Pedal torque self-learning method and device, vehicle and storage medium

Abstract

This invention relates to the field of vehicle power control technology, and discloses a pedal torque self-learning method, device, vehicle, and storage medium. The invention maps the acquired accelerator pedal opening and vehicle speed to target pedal opening points and target vehicle speed points based on preset accelerator offset and vehicle speed segmentation strategies, respectively. Then, the target vehicle speed point and its corresponding actual acceleration value are used as sample parameters to update the sample parameter set corresponding to the target pedal opening point. Based on the updated sample parameter set, a preset acceleration function is fitted to obtain the acceleration curve corresponding to the target pedal opening point, which is then converted into a pedal torque curve. This eliminates the need to preset a large number of calibration curves in the software, saving memory space. By continuously collecting driving data for pedal torque self-learning, it not only automates the manual calibration process but also makes real-time power corrections based on the user's actual driving habits, achieving the user's desired effect and improving the accuracy of torque control.

Description

Technical Field

[0001] This invention relates to the field of vehicle power control technology, specifically to a pedal torque self-learning method, device, vehicle, and storage medium. Background Technology

[0002] Existing methods for correcting accelerator pedal torque can only be used to make corrections based on the vehicle's preset pedal lookup map (MAP). Furthermore, the torque correction coefficient and torque analysis still rely on the vehicle's preset MAP data. This requires calibration engineers to perform single-vehicle calibration for different models and driving styles, resulting in long development cycles, high adaptation costs, and excessive reliance on the calibration data of calibration engineers. It is impossible to fully learn the driver's habits. If the vehicle's driving style data needs to be modified, over-the-air (OTA) technology is required to update the data, making it impossible to achieve real-time, adaptive torque correction based on user habits on the device side. Summary of the Invention

[0003] This invention provides a pedal torque self-learning method, device, vehicle, and storage medium to solve the problem that manually calibrated MAP data cannot achieve real-time and adaptive torque correction based on user habits.

[0004] In a first aspect, the present invention provides a pedal torque self-learning method, the method comprising: acquiring vehicle driving data, the driving data including at least accelerator pedal opening, vehicle speed, and corresponding actual acceleration value; mapping the accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points based on a preset accelerator offset strategy and a vehicle speed segmentation strategy, wherein the accelerator offset strategy is used to map all accelerator pedal openings falling within a continuous opening range corresponding to the target pedal opening point to the target pedal opening point, and the vehicle speed segmentation strategy is used to map all vehicle speeds falling within a continuous vehicle speed range corresponding to the target vehicle speed point to the target vehicle speed point; updating the target vehicle speed point and the corresponding actual acceleration value as sample parameters to the sample parameter set corresponding to the target pedal opening point; fitting a preset acceleration function based on the updated sample parameter set to obtain an acceleration curve corresponding to the target pedal opening point; and converting the acceleration curve corresponding to the target pedal opening point into a corresponding pedal torque curve.

[0005] The pedal torque self-learning method provided by this invention maps the acquired accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points based on preset accelerator offset strategies and vehicle speed segmentation strategies, respectively. Then, the target vehicle speed point and the corresponding actual acceleration value are used as sample parameters to update the sample parameter set corresponding to the target pedal opening point. Based on the updated sample parameter set, a preset acceleration function is fitted to obtain the acceleration curve corresponding to the target pedal opening point. The acceleration curve is then converted into a pedal torque curve. This eliminates the need to preset a large number of calibration curves in the software, saving memory space. By continuously collecting driving data for pedal torque self-learning, it not only automates the manual calibration process but also makes real-time power corrections based on the user's actual driving habits to achieve the user's desired effect and improve the accuracy of torque control.

[0006] In an optional implementation, the method further includes: acquiring current driving data during vehicle operation, the current driving data including current accelerator pedal opening and current vehicle speed; acquiring a pedal torque curve corresponding to the current accelerator pedal opening; determining a corresponding driving demand torque from the pedal torque curve based on the current vehicle speed, and controlling vehicle operation based on the driving demand torque; acquiring the actual acceleration value of the vehicle at the current moment; using the current accelerator pedal opening, current vehicle speed, and the actual acceleration value as new vehicle driving data, and executing the step of mapping the accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points based on a preset accelerator offset strategy and vehicle speed segmentation strategy, respectively, to update the pedal torque curve corresponding to the current accelerator pedal opening online.

[0007] In an optional implementation, before using the current accelerator pedal opening, current vehicle speed, and actual acceleration value as new vehicle driving data, the method further includes: comparing the current accelerator pedal opening, current vehicle speed, and vehicle driving parameters with preset self-learning enabling conditions, wherein the preset self-learning enabling conditions include at least one of the following: the current accelerator pedal opening is within a preset accelerator pedal opening learning range, the current vehicle speed is within a preset vehicle speed learning range, the rate of change of accelerator pedal opening is less than a preset rate of change threshold, the vehicle has not slipped or the electronic stability program has not intervened, the vehicle is not in intelligent driving assistance mode, and the self-learning function is activated; when the current accelerator pedal opening, current vehicle speed, and vehicle driving parameters meet the self-learning enabling conditions, the current accelerator pedal opening, current vehicle speed, and actual acceleration value are used as new vehicle driving data.

[0008] In one optional implementation, updating the sample parameter set corresponding to the target pedal opening point with the target vehicle speed point and the corresponding actual acceleration value as sample parameters includes: if the currently stored sample parameter set includes the target vehicle speed point and the corresponding acceleration record value, fusing the actual acceleration value and the acceleration record value to obtain an acceleration fusion value; updating the acceleration record value to the acceleration fusion value; if the currently stored sample parameter set does not include the target vehicle speed point, adding the target vehicle speed point and the corresponding actual acceleration value as sample parameters to the sample parameter set.

[0009] When a new target vehicle speed point is obtained, the present invention can add it as a new sample to continuously expand the coverage of the parameter set. For existing target vehicle speed points, through data fusion processing, the accumulated value of historical data is preserved, and new actual measurement values ​​are introduced, so that the acceleration fusion value is closer to the real working condition, ensuring the dynamic improvement and continuous optimization of the sample parameter set.

[0010] In one optional implementation, the preset acceleration function is a piecewise function. The step of fitting the preset acceleration function based on the updated sample parameter set to obtain the acceleration curve corresponding to the target pedal opening point includes: selecting the vehicle speed point corresponding to the maximum acceleration from the updated sample parameter set; using the vehicle speed point corresponding to the maximum acceleration as the common fitting point for the piecewise function, fitting the piecewise function based on the preset starting acceleration value and the updated sample parameter set to obtain the acceleration curve corresponding to the target pedal opening point.

[0011] This invention selects the vehicle speed point corresponding to the maximum acceleration as the segmented common fitting point, which fits the actual acceleration characteristics of the vehicle, accurately matches the speed change pattern of the entire vehicle, and greatly improves the fitting accuracy of the acceleration curve. The use of a piecewise function for fitting makes the acceleration curve more closely fit the actual vehicle driving data, providing a reliable basis for the subsequent conversion of the pedal torque curve.

[0012] In one optional implementation, converting the acceleration curve corresponding to the target pedal opening point into a corresponding pedal torque curve includes: discretizing the acceleration curve to obtain multiple vehicle speed points and corresponding acceleration fitting values; calculating the vehicle resistance value based on the actual vehicle acceleration value and the actual vehicle driving torque value; for any discrete vehicle speed point, calculating the driver's driving demand torque based on the vehicle resistance value and the corresponding acceleration fitting value; and fitting a preset torque function based on all vehicle speed points and the corresponding driving demand torque to generate a pedal torque curve.

[0013] This invention calculates vehicle resistance based on actual vehicle acceleration and actual driving torque, abandoning the traditional method of fixing resistance parameters. This allows the resistance value to dynamically adapt to actual vehicle driving conditions, improving the accuracy of torque calculation. Furthermore, it calculates the required torque for each discrete vehicle speed point, accurately matching the power demand at different vehicle speeds and aligning with the driver's driving intentions.

[0014] In one optional implementation, the method further includes: obtaining the acceleration fitting value corresponding to the current vehicle speed from the acceleration curve; calculating the deviation value between the acceleration fitting value and the actual acceleration value; performing closed-loop adjustment on the deviation value to obtain a compensation torque; superimposing the compensation torque with the driving demand torque in the fitted pedal torque curve to generate an updated demand torque, and obtaining an updated pedal torque curve.

[0015] This invention introduces closed-loop acceleration feedback and torque compensation, which can effectively limit the vehicle's output torque to not exceed the safe operating condition threshold, realize the safety limit constraint of driving demand torque, and improve the accuracy and safety of power output.

[0016] In an optional embodiment, the method further includes: obtaining a first pedal torque curve corresponding to a first pedal opening point and a second pedal torque curve corresponding to a second pedal opening point, wherein the first pedal opening point and the second pedal opening point are adjacent; determining a pedal opening value to be processed, wherein the pedal opening value to be processed is located between the first pedal opening point and the second pedal opening point; calculating a linear difference coefficient based on the pedal opening value to be processed, the first pedal opening point, and the second pedal opening point; and generating a pedal torque curve corresponding to the pedal opening value to be processed through linear difference operation based on the linear difference coefficient, the first pedal torque curve, and the second pedal torque curve.

[0017] This invention calibrates the pedal torque curves corresponding to a finite number of pedal opening points, and can cover any pedal opening within a continuous range through linear interpolation, reducing calibration workload and data storage. Furthermore, through the linear interpolation algorithm, a continuous and smooth transition between pedal opening and torque curves can be achieved.

[0018] In an optional implementation, the method further includes: in response to a self-learning reset command, clearing the currently stored pedal torque curve data corresponding to each accelerator pedal opening to zero.

[0019] Secondly, the present invention provides a pedal torque self-learning device, the device comprising: a data acquisition module for acquiring vehicle driving data, the driving data including at least accelerator pedal opening, vehicle speed, and corresponding actual acceleration value; a data mapping module for mapping the accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points based on a preset accelerator offset strategy and a vehicle speed segmentation strategy, wherein the accelerator offset strategy maps all accelerator pedal openings falling within a continuous opening range corresponding to the target pedal opening point to the target pedal opening point, and the vehicle speed segmentation strategy maps all vehicle speeds falling within a continuous vehicle speed range corresponding to the target vehicle speed point to the target vehicle speed point; a parameter set update module for updating the sample parameter set corresponding to the target pedal opening point with the target vehicle speed point and the corresponding actual acceleration value as sample parameters; an acceleration curve fitting module for fitting a preset acceleration function based on the updated sample parameter set to obtain an acceleration curve corresponding to the target pedal opening point; and a pedal torque curve generation module for converting the acceleration curve corresponding to the target pedal opening point into a corresponding pedal torque curve.

[0020] Thirdly, the present invention provides a vehicle including a controller, the controller including a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the pedal torque self-learning method of the first aspect or any corresponding embodiment described above.

[0021] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the pedal torque self-learning method of the first aspect or any corresponding embodiment thereof.

[0022] The present invention has the following technical effects: The pedal torque self-learning method provided by this invention maps the acquired accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points based on preset accelerator offset strategies and vehicle speed segmentation strategies, respectively. Then, the target vehicle speed point and the corresponding actual acceleration value are used as sample parameters to update the sample parameter set corresponding to the target pedal opening point. Based on the updated sample parameter set, a preset acceleration function is fitted to obtain the acceleration curve corresponding to the target pedal opening point. The acceleration curve is then converted into a pedal torque curve. This eliminates the need to preset a large number of calibration curves in the software, saving memory space. By continuously collecting driving data for pedal torque self-learning, it not only automates the manual calibration process but also makes real-time power corrections based on the user's actual driving habits to achieve the user's desired effect and improve the accuracy of torque control. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a schematic flowchart of the first method for pedal torque self-learning according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the process of obtaining the acceleration point and pedal opening point according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the second process of the pedal torque self-learning method according to an embodiment of the present invention; Figure 4 This is an example diagram of obtaining acceleration curves according to an embodiment of the present invention; Figure 5 This is an example diagram of acceleration curves according to an embodiment of the present invention; Figure 6 This is a flowchart illustrating acceleration curve fitting according to an embodiment of the present invention; Figure 7 This is a flowchart illustrating pedal torque curve fitting according to an embodiment of the present invention; Figure 8 This is a flowchart illustrating the pedal torque curve correction according to an embodiment of the present invention; Figure 9 This is a flowchart illustrating the self-learning process of pedal torque according to an embodiment of the present invention; Figure 10 This is a structural block diagram of a vehicle according to an embodiment of the present invention; Figure 11 This is a structural block diagram of the pedal torque self-learning device according to an embodiment of the present invention; Figure 12 This is a schematic diagram of the hardware structure of the controller according to an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0027] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0028] According to an embodiment of the present invention, a pedal torque self-learning method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0029] This embodiment provides a pedal torque self-learning method, which can be used in vehicle controllers. Figure 1 This is a flowchart of the pedal torque self-learning method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: Obtain vehicle driving data.

[0030] The vehicle driving data includes at least the accelerator pedal opening, vehicle speed, and the corresponding actual acceleration value.

[0031] Because the driver's control over the vehicle is reflected in the opening of the accelerator pedal, the brake pedal, and the steering wheel angle, different operations will produce different torques, and the vehicle speed will change significantly, ultimately resulting in different accelerations. Vehicle acceleration can intuitively reflect the vehicle's power performance and can represent the driver's driving habits. Users are also quite sensitive to changes in vehicle acceleration. In existing solutions, the acceleration values ​​are mostly preset calibration lookup values ​​in the software and cannot be changed. This invention obtains the acceleration value expected by the user by fitting and learning the acquired vehicle driving data (including acceleration values). This acceleration value can also be adjusted as the user's driving habits change.

[0032] This invention can acquire vehicle driving data during vehicle operation, including but not limited to accelerator pedal opening, vehicle speed, and corresponding actual acceleration values. Specifically, when the pedal torque self-learning function is restarted, multiple vehicle speeds and corresponding actual acceleration values ​​at any accelerator pedal opening can be acquired. Subsequent steps are then executed to obtain a sample parameter set. Based on this sample parameter set, acceleration curves and pedal torque curves are generated. When driving the vehicle subsequently based on the pedal torque curves, the real-time acquired vehicle driving data can be used to execute subsequent steps to update the sample parameter set, thereby obtaining the real-time self-learned acceleration curves and pedal torque curves. This is merely an example.

[0033] Step S102: Based on the preset throttle offset strategy and vehicle speed segmentation strategy, the throttle pedal opening and vehicle speed are mapped to the corresponding target pedal opening point and target vehicle speed point, respectively.

[0034] Among them, the throttle offset strategy is used to map all throttle pedal openings that fall within the continuous opening range corresponding to the target pedal opening point to the target pedal opening point, and the vehicle speed segmentation strategy is used to map all vehicle speeds that fall within the continuous vehicle speed range corresponding to the target vehicle speed point to the target vehicle speed point.

[0035] To prevent errors caused by slight fluctuations in the driver's throttle input, and to leverage the equidistant upper and lower range settings that can characterize the driver's driving habits to some extent, this invention employs a throttle offset strategy. This strategy maps all throttle pedal openings falling within a continuous range corresponding to the target pedal opening point to the target pedal opening point. This uniformly maps slightly fluctuating throttle pedal openings to a fixed target pedal opening point, preventing frequent jumps in the throttle signal due to driver foot vibrations or road bumps, resulting in more stable power control. Furthermore, the equidistant upper and lower range settings for the throttle learning band not only conform to the actual physical operation characteristics of the throttle pedal but also objectively and completely cover the driver's normal operating range, better reflecting actual driving behavior. For example, pedal values ​​within the actual throttle pedal opening range of 29%-31% can be used as... The 30% accelerator pedal learning zone (pedal opening point) indicates the driver's desired power demand. If the frequency of the driver's actual pedal opening being between 29% and 30% is higher within this zone, it suggests a more conservative power demand. Conversely, a lower frequency indicates a more aggressive power demand. Similarly, pedal values ​​within 34%-36%, 39%-41%, 49%-51%, 69%-71%, 79%-81%, and 98%-100% can be designated as 35%, 40%, 50%, 70%, 80%, and 100% accelerator pedal learning zones, respectively. These are just examples; by setting multiple symmetrical learning zones, accelerator pedal operations under various conditions, such as idling, city driving, and rapid acceleration, can be covered, enabling accurate recognition of driving intentions in different driving scenarios.

[0036] To improve the efficiency of acceleration value acquisition by combining accelerator pedal offset strategy, this invention embodiment can set a vehicle speed segmentation strategy to map all vehicle speeds falling within the continuous vehicle speed range corresponding to the target vehicle speed point to the target vehicle speed point. The vehicle speed segmentation interval covers common operating conditions, and the self-learned vehicle speed range is limited to 0 kph-120 kph. Considering that the acceleration change rate corresponding to the vehicle speed in the intermediate speed range (56-84 kph) is not large, this intermediate speed range can be ignored to reduce fitting costs. (Self-learning), for example, the vehicle speed values ​​within 9kph-11kph, 14kph-16kph, 19kph-21kph, 54kph-56kph, 84kph-86kph, 104kph-106kph, and 119kph-121kph are respectively used as vehicle speed learning intervals (vehicle speed points) of 10kph, 15kph, 20kph, 55kph, 85kph, 105kph, and 120kph, which is only used as an example.

[0037] The sample parameter set can be stored in the following formats: accelerations a11 a12 a13 a14 a15 a16 a17 when the pedal opening is 30% and the vehicle speed reaches 10kph, 15kph...120kph; accelerations a21 a22 a23 a24 a25 a26 a27 when the pedal opening is 35% and the vehicle speed reaches 10kph, 15kph...120kph; ...; accelerations a71 a72 a73 a74 a75 a76 a77 when the pedal opening is 100% and the vehicle speed reaches 10kph, 15kph...120kph. Each pedal opening point corresponds to a sample parameter set containing all vehicle speeds and corresponding acceleration values ​​at the current pedal opening point. This is just an example.

[0038] In this embodiment of the invention, the collected accelerator pedal opening and vehicle speed can be mapped to target pedal opening points and target vehicle speed points based on an accelerator pedal offset strategy and a vehicle speed segmentation strategy, respectively. The mapping process for pedal opening points and vehicle speed points is as follows: Figure 2 As shown.

[0039] Step S103: The target vehicle speed point and the corresponding actual acceleration value are used as sample parameters and updated to the sample parameter set corresponding to the target pedal opening point.

[0040] In this embodiment of the invention, the target vehicle speed point and actual acceleration value corresponding to the target pedal opening point obtained through the above steps can be used as parameter samples and added to the template parameter set corresponding to the target pedal opening point to complete the update of the sample parameter set.

[0041] Step S104: Based on the updated sample parameter set, fit the preset acceleration function to obtain the acceleration curve corresponding to the target pedal opening point.

[0042] Based on the updated sample parameter set, this invention can fit a preset acceleration function to obtain the acceleration curve corresponding to the target pedal opening point. The preset acceleration function can be an acceleration function form that conforms to the vehicle's driving characteristics, such as a quadratic function, a cubic function, or a piecewise function. The independent variable of the function is the target vehicle speed point, and the dependent variable is the actual acceleration value. Common fitting algorithms such as the least squares method can be used to solve the parameters of the preset acceleration function using the "target vehicle speed point - actual acceleration value" data in the sample parameter set, and obtain the fitted acceleration curve (i.e., the correspondence between the vehicle speed point and the acceleration value). This is only an example and is not intended to limit the scope.

[0043] Step S105: Convert the acceleration curve corresponding to the target pedal opening point into the corresponding pedal torque curve.

[0044] Since there is a fixed mechanical relationship between vehicle acceleration and driving torque, this embodiment of the invention can convert the pedal torque curve corresponding to the target pedal opening point into a pedal torque curve corresponding to the target pedal opening point through a preset mechanical conversion formula. In this pedal torque curve, the independent variable is the vehicle speed point, and the dependent variable is the driving demand torque. This pedal torque curve can be directly used for vehicle torque control. When the driver presses the accelerator to the target pedal opening point, the vehicle can determine the corresponding driving torque based on the current vehicle speed through this curve, thereby achieving precise torque control and improving the driving experience and vehicle driving stability. This is just an example.

[0045] The above process can be executed repeatedly, that is, the vehicle continuously collects driving data and continuously updates the sample parameter set corresponding to each target pedal opening point, thereby continuously optimizing the acceleration curve and pedal torque curve, so that the torque control parameters can adapt to different driving conditions, road conditions and driver habits, without relying on preset fixed MAP calibration, reducing the calibration workload of a single vehicle, and improving the accuracy and adaptability of torque control.

[0046] The pedal torque self-learning method provided in this embodiment maps the acquired accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points based on preset accelerator offset strategies and vehicle speed segmentation strategies, respectively. Then, the target vehicle speed point and the corresponding actual acceleration value are used as sample parameters to update the sample parameter set corresponding to the target pedal opening point. Based on the updated sample parameter set, a preset acceleration function is fitted to obtain the acceleration curve corresponding to the target pedal opening point. The acceleration curve is then converted into a pedal torque curve. This eliminates the need to preset a large number of calibration curves in the software, saving memory space. By continuously collecting driving data for pedal torque self-learning, it not only automates the manual calibration process but also makes real-time power corrections based on the user's actual driving habits to achieve the user's desired effect and improve the accuracy of torque control.

[0047] This embodiment provides a pedal torque self-learning method, which can be used in vehicle controllers. Figure 3 This is a flowchart of the pedal torque self-learning method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Obtain vehicle driving data. This driving data includes at least the accelerator pedal opening, vehicle speed, and corresponding actual acceleration value. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0048] Step S302: Based on a preset throttle offset strategy and vehicle speed segmentation strategy, the throttle pedal opening and vehicle speed are mapped to corresponding target pedal opening points and target vehicle speed points, respectively. Specifically, the throttle offset strategy maps all throttle pedal openings falling within the continuous opening range corresponding to the target pedal opening point to the target pedal opening point; the vehicle speed segmentation strategy maps all vehicle speeds falling within the continuous speed range corresponding to the target vehicle speed point to the target vehicle speed point. For details, please refer to [link to details]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0049] Step S303: The target vehicle speed point and the corresponding actual acceleration value are used as sample parameters and updated to the sample parameter set corresponding to the target pedal opening point.

[0050] Specifically, if the currently stored sample parameter set includes the target vehicle speed point and the corresponding acceleration record value, the actual acceleration value and the acceleration record value are fused to obtain the acceleration fusion value; the acceleration record value is then updated to the acceleration fusion value; if the currently stored sample parameter set does not include the target vehicle speed point, the target vehicle speed point and the corresponding actual acceleration value are added to the sample parameter set as sample parameters.

[0051] In the process of updating the sample parameter set, this embodiment of the invention can determine whether the target vehicle speed point and the corresponding acceleration value have been recorded in the currently stored sample parameter set. If the sample parameter set includes the target vehicle speed point and the corresponding acceleration record value, the actual acceleration value and the acceleration record value obtained above can be fused to obtain the acceleration fusion value. The fusion processing method is not limited. The actual acceleration value and the acceleration record value can be averaged, or a weighted fusion processing can be performed. For example, the weights of the two can be determined according to the order of acquisition time, and the weight corresponding to the actual acceleration value can be set to be larger to ensure that the fitted acceleration curve can adapt to the dynamic adjustment of vehicle operating conditions and driver driving habits in a timely manner. This is just an example. Then, the acceleration record value can be updated to the acceleration fusion value to ensure that the acceleration value is in a state of continuous updating. The self-learning torque can also be quickly and synchronously adjusted, and the memory pressure of the controller storing data can also be reduced.

[0052] If the target vehicle speed point is not included in the currently stored sample parameter set, the target vehicle speed point and its corresponding actual acceleration value can be added directly to the sample parameter set as sample parameters.

[0053] When a new target vehicle speed point is obtained, the present invention can add it as a new sample to continuously expand the coverage of the parameter set. For existing target vehicle speed points, through data fusion processing, the accumulated value of historical data is preserved, and new actual measurement values ​​are introduced, so that the acceleration fusion value is closer to the real working condition, ensuring the dynamic improvement and continuous optimization of the sample parameter set.

[0054] Step S304: Based on the updated sample parameter set, fit the preset acceleration function to obtain the acceleration curve corresponding to the target pedal opening point.

[0055] Specifically, the preset acceleration function is a piecewise function, and step S304 above includes: Step S3041: Select the vehicle speed point corresponding to the maximum acceleration from the updated sample parameter set.

[0056] This invention does not limit the method of selecting the vehicle speed point corresponding to the maximum acceleration. For example, the vehicle speed point corresponding to the maximum acceleration in the sample parameter set can be directly selected. Alternatively, an upper limit value for acceleration can be set to select the vehicle speed point that is less than the upper limit value and is the vehicle speed point corresponding to the maximum acceleration. Or, based on actual vehicle driving experience, it can be determined that after the user presses the fixed accelerator pedal, the maximum vehicle acceleration generally occurs in the low speed range of 0-15 kph. This value will affect the overall acceleration performance of the vehicle. Because a vehicle speed segmentation strategy is set, the acceleration values ​​corresponding to the 10 kph and 15 kph vehicle speed points can be extracted respectively, and then the value with the larger acceleration between the two points can be taken as the maximum acceleration. This is just an example.

[0057] Step S3042: Using the vehicle speed point corresponding to the maximum acceleration as the common fitting point for the segment, the piecewise function is fitted based on the preset starting acceleration value and the updated sample parameter set to obtain the acceleration curve corresponding to the target pedal opening point.

[0058] This invention allows for setting different starting acceleration values ​​for different vehicle models with varying acceleration performance. For example, it sets the acceleration value corresponding to a vehicle speed of 0 kph under constant throttle as the starting acceleration value. This enables the preset starting acceleration values ​​for vehicles with different acceleration performance, allowing the fitted curve to accurately match the vehicle's power characteristics and improving the versatility of the solution. To improve the similarity between the fitted equation and the actual vehicle acceleration curve, the acceleration function can be set as a piecewise function, which is a quadratic function in one variable. The vehicle speed point corresponding to the maximum acceleration is used as the common fitting point for each piecewise function. This establishes the acceleration curve for the entire vehicle speed range at the target pedal opening point. By using the vehicle speed point corresponding to the maximum acceleration as the common fitting point, the two segments of the quadratic function are connected at that point, avoiding abrupt changes, inflection points, or jumps in the curve. This ensures the smoothness of the vehicle's acceleration as it changes with speed, improving power control and driving smoothness. Simultaneously, the least squares method is used to fit the key parameters of the equation. Solving for the equation parameters with the minimum error ensures curve smoothness and allows for minimizing the sum of squared residuals to find optimal parameters, reducing fitting errors and making the acceleration curve more closely resemble real vehicle driving data. The fitting method is not limited. Specifically, considering the significant difference in acceleration characteristics between low and high speeds, with the maximum acceleration being the turning point of the acceleration trend, piecewise fitting is performed using the vehicle speed corresponding to the maximum acceleration as a decomposition. All vehicle speeds less than the common fitting point are fitted with a piecewise function Y1, and all vehicle speeds greater than the common fitting point are fitted with a piecewise function Y2. This accurately reflects the actual physical laws of strong acceleration at low speeds and weak acceleration at high speeds, significantly improving fitting accuracy. Furthermore, each segment is independently optimized using the least squares method to minimize the sum of squared residuals, improving fitting accuracy in both low-speed and high-speed intervals. The common fitting point ensures a natural transition between the two curve segments, balancing fitting accuracy and overall smoothness. Figure 4 As shown, the acceleration curve at the target pedal opening point is finally obtained, as follows. Figure 5 As shown, at the target pedal opening point, the acceleration is monotonically increasing before the vehicle acceleration reaches its maximum value, and monotonically decreasing after the vehicle acceleration reaches its maximum value. The process for fitting the acceleration curve is described in [link to documentation]. Figure 6 As shown.

[0059] Specifically, the piecewise functions Y1 and Y2 can be fitted using the following steps: Assume the fitting function is Where a, b, and c are the parameters to be fitted, and the vehicle speed point corresponding to the maximum acceleration is known. ),in, Indicates the vehicle speed point. This represents the maximum acceleration value, combined with the extreme value formula:

[0060]

[0061] Substituting the extremum formula into the above fitted function equation, we get: Then, the objective function is defined as the sum of squares of the residuals:

[0062] Where n represents the number of vehicle speed points used in Y2 curve fitting, and i represents the i-th vehicle speed point ( Then, partial derivatives of the above equation with respect to parameter a can be obtained, and the solution can be made by setting... Minimum value value.

[0063] The embodiments of the present invention will Substituting the values ​​into the maximum / minimum formula, we can solve for the values ​​of b and c to obtain the fitted Y2 equation. Following the same method, we can fit the Y1 equation, which will not be elaborated here.

[0064] Furthermore, the validity of the equation parameters can be verified during the curve fitting process. When parameter a does not meet the requirements, the parameters in this group should be discarded. This includes, but is not limited to: the fitted parameters do not conform to the characteristics of a quadratic function formula, such as the function being a parabola opening downwards, in which case parameter a should be less than 0; under the same vehicle speed conditions, the larger the accelerator pedal opening, the larger the fitted target acceleration value should also be. This is just an example.

[0065] This invention selects the vehicle speed point corresponding to the maximum acceleration as the segmented common fitting point, which fits the actual acceleration characteristics of the vehicle, accurately matches the speed change pattern of the entire vehicle, and greatly improves the fitting accuracy of the acceleration curve. The use of a piecewise function for fitting makes the acceleration curve more closely fit the actual vehicle driving data, providing a reliable basis for the subsequent conversion of the pedal torque curve.

[0066] Step S305: Convert the acceleration curve corresponding to the target pedal opening point into the corresponding pedal torque curve.

[0067] Specifically, the acceleration curve is converted into a corresponding pedal torque curve through the following steps: the acceleration curve is discretized and sampled to obtain multiple vehicle speed points and corresponding acceleration fitting values; the vehicle resistance value is calculated based on the actual vehicle acceleration value and the actual vehicle driving torque value; for any discrete vehicle speed point, the driver's required torque is calculated based on the vehicle resistance value and the corresponding acceleration fitting value; based on all vehicle speed points and the corresponding required torque, a preset torque function is fitted to generate the pedal torque curve.

[0068] This invention embodiment can discretize the acceleration curve obtained by the above fitting to obtain multiple vehicle speed points and corresponding acceleration fitting values, ensuring comprehensive sample coverage and accurate data for torque calculation, providing reliable support for subsequent torque fitting, avoiding torque curve deviations caused by insufficient sampling, and further ensuring the smoothness of the pedal torque curve, reducing the jerkiness of power output, and improving the smoothness of the vehicle's power control and driving experience. Then, acceleration can be converted into torque using dynamic formulas, and the vehicle resistance value can be calculated based on the actual vehicle acceleration value and the actual vehicle driving torque value using the following formula:

[0069] in, This indicates the actual driving torque value of the vehicle. The value represents the vehicle's actual acceleration, f represents the vehicle's resistance, and m represents the vehicle's weight.

[0070] Then, using the following formula, for any discrete vehicle speed point, based on the vehicle resistance value and the corresponding acceleration fitting value, the driver's required torque is calculated:

[0071] in, Indicates the torque required for driving; This represents the fitted acceleration value.

[0072] The embodiments of the present invention can fit the torque function based on all vehicle speed points and the calculated driving demand torque to generate a pedal torque curve.

[0073] This invention calculates vehicle resistance based on actual vehicle acceleration and actual driving torque, abandoning the traditional method of fixing resistance parameters. This allows the resistance value to dynamically adapt to real-world driving conditions, achieving dynamic self-adaptation of the driving torque demand. Furthermore, it combines discretized acceleration fitting values ​​to calculate the driving torque demand, avoiding the torque calculation errors caused by fixed table lookups and simple compensations in existing technologies. This ensures that the driving torque demand accurately matches the driver's actual driving intentions and the current vehicle operating state. Moreover, it introduces real-time calculated vehicle resistance values ​​as core intermediate parameters, forming a complete closed loop of "calculating vehicle resistance based on real-world test parameters, and then calculating the driving torque demand using vehicle resistance as the core parameter." This ensures that the fitted pedal torque curve not only matches the driver's pedal operation but also adapts to changes in real-time vehicle operating resistance, improving the accuracy of torque calculation.

[0074] Furthermore, the first pedal torque curve corresponding to the first pedal opening point and the second pedal torque curve corresponding to the second pedal opening point are obtained, with the first and second pedal opening points being adjacent; the pedal opening value to be processed is determined, which is located between the first and second pedal opening points; based on the pedal opening value to be processed, the first pedal opening point, and the second pedal opening point, a linear difference coefficient is calculated; based on the linear difference coefficient, the first pedal torque curve, and the second pedal torque curve, a pedal torque curve corresponding to the pedal opening value to be processed is generated through linear difference operation.

[0075] The present invention only fits the pedal torque curve at the pedal opening point. Therefore, the linear interpolation method can be used to calculate the torque curve corresponding to 0-100% throttle opening. When the torque curve switches due to changes in throttle opening, filtering and smoothing are performed. The process is described in [link to process]. Figure 7 As shown, for example, through the above steps, the first pedal torque curve corresponding to the first pedal opening point of 30% is T3, and the second pedal torque curve corresponding to the second pedal opening point of 50% is T5. If the pedal opening value to be processed is between the first pedal opening point and the second pedal opening point, that is, between 30% and 50%, and is K1, then based on the pedal opening value to be processed, the first pedal opening point, and the second pedal opening point, a linear difference coefficient can be calculated. Then, based on the linear difference coefficient, the first pedal torque curve, and the second pedal torque curve, a pedal torque curve corresponding to the pedal opening value to be processed can be generated through linear difference operation. That is, the pedal torque curve corresponding to K1 is: [(K1-30) / (50-30)](T5-T3)+T3 This invention calibrates the pedal torque curves corresponding to a limited number of pedal opening points, and can cover any pedal opening within a continuous range through linear interpolation. This reduces calibration workload and data storage while ensuring that any pedal operation corresponds to accurate torque output, adapting to all pedal operation scenarios for the driver. Furthermore, through the linear interpolation algorithm, a continuous and smooth transition between pedal opening and torque curves can be achieved, ensuring that the torque curves corresponding to different opening ranges transition naturally and continuously, reducing the jerking sensation of power output, avoiding driving discomfort caused by sudden torque changes, and improving the smoothness of vehicle power control and driving experience.

[0076] Furthermore, after obtaining the pedal torque curve, the acceleration fitting value corresponding to the current vehicle speed can be obtained from the acceleration curve; the deviation value between the acceleration fitting value and the actual acceleration value can be calculated; the deviation value can be adjusted in a closed loop to obtain the compensation torque; the compensation torque can be superimposed with the driving demand torque in the fitted pedal torque curve to generate the updated demand torque, and the updated pedal torque curve can be obtained.

[0077] This invention embodiment can retrieve the acceleration fitting value corresponding to the current vehicle speed from the acceleration curve, then calculate the deviation between the fitted acceleration value and the actual acceleration value, and perform closed-loop adjustment on the deviation value to obtain the compensation torque. The closed-loop adjustment method can be to input the deviation value into a proportional-integral (PI) controller for closed-loop control calculation and output the compensation torque (this is just an example). Then, the compensation torque can be superimposed on the driving demand torque in the fitted pedal torque curve to obtain an updated demand torque and an updated pedal torque curve for subsequent vehicle power control. See the flowchart below. Figure 8 As shown.

[0078] This invention introduces closed-loop acceleration feedback and torque compensation, which can effectively limit the vehicle's output torque to not exceed the safe operating condition threshold, realize the safety limit constraint of driving demand torque, and improve the accuracy and safety of power output.

[0079] In one alternative implementation, in response to a self-learning reset command, the currently stored pedal torque curve data corresponding to each accelerator pedal opening is cleared to zero.

[0080] In this embodiment of the invention, the driver can reset all acceleration values ​​with one click through the vehicle-machine interface or other means to relearn. After the controller responds to the self-learning reset command, it can clear the currently stored pedal torque curve data corresponding to each accelerator pedal opening to start self-learning again.

[0081] This invention supports drivers to reset acceleration learning values ​​with one click, improving the convenience of vehicle adaptive calibration. It can also correct learning deviations caused by environmental changes and other factors in a timely manner through the reset function, avoiding abnormal torque due to long-term accumulated errors and improving driving safety.

[0082] In one optional implementation, during the actual application process after obtaining the pedal torque curve, the following steps can be taken: First, the current driving data during vehicle operation can be acquired, including the current accelerator pedal opening and the current vehicle speed. Then, the pedal torque curve corresponding to the current accelerator pedal opening can be obtained. Based on the current vehicle speed, the corresponding driving torque requirement is determined from the pedal torque curve, and the vehicle is controlled based on this driving torque requirement. Next, the actual acceleration value of the vehicle at the current moment can be acquired. Finally, the current accelerator pedal opening, current vehicle speed, and actual acceleration value are used as new vehicle driving data. Then, based on a preset throttle offset strategy and vehicle speed segmentation strategy, the steps of mapping the accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points are executed to update the pedal torque curve corresponding to the current accelerator pedal opening online.

[0083] In this embodiment of the invention, during actual vehicle operation, current driving data can be acquired, including but not limited to the current accelerator pedal opening and current vehicle speed. Then, based on the current accelerator pedal opening, the corresponding pedal torque curve is retrieved. Using the current vehicle speed as an index, the required driving torque is determined from the pedal torque curve. The vehicle's power output is then controlled based on this required driving torque. Simultaneously, the actual acceleration value of the vehicle at the current moment is collected. The current accelerator pedal opening, current vehicle speed, and actual acceleration value are used as new vehicle driving data. Mapping is performed based on a preset throttle offset strategy and vehicle speed segmentation strategy to obtain the target pedal opening point and target vehicle speed point. The sample parameter set is then updated, and an acceleration function is fitted based on the sample parameter set to obtain an acceleration curve. Finally, the acceleration curve is converted into a pedal torque curve. The process logic can be found in [reference needed]. Figure 9 As shown, detailed descriptions will not be repeated here.

[0084] This invention collects accelerator pedal opening, vehicle speed, and actual acceleration data in real time during actual vehicle operation, and performs closed-loop dynamic correction on the pedal torque curve to make the torque output more consistent with actual operating conditions and improve control accuracy.

[0085] In one optional implementation, before using the current accelerator pedal opening, current vehicle speed, and actual acceleration value as new vehicle driving data, the current accelerator pedal opening, current vehicle speed, and vehicle driving parameters can be compared with preset self-learning enabling conditions. The preset self-learning enabling conditions include at least one of the following: the current accelerator pedal opening is within a preset accelerator pedal opening learning range, the current vehicle speed is within a preset vehicle speed learning range, the rate of change of accelerator pedal opening is less than a preset rate of change threshold, the vehicle has not slipped or the electronic stability program has not intervened, the vehicle is not in intelligent driving assistance mode, and the self-learning function is activated. Only when the current accelerator pedal opening, current vehicle speed, and vehicle driving parameters meet the self-learning enabling conditions can the current accelerator pedal opening, current vehicle speed, and actual acceleration value be used as new vehicle driving data.

[0086] To ensure the representativeness of the selected acceleration feature values ​​in this embodiment of the invention, since the target acceleration value calculated in a special scenario may not match the driver's expectations and is not representative, it is not used as the acceleration value selection point. Therefore, before updating the curve using the current accelerator pedal opening, current vehicle speed, and actual acceleration value, it is necessary to determine whether the self-learning enabling conditions are met. The self-learning enabling conditions include at least one of the following: the accelerator pedal opening is within a preset accelerator pedal opening learning range, and the actual vehicle speed is within a preset vehicle speed learning range (e.g., 0-56kph, 84-...). (120kph) The change in accelerator pedal opening is less than the preset rate of change threshold. Sudden changes in accelerator pedal opening do not necessarily indicate driver habits, vehicle slippage, or electronic stability program intervention. Adaptive cruise control and other intelligent driving assistance modes do not learn. Upper and lower limits for self-learning acceleration values ​​can also be set, and acceleration values ​​exceeding the limits can be discarded. Self-learning function is active. These are just examples. Only when the current accelerator pedal opening, current vehicle speed, and vehicle driving parameters meet the self-learning enable conditions can the current accelerator pedal opening, current vehicle speed, and actual acceleration value be used as new vehicle driving data.

[0087] The pedal torque self-learning method provided by this invention learns the characteristics of the driver's throttle opening changes, which can better help users adjust to their preferred driving style. Furthermore, the stepless torque adjustment feature provides users with a "personalized" and enjoyable driving experience. Eliminating the need for numerous pre-set calibration lookup tables in the software saves software space and significantly reduces the workload of calibration engineers and the cost of OTA updates for enterprises.

[0088] This embodiment also provides a vehicle, such as Figure 10 As shown, the vehicle also includes a controller 1001, which includes a memory and a processor. The memory and the processor are interconnected. The memory stores computer instructions, and the processor executes the aforementioned pedal torque self-learning method by executing the computer instructions.

[0089] This embodiment also provides a pedal torque self-learning device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0090] This embodiment provides a pedal torque self-learning device, such as... Figure 11 As shown, it includes: a data acquisition module 1101, used to acquire vehicle driving data, which includes at least the accelerator pedal opening, vehicle speed, and corresponding actual acceleration value; and a data mapping module 1102, used to map the accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points based on a preset accelerator offset strategy and vehicle speed segmentation strategy. The accelerator offset strategy is used to map all accelerator pedal openings falling within the continuous opening range corresponding to the target pedal opening point to the target pedal opening point, and the vehicle speed segmentation strategy is used to map all accelerator pedal openings falling within the target vehicle speed point to the target pedal opening point. The system maps all vehicle speeds within the corresponding continuous speed range to the target vehicle speed point; the parameter set update module 1103 is used to update the sample parameter set corresponding to the target pedal opening point by using the target vehicle speed point and the corresponding actual acceleration value as sample parameters; the acceleration curve fitting module 1104 is used to fit a preset acceleration function based on the updated sample parameter set to obtain the acceleration curve corresponding to the target pedal opening point; the pedal torque curve generation module 1105 is used to convert the acceleration curve corresponding to the target pedal opening point into the corresponding pedal torque curve.

[0091] In some optional implementations, the pedal torque self-learning device further includes: a data acquisition module for acquiring current driving data during vehicle operation, including the current accelerator pedal opening and the current vehicle speed; a torque curve query module for acquiring the pedal torque curve corresponding to the current accelerator pedal opening; a demand torque determination module for determining the corresponding driving demand torque from the pedal torque curve based on the current vehicle speed, and controlling vehicle operation based on the driving demand torque; an acceleration acquisition module for acquiring the actual acceleration value of the vehicle at the current moment; and a sample parameter update module for using the current accelerator pedal opening, the current vehicle speed, and the actual acceleration value as new vehicle driving data, and executing a step based on a preset accelerator offset strategy and a vehicle speed segmentation strategy to map the accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points, respectively, to update the pedal torque curve corresponding to the current accelerator pedal opening online.

[0092] In some optional implementations, before using the current accelerator pedal opening, current vehicle speed, and actual acceleration value as new vehicle driving data, the pedal torque self-learning device further includes: an enable condition judgment module, used to compare the current accelerator pedal opening, current vehicle speed, and vehicle driving parameters with preset self-learning enable conditions, wherein the preset self-learning enable conditions include at least one of the following: the current accelerator pedal opening is within a preset accelerator pedal opening learning range, the current vehicle speed is within a preset vehicle speed learning range, the accelerator pedal opening change rate is less than a preset change rate threshold, the vehicle has not slipped or the electronic stability program has not intervened, the vehicle is not in intelligent driving assistance mode, and the self-learning function is activated; and a data update module, used to use the current accelerator pedal opening, current vehicle speed, and actual acceleration value as new vehicle driving data when the current accelerator pedal opening, current vehicle speed, and vehicle driving parameters meet the self-learning enable conditions.

[0093] In some optional implementations, the parameter set update module 1103 includes: a data fusion unit, configured to, if the currently stored sample parameter set includes a target vehicle speed point and a corresponding acceleration record value, fuse the actual acceleration value and the acceleration record value to obtain an acceleration fusion value; and update the acceleration record value to the acceleration fusion value; and a data addition unit, configured to, if the currently stored sample parameter set does not include a target vehicle speed point, add the target vehicle speed point and the corresponding actual acceleration value as sample parameters to the sample parameter set.

[0094] In some optional implementations, the acceleration curve fitting module 1104 includes: a vehicle speed point filtering unit, used to filter out the vehicle speed point corresponding to the maximum acceleration from the updated sample parameter set; and a curve fitting unit, used to fit the piecewise function based on the preset starting acceleration value and the updated sample parameter set, using the vehicle speed point corresponding to the maximum acceleration as the segmented common fitting point, to obtain the acceleration curve corresponding to the target pedal opening point.

[0095] In some optional implementations, the pedal torque curve generation module 1105 includes: a data sampling unit for discretizing the acceleration curve to obtain multiple vehicle speed points and corresponding acceleration fitting values; a resistance calculation unit for calculating vehicle resistance values ​​based on the actual vehicle acceleration values ​​and the actual vehicle driving torque values; a demand torque calculation unit for calculating the driver's driving demand torque for any discrete vehicle speed point based on the vehicle resistance value and the corresponding acceleration fitting value; and a torque curve fitting unit for fitting a preset torque function based on all vehicle speed points and the corresponding driving demand torque to generate a pedal torque curve.

[0096] In some optional implementations, the pedal torque self-learning device further includes: a fitting value acquisition module for acquiring the fitting acceleration value corresponding to the current vehicle speed from the acceleration curve; a deviation value calculation module for calculating the deviation value between the fitting acceleration value and the actual acceleration value; a compensation torque determination module for performing closed-loop adjustment on the deviation value to obtain the compensation torque; and a torque curve update module for superimposing the compensation torque with the driving demand torque in the fitted pedal torque curve to generate the updated demand torque and obtain the updated pedal torque curve.

[0097] In some optional embodiments, the pedal torque self-learning device further includes: a curve acquisition module, used to acquire a first pedal torque curve corresponding to a first pedal opening point and a second pedal torque curve corresponding to a second pedal opening point, wherein the first pedal opening point and the second pedal opening point are adjacent; an opening value determination module, used to determine a pedal opening value to be processed, wherein the pedal opening value to be processed is located between the first pedal opening point and the second pedal opening point; a difference coefficient determination module, used to calculate a linear difference coefficient based on the pedal opening value to be processed, the first pedal opening point, and the second pedal opening point; and a difference processing module, used to generate a pedal torque curve corresponding to the pedal opening value to be processed through linear difference operation based on the linear difference coefficient, the first pedal torque curve, and the second pedal torque curve.

[0098] The pedal torque self-learning device provided in this embodiment of the invention can execute the pedal torque self-learning method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0099] Figure 12 This is a schematic diagram of the structure of a controller in a vehicle provided by an embodiment of the present invention.

[0100] The following is a detailed reference. Figure 12 The diagram illustrates a structural schematic suitable for implementing a controller in an embodiment of the present invention. The controller may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 1201, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1202 or a program loaded from memory 1208 into random access memory (RAM) 1203. The RAM 1203 also stores various programs and data required for controller operation. The processor 1201, ROM 1202, and RAM 1203 are interconnected via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0101] Typically, the following devices can be connected to I / O interface 1205: input devices 1206 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 1207 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; memory 1208 including, for example, magnetic tape, hard disk, etc.; and communication devices 1209. Communication device 1209 allows the controller to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 12 A controller with various devices is shown, but it should be understood that it is not required to implement or have all of the devices shown, and may alternatively implement or have more or fewer devices.

[0102] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 1209, or installed from a memory 1208, or installed from a ROM 1202. When the computer program is executed by the processor 1201, it performs the functions defined in the pedal torque self-learning method of the embodiments of the present invention.

[0103] Figure 12 The controller shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0104] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the pedal torque self-learning method shown in the above embodiments is implemented.

[0105] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0106] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined herein.

Claims

1. A pedal torque self-learning method, characterized in that, The method includes: Acquire vehicle driving data, which includes at least the accelerator pedal opening, vehicle speed, and corresponding actual acceleration value; Based on the preset throttle offset strategy and vehicle speed segmentation strategy, the throttle pedal opening and vehicle speed are mapped to the corresponding target pedal opening point and target vehicle speed point, respectively. The throttle offset strategy is used to map all throttle pedal openings that fall within the continuous opening range corresponding to the target pedal opening point to the target pedal opening point. The vehicle speed segmentation strategy is used to map all vehicle speeds that fall within the continuous vehicle speed range corresponding to the target vehicle speed point to the target vehicle speed point. The target vehicle speed point and the corresponding actual acceleration value are used as sample parameters and updated to the sample parameter set corresponding to the target pedal opening point. Based on the updated sample parameter set, the preset acceleration function is fitted to obtain the acceleration curve corresponding to the target pedal opening point; The acceleration curve corresponding to the target pedal opening point is converted into the corresponding pedal torque curve.

2. The method according to claim 1, characterized in that, The method further includes: Acquire current driving data during vehicle operation, including current accelerator pedal opening and current vehicle speed; Obtain the pedal torque curve corresponding to the current accelerator pedal opening; Based on the current vehicle speed, the corresponding driving demand torque is determined from the pedal torque curve, and the vehicle is controlled to drive based on the driving demand torque. Obtain the actual acceleration value of the vehicle at the current moment; Using the current accelerator pedal opening, current vehicle speed, and actual acceleration value as new vehicle driving data, the steps of mapping the accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points based on the preset accelerator offset strategy and vehicle speed segmentation strategy are executed online to update the pedal torque curve corresponding to the current accelerator pedal opening.

3. The method according to claim 2, characterized in that, Before using the current accelerator pedal opening, current vehicle speed, and the actual acceleration value as new vehicle driving data, the method further includes: The current accelerator pedal opening, current vehicle speed, and vehicle driving parameters are compared with preset self-learning enabling conditions, which include at least one of the following: the current accelerator pedal opening is within a preset accelerator pedal opening learning range, the current vehicle speed is within a preset vehicle speed learning range, the accelerator pedal opening change rate is less than a preset change rate threshold, the vehicle has not slipped or the electronic stability program has not intervened, the vehicle is not in intelligent driving assistance mode, and the self-learning function is activated. When the current accelerator pedal opening, current vehicle speed, and vehicle driving parameters meet the self-learning enable conditions, the current accelerator pedal opening, current vehicle speed, and the actual acceleration value are used as new vehicle driving data.

4. The method according to claim 1, characterized in that, The step of updating the sample parameter set corresponding to the target pedal opening point by using the target vehicle speed point and the corresponding actual acceleration value as sample parameters includes: If the currently stored sample parameter set includes the target vehicle speed point and the corresponding acceleration record value, the actual acceleration value and the acceleration record value are fused to obtain the acceleration fusion value; Update the recorded acceleration value to the fused acceleration value; If the target vehicle speed point is not included in the currently stored sample parameter set, the target vehicle speed point and the corresponding actual acceleration value are added to the sample parameter set as sample parameters.

5. The method according to claim 1, characterized in that, The preset acceleration function is a piecewise function. The process of fitting the preset acceleration function based on the updated sample parameter set to obtain the acceleration curve corresponding to the target pedal opening point includes: The vehicle speed points corresponding to the maximum acceleration are selected from the updated sample parameter set; Using the vehicle speed point corresponding to the maximum acceleration as the common fitting point for the segment, and based on the preset starting acceleration value and the updated sample parameter set, the piecewise function is fitted to obtain the acceleration curve corresponding to the target pedal opening point.

6. The method according to claim 1, characterized in that, The step of converting the acceleration curve corresponding to the target pedal opening point into the corresponding pedal torque curve includes: The acceleration curve is discretized and sampled to obtain multiple vehicle speed points and corresponding acceleration fitting values; Calculate the vehicle resistance value based on the vehicle's actual acceleration and actual driving torque values; For any discrete vehicle speed point, the required torque for driving is calculated based on the vehicle resistance value and the corresponding acceleration fitting value. Based on all vehicle speed points and the corresponding driving torque requirements, a preset torque function is fitted to generate a pedal torque curve.

7. The method according to claim 1 or 6, characterized in that, The method further includes: Obtain the fitted acceleration value corresponding to the current vehicle speed from the acceleration curve; Calculate the deviation between the fitted acceleration value and the actual acceleration value; The deviation value is adjusted in a closed loop to obtain the compensation torque; The compensated torque is superimposed on the driving demand torque in the fitted pedal torque curve to generate the updated demand torque, and thus the updated pedal torque curve is obtained.

8. The method according to claim 1 or 6, characterized in that, The method further includes: Obtain the first pedal torque curve corresponding to the first pedal opening point and the second pedal torque curve corresponding to the second pedal opening point, wherein the first pedal opening point and the second pedal opening point are adjacent. Determine the pedal opening value to be processed, wherein the pedal opening value to be processed is located between the first pedal opening point and the second pedal opening point; Based on the pedal opening value to be processed, the first pedal opening point, and the second pedal opening point, calculate the linear difference coefficient; Based on the linear difference coefficient, the first pedal torque curve, and the second pedal torque curve, a pedal torque curve corresponding to the pedal opening value to be processed is generated through linear difference calculation.

9. The method according to claim 1, characterized in that, The method further includes: In response to the self-learning reset command, the pedal torque curve data corresponding to each accelerator pedal opening currently stored is cleared to zero.

10. A pedal torque self-learning device, characterized in that, The device includes: The data acquisition module is used to acquire vehicle driving data, which includes at least the accelerator pedal opening, vehicle speed, and corresponding actual acceleration value. The data mapping module is used to map the accelerator pedal opening and vehicle speed to corresponding target pedal opening points and target vehicle speed points based on a preset throttle offset strategy and vehicle speed segmentation strategy. The throttle offset strategy is used to map all accelerator pedal openings that fall within the continuous opening range corresponding to the target pedal opening point to the target pedal opening point. The vehicle speed segmentation strategy is used to map all vehicle speeds that fall within the continuous vehicle speed range corresponding to the target vehicle speed point to the target vehicle speed point. The parameter set update module is used to update the sample parameter set corresponding to the target pedal opening point by taking the target vehicle speed point and the corresponding actual acceleration value as sample parameters. The acceleration curve fitting module is used to fit a preset acceleration function based on the updated sample parameter set to obtain the acceleration curve corresponding to the target pedal opening point. The pedal torque curve generation module is used to convert the acceleration curve corresponding to the target pedal opening point into the corresponding pedal torque curve.

11. A vehicle, characterized in that, The vehicle includes a controller, which includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the pedal torque self-learning method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the pedal torque self-learning method according to any one of claims 1 to 9.

Images