reference position value of the clutch according to the parameters through the clutch control model; the clutch control model is trained by the method according to any one of claims 1 to 3 above; The clutch is controlled according to the reference position value.

5. A model training device, characterized in that: The device comprises: a position value acquisition module, configured to acquire a first position value of the clutch when a first preset condition is satisfied, wherein the first preset condition includes clutch engagement, and the first position value of the clutch is a slip point position value of the clutch; a parameter acquisition module, configured to acquire a parameter corresponding to the first position value, the parameter comprising at least one of a gear position, a load, and a slope; a training module, configured to use the first position value and the parameter as training data, and train a clutch control model using the training data, wherein the clutch control model is configured to output a reference position value for controlling the clutch; The position value acquisition module is also used to: Acquiring a fully disengaged position value of the clutch and a fully engaged position value of the clutch; The training module is also used to: using the first position value, the parameter, the fully disengaged position value, and the fully engaged position value as training data, and training a clutch control model using the training data; The position value acquisition module is specifically used for: comparing the position value of the clutch with the position value of the last acquisition point; The larger value is determined as the complete separation position value, and the smaller value is determined as the complete binding position value.

6. A clutch control device, characterized in that: The device comprises: a parameter acquisition module, configured to acquire vehicle parameters, wherein the parameters include at least one of a gear position, a load, and a slope; a target position value acquisition module, configured to input the parameters into a clutch control model and obtain a reference position value of the clutch according to the parameters through the clutch control model; the clutch control model is trained by the method described in any one of claims 1 to 3; A control module is configured to control the clutch according to the reference position value.

7. A device, characterized in that The device includes a processor and a memory; The processor is configured to execute instructions stored in the memory, so that the device performs the method according to any one of claims 1 to 3.

8. A computer-readable storage medium, characterized in that The method comprises instructions for instructing a device to execute the method according to any one of claims 1 to 3.

Images