Vehicle torque control method and device, vehicle and medium

Abstract

The invention discloses a vehicle torque control method and device, a vehicle and a medium, the vehicle torque control method and device are applied to a vehicle torque control system, the vehicle torque control system is arranged in the vehicle, and the method comprises the steps that vehicle driving parameters and a basic torque coefficient issued by a cloud end are obtained, and determining a steady-state torque coefficient, a transient torque coefficient and driving control demand information according to the vehicle driving parameters, selecting the steady-state torque coefficient or the transient torque coefficient according to the driving control demand information to adjust the basic torque coefficient to obtain a target torque coefficient, and controlling the vehicle torque by adopting the target torque coefficient. According to the method, the basic torque coefficient issued by the cloud can be dynamically adjusted based on the vehicle driving parameters, the target torque coefficient is obtained, vehicle torque control is carried out on the basis of the target torque coefficient, the self-adaptive intelligent level of torque control is improved, and the response speed of vehicle control and the user experience are guaranteed.

Description

Technical Field

[0001] This application belongs to the field of torque control, specifically relating to a vehicle torque control method, device, vehicle, and medium. Background Technology

[0002] In related technologies, a "cloud-vehicle" collaborative architecture is typically used for intelligent torque control. The cloud acts as the core decision-making center, capable of calculating and issuing one or more control parameters representing each driver's driving style. The vehicle typically passively receives and stores these control parameters from the cloud, and adjusts the final target torque output accordingly.

[0003] However, in actual use, cloud-based control parameters are often generated based on historical data or global optimization goals, while the vehicle lacks the ability to autonomously optimize cloud-based parameters based on local real-time driving data. When faced with unexpected situations or dynamic changes, the control parameters issued by the cloud may deviate from the user's current actual driving needs. Because the vehicle cannot correct these deviations in a timely and automatic manner based on local real-time data, the adaptive intelligence level of torque control is limited, thereby affecting the vehicle's handling response speed and user experience. Summary of the Invention

[0004] The purpose of this application is to provide a vehicle torque control method, device, vehicle, and medium that can solve the problem of discrepancies between the control parameters sent from the cloud and the user's current actual driving needs.

[0005] To solve the above-mentioned technical problems, this application is implemented as follows: In a first aspect, embodiments of this application provide a vehicle torque control method, applied to a vehicle torque control system, wherein the vehicle torque control system is disposed in a vehicle, and the method includes: Obtain vehicle driving parameters and basic torque coefficients sent from the cloud; Based on the vehicle driving parameters, determine the steady-state torque coefficient, transient torque coefficient, and driving control requirements. Based on the driving control requirements information, the steady-state torque coefficient or the transient torque coefficient is selected to adjust the base torque coefficient to obtain the target torque coefficient; The target torque coefficient is used to control the vehicle torque.

[0006] Optionally, determining the steady-state torque coefficient, transient torque coefficient, and driving control requirements information based on the vehicle driving parameters includes: Determine the stable driving range based on the vehicle driving parameters; Within the stable driving range, the count of user effort actions is determined based on the vehicle driving parameters; wherein, the user effort action represents the additional pedal operation performed by the user to correct the deviation between the actual vehicle driving state and the expected vehicle driving state. The effort level index is determined based on the number of effort actions within a preset statistical mileage. The rate of change of effort is determined based on several of the aforementioned effort indicators; If the rate of change of effort is greater than a preset threshold, the steady-state torque coefficient is determined based on the rate of change of effort and the preset steady-state coefficient correction information. The transient torque coefficient is obtained by identifying the vehicle driving parameters using a trained transient coefficient identification model. The vehicle driving parameters are identified using a trained driving control demand recognition model to obtain the driving control demand information.

[0007] Optionally, the vehicle driving parameters include torque adaptive mode status, gear information, vehicle speed, accelerator pedal opening, target torque, and longitudinal acceleration; the stable driving range includes a stable speed range, a stable acceleration range, a stable deceleration range, and a stable feedback range; determining the stable driving range based on the vehicle driving parameters includes: When the torque adaptive mode is enabled, the gear information is in driving gear, the vehicle speed is greater than a preset first threshold, and the accelerator pedal opening is greater than a preset second threshold, a first time window is obtained. The first time window includes a plurality of second time windows arranged in chronological order. The first time window also includes a random time window. The starting point of the random time window is the starting point of the first time window, and the ending point of the random time window is any time point in the first time window. Within the first time window, several second time windows, and the random time window, the vehicle speed range, the peak value of longitudinal acceleration, the valley value of longitudinal acceleration, and the acceleration range are determined based on the vehicle speed and the longitudinal acceleration, respectively. If the target torque is greater than zero, and if several speed ranges within the first time window, the second time window, and the random time window are all less than a preset third threshold, then the first time window is taken as a stable speed range. If, when the target torque is greater than zero, several longitudinal acceleration valleys within the first time window, the second time window, and the random time window are all greater than a preset fourth threshold and several acceleration ranges are all less than a preset fifth threshold, then the first time window is taken as a stable acceleration interval. If, when the target torque is less than zero, several longitudinal acceleration peaks within the first time window, the second time window, and the random time window are all less than a preset sixth threshold and several acceleration ranges are all less than a preset fifth threshold, then the first time window is taken as a stable deceleration interval. If, when the target torque is less than zero, several longitudinal acceleration peaks within the first time window, the second time window, and the random time window are all less than a preset seventh threshold and several acceleration ranges are all less than a preset fifth threshold, then, when the target torque is less than a preset eighth threshold, the first time window is taken as a stable feedback interval.

[0008] Optionally, determining the effort count of the user's effort action based on the vehicle driving parameters within the stable driving range includes: For the stable vehicle speed range, the stable acceleration range, the stable deceleration range, and the stable feedback range, a number of second time windows are determined corresponding to the stable vehicle speed range, the stable acceleration range, the stable deceleration range, and the stable feedback range, respectively. Within several second time windows corresponding to the stable vehicle speed range, the stable acceleration range, and the stable deceleration range, the rising edge difference sequence of the trough and falling edge difference sequence of the accelerator pedal opening are obtained respectively; the rising edge difference sequence of the trough includes the opening difference between each extreme point of the accelerator pedal opening in the second time window and the next adjacent extreme point of the peak; the falling edge difference sequence of the peak includes the opening difference between each extreme point of the accelerator pedal opening in the second time window and the next adjacent extreme point of the trough. For any second time window, if the maximum value in the difference sequence of the rising edge of the trough or the maximum value in the difference sequence of the falling edge of the peak is greater than a preset ninth threshold, then there is a user effort action in the second time window, and the effort action count is generated.

[0009] Optionally, the vehicle driving parameters further include driving mileage, and the effort index includes a driving effort index and a feedback effort index; determining the effort index based on the number of effort actions within a preset statistical mileage includes: When the driving mileage is greater than or equal to the preset statistical mileage, the count of the effort actions within the stable speed range, the stable acceleration range, the stable deceleration range, and the stable feedback range within the preset statistical mileage is obtained respectively. The driving effort index is determined based on the number of effort actions within the stable speed range, the stable acceleration range, and the stable deceleration range. The feedback effort index is determined based on the number of effort actions within the stable feedback interval.

[0010] Optionally, the effort change rate includes the driving effort change rate and the feedback effort change rate, and determining the effort change rate based on several effort indicators includes: Take any of the preset statistical mileages as the current statistical mileage, and obtain the driving effort index and the feedback effort index in the current statistical mileage; Take the previous statistical mileage of the current statistical mileage as the reference statistical mileage, and obtain the driving effort index and the feedback effort index in the reference statistical mileage. The rate of change of driving effort is determined based on the driving effort index in the current statistical mileage and the driving effort index in the reference statistical mileage; The rate of change of feedback effort is determined based on the feedback effort index in the current statistical mileage and the feedback effort index in the reference statistical mileage.

[0011] Optionally, adjusting the base torque coefficient based on the steady-state torque coefficient or the transient torque coefficient according to the driving control requirement information to obtain the target torque coefficient includes: When the driving control demand information indicates that the user has an instantaneous driving control demand, the transient torque coefficient is selected to adjust the basic torque coefficient to obtain the target torque coefficient; When the driving control demand information indicates that the user does not have instantaneous driving control needs, the steady-state torque coefficient is selected to adjust the base torque coefficient to obtain the target torque coefficient.

[0012] Secondly, embodiments of this application provide a vehicle torque control device, applied to a vehicle torque control system, wherein the vehicle torque control system is disposed in a vehicle, and the device includes: The parameter acquisition module is used to acquire vehicle driving parameters and the basic torque coefficient sent from the cloud. The coefficient determination module is used to determine the steady-state torque coefficient, transient torque coefficient, and driving control requirements based on the vehicle driving parameters. The coefficient adjustment module is used to select the steady-state torque coefficient or the transient torque coefficient according to the driving control requirement information to adjust the base torque coefficient to obtain the target torque coefficient; A torque control module is used to control the vehicle torque using the target torque coefficient.

[0013] Thirdly, embodiments of this application provide a vehicle including a processor, a memory, and a program or instructions stored in the memory and capable of running on the processor, wherein the program or instructions, when executed by the processor, implement the method described above.

[0014] Fourthly, a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the method described above.

[0015] The embodiments of this application have the following advantages: In this embodiment, vehicle driving parameters and a base torque coefficient transmitted from the cloud are obtained. Based on the vehicle driving parameters, a steady-state torque coefficient, a transient torque coefficient, and driving control requirements are determined. The base torque coefficient is then adjusted using either the steady-state torque coefficient or the transient torque coefficient based on the driving control requirements to obtain a target torque coefficient. This target torque coefficient is then used to control the vehicle torque. This application can determine the steady-state torque coefficient, transient torque coefficient, and driving control requirements based on vehicle driving parameters, and then dynamically adjust the base torque coefficient transmitted from the cloud. This not only improves the adaptive intelligence level of torque control but also ensures the responsiveness of vehicle handling and the user experience. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0017] Figure 1 This is a flowchart illustrating the steps of a vehicle torque control method according to an embodiment of this application; Figure 2 This is a schematic diagram illustrating the relationship between effort index and steady-state torque coefficient according to an embodiment of this application; Figure 3 This is a flowchart illustrating the steps for determining a stable driving range according to an embodiment of this application; Figure 4 This is a schematic diagram of the pedal opening degree in a first time window provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a vehicle torque control device provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the various embodiments of this application will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details have been presented in the various embodiments of this application to enable readers to better understand this application. However, the technical solutions claimed in this application can be implemented even without these technical details and various changes and updates based on the following embodiments. The division of the various embodiments below is for the convenience of description and should not constitute any limitation on the specific implementation of this application. The various embodiments can be combined with and referenced by each other without contradiction.

[0019] Vehicle torque control, as one of the core functions of the electronic control system of new energy vehicles, directly affects the vehicle's drivability, comfort, and the user's driving experience. Traditional vehicle drive torque control strategies primarily rely on a preset torque map, which typically uses vehicle speed and accelerator pedal opening as key input parameters to directly determine the target drive torque value through a lookup table. While this method is widely used in practice, its core problems lie in the following two aspects: First, there is a lack of personalized adaptation capabilities. Preset torque mapping tables are typically based on statistical averages of large sample data or engineering calibration experience, resulting in fixed output characteristics that cannot adapt to the diverse driving style preferences of different drivers. For example, some drivers prefer aggressive power response, while others prefer a smooth and comfortable driving experience. For specific users, fixed torque output characteristics may not meet their power expectations, leading to long-term driving fatigue or motion sickness. Although some models offer driving modes such as Eco, Normal, and Sport for users to manually select, the following problems still exist: drivers need to actively switch modes; some users have low usage rates for different modes—for example, aggressive users may use Sport mode for extended periods, while mild-mannered users may use Eco mode; pseudo-personalization—fixed parameters are still used within a single mode, failing to adapt to the driver's operating habits in real time; for example, mild-mannered drivers may still feel excessive torque in Sport mode; and scenario fragmentation—no correlation strategy is established between steady-state and transient conditions, resulting in a step-like phenomenon in torque output when switching modes.

[0020] Secondly, the intelligence and adaptive capabilities are insufficient. Although existing technologies employ a "cloud-vehicle" collaborative architecture for intelligent torque control and introduce a "driving style factor" to adjust the preset torque map, most of these solutions are still in the static or semi-static adjustment stage. Specifically, the driving style factor, after being periodically calculated and distributed from the cloud, remains fixed for a considerable driving period on the vehicle, unable to adjust in real time and quickly based on the driver's current journey or changes in behavior over the last few hundred kilometers. This response delay prevents the vehicle's torque control from accurately tracking subtle or gradual changes in the user's driving style, making it difficult to achieve the continuous optimization goal of "getting better with age."

[0021] When faced with unexpected situations or dynamic changes, the control parameters sent from the cloud may deviate from the user's actual driving needs. Because the vehicle cannot correct these deviations in a timely and automatic manner based on local real-time data, the adaptive intelligence level of torque control is limited, which in turn affects the vehicle's handling response speed and user experience.

[0022] Therefore, this application provides a vehicle torque control method, device, vehicle, and medium that can determine the steady-state torque coefficient, transient torque coefficient, and driving control demand information based on vehicle driving parameters, and then dynamically adjust the basic torque coefficient sent from the cloud. This not only improves the adaptive intelligence level of torque control, but also ensures the response speed of vehicle operation and user experience.

[0023] Reference Figure 1 The diagram shows a flowchart of a vehicle torque control method according to an embodiment of this application.

[0024] In this embodiment, the vehicle torque control method can be applied to a vehicle torque control system. A vehicle torque control system refers to a system used to control the driving torque of a vehicle, and can be applied to the electronic control system of new energy vehicles or traditional fuel vehicles. It can dynamically adjust the torque output according to driving needs and vehicle status to optimize driving performance and energy efficiency. In this embodiment, the vehicle torque control system can be installed in the vehicle, and can interact with the cloud to obtain a basic torque coefficient.

[0025] The method may specifically include the following steps: Step 101: Obtain vehicle driving parameters and basic torque coefficients sent from the cloud.

[0026] In this embodiment, vehicle driving parameters can be acquired first. These parameters can be key signals collected during actual vehicle operation. Vehicle driving parameters may include torque adaptive mode status, gear information, vehicle speed, accelerator pedal opening, target torque, longitudinal acceleration, and mileage, and can also be set by those skilled in the art. In a specific implementation, vehicle driving parameters can be acquired in real time from the vehicle's CAN network.

[0027] The torque adaptive mode indicates that the vehicle's torque control system automatically adjusts the torque output based on the current driving environment or user needs. The torque adaptive mode can be either active or deactivated.

[0028] Gear information can refer to the current gear position of the vehicle's transmission, such as P (Park), R (Reverse), N (Neutral), D (Drive), etc.

[0029] Vehicle speed can refer to the current speed of a vehicle, and the unit can be kilometers per hour (km / h).

[0030] Accelerator pedal opening refers to the angle or depth at which the driver presses the accelerator pedal, and the unit can be a percentage (%). It can reflect the driver's power demand.

[0031] Target torque can refer to the desired output torque value calculated by the vehicle's torque control system based on current driving needs.

[0032] Longitudinal acceleration refers to the acceleration of a vehicle in the direction of travel, and its unit can be meters per second squared (m / s²). 2 (), can be used to describe how fast a vehicle accelerates or decelerates.

[0033] Mileage refers to the total distance a vehicle has traveled since it left the factory or was last reset, expressed in kilometers (km).

[0034] In this embodiment, a base torque coefficient can be obtained from the cloud. The base torque coefficient reflects the current user's driving style preferences derived from long-term, macroscopic driving behavior analysis. In this embodiment, the base torque coefficient may include a base drive torque coefficient and a base feedback torque coefficient.

[0035] In practice, the base torque coefficient can be calculated and distributed periodically (e.g., every 3-6 months) for each driver via the cloud. The cloud can be a cloud-based big data platform. The base torque coefficient is generated based on statistical analysis of massive amounts of driving data. Specifically, the base torque coefficient can be generated in the cloud using the following methods: Cloud-based big data platforms can periodically (e.g., every 3-6 months) collect anonymized driving data covering a broad user base. Driving data includes, but is not limited to: vehicle speed, accelerator pedal opening, longitudinal acceleration, steering wheel angle, following distance, and lane departure frequency. Driving data can be cleaned and preprocessed to remove noise and outliers.

[0036] Then, the cloud-based big data platform can extract driving style feature indicators that characterize a user's driving style from the preprocessed driving data. For example, features used to quantify driving style may include: average accelerator pedal opening, frequency of rapid acceleration, and distribution of pedal opening change rate; features used to quantify feedback style may include: preference for coasting recovery intensity.

[0037] Cloud-based big data platforms can employ unsupervised machine learning clustering algorithms (such as K-Means and Gaussian Mixture Models, GMM) to perform cluster analysis on all users. Specifically, unsupervised machine learning clustering algorithms can group users with similar driving style characteristics into the same group, thus forming several typical driving style categories (such as "aggressive," "comfort," and "economy"). For each cluster center of a driving style category, the cloud-based big data platform can assign a standardized base torque coefficient. For example, when the driving style category is aggressive, the base driving torque coefficient of the cluster center may be 1, and when the driving style category is comfort, the base driving torque coefficient of the cluster center may be 0.

[0038] Finally, the cloud-based big data platform can acquire the current user's historical driving data, calculate the feature distance between the current user and various driving style categories based on this data, and then categorize the current user into the closest driving style category. Subsequently, considering the current user's subtle feature deviations within the current driving style category, the basic drive torque coefficient or basic feedback torque coefficient is fine-tuned to ultimately generate a basic drive torque coefficient or basic feedback torque coefficient specific to the current user within the range [0,1], which is then transmitted to the vehicle's torque control system via the network.

[0039] Step 102: Determine the steady-state torque coefficient, transient torque coefficient, and driving control requirements based on the vehicle's driving parameters.

[0040] In this embodiment, the steady-state torque coefficient can be determined based on vehicle driving parameters. The steady-state torque coefficient can represent the driver's long-term, habitual torque preference. It can be obtained by progressively fine-tuning the base torque coefficient sent from the cloud based on an effort index. The steady-state torque coefficient can reflect the driver's intrinsic expectations for smooth power response and energy recovery intensity during stable driving without external stimuli.

[0041] In this embodiment, the transient torque coefficient can also be determined based on vehicle driving parameters. The transient torque coefficient can represent the driver's short-term, instantaneous, and intense driving intentions. The transient torque coefficient can be quickly calculated by a real-time recognition model based on intense operation signals (such as rapid acceleration and deceleration) within a very short time window (such as the most recent 1 minute). The transient torque coefficient can ensure that when the driver has a clear need for overtaking, acceleration, etc., the vehicle can provide agile and strong instantaneous power response in a timely manner.

[0042] In this embodiment, driving control demand information can also be determined based on vehicle driving parameters. Driving control demand information can represent the driver's specific needs for vehicle power or control derived from vehicle driving parameters (such as vehicle speed, acceleration, etc.). For example, whether the driver needs rapid acceleration or smooth driving. In this embodiment, driving control demand information can indicate whether the user has instantaneous driving control needs or not.

[0043] Step 103: Based on the driving control requirements information, select the steady-state torque coefficient or transient torque coefficient to adjust the basic torque coefficient to obtain the target torque coefficient.

[0044] In this embodiment, the base torque coefficient can be adjusted by selecting either a steady-state torque coefficient or a transient torque coefficient based on driving control demand information to obtain a target torque coefficient. For example, if the driving control demand information indicates that the user has instantaneous driving control needs, the base torque coefficient can be adjusted by selecting the transient torque coefficient to obtain the target torque coefficient. If the driving control demand information indicates that the user does not have instantaneous driving control needs, the base torque coefficient can be adjusted by selecting the steady-state torque coefficient to obtain the target torque coefficient.

[0045] Step 104: Control the vehicle torque using the target torque coefficient.

[0046] In this embodiment, the vehicle torque control system incorporates a basic torque mapping table and a filtered torque mapping table covering different driving modes, such as Eco, Normal, and Sport modes. The basic torque mapping table can refer to a predefined torque output reference table within the vehicle torque control system. The filtered torque mapping table can refer to a parameter table used to smooth torque output, preventing abrupt or unstable torque output.

[0047] The target torque coefficient can be used to interpolate and weighted fuse the basic torque mapping table and the filtered torque mapping table.

[0048] Specifically, the revised torque mapping table can be obtained in the following way: Final_Pedal_Map=(Factor)*Base_Map_Sport+(1-Factor)*Base_Map_Eco In this table, Final_Pedal_Map represents the revised torque mapping table, Factor represents the target torque coefficient, Base_Map_Sport represents the base torque mapping table for Sport mode, and Base_Map_Eco represents the base torque mapping table for Eco mode. In practice, Base_Map_Sport and Base_Map_Eco can also be replaced with the base torque mapping tables for other driving modes.

[0049] In each control cycle (e.g., 10ms), the vehicle torque control system can look up the corrected torque mapping table Final_Pedal_Map based on the real-time acquired vehicle speed and accelerator pedal opening signal to directly obtain the target torque value at the current moment. This target torque value is sent to the vehicle controller (VCU) in real time via the CAN bus, and the VCU executes the final power distribution to achieve control of the vehicle torque.

[0050] In this embodiment, vehicle driving parameters and a base torque coefficient transmitted from the cloud are obtained. Based on the vehicle driving parameters, a steady-state torque coefficient, a transient torque coefficient, and driving control requirements are determined. The base torque coefficient is then adjusted using either the steady-state torque coefficient or the transient torque coefficient based on the driving control requirements to obtain a target torque coefficient. This target torque coefficient is then used to control the vehicle torque. This application can determine the steady-state torque coefficient, transient torque coefficient, and driving control requirements based on vehicle driving parameters, and then dynamically adjust the base torque coefficient transmitted from the cloud. This not only improves the adaptive intelligence level of torque control but also ensures the responsiveness of vehicle handling and the user experience.

[0051] This application perfectly aligns with the advanced architectural concept of "cloud-based big data mining for long-term characteristics, and vehicle-side real-time data for short-term adaptive control." The cloud is responsible for mining the user's macro driving style from ultra-long-term, massive data and issuing a basic torque coefficient; the vehicle is responsible for fine-tuning the basic torque coefficient based on recent, local data to obtain the target torque coefficient and verifying the effect. This division of labor fully utilizes the powerful computing and storage capabilities of the cloud for complex pattern analysis, while leveraging the advantages of rapid response and data privacy and security on the vehicle side. It solves the problem that pure cloud solutions cannot meet real-time requirements due to update delays, forming a complementary advantage and comprehensively improving the agility and accuracy of the vehicle torque control system.

[0052] In one optional embodiment of this application, step 102 includes the following steps: S11, determine the stable driving range based on vehicle driving parameters; S12, within the stable driving range, determine the count of the user's effort action based on the vehicle driving parameters; whereby the user's effort action refers to the additional pedal operation performed by the user to correct the deviation between the actual vehicle driving state and the expected vehicle driving state. S13, determine the effort index based on the number of effort actions within the preset statistical mileage; S14, Determine the rate of change of effort based on several effort indicators; S15, if the rate of change of effort is greater than the preset threshold, the steady-state torque coefficient is determined based on the rate of change of effort and the preset steady-state coefficient correction information. S16, The trained transient coefficient recognition model is used to identify the vehicle driving parameters and obtain the transient torque coefficient; S17 uses a trained driving control demand recognition model to identify vehicle driving parameters and obtain driving control demand information.

[0053] In this embodiment, a stable driving range can be determined based on vehicle driving parameters. A stable driving range can represent a specific time period during which the vehicle is in a dynamic equilibrium state, such as uniform speed, uniform acceleration, uniform deceleration, or stable energy recovery.

[0054] Within a stable driving range, the effort action count of the user's efforts can be determined based on vehicle driving parameters. The user's effort action refers to the additional pedal operation performed by the user to correct the deviation between the actual and expected vehicle driving state. This additional pedal operation can be an additional operation on the accelerator pedal. The effort action count can refer to the number of times the user's effort action occurs.

[0055] Then, the effort index can be determined based on the number of effort actions within a preset statistical mileage. The preset statistical mileage can be set according to actual conditions, for example, 500 kilometers. The effort index represents the degree of matching between the current torque coefficient and the user's habits. The effort index can include a driving effort index and a feedback effort index. The driving effort index represents the quantified value of the frequency of additional accelerator pedal operations performed by the driver to maintain the expected vehicle state (such as desired acceleration or speed) under driving conditions such as acceleration and constant speed. The feedback effort index represents the quantified value of the frequency of additional accelerator pedal operations performed by the driver through fine adjustment of the accelerator pedal opening to maintain the expected vehicle state (such as desired deceleration or energy recovery intensity) under feedback conditions such as coasting and deceleration.

[0056] The higher the effort index, the more extra pedal operations the user makes to correct the deviation between the actual vehicle driving state and the expected vehicle driving state, which means the worse the match between the current torque coefficient and the driver's habits.

[0057] In this embodiment, the effort change rate can be determined based on several effort indicators. The effort change rate measures the relative change in effort indicators between adjacent statistical weeks. The effort change rate can include the driving effort change rate and the feedback effort change rate. It is understood that the driving effort change rate can be the relative change in the driving effort indicator between adjacent statistical weeks. The feedback effort change rate can be the relative change in the feedback effort indicator between adjacent statistical weeks.

[0058] The rate of change in effort can be used to determine whether the match between the current torque coefficient and the driver's habits is deteriorating or improving. A large positive value in the rate of change in effort indicates that the adjustment direction of the steady-state torque coefficient during adjacent statistical cycles is incorrect or insufficient.

[0059] Therefore, if the rate of change of effort is greater than the preset threshold, the steady-state torque coefficient can be determined based on the rate of change of effort and the preset steady-state coefficient correction information.

[0060] The steady-state torque coefficient can include both the steady-state drive torque coefficient and the steady-state feedback torque coefficient. It can be understood that the steady-state drive torque coefficient can be the steady-state torque coefficient in the drive state, and the steady-state feedback torque coefficient can be the steady-state torque coefficient in the feedback state. In specific implementations, the preset threshold can be set according to actual conditions, for example, to 0.1.

[0061] If the rate of change of effort is less than or equal to a preset threshold, the steady-state torque coefficient obtained within the current preset statistical mileage can be used as the steady-state torque coefficient within the next preset statistical mileage.

[0062] In the specific implementation, taking a preset threshold of 0.1 and a preset statistical mileage of 500km as an example, if the driving effort change rate... If the value is greater than 0.1, the correction logic will be triggered, and the steady-state drive torque coefficient will be determined based on the rate of change of effort and the preset steady-state coefficient correction information. If the rate of change of drive effort... If the value is ≤0.1, the steady-state torque coefficient correction logic will not be triggered, and the steady-state drive torque coefficient will still be executed according to the steady-state drive torque coefficient of the current 500km cycle.

[0063] If the rate of change in effort is fed back If the value is greater than 0.1, the correction logic will be triggered, and the steady-state feedback torque coefficient will be determined based on the effort change rate and the preset steady-state coefficient correction information. If the feedback effort change rate... If the value is ≤0.1, the steady-state torque coefficient correction logic will not be triggered, and the steady-state feedback torque coefficient in the next 500km cycle will still be executed according to the steady-state feedback torque coefficient of the current 500km cycle.

[0064] The steady-state torque coefficient correction logic is as follows: the steady-state torque coefficient is slightly adjusted in the direction of decreasing effort index. For example, the steady-state drive torque coefficient within the (n-1)th preset statistical mileage of 500km is... =0.5, the corresponding driving effort index is =0.02; the steady-state driving torque coefficient within the nth preset statistical mileage of 500km is =0.55, corresponding to the driving effort index is =0.04. Since the steady-state drive torque coefficient increases from 0.5 to 0.55, but the drive effort index increases from 0.2 to 0.04, the steady-state drive torque coefficient within the (n+1)th 500km should be less than 0.55. That is, the direction of the steady-state drive torque coefficient correction is the direction of the decrease in the drive effort index.

[0065] In a specific implementation, the preset steady-state coefficient correction information may include preset driving steady-state coefficient correction information and feedback steady-state coefficient correction information.

[0066] If the rate of change of driving effort is greater than the preset threshold, the driving steady-state coefficient correction value can be determined based on the rate of change of driving effort and the preset driving steady-state coefficient correction information. Then, the steady-state driving torque coefficient within the current statistical mileage (e.g., the current 500km) can be adjusted based on the driving steady-state coefficient correction value to obtain the steady-state driving torque coefficient within the next statistical mileage (e.g., the next 500km).

[0067] The driving steady-state coefficient correction information can be represented by the following formula:

[0068] in, This represents the correction value of the driving steady-state coefficient for the nth statistical mileage; This represents the driving effort index for the nth statistical mileage; This represents the driving effort index for the (n-1)th statistical mileage; This represents the steady-state drive torque coefficient for the nth statistical mileage. The adaptive learning rate is expressed by the following formula: Where n is the correction count counter, Let τ be the initial learning rate (e.g., 0.1) and τ be the decay constant (e.g., 3). It is understandable that in the initial correction phase (when n is small, i.e., within the first n 500km cycles), using this adaptive learning rate calculation formula allows for rapid approximation of the optimal value of the drive steady-state torque coefficient with a larger step size. In the later phase (when n is larger), a smaller step size is used for fine-tuning to prevent the drive steady-state torque coefficient from oscillating near the optimal value. This indicates the correction direction term, with a value of +1 or -1. This ensures that the correction always proceeds in the direction that reduces the effort index, that is, adjusting the drive steady-state torque coefficient in a direction that is more in line with the driver's habits and requires less effort. This represents the correction magnitude term, where γ is the shape parameter (usually taken as 1), driving the rate of change of effort. Rate of change of driving effort The larger the value, the greater the correction range, enabling rapid adjustment of the drive steady-state torque coefficient; the rate of change of drive effort. The smaller the value, the smaller the correction range, enabling fine-tuning of the drive steady-state torque coefficient; This represents the boundary protection function, where δ is the width of the boundary buffer (e.g., 0.05). The driving steady-state torque coefficient at the nth statistical mileage... As the value approaches the left or right boundaries (0 or 1) of its permissible range, the value of the boundary protection function linearly decays to 0, thereby forcing the correction value of the driving steady-state coefficient for the nth statistical mileage. It also approaches 0, effectively preventing the steady-state torque coefficient of the drive from going out of bounds and ensuring the stability of torque control.

[0069]

[0070] in, Represents the boundary protection function. δ represents the driving steady-state torque coefficient for the nth statistical mileage, and δ is the width of the boundary buffer.

[0071] If the rate of change of feedback effort is greater than the preset threshold, the feedback steady-state coefficient correction value can be determined based on the rate of change of feedback effort and the preset feedback steady-state coefficient correction information. Then, the steady-state feedback torque coefficient within the current statistical mileage (e.g., the current 500km) can be adjusted based on the feedback steady-state coefficient correction value to obtain the steady-state feedback torque coefficient within the next statistical mileage (e.g., the next 500km).

[0072] The feedback steady-state coefficient correction information can be represented by the following formula:

[0073] in, This represents the feedback steady-state coefficient correction value for the nth statistical mileage; This represents the feedback effort index in the nth statistical mileage; This represents the feedback effort index in the (n-1)th statistical mileage; This represents the steady-state feedback torque coefficient for the nth statistical mileage; The adaptive learning rate is expressed by the following formula: Where n is the correction count counter, Let τ be the initial learning rate (e.g., 0.1) and τ be the decay constant (e.g., 3). It is understandable that in the initial correction phase (when n is small, i.e., within the first n 500km cycles), using this adaptive learning rate calculation formula allows for rapid approximation of the optimal value of the feedback steady-state torque coefficient with a larger step size. In the later phase (when n is larger), a smaller step size is used for fine-tuning to prevent the feedback steady-state torque coefficient from oscillating near its optimal value. This indicates the correction direction term, with a value of +1 or -1. This ensures that the correction always proceeds in the direction that reduces the effort index, that is, adjusting the feedback steady-state torque coefficient in a direction that is more in line with the driver's habits and requires less effort. This represents the correction magnitude term, where γ is the shape parameter (usually set to 1), and the feedback effort rate of change. Rate of change in feedback effort The larger the value, the greater the correction range, enabling rapid adjustment of the feedback steady-state torque coefficient; feedback effort change rate. The smaller the value, the smaller the correction range, enabling fine-tuning of the feedback steady-state torque coefficient; This represents the boundary protection function, where δ is the width of the boundary buffer (e.g., 0.05). The feedback steady-state torque coefficient at the nth statistical mileage... When the value of the boundary protection function approaches the left or right boundary (0 or 1) of its permissible range, it linearly decays to 0, thereby forcing the correction value of the feedback steady-state coefficient for the nth statistical mileage. It also approaches 0, effectively preventing the feedback steady-state torque coefficient from exceeding the limit and ensuring the stability of torque control.

[0074]

[0075] in, Represents the boundary protection function. δ represents the feedback steady-state torque coefficient for the nth statistical mileage, and δ is the width of the boundary buffer zone.

[0076] In the specific implementation, you can refer to Figure 2 , Figure 2 This diagram illustrates the relationship between an effort index and a steady-state torque coefficient according to an embodiment of this application.

[0077] like Figure 2 As shown, the vertical axis of the effort index diagram represents the effort index, and the horizontal axis represents the statistical mileage. Similarly, the vertical axis of the steady-state torque coefficient diagram represents the steady-state torque coefficient, and the horizontal axis also represents the statistical mileage.

[0078] like Figure 2 As shown, in Figure 2 In the steady-state torque coefficient diagram, the steady-state torque coefficient corresponding to the statistical mileage within the second reference range is 0.548, which is greater than the steady-state torque coefficient of 0.509 corresponding to the statistical mileage within the first reference range. Furthermore, in Figure 2 In the effort index diagram, when the statistical mileage is at the end of the second reference interval, the corresponding effort index is 0.042, which is greater than the effort index of 0.022 corresponding to the statistical mileage at the end of the first reference interval. At this point, it can be determined that the steady-state torque coefficient corresponding to the statistical mileage in the second reference interval does not meet the optimization goal of reducing the effort index and thus alleviating the driver's operational burden. Therefore, the steady-state torque coefficient needs to be corrected. After correction, in the next interval adjacent to the second reference interval, the steady-state torque coefficient should be less than 0.548.

[0079] In this embodiment, a trained transient coefficient recognition model can be used to identify vehicle driving parameters to obtain transient torque coefficients. Specifically, vehicle driving parameters can be input into the trained transient coefficient recognition model to obtain the transient torque coefficients output by the trained transient coefficient recognition model.

[0080] In this embodiment, a trained driving control demand recognition model can be used to identify vehicle driving parameters to obtain driving control demand information. Specifically, vehicle driving parameters can be input into the trained driving control demand recognition model to obtain the driving control demand information output by the trained driving control demand recognition model.

[0081] In specific implementations, the transient coefficient identification model or driving control demand identification model can be any one of the following or a combination of the following: a state machine model based on rule thresholds, a classification or regression model based on traditional machine learning, and an end-to-end model based on deep learning.

[0082] This application analyzes vehicle driving parameters to determine a stable driving range, and then calculates the user's effort action count to evaluate the effort index and rate of change. This allows for dynamic adjustment of the steady-state torque coefficient, ensuring a high degree of match between the torque coefficient and user habits. Through transient coefficient recognition and driving control demand recognition models, it can identify transient torque coefficients and driving control demand information in real time, improving the accuracy and comfort of the driving experience. Furthermore, based on the correction logic of the effort change rate, it can intelligently adjust the torque coefficient, avoiding frequent additional pedal operations by the user and optimizing driving efficiency and energy consumption.

[0083] In one optional embodiment of this application, the vehicle driving parameters include torque adaptive mode status, gear information, vehicle speed, accelerator pedal opening, target torque, and longitudinal acceleration.

[0084] Stable driving range includes stable speed range, stable acceleration range, stable deceleration range, and stable feedback range.

[0085] Among them, the stable speed range can represent the period of time during which the vehicle maintains a constant speed while in driving mode, such as cruise and other uniform speed driving scenarios.

[0086] The stable acceleration range can represent the period during which a vehicle maintains a constant acceleration while in driving mode, such as a smooth acceleration scenario.

[0087] The stable deceleration range can represent the period during which a vehicle maintains a constant deceleration while in driving mode, such as a smooth coasting deceleration scenario.

[0088] The stable feedback range can be defined as the period during which a vehicle, in a feedback state, maintains a constant deceleration and its kinetic energy is continuously converted into electrical energy.

[0089] Step S11 also includes the following steps: S21, when the torque adaptive mode is on, the gear information is in driving gear, the vehicle speed is greater than a preset first threshold, and the accelerator pedal opening is greater than a preset second threshold, a first time window is obtained. The first time window includes several second time windows arranged in chronological order. The first time window also includes random time windows. The starting point of the random time window is the starting point of the first time window, and the ending point of the random time window is any time point in the first time window. S22, in the first time window, several second time windows and random time windows, determine the vehicle speed range, longitudinal acceleration peak value, longitudinal acceleration valley value and acceleration range according to the vehicle speed and longitudinal acceleration respectively; S23, if the target torque is greater than zero, and if several speed ranges within the first time window, the second time window, and the random time window are all less than the preset third threshold, then the first time window is taken as the stable speed range. S24, if, when the target torque is greater than zero, several longitudinal acceleration valleys in the first time window, the second time window, and the random time window are all greater than the preset fourth threshold and several acceleration ranges are all less than the preset fifth threshold, then the first time window is taken as the stable acceleration interval. S25, if, when the target torque is less than zero, several longitudinal acceleration peaks within the first time window, the second time window, and the random time window are all less than the preset sixth threshold and several acceleration ranges are all less than the preset fifth threshold, then the first time window is taken as the stable deceleration interval. S26, if, when the target torque is less than zero, several longitudinal acceleration peaks within the first time window, the second time window, and the random time window are all less than a preset seventh threshold and several acceleration ranges are all less than a preset fifth threshold, then when the target torque is less than a preset eighth threshold, the first time window is taken as a stable feedback interval.

[0090] In this embodiment, when the torque adaptive mode is enabled, the gear is in the driving gear, the vehicle speed is greater than a preset first threshold, and the accelerator pedal opening is greater than a preset second threshold, a stable driving range can be determined. The preset first threshold can be set according to actual conditions, for example, to 5 km / h. The preset second threshold can also be set according to actual conditions, for example, to 2%.

[0091] In this embodiment, a multi-window approach can be used to determine the stable driving range. A first time window can be obtained, which includes several second time windows arranged in chronological order. The first time window also includes random time windows, where the starting point of the random time window is the starting point of the first time window, and the ending point of the random time window is any point in the first time window. The duration of the first time window can be set according to actual conditions, for example, 5 seconds or 3 seconds. The duration of the second time windows can also be set according to actual conditions, for example, 500ms. It is understood that the duration of the random time window is less than or equal to the duration of the first time window.

[0092] In this embodiment, the duration of the first time window can be the same or different when determining different stable driving ranges. Within the same first time window, the direction of the target torque is consistent; for example, the target torque is greater than 0 in both the stable speed range and the stable acceleration range, and less than 0 in both the stable deceleration range and the stable feedback range.

[0093] In this embodiment of the application, the vehicle speed range, longitudinal acceleration peak value, longitudinal acceleration valley value and acceleration range can be determined based on the vehicle speed and longitudinal acceleration in a first time window, several second time windows and a random time window, respectively.

[0094] Among them, the speed range can be the difference between the highest speed and the lowest speed within a specified time window.

[0095] The peak longitudinal acceleration can be the maximum value reached by the longitudinal acceleration signal within a specified time window.

[0096] The longitudinal acceleration valley can be the minimum value reached by the longitudinal acceleration signal within a specified time window.

[0097] The acceleration range can be the difference between the peak value and the valley value of longitudinal acceleration within a specified time window.

[0098] In this embodiment, when the target torque is greater than zero, if several speed ranges within the first time window, the second time window, and the random time window are all less than a preset third threshold, then the first time window can be used as a stable speed range. The preset third threshold can be set according to actual conditions, for example, 10 km / h.

[0099] In the specific implementation, the following example illustrates the situation where the torque adaptive mode is enabled, the gear information is in the driving gear, the vehicle speed is greater than the preset first threshold, and the accelerator pedal opening is greater than the preset second threshold. The duration of the first time window is set to 5 seconds, the duration of the second time window is set to 500ms, and the preset third threshold is set to 10km / h.

[0100] When the target torque is greater than 0, within a 5-second first time window, the following conditions must be met simultaneously: The speed difference within the entire first time window is less than 10 km / h; the speed difference within each second time window (500 ms) within the first time window is less than 10 km / h; and the speed difference within each random time window within the first time window is less than 10 km / h. If all three conditions are met, the vehicle is considered to be in a stable speed state within this 5-second first time window, and this first time window is considered a stable speed range.

[0101] In this embodiment, when the target torque is greater than zero, if several longitudinal acceleration valleys within the first time window, the second time window, and the random time window are all greater than a preset fourth threshold and several acceleration ranges are all less than a preset fifth threshold, then the first time window can be used as a stable acceleration interval. The preset fourth threshold can be set according to actual conditions, for example, 0.1 m / s². The preset fifth threshold can be set according to actual conditions, for example, 0.5 m / s².

[0102] In the specific implementation, the following example illustrates the situation where the torque adaptive mode is enabled, the gear information is in the driving gear, the vehicle speed is greater than the preset first threshold, and the accelerator pedal opening is greater than the preset second threshold. The duration of the first time window is set to 3 seconds, the duration of the second time window is set to 500ms, the preset fourth threshold is set to 0.1m / s², and the preset fifth threshold is set to 0.5m / s².

[0103] When the target torque is greater than 0, within a 3-second first time window, the following conditions must be met simultaneously: Within the entire first time window, the longitudinal acceleration trough is greater than 0.1 m / s² and the acceleration range is less than 0.5 m / s²; within each second time window (500 ms) within the first time window, the longitudinal acceleration trough is greater than 0.1 m / s² and the acceleration range is less than 0.5 m / s²; within each random time window within the first time window, the longitudinal acceleration trough is greater than 0.1 m / s² and the acceleration range is less than 0.5 m / s². If all three conditions are met simultaneously, the vehicle is considered to be in a stable acceleration state within this 3-second first time window, and this first time window is the stable acceleration range.

[0104] In this embodiment, when the target torque is less than zero, if several longitudinal acceleration peaks within the first time window, the second time window, and the random time window are all less than a preset sixth threshold and several acceleration ranges are all less than a preset fifth threshold, then the first time window can be used as a stable deceleration interval. The preset sixth threshold can be set according to actual conditions, for example, 0.1 m / s².

[0105] In the specific implementation, the following example illustrates the situation where the torque adaptive mode is enabled, the gear information is in the driving gear, the vehicle speed is greater than the preset first threshold, and the accelerator pedal opening is greater than the preset second threshold. The duration of the first time window is set to 3 seconds, the duration of the second time window is set to 500ms, the preset sixth threshold is set to 0.1m / s², and the preset fifth threshold is set to 0.5m / s².

[0106] When the target torque is less than 0, within a 3-second first time window, the following conditions must be met simultaneously: Within the entire first time window, the peak longitudinal acceleration is less than 0.1 m / s² and the acceleration range is less than 0.5 m / s²; within each second time window (500 ms) within the first time window, the peak longitudinal acceleration is less than 0.1 m / s² and the acceleration range is less than 0.5 m / s²; within each random time window within the first time window, the peak longitudinal acceleration is less than 0.1 m / s² and the acceleration range is less than 0.5 m / s². If all three conditions are met simultaneously, the vehicle is considered to be in a steady deceleration state within this 3-second first time window, and this first time window is the steady deceleration range.

[0107] In this embodiment, when the target torque is less than zero, if several longitudinal acceleration peaks within the first time window, the second time window, and the random time window are all less than a preset seventh threshold and several acceleration ranges are all less than a preset fifth threshold, then the first time window can be used as a stable feedback interval when the target torque is less than a preset eighth threshold. The preset seventh threshold can be set according to actual conditions, for example, -0.1 m / s². The preset eighth threshold can be set according to actual conditions, for example, -20 Nm.

[0108] In the specific implementation, with the torque adaptive mode on, the gear information in the driving gear, the vehicle speed greater than the preset first threshold, and the accelerator pedal opening greater than the preset second threshold, the following example illustrates the implementation: the duration of the first time window is set to 3 seconds, the duration of the second time window is set to 500ms, the preset fifth threshold is set to 0.5m / s², the preset seventh threshold is set to -0.1m / s², and the preset eighth threshold is set to -20Nm.

[0109] When the target torque is less than 0, within a 3-second first time window, the following conditions must be met simultaneously: Within the entire first time window, the peak longitudinal acceleration is less than -0.1 m / s², the acceleration range is less than 0.5 m / s², and the target torque is less than -20 Nm; within each second time window (500 ms) within the first time window, the peak longitudinal acceleration is less than -0.1 m / s², the acceleration range is less than 0.5 m / s², and the target torque is less than -20 Nm; within each random time window within the first time window, the peak longitudinal acceleration is less than -0.1 m / s², the acceleration range is less than 0.5 m / s², and the target torque is less than -20 Nm. If all three conditions are met simultaneously, the vehicle is considered to be in a stable feedback state within this 3-second first time window, and this first time window is the stable feedback interval.

[0110] In the specific implementation, you can refer to Figure 3 , Figure 3 A flowchart illustrating the steps for determining a stable driving range according to an embodiment of this application is shown; like Figure 3 As shown, under the condition that the preset conditions are met, the parameters of the second time window are calculated based on the vehicle status parameters within the second time window.

[0111] In this embodiment of the application, the preset conditions may be that the torque adaptive mode is enabled, the gear information is in the driving gear, the vehicle speed is greater than a preset first threshold, and the accelerator pedal opening is greater than a preset second threshold.

[0112] The parameters for the second time window can be calculated based on the vehicle state parameters within the second time window. This can be achieved by determining the speed range, peak value, valley value, and acceleration range within the second time window based on the vehicle speed and longitudinal acceleration within the second time window.

[0113] Under the condition that the preset conditions are met, the parameters of the first time window are calculated based on the vehicle status parameters within the first time window.

[0114] In this embodiment of the application, the preset conditions may be that the torque adaptive mode is enabled, the gear information is in the driving gear, the vehicle speed is greater than a preset first threshold, and the accelerator pedal opening is greater than a preset second threshold.

[0115] The parameters for the first time window can be calculated based on the vehicle state parameters within the first time window. This can be done by determining the speed range, peak value, valley value, and acceleration range within the first time window based on the vehicle speed and longitudinal acceleration within the first time window.

[0116] Specifically, since the first time window includes several second time windows, the speed difference, longitudinal acceleration peak value, longitudinal acceleration valley value and acceleration range within the first time window can also be determined by the speed difference, longitudinal acceleration peak value, longitudinal acceleration valley value and acceleration range within the second time window.

[0117] Then, the stable driving range can be determined based on the first time window parameters and the second time window parameters.

[0118] Specifically, since the first time window also includes a random time window, the starting point of the random time window is the starting point of the first time window, and the ending point of the random time window is any time point in the first time window, after determining the parameters of the first time window, the speed range, peak value of longitudinal acceleration, valley value of longitudinal acceleration and speed range of the random time window can also be determined based on the vehicle speed and longitudinal acceleration within the random time window. The stable driving range can then be determined by referring to the process in S23-S26 of this application, which will not be elaborated here.

[0119] This embodiment significantly improves the accuracy and robustness of stable driving range identification by employing a multi-window layered verification mechanism. Under general conditions, this method performs multiple verifications on the first time window, the fixed-duration second time window, and the randomly starting intermediate window. This effectively eliminates misjudgments caused by instantaneous disturbances and local fluctuations, ensuring that the identified stable speed range, stable acceleration range, stable deceleration range, and stable feedback range truly reflect the vehicle's steady-state driving characteristics, thereby guaranteeing the effectiveness and stability of the entire adaptive correction system.

[0120] In one optional embodiment of this application, step S12 further includes the following steps: S31, for the stable speed range, stable acceleration range, stable deceleration range and stable feedback range, determine several second time windows corresponding to the stable speed range, stable acceleration range, stable deceleration range and stable feedback range respectively; S32, within several second time windows corresponding to the stable vehicle speed range, stable acceleration range, and stable deceleration range, respectively, the rising edge difference sequence of the trough and falling edge difference sequence of the accelerator pedal opening are obtained; the rising edge difference sequence of the trough includes the opening difference between each extreme point of the accelerator pedal opening in the second time window and the next adjacent extreme point of the peak; the falling edge difference sequence of the peak includes the opening difference between each extreme point of the accelerator pedal opening in the second time window and the next adjacent extreme point of the trough. S33, for any second time window, if the maximum value in the difference sequence of the rising edge of the trough or the maximum value in the difference sequence of the falling edge of the peak is greater than a preset ninth threshold, then there is a user effort action in the second time window, and the effort action count is generated.

[0121] In this embodiment of the application, several second time windows can be determined for the stable vehicle speed range, stable acceleration range, stable deceleration range, and stable feedback range, respectively.

[0122] Within several second time windows corresponding to the stable vehicle speed range, stable acceleration range, stable deceleration range, and stable feedback range, the trough rising edge difference sequence and peak falling edge difference sequence of the accelerator pedal opening are obtained respectively. The trough rising edge difference sequence includes the opening difference between each trough extreme point of the accelerator pedal opening within the second time window and the next adjacent peak extreme point. The peak falling edge difference sequence includes the opening difference between each peak extreme point of the accelerator pedal opening within the second time window and the next adjacent trough extreme point.

[0123] In practical implementation, the accelerator pedal opening within the second time window can be represented as a continuous curve changing over time. This continuous curve may contain peaks and troughs. The peak extreme point refers to the highest point of accelerator pedal opening within a local range, which can be represented by the position where the driver depresses the accelerator pedal the deepest. The trough extreme point is the lowest point of accelerator pedal opening within a local range, which can be represented by the position where the driver releases the accelerator pedal the most.

[0124] The trough rising edge difference sequence includes the difference in accelerator pedal opening between each trough extreme point and the next adjacent peak extreme point within the second time window. The existence of the trough rising edge indicates the presence of a "U"-shaped trough trajectory in the continuous curve, and that the driver depresses the accelerator pedal at the trough extreme point of the "U"-shaped trough, thus creating the rising edge of the "U"-shaped trough.

[0125] The peak-falling-edge difference sequence includes the difference in accelerator pedal opening between each peak extreme point and the next adjacent trough extreme point within the second time window. The presence of a peak-falling edge indicates the existence of an inverted "U"-shaped peak trajectory in the continuous curve, and that the driver releases the accelerator pedal at the peak extreme point of the inverted "U"-shaped peak, thus resulting in a falling edge of the inverted "U"-shaped peak.

[0126] The opening difference is the difference between the opening value at a peak extreme point and the opening value at the next adjacent trough extreme point, or the opening difference is the difference between the opening value at a trough extreme point and the opening value at the next adjacent peak extreme point. The opening difference quantifies the magnitude of a single pedal operation by the driver.

[0127] In this embodiment of the application, for any second time window, if the maximum value in the difference sequence of rising troughs or falling peaks is greater than a preset ninth threshold, then there is a user effort action in the second time window, and an effort action count is generated.

[0128] If the maximum value of the difference sequence of rising edges of the trough is greater than the preset ninth threshold, it means that at the extreme point of the trough of the "U"-shaped trough, the driver has pressed the accelerator pedal, so there is a rising edge of the "U"-shaped trough, and the magnitude of the driver pressing the accelerator pedal is greater than the preset ninth threshold.

[0129] If the maximum value of the difference sequence of the falling edge of the wave peak is greater than the preset ninth threshold, it means that at the peak extreme point of the inverted "U"-shaped wave peak, the driver has released the accelerator pedal, so there is a falling edge of the inverted "U"-shaped wave peak, and the magnitude of the driver's operation of releasing the accelerator pedal is greater than the preset ninth threshold.

[0130] The preset ninth threshold can be set according to the actual situation, for example, it can be set to 3%.

[0131] In the specific implementation, you can refer to Figure 4 , Figure 4 A schematic diagram of the pedal opening degree in a first time window provided in an embodiment of this application is shown.

[0132] like Figure 4 As shown, the vertical axis represents the pedal opening, and the horizontal axis represents time.

[0133] The following example illustrates the concept of a first time window of 5 seconds, a second time window of 500ms, and a preset ninth threshold of 3%.

[0134] Within the second time window corresponding to 0-0.5 seconds, although the difference in accelerator pedal opening fluctuates by more than 3%, no "U"-shaped trough or inverted "U"-shaped peak trajectory appears within this window. Consequently, there are no rising edges of the "U"-shaped troughs or falling edges of the inverted "U"-shaped peaks. In other words, the difference sequence of rising edges of accelerator pedal opening troughs and falling edges of peaks cannot be obtained within the second time window corresponding to 0-0.5 seconds. Therefore, there is no user effort action within this second time window.

[0135] Within the second time window corresponding to 2.5-3.0 seconds, a "U"-shaped trough trajectory appeared, and there was a rising edge of the "U"-shaped trough. This indicates that at the extreme point of the "U"-shaped trough, the driver pressed the accelerator pedal. Furthermore, the difference in opening between the extreme point of the trough and the next adjacent extreme point of the peak is greater than 3%, indicating that at the extreme point of the "U"-shaped trough, the driver's operation amplitude of pressing the accelerator pedal is greater than 3%. Therefore, there was a user effort action within the second time window corresponding to 2.5-3.0 seconds.

[0136] like Figure 4 As shown, within the first time window corresponding to 0-5.0 seconds, according to the above discussion, there is one user effort action within the second time window corresponding to 2.5-3.0 seconds. However, within the first time window corresponding to 0.0-5.0 seconds, in the other second time windows except for 2.5-3.0 seconds, the maximum value in the difference sequence of the rising edge of the trough or the maximum value in the difference sequence of the falling edge of the peak does not meet the condition of being greater than 3%. Therefore, there is only one user effort action within the first time window corresponding to 0-5.0 seconds.

[0137] This application achieves objective identification and accurate statistics of user effort by quantitatively analyzing pedal operation characteristics within stable driving ranges. Within each identified stable range, a second time window of fixed duration is used to calculate the difference sequence of trough rising edges and peak falling edges, which, combined with preset thresholds, effectively distinguishes between the driver's active control intentions and additional operations performed to correct vehicle state deviations. This provides a stable and reliable data foundation for generating effort indicators, ensuring the accuracy and effectiveness of subsequent adaptive correction processes.

[0138] In one optional embodiment of this application, the vehicle driving parameters further include driving mileage, and the effort index includes driving effort index and feedback effort index.

[0139] Step S13 also includes the following steps: S41, when the driving mileage is greater than or equal to the preset statistical mileage, obtain the effort action counts in the stable speed range, stable acceleration range, stable deceleration range and stable feedback range within the preset statistical mileage respectively. S42, determine the driving effort index based on the effort action count within the stable speed range, stable acceleration range, and stable deceleration range; S43, determine the feedback effort index based on the number of effort actions within the stable feedback interval.

[0140] In this embodiment of the application, when the driving mileage is greater than or equal to the preset statistical mileage, the effort action counts within the stable speed range, stable acceleration range, stable deceleration range and stable feedback range within the preset statistical mileage can be obtained respectively.

[0141] In practice, taking a preset statistical mileage of 500km as an example, the number of effort actions in the stable speed range, stable acceleration range, stable deceleration range and stable feedback range can be accumulated within a 500km driving distance.

[0142] In this embodiment, the driving effort index can be determined based on the number of effort actions within the stable speed range, stable acceleration range, and stable deceleration range.

[0143] In practical implementation, taking a preset statistical mileage of 500km as an example, the driving effort index is... = (Number of effort actions in the stable speed range + Number of effort actions in the stable acceleration range + Number of effort actions in the stable deceleration range) / 500. Where, This indicates the driving effort index, and 500 refers to the preset statistical mileage.

[0144] In this embodiment, the feedback effort index can be determined based on the number of effort actions within the stable feedback interval.

[0145] In practical implementation, taking a preset statistical mileage of 500km as an example, the feedback effort index is... =Number of effort actions within the stable feedback range / 500. Wherein, This indicates the feedback effort index; 500 refers to the preset statistical mileage.

[0146] This application standardizes the number of effort actions based on a preset statistical mileage, effectively generating driving and feedback effort indices. After the driving mileage reaches a set threshold, the number of effort actions within each stable driving range is accumulated, and the operation frequency per unit mileage is calculated based on the statistical mileage. This transforms the original counts into standardized indices that can be compared across periods, eliminating statistical biases caused by differences in driving mileage. This allows the driving and feedback effort indices to objectively and quantitatively reflect the degree of matching between torque characteristics and driver habits, providing a stable and reliable evaluation basis for subsequent calculation of effort change rate and correction of steady-state torque coefficient.

[0147] In one alternative embodiment of this application, the effort change rate includes the driving effort change rate and the feedback effort change rate.

[0148] Step S14 also includes the following steps: S51, take any preset statistical mileage as the current statistical mileage, and obtain the driving effort index and the feedback effort index in the current statistical mileage; S52, take the previous statistical mileage of the current statistical mileage as the reference statistical mileage, and obtain the driving effort index and the feedback effort index in the reference statistical mileage. S53, determine the rate of change of driving effort based on the driving effort index in the current statistical mileage and the driving effort index in the reference statistical mileage; S54. Determine the rate of change of feedback effort based on the feedback effort index in the current statistical mileage and the feedback effort index in the reference statistical mileage.

[0149] In this embodiment of the application, any preset statistical mileage can be used as the current statistical mileage to obtain the driving effort index and the feedback effort index in the current statistical mileage.

[0150] Use the previous statistical mileage as the reference statistical mileage to obtain the driving effort index and the feedback effort index from the reference statistical mileage.

[0151] In this embodiment of the application, the rate of change of driving effort can be determined based on the driving effort index in the current statistical mileage and the driving effort index in the reference statistical mileage.

[0152] In practical implementation, the rate of change of driving effort can be calculated using the following formula:

[0153] in, This represents the rate of change of driving effort, where n represents the nth statistical mileage and n-1 represents the (n-1)th statistical mileage. This represents the driving effort index in the nth statistical mileage, such as the driving effort index in the current statistical mileage. This represents the driving effort index in the (n-1)th statistical mileage, such as the driving effort index in the reference statistical mileage.

[0154] In this embodiment of the application, the rate of change of feedback effort can be determined based on the feedback effort index in the current statistical mileage and the feedback effort index in the reference statistical mileage.

[0155]

[0156] in, This represents the rate of change in feedback effort, where n represents the nth statistical mileage and n-1 represents the (n-1)th statistical mileage. This represents the feedback effort index in the nth statistical mileage, such as the feedback effort index in the current statistical mileage; This represents the feedback effort index in the (n-1)th statistical mileage, such as the feedback effort index in the reference statistical mileage.

[0157] In existing technologies, the basic torque coefficient delivered from the cloud is typically used statically at the vehicle end, failing to respond promptly to short-term changes in driver habits. This application goes beyond vague style recognition, innovatively defining a quantifiable evaluation standard called "effort intensity index," directly linking it to the applicability of the steady-state torque coefficient. By calculating the relative rate of change of the effort intensity index over adjacent statistical periods, a key decision-making basis is provided for the correction of the steady-state torque coefficient, enabling precise control of the correction process. By comparing the driving effort intensity index and feedback effort intensity index of the current statistical mileage with those of the previous statistical mileage, the rate of change of driving effort intensity and the rate of change of feedback effort intensity are obtained, respectively. This quantitatively reflects the dynamic trend of the matching degree between torque characteristics and driver habits. When the rate of change exceeds a preset threshold, it indicates that the matching degree is deteriorating, thereby triggering the correction logic. This data-driven and model-based approach significantly improves the objectivity, convergence, and robustness of the optimization process compared to traditional empirical calibration or static use of basic torque coefficients. This rate-of-change triggering mechanism ensures that the system is adjusted only when necessary, avoiding overcorrection, ensuring timely adaptive optimization, and preventing control performance oscillations or deterioration caused by blind adjustments. This ensures that the vehicle torque control system continuously and stably evolves towards a better state.

[0158] This application enables continuous and automated fine-tuning of the steady-state torque coefficient to adapt to the driver's latest operating habits. It effectively solves the problem of "misfit" driving experience caused by fixed torque maps or long-term updates, making the vehicle's power output more in line with the driver's expectations, reducing unnecessary operations by the driver to achieve the expected dynamics of the vehicle, thereby reducing fatigue and motion sickness during long-distance driving, and achieving the personalized adaptation goal of making the vehicle "easier to drive the longer it is driven".

[0159] In one optional embodiment of this application, step 103 includes the following steps: S61, when the driving control demand information indicates that the user has instantaneous driving control demand, the transient torque coefficient is selected to adjust the base torque coefficient to obtain the target torque coefficient; S62, when the driving control demand information indicates that the user does not have instantaneous driving control demand, selects the steady-state torque coefficient to adjust the base torque coefficient to obtain the target torque coefficient.

[0160] In this embodiment of the application, when the driving control demand information indicates that the user has instantaneous driving control demand, it means that the user has instantaneous power demand. The transient torque coefficient can be selected to adjust the basic torque coefficient to obtain the target torque coefficient, which can meet the user's instantaneous power demand.

[0161] If the driving control demand information indicates that the user does not have instantaneous driving control needs, it means that the user does not have instantaneous power needs. In this case, the steady-state torque coefficient can be selected to adjust the base torque coefficient to obtain the target torque coefficient, which can ensure driving comfort and conformity with driving habits.

[0162] In this way, the vehicle torque control system of this application not only ensures the comfort and habituality of daily driving, but also provides a fast and agile power response when stimulated by external environment or when the driver has a clear intention to drive aggressively, thus achieving a seamless connection between steady-state and transient driving styles. Reference Figure 5 This illustration shows a structural schematic diagram of a vehicle torque control device according to an embodiment of this application, applied to a vehicle torque control system. The vehicle torque control system is installed in a vehicle, and the device includes: The parameter acquisition module 501 is used to acquire vehicle driving parameters and the basic torque coefficient sent from the cloud. The coefficient determination module 502 is used to determine the steady-state torque coefficient, transient torque coefficient and driving control requirement information based on the vehicle driving parameters. The coefficient adjustment module 503 is used to select the steady-state torque coefficient or the transient torque coefficient according to the driving control requirement information to adjust the basic torque coefficient to obtain the target torque coefficient; The torque control module 504 is used to control the vehicle torque using the target torque coefficient.

[0163] In one optional embodiment of this application, the coefficient determination module 502 includes: The stable driving range determination submodule is used to determine the stable driving range based on the vehicle driving parameters. The effort action counting submodule is used to determine the effort action count of the user's effort actions based on the vehicle driving parameters within the stable driving range; wherein, the user's effort action refers to the additional pedal operation performed by the user to correct the deviation between the actual vehicle driving state and the expected vehicle driving state. The effort index determination submodule is used to determine the effort index based on the number of effort actions within a preset statistical mileage. The effort change rate determination submodule is used to determine the effort change rate based on several effort indicators. The steady-state torque coefficient determination submodule is used to determine the steady-state torque coefficient based on the effort change rate and preset steady-state coefficient correction information if the effort change rate is greater than a preset threshold. The transient torque coefficient determination submodule is used to identify the vehicle driving parameters using a trained transient coefficient recognition model to obtain the transient torque coefficient. The driving control demand information determination submodule is used to identify the vehicle driving parameters using a trained driving control demand recognition model to obtain the driving control demand information.

[0164] In one optional embodiment of this application, the vehicle driving parameters include torque adaptive mode status, gear information, vehicle speed, accelerator pedal opening, target torque, and longitudinal acceleration; the stable driving range includes a stable speed range, a stable acceleration range, a stable deceleration range, and a stable feedback range; the stable driving range determination submodule includes: A general condition unit is used to acquire a first time window when the torque adaptive mode is on, the gear information is in driving gear, the vehicle speed is greater than a preset first threshold, and the accelerator pedal opening is greater than a preset second threshold. The first time window includes a plurality of second time windows arranged in chronological order. The first time window also includes a random time window. The starting point of the random time window is the starting point of the first time window, and the ending point of the random time window is any time point in the first time window. The parameter determination unit is used to determine the vehicle speed range, the longitudinal acceleration peak value, the longitudinal acceleration valley value, and the acceleration range respectively based on the vehicle speed and the longitudinal acceleration in the first time window, a plurality of second time windows, and the random time window. The stable vehicle speed range determination unit is used to determine the first time window as the stable vehicle speed range if, when the target torque is greater than zero, several speed ranges within the first time window, the second time window, and the random time window are all less than a preset third threshold. The stable acceleration interval determination unit is used to determine the first time window as the stable acceleration interval if, when the target torque is greater than zero, several longitudinal acceleration valleys in the first time window, the second time window, and the random time window are all greater than a preset fourth threshold and several vehicle speed ranges are all less than a preset fifth threshold. The stable deceleration range determination unit is used to determine the first time window as the stable deceleration range if, when the target torque is less than zero, several longitudinal acceleration peaks within the first time window, the second time window, and the random time window are all less than a preset sixth threshold and several vehicle speed ranges are all less than a preset fifth threshold. The stable feedback interval determination unit is used to determine the first time window as the stable feedback interval when the target torque is less than a preset eighth threshold, if several longitudinal acceleration peaks within the first time window, the second time window, and the random time window are all less than a preset seventh threshold and several vehicle speed ranges are all less than a preset fifth threshold.

[0165] In one optional embodiment of this application, the effort action counting submodule includes: The second time window determination unit is used to determine a plurality of second time windows corresponding to the stable vehicle speed range, the stable acceleration range, the stable deceleration range, and the stable feedback range, respectively. The pedal opening difference determination unit is used to acquire, within a plurality of second time windows corresponding to the stable vehicle speed range, the stable acceleration range, the stable deceleration range, and the stable feedback range, respectively, a trough rising edge difference sequence and a peak falling edge difference sequence of the accelerator pedal opening; the trough rising edge difference sequence includes the opening difference between each trough extreme point of the accelerator pedal opening within the second time window and the next adjacent peak extreme point; the peak falling edge difference sequence includes the opening difference between each peak extreme point of the accelerator pedal opening within the second time window and the next adjacent trough extreme point. The effort action counting unit is used to generate the effort action count if, for any second time window, the maximum value in the difference sequence of the rising edge of the trough or the maximum value in the difference sequence of the falling edge of the peak is greater than a preset ninth threshold.

[0166] In one optional embodiment of this application, the vehicle driving parameters further include driving mileage, the effort index includes a driving effort index and a feedback effort index, and the effort index determination submodule includes: The effort action acquisition unit is used to acquire the effort action counts within the stable speed range, the stable acceleration range, the stable deceleration range, and the stable feedback range within the preset statistical mileage, respectively, when the driving mileage is greater than or equal to the preset statistical mileage. A driving effort index determination unit is used to determine a driving effort index based on the number of effort actions within the stable vehicle speed range, the stable acceleration range, and the stable deceleration range. The feedback effort index determination unit is used to determine the feedback effort index based on the number of effort actions within the stable feedback interval.

[0167] In one optional embodiment of this application, the effort change rate includes a driving effort change rate and a feedback effort change rate, and the effort change rate determination submodule includes: The current statistical mileage indicator acquisition unit is used to take any of the preset statistical mileages as the current statistical mileage and acquire the driving effort indicator and the feedback effort indicator in the current statistical mileage. The reference statistical mileage indicator acquisition unit is used to take the previous statistical mileage of the current statistical mileage as the reference statistical mileage and acquire the driving effort indicator and the feedback effort indicator in the reference statistical mileage. The driving effort change rate acquisition unit is used to determine the driving effort change rate based on the driving effort index in the current statistical mileage and the driving effort index in the reference statistical mileage. The feedback effort rate change acquisition unit is used to determine the feedback effort rate change based on the feedback effort index in the current statistical mileage and the feedback effort index in the reference statistical mileage.

[0168] In one optional embodiment of this application, the torque control module 504 includes: The transient torque adjustment submodule is used to select a transient torque coefficient to adjust the base torque coefficient when the driving control demand information indicates that the user has an instantaneous driving control demand, so as to obtain a target torque coefficient; The steady-state torque adjustment submodule is used to select a steady-state torque coefficient to adjust the base torque coefficient when the driving control demand information indicates that the user does not have instantaneous driving control demand, so as to obtain the target torque coefficient.

[0169] As the apparatus embodiment is basically similar to the method embodiment, it is described in a relatively simple manner. For relevant details, please refer to the description of the method embodiment.

[0170] One embodiment of this application also provides a vehicle that may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method described above.

[0171] An embodiment of this application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, it implements the method described above.

[0172] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0173] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0174] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0175] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0176] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0178] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other modifications and updates to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all modifications and updates falling within the scope of the embodiments of the present application.

[0179] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the aforementioned element.

[0180] The above provides a detailed description of a vehicle torque control method, device, vehicle, and medium. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A vehicle torque control method, characterized in that, The method, applied to a vehicle torque control system located in a vehicle, includes: Obtain vehicle driving parameters and basic torque coefficients sent from the cloud; Based on the vehicle driving parameters, determine the steady-state torque coefficient, transient torque coefficient, and driving control requirements. Based on the driving control requirements information, the steady-state torque coefficient or the transient torque coefficient is selected to adjust the base torque coefficient to obtain the target torque coefficient; The target torque coefficient is used to control the vehicle torque.

2. The method according to claim 1, characterized in that, The process of determining the steady-state torque coefficient, transient torque coefficient, and driving control requirements based on the vehicle driving parameters includes: Determine the stable driving range based on the vehicle driving parameters; Within the stable driving range, the count of user effort actions is determined based on the vehicle driving parameters; wherein, the user effort action represents the additional pedal operation performed by the user to correct the deviation between the actual vehicle driving state and the expected vehicle driving state. The effort level index is determined based on the number of effort actions within a preset statistical mileage. The rate of change of effort is determined based on several of the aforementioned effort indicators; If the rate of change of effort is greater than a preset threshold, the steady-state torque coefficient is determined based on the rate of change of effort and the preset steady-state coefficient correction information. The transient torque coefficient is obtained by identifying the vehicle driving parameters using a trained transient coefficient identification model. The vehicle driving parameters are identified using a trained driving control demand recognition model to obtain the driving control demand information.

3. The method according to claim 2, characterized in that, The vehicle driving parameters include torque adaptive mode status, gear information, vehicle speed, accelerator pedal opening, target torque, and longitudinal acceleration. The stable driving range includes stable vehicle speed range, stable acceleration range, stable deceleration range, and stable feedback range. Determining the stable driving range based on the vehicle driving parameters includes: When the torque adaptive mode is enabled, the gear information is in driving gear, the vehicle speed is greater than a preset first threshold, and the accelerator pedal opening is greater than a preset second threshold, a first time window is obtained. The first time window includes a plurality of second time windows arranged in chronological order. The first time window also includes a random time window. The starting point of the random time window is the starting point of the first time window, and the ending point of the random time window is any time point in the first time window. Within the first time window, several second time windows, and the random time window, the vehicle speed range, the peak value of longitudinal acceleration, the valley value of longitudinal acceleration, and the acceleration range are determined based on the vehicle speed and the longitudinal acceleration, respectively. If the target torque is greater than zero, and if several speed ranges within the first time window, the second time window, and the random time window are all less than a preset third threshold, then the first time window is taken as a stable speed range. If, when the target torque is greater than zero, several longitudinal acceleration valleys within the first time window, the second time window, and the random time window are all greater than a preset fourth threshold and several acceleration ranges are all less than a preset fifth threshold, then the first time window is taken as a stable acceleration interval. If, when the target torque is less than zero, several longitudinal acceleration peaks within the first time window, the second time window, and the random time window are all less than a preset sixth threshold and several acceleration ranges are all less than a preset fifth threshold, then the first time window is taken as a stable deceleration interval. If, when the target torque is less than zero, several longitudinal acceleration peaks within the first time window, the second time window, and the random time window are all less than a preset seventh threshold and several acceleration ranges are all less than a preset fifth threshold, then, when the target torque is less than a preset eighth threshold, the first time window is taken as a stable feedback interval.

4. The method according to claim 3, characterized in that, Within the stable driving range, determining the user's effort action count based on the vehicle driving parameters includes: For the stable vehicle speed range, the stable acceleration range, the stable deceleration range, and the stable feedback range, a number of second time windows are determined corresponding to the stable vehicle speed range, the stable acceleration range, the stable deceleration range, and the stable feedback range, respectively. Within several second time windows corresponding to the stable vehicle speed range, the stable acceleration range, the stable deceleration range, and the stable feedback range, the trough rising edge difference sequence and the peak falling edge difference sequence of the accelerator pedal opening are respectively obtained; the trough rising edge difference sequence includes the opening difference between each trough extreme point of the accelerator pedal opening within the second time window and the next adjacent peak extreme point; the peak falling edge difference sequence includes the opening difference between each peak extreme point of the accelerator pedal opening within the second time window and the next adjacent trough extreme point. For any second time window, if the maximum value in the difference sequence of rising troughs or the maximum value in the difference sequence of falling peaks is greater than a preset ninth threshold, then there is a user effort action in the second time window, and the effort action count is generated.

5. The method according to claim 4, characterized in that, The vehicle driving parameters also include mileage, and the effort index includes a driving effort index and a feedback effort index; determining the effort index based on the number of effort actions within a preset statistical mileage includes: When the driving mileage is greater than or equal to the preset statistical mileage, the count of the effort actions within the stable speed range, the stable acceleration range, the stable deceleration range, and the stable feedback range within the preset statistical mileage is obtained respectively. The driving effort index is determined based on the number of effort actions within the stable speed range, the stable acceleration range, and the stable deceleration range. The feedback effort index is determined based on the number of effort actions within the stable feedback interval.

6. The method according to claim 5, characterized in that, The effort change rate includes the driving effort change rate and the feedback effort change rate. Determining the effort change rate based on several effort indicators includes: Take any of the preset statistical mileages as the current statistical mileage, and obtain the driving effort index and the feedback effort index in the current statistical mileage; Take the previous statistical mileage of the current statistical mileage as the reference statistical mileage, and obtain the driving effort index and the feedback effort index in the reference statistical mileage. The rate of change of driving effort is determined based on the driving effort index in the current statistical mileage and the driving effort index in the reference statistical mileage; The rate of change of feedback effort is determined based on the feedback effort index in the current statistical mileage and the feedback effort index in the reference statistical mileage.

7. The method according to claim 1, characterized in that, The step of adjusting the base torque coefficient by selecting the steady-state torque coefficient or the transient torque coefficient based on the driving control requirement information to obtain the target torque coefficient includes: When the driving control demand information indicates that the user has an instantaneous driving control demand, the transient torque coefficient is selected to adjust the basic torque coefficient to obtain the target torque coefficient; When the driving control demand information indicates that the user does not have instantaneous driving control needs, the steady-state torque coefficient is selected to adjust the base torque coefficient to obtain the target torque coefficient.

8. A vehicle torque control device, characterized in that, An application in a vehicle torque control system, wherein the vehicle torque control system is installed in a vehicle, the device includes: The parameter acquisition module is used to acquire vehicle driving parameters and the basic torque coefficient sent from the cloud. The coefficient determination module is used to determine the steady-state torque coefficient, transient torque coefficient, and driving control requirements based on the vehicle driving parameters. The coefficient adjustment module is used to select the steady-state torque coefficient or the transient torque coefficient according to the driving control requirement information to adjust the base torque coefficient to obtain the target torque coefficient; A torque control module is used to control the vehicle torque using the target torque coefficient.

9. A vehicle, characterized in that, It includes a processor, a memory, and a program or instructions stored on the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the method as described in any one of claims 1-7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the method as described in any one of claims 1-7.

Images