Vehicle chassis control and adjustment method and device, electronic equipment and medium

Abstract

The invention provides a vehicle chassis control adjustment method and device, electronic equipment and a medium, and relates to the field of vehicle control. Comprising the steps of determining a to-be-adjusted chassis control scheme in response to a vehicle chassis adjustment trigger event; acquiring vehicle state data for the to-be-adjusted chassis control scheme; a control effect strategy determined by the vehicle state data based on historical state data is evaluated, an adjustment value meeting the target control effect is determined, and the adjustment value is used for representing adjustment content of control parameters corresponding to the to-be-adjusted chassis control scheme; and adjusting control parameters of the to-be-adjusted chassis control scheme according to the adjustment value. According to the method, evaluation is carried out through the control effect strategy determined based on the historical state data, the control parameters of the vehicle are adjusted, low efficiency and high cost of manual subjective evaluation are avoided, the adjustment efficiency and cost effectiveness are remarkably improved, and the overall performance of optimizing the control parameters of the vehicle chassis is higher than that of manual calibration.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of vehicle control, and particularly relates to a vehicle chassis control adjustment method and device, an electronic device and a medium. BACKGROUND

[0002] In the field of vehicle chassis parameter control and adjustment, it is necessary to adjust the chassis damping force parameter table in a targeted manner to achieve the purpose of parameter calibration. SUMMARY

[0003] The present disclosure provides a vehicle chassis control adjustment method and device, an electronic device and a medium.

[0004] The first aspect embodiment of the present disclosure provides a vehicle chassis control adjustment method, comprising: in response to a vehicle chassis adjustment trigger event, determining a to-be-adjusted chassis control scheme; obtaining vehicle state data corresponding to the to-be-adjusted chassis control scheme; evaluating the vehicle state data based on historical state data to determine a control effect strategy, and determining an adjustment value that meets a target control effect, the adjustment value being used to represent the adjustment content of the control parameter corresponding to the to-be-adjusted chassis control scheme; and adjusting the control parameter of the to-be-adjusted chassis control scheme according to the adjustment value.

[0005] In some embodiments of the present disclosure, in response to the vehicle chassis adjustment trigger event, the to-be-adjusted chassis control scheme is determined, comprising: based on the vehicle chassis adjustment trigger event, determining the to-be-adjusted chassis control scheme under at least one driving style and / or at least one working condition indicated by the vehicle chassis adjustment trigger event.

[0006] In some embodiments of the present disclosure, the to-be-adjusted chassis control scheme is further determined, comprising: determining the to-be-adjusted chassis damping force parameter corresponding to the to-be-adjusted chassis control scheme under at least one driving style and / or at least one working condition.

[0007] In some embodiments of the present disclosure, the vehicle state data corresponding to the to-be-adjusted chassis control scheme is obtained, comprising: performing vehicle simulation according to the to-be-adjusted chassis damping force parameter corresponding to the to-be-adjusted chassis control scheme, and obtaining the vehicle state data corresponding to the to-be-adjusted chassis damping force parameter.

[0008] In some embodiments of the present disclosure, the vehicle state data is evaluated based on historical state data to determine a control effect strategy, and an adjustment value that meets a target control effect is determined, comprising: performing feature extraction on the vehicle state data to determine a state data feature value; based on the control effect strategy determined based on the historical state data, analyzing the state data feature value to obtain a control effect evaluation corresponding to the vehicle state data; based on the control effect evaluation and the target control effect, determining an adjustment scheme for adjusting the to-be-adjusted chassis damping force parameter to the target control effect; and determining the adjustment value of the to-be-adjusted chassis damping force parameter according to the adjustment scheme.

[0009] In some embodiments of the present disclosure, based on the control effect strategy determined based on the historical state data, the state data feature values are analyzed to obtain a control effect evaluation corresponding to the vehicle state data, including: based on the state data feature values, analyzing through a control effect evaluation model corresponding to the control effect strategy to determine the control effect evaluation, and the control effect evaluation model is used to implement the control effect strategy determined based on the historical state data.

[0010] In some embodiments of the present disclosure, based on the control effect evaluation and the target control effect, an adjustment scheme for adjusting the to-be-adjusted chassis damping force parameter to the target control effect is determined, including: determining the adjustment scheme for adjusting the chassis damping force parameter according to the control effect evaluation and the target control effect; determining the adjustment value of the to-be-adjusted chassis damping force parameter based on the vehicle state data and the adjustment scheme; if the adjustment value does not meet the target control effect, updating the adjustment scheme according to the control effect evaluation corresponding to the adjusted vehicle state data, and re-determining the adjustment value based on the updated adjustment scheme until the target control effect is met, and determining the adjustment scheme.

[0011] In some embodiments of the present disclosure, the control parameter of the to-be-adjusted chassis control scheme is adjusted according to the adjustment value, including: updating the chassis damping force parameter adjusted based on the adjustment value to the to-be-adjusted chassis control scheme.

[0012] In some embodiments of the present disclosure, the control effect strategy determined based on the historical state data includes: obtaining the control effect evaluation model corresponding to the control effect strategy from the cloud server; or obtaining the control effect evaluation model corresponding to the control effect strategy from the vehicle locally.

[0013] In some embodiments of the present disclosure, the control effect strategy determined based on the historical state data includes: performing feature extraction on the actual running state of the vehicle to determine the state data sample of the vehicle; determining the control effect label of the state data sample based on the state data sample; training the control effect evaluation model based on the state data sample and the control effect label.

[0014] In some embodiments of the present disclosure, the actual running state of the vehicle is feature extracted to determine the state data sample of the vehicle, including: determining the time sequence original data of the actual running state of the vehicle based on a preset sampling time length; pre-processing and data format conversion are performed on the time sequence original data to obtain processed data; at least one of time domain feature extraction, frequency domain feature extraction, signal interaction feature extraction, and dynamics feature extraction is performed on the processed data to determine the state data sample of the vehicle, and the state data sample includes the historical state data of the vehicle and the scores of the multiple evaluation indexes corresponding to the historical state data.

[0015] In some embodiments of the present disclosure, based on the state data sample, the control effect label of the state data sample is determined, including: determining the weight coefficient of the plurality of evaluation indexes of the control effect evaluation model; and determining the control effect label based on the score of each evaluation index in the state data sample and the weight coefficient.

[0016] In the above embodiment, by forming a virtual tuning environment based on vehicle simulation and control effect evaluation model, an automatic closed loop from parameter adjustment, performance simulation to intelligent evaluation is realized. By replacing artificial subjective evaluation with the control effect evaluation model, the efficiency and cost-effectiveness of chassis control parameter calibration are significantly improved.

[0017] The second aspect embodiment of the present disclosure provides a vehicle chassis control adjustment device, including: a determination module, an acquisition module, an evaluation module, and an adjustment module. The determination module is configured to determine a to-be-adjusted chassis control scheme in response to a vehicle chassis adjustment trigger event. The acquisition module is configured to acquire vehicle state data corresponding to the to-be-adjusted chassis control scheme. The evaluation module is configured to evaluate a control effect strategy determined based on historical state data on the vehicle state data, and determine an adjustment value that satisfies a target control effect, the adjustment value being used to represent the adjustment content of the control parameter corresponding to the to-be-adjusted chassis control scheme. The adjustment module is configured to adjust the control parameter of the to-be-adjusted chassis control scheme according to the adjustment value.

[0018] In some embodiments of the present disclosure, the determination module is configured to determine the to-be-adjusted chassis control scheme under at least one driving style and / or at least one working condition indicated by the vehicle chassis adjustment trigger event.

[0019] In some embodiments of the present disclosure, the determination module is configured to determine the to-be-adjusted chassis damping force parameter corresponding to the to-be-adjusted chassis control scheme under at least one driving style and / or at least one working condition.

[0020] In some embodiments of the present disclosure, the acquisition module is configured to perform vehicle simulation according to the to-be-adjusted chassis damping force parameter corresponding to the to-be-adjusted chassis control scheme, and acquire vehicle state data corresponding to the to-be-adjusted chassis damping force parameter.

[0021] In some embodiments of the present disclosure, the evaluation module is configured to perform feature extraction on the vehicle state data to determine a state data feature value, analyze the state data feature value based on the control effect strategy determined based on the historical state data, obtain a control effect evaluation corresponding to the vehicle state data, determine an adjustment scheme for adjusting the to-be-adjusted chassis damping force parameter to the target control effect based on the control effect evaluation and the target control effect, and determine an adjustment value of the to-be-adjusted chassis damping force parameter according to the adjustment scheme.

[0022] In some embodiments of the present disclosure, the evaluation module is further configured to: based on the state data feature value, analyze a control effect evaluation model corresponding to the control effect strategy by control effect strategy, to determine a control effect evaluation, and the control effect evaluation model is configured to implement the control effect strategy determined by the historical state data.

[0023] In some embodiments of the present disclosure, the evaluation module is configured to: determine an adjustment scheme for adjusting the chassis damping force parameter according to the control effect evaluation and the target control effect; determine an adjustment value of the chassis damping force parameter to be adjusted based on the vehicle state data and the adjustment scheme; if the adjustment value does not meet the target control effect, update the adjustment scheme according to the control effect evaluation corresponding to the adjusted vehicle state data, and determine the adjustment value again based on the updated adjustment scheme until the target control effect is met, to determine the adjustment scheme.

[0024] In some embodiments of the present disclosure, the adjustment module is configured to: update the chassis damping force parameter adjusted based on the adjustment value to the chassis control scheme to be adjusted.

[0025] In some embodiments of the present disclosure, the device further comprises a training module configured to: perform feature extraction on an actual running state of the vehicle to determine a state data sample of the vehicle; determine a control effect label of the state data sample based on the state data sample; and train a control effect evaluation model based on the state data sample and the control effect label.

[0026] In some embodiments of the present disclosure, the training module is configured to: determine time sequence raw data of the actual running state of the vehicle based on a preset sampling duration; perform preprocessing and data format conversion on the time sequence raw data to obtain processed data; and perform at least one of time domain feature extraction, frequency domain feature extraction, signal interaction feature extraction, and dynamics feature extraction on the processed data to determine the state data sample of the vehicle, the state data sample comprising historical state data of the vehicle and score values of a plurality of evaluation indexes corresponding to the historical state data.

[0027] In some embodiments of the present disclosure, the training module is configured to: determine weight coefficients of a plurality of evaluation indexes of the control effect evaluation model; and determine the control effect label based on the score values of each evaluation index in the state data sample and the weight coefficients.

[0028] In the above embodiments, the vehicle chassis control adjustment device combines vehicle simulation and a control effect evaluation model to evaluate the control parameters of the adjusted vehicle chassis, iteratively adjusts the adjustment scheme, and realizes the adjustment of the vehicle control parameters, thereby avoiding the inefficiency and high cost of manual subjective evaluation, realizing efficient calibration of the control parameters related to the damping force of the vehicle chassis, and further reducing the cost.

[0029] A third aspect of the present disclosure provides an electronic device configured to perform the method described in any one of the first aspect of the present disclosure, or the electronic device comprises the apparatus described in any one of the second aspect of the present disclosure.

[0030] A fourth aspect of the present disclosure provides a computer-readable storage medium storing computer instructions for causing a computer to perform the method described in any one of the first aspect of the present disclosure.

[0031] A fifth aspect of the present disclosure provides a program product comprising computer instructions for causing a computer to perform the method described in any one of the first aspect of the present disclosure.

[0032] A sixth aspect of the present disclosure provides a chip comprising at least one processor and a communication interface; the communication interface is configured to receive a signal input into the chip or output a signal from the chip, the processor is in communication with the communication interface and implements the method described in any one of the first aspect of the present disclosure through a logic circuit or an execution of code instructions.

[0033] In summary, the vehicle chassis control adjustment method provided by the present disclosure realizes an automatic closed loop from parameter adjustment, performance simulation to intelligent evaluation by fusing multi-source sensor data to construct dynamic characteristics and forming a virtual tuning environment based on vehicle simulation and control effect evaluation model. By replacing artificial subjective evaluation with the control effect evaluation model, the development efficiency, tuning efficiency and accuracy are significantly improved, and through the configuration of personalized weights, the chassis performance adaptive matching of "thousand faces" is realized.

[0034] Further, under the premise of ensuring the safety boundary, the vehicle dynamic performance can accurately match the diversified driving preferences and complex working condition requirements.

[0035] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0036] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure, and do not constitute an undue limitation on the present disclosure.

[0037] Figure 1 A flowchart of a vehicle chassis control adjustment method according to an embodiment of the present disclosure is shown in FIG. 1; Figure 2 A flowchart of another vehicle chassis control adjustment method according to an embodiment of the present disclosure is shown in FIG. 2; Figure 3 A flowchart of another vehicle chassis control adjustment method according to an embodiment of the present disclosure is shown in FIG. 3; Figure 4 A flowchart of another vehicle chassis control adjustment method proposed for an embodiment of the present disclosure is shown in FIG. 8. Figure 5 A flowchart of a vehicle chassis CDC damping calibration is shown in FIG. 9. Figure 6 A structural diagram of a vehicle chassis control adjustment device proposed for an embodiment of the present disclosure is shown in FIG. 10. Figure 7 A structural diagram of an electronic device proposed for an embodiment of the present disclosure is shown in FIG. 11. Figure 8 A block diagram of a vehicle according to an exemplary embodiment is shown in FIG. 12. Figure 9 A structural diagram of a chip provided by an embodiment of the present disclosure is shown in FIG. 13. DETAILED DESCRIPTION

[0038] Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings, in which examples of the embodiments are shown, and in which like or similar designations denote like or similar elements or elements having the same or similar functions throughout. The embodiments described below by reference to the drawings are exemplary and are intended to explain the present disclosure, and cannot be understood as limiting the present disclosure.

[0039] Vehicle chassis CDC (Continuous Damping Control) damping calibration involves a large amount of calibration parameters, and the size of the electromagnetic valve control current needs to be determined for different vehicle speeds and different vehicle attitudes, and there is a coupling and constraint relationship between them. In the related art, the CDC damping force parameter table needs to be calibrated in multiple styles (comfort, sport, sport+), and each style needs to be calibrated for 15 typical working conditions (such as using dcbase + skyhook control strategy for straight line working condition), and each working condition has 8-15 tables, and each table has more than 100 parameters; such a large amount of parameter calibration task, the chassis calibration engineer mainly confirms the optimal effect through real vehicle debugging + subjective evaluation, and it takes 5-8 weeks to calibrate all parameters of each style to the optimal level subjectively considered, and the test cost is high.

[0040] Therefore, in order to solve the problem of low efficiency and high cost of manual parameter calibration, the present disclosure proposes a method for rapid chassis CDC intelligent calibration based on an artificial intelligence model, which is different from the work paradigm of manual calibration by calibration engineers, and can realize optimization and efficiency.

[0041] The vehicle chassis control adjustment method provided by the present application will be described in detail below with reference to the accompanying drawings.

[0042] Figure 1A flowchart of a vehicle chassis control adjustment method is proposed for the embodiments of the present disclosure. As shown in Figure 1 the flowchart includes the following steps.

[0043] Step 101, in response to a vehicle chassis adjustment trigger event, determine the chassis control scheme to be adjusted.

[0044] In some embodiments, the vehicle chassis adjustment trigger event can be a switch that starts the vehicle chassis control adjustment method proposed by the present disclosure.

[0045] In some embodiments, the vehicle chassis adjustment trigger event can be at least one of a mode switching instruction or a performance optimization target or a working condition calibration requirement.

[0046] In some embodiments, the mode switching instruction can be that the driver selects a different driving style through a button or knob, for example, sets the current vehicle to be calibrated to any one of the driving modes such as "comfort", "sport", "sport +" and the like.

[0047] In some embodiments, the performance optimization target can be that an engineer or through an algorithm decides to fine-tune or optimize the damping force parameter table of a certain driving style.

[0048] In some embodiments, the working condition calibration requirement can be to fine-tune or optimize the damping force parameter table for a certain specific working condition.

[0049] In some embodiments, the vehicle chassis adjustment trigger event can be at least two of the mode switching instruction, the performance optimization target, and the working condition calibration requirement.

[0050] In some embodiments, in response to the vehicle chassis adjustment trigger event, determining the chassis control scheme to be adjusted includes: based on the vehicle chassis adjustment trigger event, determining the chassis control scheme to be adjusted in at least one driving style and / or at least one working condition indicated by the vehicle chassis adjustment trigger event.

[0051] In some embodiments, determining the chassis control scheme to be adjusted in at least one driving style and / or at least one working condition indicated by the vehicle chassis adjustment trigger event can be to determine the damping force parameter table in at least one working condition corresponding to a certain specific driving style, and take the damping force parameter table as the chassis control scheme to be adjusted.

[0052] In some embodiments, determining the chassis control scheme to be adjusted in at least one driving style and / or at least one working condition indicated by the vehicle chassis adjustment trigger event can be to determine the damping force parameter table in at least one driving style corresponding to a certain specific working condition, and take the damping force parameter table as the chassis control scheme to be adjusted.

[0053] In some embodiments, determining the to-be-adjusted chassis control scheme under the at least one driving style and / or the at least one working condition indicated by the vehicle chassis adjustment trigger event can be determining a plurality of damping force parameter tables corresponding to the at least one working condition respectively under a plurality of driving styles, and taking the damping force parameter tables as the to-be-adjusted chassis control scheme.

[0054] In some embodiments, the to-be-adjusted chassis control scheme is that each damping force parameter in the corresponding damping force parameter table is calibrated or adjusted, so that the vehicle can determine the optimal damping force control parameter by table lookup during actual application, thereby achieving the best control effect of the chassis damping force of the vehicle.

[0055] In some embodiments, the to-be-adjusted chassis control scheme can be adjusting all damping force parameter tables or only part of them. In other words, when all damping force parameter tables need to be adjusted, all damping force parameter tables are obtained, and if only part of them need to be adjusted, only the damping force parameter tables that need to be adjusted are obtained.

[0056] In some embodiments, determining the to-be-adjusted chassis control scheme when the vehicle chassis adjustment trigger event is triggered can be calibrating the damping force parameter table used for a specific working condition under a specific driving style in CDC calibration.

[0057] In some embodiments, in response to the vehicle chassis adjustment trigger event, determining the to-be-adjusted chassis control scheme can be determining the damping force parameter table used for the at least one working condition under the at least one driving style to be calibrated.

[0058] Specifically, the at least one driving style or the at least one working condition can be one or more working conditions corresponding to one driving style, or one or more driving styles corresponding to one working condition, etc. Or it can be a specific working condition corresponding to a specific driving style. In different scenarios or needs, the damping force parameter table of the to-be-adjusted chassis control scheme determined can have one parameter table or multiple parameter tables, which is not limited by the present disclosure.

[0059] For example, when the trigger event is "switching to sports mode", the to-be-adjusted chassis control scheme can be the damping force parameter table corresponding to all working conditions under the "sports" driving style.

[0060] In some embodiments, determining the to-be-adjusted chassis control scheme further comprises: determining the to-be-adjusted chassis damping force parameter corresponding to the to-be-adjusted chassis control scheme under the at least one driving style and / or the at least one working condition.

[0061] In some embodiments, the to-be-adjusted chassis damping force parameter can be a control parameter for controlling the damping force of the vehicle chassis CDC, and can also be understood as a damping force parameter that needs to be calibrated / calibrated.

[0062] In some embodiments, the to-be-adjusted chassis damping force parameters can include a plurality of parameter types, and different to-be-adjusted chassis damping force parameters, i.e., different parameter values corresponding to the plurality of parameter types. There is a to-be-adjusted reference value for each control parameter in the to-be-adjusted chassis damping force parameters.

[0063] For example, the to-be-adjusted chassis damping force parameters can be parameters in the CDC damping force parameter table.

[0064] In some embodiments, for a group of to-be-adjusted chassis damping force parameters, the vehicle chassis CDC can be controlled to reach the corresponding damping force during vehicle operation. It can be understood that the vehicle chassis damping force achieved by this group of parameters can be good or bad, i.e., the vehicle comfort experienced by the driver and passenger under the control of different parameter values of this group of control parameters is different, and the to-be-adjusted chassis damping force parameters need to be adjusted to improve the vehicle driving experience.

[0065] In some embodiments, after the to-be-adjusted chassis control scheme is determined, the to-be-adjusted chassis damping force parameters need to be determined in the obtained at least one damping force parameter table. The to-be-adjusted chassis damping force parameters are the parameters that need to be adjusted by the to-be-adjusted chassis control scheme, and the to-be-adjusted chassis damping force parameters can include one or more control parameters.

[0066] Specifically, for each damping force parameter table, one or more damping force parameters corresponding to the to-be-adjusted chassis control scheme can be determined in the table as the to-be-adjusted chassis damping force parameters. When there are a plurality of damping force parameter tables, the parameters are selected for each table, and one or more control parameters that meet the to-be-adjusted chassis control scheme are selected.

[0067] In some embodiments, the to-be-adjusted chassis damping force parameters can be determined in the damping force parameter table by performing an action selection to select one or more control parameters in the damping force parameter table.

[0068] In some embodiments, the control parameters related to controlling the vehicle chassis damping force in the damping force parameter table can include at least one of the following: solenoid current value; suspension speed; oil temperature; response hysteresis compensation parameter; hysteresis characteristic parameter; nonlinear compensation parameter; working current boundary; and fault mode default value.

[0069] Step 102, obtaining vehicle state data for the to-be-adjusted chassis control scheme.

[0070] In some embodiments, obtaining the vehicle state data for the to-be-adjusted chassis control scheme can be taking the to-be-adjusted chassis damping force parameter of the to-be-adjusted chassis control scheme as a parameter for chassis control of the vehicle, and the vehicle can exhibit different vehicle states under different to-be-adjusted chassis damping force parameters or different values of the same to-be-adjusted chassis damping force parameter.

[0071] In some embodiments, obtaining the vehicle state data for the to-be-adjusted chassis control scheme can be generating a control instruction for the vehicle chassis based on the to-be-adjusted chassis damping force parameter during actual operation of the vehicle, and collecting vehicle state data of the vehicle under the control of the control instruction in real time.

[0072] In some embodiments, obtaining the vehicle state data for the to-be-adjusted chassis control scheme can be taking the to-be-adjusted chassis damping force parameter as a parameter for vehicle simulation to obtain vehicle state data of vehicle simulation under a specific driving style in a specific working condition.

[0073] In some embodiments, the vehicle state data includes at least one of the following: vehicle vertical acceleration; vehicle angular velocity; vehicle speed; shock absorber speed; roll angle; pitch angle; yaw angle.

[0074] In some embodiments, for a set of to-be-adjusted chassis damping force parameters, the vehicle driving experience achieved under different driving styles can also be different, and by using the set of to-be-adjusted chassis damping force parameters for control under different driving styles of the vehicle, corresponding vehicle state data can be obtained, which reflects the vehicle state of the vehicle under the control of a set of to-be-adjusted chassis damping force parameters under a certain driving style.

[0075] In some embodiments, the vehicle state data can be obtained by real-time detection by sensors provided on the vehicle, and the vehicle state data includes detection values at multiple positions, such as vertical acceleration detected by sensors installed on the vehicle seat, roll angle detected by sensors installed on the vehicle body, etc.

[0076] In some embodiments, obtaining the vehicle state data for the to-be-adjusted chassis control scheme includes: performing vehicle simulation according to the to-be-adjusted chassis damping force parameter to determine vehicle state data corresponding to the to-be-adjusted chassis damping force parameter.

[0077] In some embodiments, performing vehicle simulation according to the to-be-adjusted chassis damping force parameter can be inputting the to-be-adjusted chassis damping force parameter into a vehicle simulation model for vehicle simulation, and the vehicle simulation model can imitate the driving style and working condition of the actual vehicle to output vehicle state data corresponding to the to-be-adjusted chassis damping force parameter.

[0078] In some embodiments, the vehicle simulation model can be a 7-DOF vehicle simulation model, or an 8-10-DOF model can also be used, or a complete multi-body dynamics model, etc., and the present disclosure is not limited thereto.

[0079] For example, the parameters selected in the MAP table are "poured" into the virtual vehicle of the 7-DOF vehicle simulation model, and then "driven" on a virtual bumpy road or a curve to obtain data such as the vibration and shaking degree of the vehicle.

[0080] In step 103, the vehicle state data is evaluated based on the control effect strategy determined based on the historical state data to determine an adjustment value that meets the target control effect.

[0081] In some embodiments, the adjustment value is used to represent the adjustment content of the control parameter corresponding to the chassis control scheme to be adjusted.

[0082] In some embodiments, the vehicle state data reflects the driving experience under the control of the to-be-adjusted chassis damping force parameter in the to-be-adjusted chassis control scheme. By evaluating the vehicle state data, it can be determined whether the current to-be-adjusted chassis damping force parameter meets the target control effect.

[0083] Further, when the current to-be-adjusted chassis damping force parameter does not meet the target control effect, the adjustment value can be further determined, and the to-be-adjusted chassis damping force parameter can be adjusted until the vehicle state data after the adjustment meets the target control effect, and then the adjustment value that meets the target control effect can be obtained.

[0084] In some embodiments, the target control effect can be that under the control of the chassis damping force parameter, the CDC system of the vehicle can output appropriate damping force to achieve the target performance of the vehicle, such as the handling, comfort, and stability, to meet the requirements of the driving style or working condition corresponding to the to-be-adjusted chassis control scheme.

[0085] In some embodiments, evaluating the vehicle state data based on the control effect strategy determined based on the historical state data to determine an adjustment value that meets the target control effect includes: extracting features of the vehicle state data to determine state data feature values; analyzing the state data feature values based on the control effect strategy determined based on the historical state data to obtain a control effect evaluation corresponding to the vehicle state data; determining an adjustment scheme for adjusting the to-be-adjusted chassis damping force parameter to the target control effect based on the control effect evaluation and the target control effect; and determining an adjustment value of the to-be-adjusted chassis damping force parameter according to the adjustment scheme.

[0086] In some embodiments, the feature extraction of the vehicle state data can be at least one of time domain feature extraction, frequency domain feature extraction, signal interaction feature extraction, and dynamics feature extraction to extract the state data feature values. In some embodiments, the feature extraction of the vehicle state data can be at least one of time domain feature extraction, frequency domain feature extraction, signal interaction feature extraction, and dynamics feature extraction to extract the state data feature values.

[0087] In some embodiments, the feature extraction on the vehicle state data can be data preprocessing and denoising, data format conversion, and the like on the vehicle state data, to obtain state data feature values.

[0088] In some embodiments, the feature extraction on the vehicle state data can be converting the vehicle state data into a format conforming to the input data of the control effect strategy, so that the state data feature values obtained by the feature extraction can be used as the input data of the control effect strategy.

[0089] In some embodiments, the control effect strategy can analyze the state data feature values to obtain an evaluation result corresponding to the state data feature values, as a control effect evaluation of the vehicle state data, i.e., an evaluation of the control effect under the control of the to-be-adjusted chassis damping force parameter.

[0090] In some embodiments, based on the state data feature values and the control effect strategy, the control effect evaluation corresponding to the state data feature values can be obtained by analyzing and calculating the state data feature values through an AI model or an association relationship reflecting the control effect of the historical state data.

[0091] In some embodiments, based on the control effect strategy determined based on the historical state data, the control effect evaluation corresponding to the vehicle state data can be obtained by analyzing the state data feature values, including: based on the state data feature values, analyzing the control effect evaluation model corresponding to the control effect strategy to determine the control effect evaluation, the control effect evaluation model being used to implement the control effect strategy determined based on the historical state data.

[0092] In some embodiments, the control effect strategy determined based on the historical state data includes: obtaining the control effect evaluation model corresponding to the control effect strategy from a cloud server, or obtaining the control effect evaluation model corresponding to the control effect strategy from a local vehicle.

[0093] In some embodiments, the control effect evaluation model corresponding to the control effect strategy can be obtained by training a model using the control effect corresponding to the historical state data.

[0094] In some embodiments, the training of the control effect evaluation model can be performed by a cloud server, and the trained model can be sent to an execution subject of the vehicle chassis control adjustment method, or the training can be performed locally on the vehicle and provided to the execution subject of the vehicle chassis control adjustment method, which is not limited in the present disclosure.

[0095] In some embodiments, the control effect evaluation model may be an evaluation model trained for each driving style, used to analyze vehicle state data for a specific driving style.

[0096] In some embodiments, the control effect evaluation model may be an evaluation model trained for all driving styles. This evaluation model can determine the corresponding driving style based on vehicle state data, thereby analyzing the vehicle state data.

[0097] In some embodiments, based on the control effect evaluation and the target control effect, an adjustment scheme is determined to adjust the chassis damping force parameter to the target control effect. This can be done by gradually updating the adjustment scheme based on the control effect evaluation and the pre-set target control effect, so that the adjustment scheme can generate an adjustment value that meets the target control effect.

[0098] In some embodiments, a judgment logic for the target control effect is preset. For example, if the obtained control effect evaluation reaches a preset value, the target control effect is satisfied. When the control effect evaluation reaches the preset value, it means that the chassis damping force parameter to be adjusted corresponding to the current vehicle state data meets the target of the chassis control scheme to be adjusted. Then, the corresponding adjustment value is determined to be 0, that is, there is no need to adjust the chassis damping force parameter to be adjusted.

[0099] In some embodiments, if the control effect evaluation does not reach the preset value, it indicates that the chassis damping force parameter to be adjusted corresponding to the current vehicle state data does not meet the target of the chassis control scheme to be adjusted. In this case, the chassis damping force parameter to be adjusted needs to be adjusted. Based on the control effect evaluation and the vehicle state data, an adjustment scheme for adjusting the chassis damping force parameter to be adjusted is determined. This adjustment scheme is used to generate an adjustment value for the chassis damping force parameter to be adjusted. The adjustment value includes at least one of the adjustment object, adjustment direction, and adjustment amount. The adjustment value is used to update the chassis damping force parameter to be adjusted to obtain a new chassis damping force parameter.

[0100] In some embodiments, if the chassis damping force parameters are updated, vehicle simulation is required after updating the chassis damping force parameters to determine the vehicle state data obtained under the parameters. The vehicle state data is then analyzed using a control effect evaluation model to determine an adjustment scheme that meets the target control effect. Through evaluation and multiple rounds of adjustment, the simulation results corresponding to the final determined adjustment scheme meet the target control effect, that is, the target performance such as handling, comfort, and stability are achieved to meet the requirements of the driving style and / or operating conditions corresponding to the chassis control scheme to be adjusted.

[0101] In some embodiments, the chassis damping force parameter to be adjusted can be an adjusted updated control parameter, so that the adjusted updated control parameter is simulated by the vehicle simulation model to obtain vehicle state data of the adjusted updated control parameter, so that the adjustment can be combined with vehicle simulation and adjustment in a loop to ultimately determine the adjustment scheme.

[0102] In some embodiments, the adjustment value of the chassis damping force parameter to be adjusted according to the adjustment scheme can be determined on the basis of the finally determined adjustment scheme, that is, the adjustment value can be generated based on the currently obtained vehicle state data, and the adjustment value is the adjustment value that meets the target control effect.

[0103] In some embodiments, the control effect evaluation can be a score value of the vehicle chassis control effect under the control of the chassis damping force parameter to be adjusted, or can be a probability value of the control effect, for example, the control effect evaluation is a probability value of 0.6 for good control effect, indicating that the control effect of the control parameter corresponding to the vehicle state data is good, but has not reached the target control effect; or the control effect evaluation is a probability value of 0.1 for poor control effect, indicating that the control effect of the control parameter corresponding to the vehicle state data is good, and if the target control effect is set to a probability value greater than or equal to 0.8 or a probability value less than or equal to 0.2, the current chassis damping force parameter to be adjusted reaches the target control effect.

[0104] Step 104, adjusting the control parameter of the chassis control scheme to be adjusted according to the adjustment value.

[0105] In some embodiments, the control parameter of the chassis control scheme to be adjusted can be the parameter in the damping force parameter table in at least one driving style and / or at least one working condition determined in step 101.

[0106] In some embodiments, adjusting the control parameter of the chassis control scheme to be adjusted according to the adjustment value can be adjusting the adjustment value obtained from the adjustment scheme that meets the target control effect in step 103 to the corresponding control parameter in the damping force parameter table to obtain an updated damping force parameter table.

[0107] In some embodiments, adjusting the control parameter of the chassis control scheme to be adjusted according to the adjustment value includes updating the chassis damping force parameter adjusted based on the adjustment value to the chassis control scheme to be adjusted.

[0108] In some embodiments, when the adjustment value that meets the target control effect is determined, it indicates that the chassis damping force parameter to be adjusted of the chassis control scheme to be adjusted can be adjusted based on the chassis damping force parameter determined based on the adjustment value, and then the adjusted chassis damping force parameter is updated to the corresponding damping force parameter table to complete the calibration of the vehicle chassis control parameter.

[0109] In some embodiments, for the to-be-adjusted chassis damping force parameter of the to-be-adjusted chassis control scheme, the parameter can be calibrated or calibrated by multiple vehicle simulations, evaluations, and adjustments to determine an adjustment value that meets the target control effect. The adjusted chassis damping force parameter is the final to-be-adjusted chassis damping force parameter, and the adjusted chassis damping force parameter is updated to the corresponding damping force parameter table.

[0110] In some embodiments, the updated control parameter in the damping force parameter table is used to determine the real-time vehicle control parameter according to the working condition by looking up the table during the real-time operation of the vehicle, so as to control the corresponding components through the controller to achieve the purpose of adjusting the state of the vehicle and improve the driving experience of the driver and the passenger.

[0111] For example, the updated MAP table is applied in the actual vehicle through a real-time closed-loop control system. The target control value is obtained by querying the MAP table based on the current vehicle state every 10-20 ms, and is output to the actuator in combination with the feedback control to achieve the optimization and adjustment of the damping force of the vehicle chassis.

[0112] In the above embodiments, the control parameter of the to-be-adjusted chassis control scheme is selected, the vehicle is simulated, and the simulation result is evaluated in combination with the control effect strategy to continuously adjust the control parameter, calibrate or calibrate the control parameter, and finally obtain the control parameter. The control parameter can control the damping force of the vehicle chassis during the actual operation of the vehicle, improve the driving experience of the driver and the passenger under different working conditions, and meet the comfort requirement.

[0113] Figure 2 Another vehicle chassis control adjustment method is provided for the embodiments of the present disclosure. Based on the embodiment shown in Figure 1 , the step 103 in Figure 2 is further described, as shown in Figure 1 , comprising the following steps. Figure 2

[0114] Step 201, determining an adjustment scheme for adjusting the chassis damping force parameter according to the control effect evaluation and the target control effect.

[0115] In some embodiments, the adjustment scheme can be a pre-set DQN, policy gradient, or other reinforcement learning strategy. In some embodiments, determining the adjustment scheme for adjusting the chassis damping force parameter according to the control effect evaluation and the target control effect can be to update the parameters of the adjustment scheme by taking the control effect evaluation as the reward, so that the updated adjustment scheme can output an adjustment value that is more consistent with the target control effect.

[0116] ​In some embodiments, the control effect evaluation can be used as feedback for the adjustment scheme to modify the parameters within the adjustment scheme, so that based on the vehicle state data, it can be predicted which adjustment value can bring the highest performance benefit, so that the control effect can reach the target control effect.

[0117] For example, the initial policy gradient is the initial weight, and the control effect evaluation is input into the policy gradient as a reward, which is high, indicating that the initial weight of the policy gradient is relatively consistent with the current adjustment direction, and the initial weight is fine-tuned so that the future output adjustment value can get a better control effect evaluation.

[0118] In some embodiments, before the next adjustment of the chassis damping force parameter, the parameters of the adjustment scheme need to be updated based on the control effect evaluation output by the control effect evaluation model, so that it can generate adjustment values more consistent with the target control effect.

[0119] For example, input the adjusted new parameters into the 7-DOF vehicle simulation model + evaluation model to obtain the reward value (performance good or bad quantitative score); use the reward feedback to update the reinforcement learning strategy (such as DQN, policy gradient, etc.); use the updated reinforcement learning strategy to continue to adjust the new parameters.

[0120] In some embodiments, based on the control effect evaluation and the target control effect, the adjustment scheme for adjusting the chassis damping force parameter can be to update the parameters of the adjustment strategy, for example, to use the comprehensive score (i.e., control effect evaluation) output by the control effect evaluation model as a reward value together with the corresponding vehicle state data and the executed action (i.e., adjustment value) to form a complete experience data, which is input into the online learning framework of the adjustment strategy (such as deep Q network or policy gradient algorithm). The learning framework uses this experience data to update its internal neural network weight parameters through time difference error calculation or policy gradient estimation and back propagation.

[0121] In the above embodiments, updating the adjustment scheme for adjusting the chassis damping force parameter aims to optimize the decision logic of the strategy, so that it can generate better adjustment values in subsequent iterations, thereby driving the chassis damping force parameter to continuously approach the direction of improving overall comfort until the target control effect is met.

[0122] Step 202, based on the vehicle state data and the adjustment scheme, determine the adjustment value of the to-be-adjusted chassis damping force parameter.

[0123] In some embodiments, based on the vehicle state data, the adjustment scheme for adjusting the chassis damping force parameter can be used to generate adjustment content for adjusting the control parameters of the to-be-adjusted chassis control scheme, i.e., including adjustment direction and adjustment amount, etc.

[0124] In some embodiments, the adjustment value corresponding to the vehicle state data can be determined by adjusting the adjustment scheme of the chassis damping force parameter, which can be calculated by using a deep Q network to input the vehicle state data (such as vehicle speed, body attitude angle, acceleration, etc.) into the deep neural network to calculate the expected long-term return value (Q value) of each action to be adjusted. The network output layer assigns a Q value to each action to be adjusted (for example, "increase the front suspension compression damping by 5%" or "reduce the filter cutoff frequency by 2 Hz"). According to the greedy strategy, the action with the highest Q value is selected, or other actions are randomly explored with a certain probability, and the selected action is determined as the adjustment value.

[0125] In some embodiments, various strategies can also be used to generate adjustment values, such as direct policy optimization methods based on policy gradient, such as proximal policy optimization (PPO), which directly learns the probability distribution of parameter adjustment and outputs continuous action values; and multi-agent deep deterministic policy gradient (MADDPG) for distributed decision-making. In addition, imitation learning can be combined to initialize the policy from expert calibration data, or meta-reinforcement learning can be used to quickly adapt the system to new driving conditions.

[0126] For example, when the vehicle state data reflects that the roll angle of the vehicle is greater than a preset threshold, the outer shock absorber compression damping can be increased, the inner shock absorber rebound damping can be reduced, the roll bar stiffness coefficient can be increased, and the front and rear axle ratio can be adjusted to determine the adjustment value.

[0127] For example, when the pitch angle of the vehicle is too small (not enough nod) during braking, the front suspension compression damping can be reduced, the front suspension can be allowed to sink, the rear suspension rebound damping can be increased, and the rear suspension can be suppressed; when accelerating, the pitch angle is too small (not enough to lift the head), the rear suspension compression damping can be reduced, the rear suspension can be allowed to compress, and the front suspension rebound damping can be increased to suppress the front suspension; when the steady-state pitch angle deviates from the target, the pitch stiffness distribution can be adjusted to change the pitch center.

[0128] For example, when the vertical acceleration of the vehicle is too large, the adjustment content can be determined according to frequency analysis, such as reducing the damping and adjusting the spring stiffness when low-frequency influence occurs, increasing the damping and actively controlling the headrest to compensate when medium-frequency influence occurs, and high-frequency filtering and increasing the rubber bushing stiffness when high-frequency influence occurs.

[0129] In some embodiments, the adjustment value is used to adjust one or more parameters of the chassis damping force parameter to be adjusted, so that the control effect can be improved after the adjusted parameters control the damping force of the vehicle chassis.

[0130] In some embodiments, after the adjustment value is determined, the adjustment value can be used to adjust the chassis damping force parameter to be adjusted of the chassis control scheme to be adjusted.

[0131] Specifically, if the adjustment value is a relative amount (such as "increase by 10%"), the adjustment is made in proportion to the original chassis damping force parameter; if it is an absolute amount (such as "set to 300 N"), the specified value is directly replaced.

[0132] In some embodiments, after adjusting the chassis damping force parameter to be adjusted, the vehicle state data corresponding to the adjusted chassis damping force parameter can be determined through the vehicle simulation model, the corresponding control effect evaluation can be obtained through the control effect evaluation model, and based on the control effect evaluation, it can be determined whether the current adjustment value meets the target control effect.

[0133] For example, the newly calibrated MAP table and other parameters are input into the vehicle simulation model to obtain data such as the degree of vibration and shaking of the vehicle, and the control effect evaluation model is used to determine whether this calibration has improved or deteriorated.

[0134] In some embodiments, if the control effect evaluation result is good, it indicates that the adjustment value determined this time has adjusted the chassis damping force parameter to be adjusted well, otherwise, it is adjusted poorly.

[0135] In some embodiments, when the control effect evaluation result indicates that the control effect meets the target control effect, the adjustment value is determined as the adjustment value that meets the target control effect.

[0136] In the above embodiments, through vehicle simulation, simulation of real vehicle driving can be realized, vehicle state data corresponding to the adjusted control parameter can be obtained, and evaluation can be performed through the control effect evaluation model to determine whether the current adjustment meets the target, thereby realizing efficient vehicle state evaluation, avoiding the inefficiency and high cost of manual subjective evaluation, and further improving the vehicle chassis control adjustment efficiency and precision.

[0137] Step 203, if the adjustment value does not meet the target control effect, the adjustment scheme is updated according to the control effect evaluation corresponding to the adjusted vehicle state data, and the adjustment value is re-determined based on the updated adjustment scheme until the target control effect is met, and the adjustment scheme is determined.

[0138] In some embodiments, if the adjustment value does not meet the target control effect, the control effect evaluation of the vehicle state data obtained after the adjusted control parameter is adjusted through the vehicle simulation can be less than a preset threshold of the target control effect, indicating that the adjustment value of this round of adjustment process does not meet the target control effect. Conversely, if the adjustment value meets the target control effect, the control effect evaluation of the vehicle state data obtained after the vehicle simulation is greater than or equal to the preset threshold of the target control effect, indicating that the adjustment value of this round of adjustment process meets the target control effect.

[0139] In some embodiments, if the vehicle state data obtained by simulating the vehicle using the adjusted parameter after adjusting the to-be-adjusted chassis damping force parameter using the adjustment value, and evaluating the vehicle state data using the control effect evaluation model, the evaluation result reflects that the target control effect has not been achieved, the adjustment scheme needs to be updated based on the evaluation result, the updated adjustment scheme is used to output the adjustment value again, and the adjustment of the control parameter is continued, and the iteration is repeated until the control effect after the adjustment of the control parameter by the adjustment value meets the target control effect, and the final adjustment scheme is obtained.

[0140] In some embodiments, by updating the related parameters in the adjustment scheme based on the control effect evaluation, the purpose of optimizing the adjustment value output by the adjustment scheme can be achieved, so as to ensure that the obtained adjustment value can make the vehicle control effect meet the target control effect.

[0141] In some embodiments, if the adjustment value meets the target control effect, it indicates that the vehicle state data corresponding to the control parameter adjusted by the adjustment value can make the vehicle control effect meet the target control effect.

[0142] In the above embodiments, the adjustment value under the vehicle state data is generated by using the adjustment scheme, so as to realize the calibration of the control parameter of the vehicle chassis, and the output result of the control effect evaluation model is combined to optimize the adjustment scheme, so that the adjustment value can adjust the control parameter to the direction of the target control effect, so as to achieve the adjustment or calibration of the vehicle control parameter, avoid the low efficiency and high cost of manual adjustment, achieve efficient parameter calibration, and further realize the accuracy of the calibrated parameters.

[0143] Figure 3 Another vehicle chassis control adjustment method is provided for the embodiments of the present disclosure. Based on the method flowchart of the vehicle chassis control adjustment method shown in the embodiments of the present disclosure, Figures 1-2 as shown in the embodiments of the present disclosure, Figure 3 the step 103 in the method of Figure 1 is further described, as shown in Figure 3 , comprising the following steps.

[0144] Step 301, feature extraction is performed on the actual running state of the vehicle to determine the state data sample of the vehicle.

[0145] In some embodiments, the actual running state of the vehicle can be vehicle historical data, and the vehicle historical data can be state data and scored scores collected by actual running of the vehicle under a specific driving style in different working conditions.

[0146] In some embodiments, the actual running state of the vehicle can be the actual running state under different working conditions in a certain driving style, for example, the vehicle in different driving styles is driven on site at different speeds and on different road surfaces, and the vehicle historical data within a preset time period is collected.

[0147] In some embodiments, the state data samples of the vehicle can be a set of state data samples corresponding to different driving styles, so that the control effect evaluation model of different driving styles can be trained respectively based on the state data samples of different driving styles.

[0148] In some embodiments, the feature extraction is performed on the actual running state of the vehicle to determine the state data samples of the vehicle, including: determining the time sequence original data of the actual running state of the vehicle based on a preset sampling time length; pre-processing and data format conversion are performed on the time sequence original data to obtain processed data; at least one of time sequence feature extraction, frequency domain feature extraction, signal interaction feature extraction, and dynamics feature extraction is performed on the processed data to determine the state data samples of the vehicle, the state data samples including historical state data of the vehicle and scores of a plurality of evaluation indexes corresponding to the historical state data.

[0149] In some embodiments, the preset sampling time length can be a pre-set time window, based on which the time sequence original data in the actual running process of the vehicle is collected.

[0150] For example, the preset sampling time length can be 1 second, and the value of the preset sampling time length is not limited by the present disclosure.

[0151] In some embodiments, the time sequence original data can be a plurality of pre-set evaluation indexes, and the scores of the evaluation indexes corresponding to the historical state data of different vehicle control parameters are obtained by real-time state data collection of the vehicle in the running process of different vehicle control parameters and artificial scoring.

[0152] In some embodiments, different evaluation indexes can be set for different driving styles, so that the test engineers can score based on different evaluation indexes to obtain corresponding scores for the historical state data corresponding to the vehicles of different driving styles.

[0153] For example, the model input data X collected is scored by subjective evaluation, and N scores are obtained for each road.

[0154] In some embodiments, the pre-processing and data format conversion of the time sequence original data to obtain the processed data can be missing value processing, abnormal value processing, smoothing processing and filtering processing on the time sequence original data, and the data format is converted into vector form data. The specific way of pre-processing and data format conversion can adopt the pre-processing and data format conversion way in related technologies, or can adopt the future data pre-processing and format conversion way, and the present disclosure is not limited thereto.

[0155] In some embodiments, at least one of time-series feature extraction, frequency domain feature extraction, signal interaction feature extraction, and dynamics feature extraction is performed on the processed data to determine the state data sample of the vehicle.

[0156] Specifically, the time-series feature extraction can be feature extraction at fixed intervals in a time-series order.

[0157] Specifically, the signal interaction feature extraction can be extraction of inter-sensor correlation, such as triaxial acceleration correlation, attitude angle correlation, acceleration and attitude angle correlation, speed and acceleration correlation, and speed difference feature.

[0158] Specifically, the frequency domain feature extraction can be frequency band division of vehicle vibration frequency band to obtain low-frequency, medium-frequency, and high-frequency features and extract peak frequency features through calculation of spectral features.

[0159] Specifically, the dynamics feature extraction can be synthesis of acceleration, acceleration change rate, attitude angle change rate, and other vehicle dynamics-related features.

[0160] In some embodiments, the historical state data includes at least one of the following: vehicle vertical acceleration; vehicle angular velocity; vehicle speed; shock absorber speed; roll angle; pitch angle; and yaw angle.

[0161] In some embodiments, the historical state data can further include seat rail vertical acceleration, steering wheel vibration acceleration, seat pressure distribution, and in-vehicle noise.

[0162] For example, for each style (comfort, sport, sport+), a plurality of sets of calibration parameters with better and worse tuning are used to run different roads at different speeds to collect evaluation model input data. According to a set of signal time-series original data with a length of 1 second, including three vertical accelerations, vehicle speed, CDC speed, roll angle, pitch angle, yaw angle, and the like, feature engineering is completed, and input features X of the evaluation model are calculated.

[0163] At step 302, a control effect label of the state data sample is determined based on the state data sample.

[0164] In some embodiments, the control effect label of the state data sample is determined based on the state data sample, which can be a comprehensive calculation of scores of a plurality of evaluation indexes corresponding to the historical state data in each set of state data samples to determine the control effect label of the set of state data samples.

[0165] For example, based on N scores, a final score is calculated as the label corresponding to X, and N is the number of evaluation indexes.

[0166] At step 303, the control effect evaluation model is trained based on the state data sample and the control effect label.

[0167] In some embodiments, for different driving styles, the corresponding state data sample and control effect label are taken as a training data pair, and the control effect evaluation model for the driving style is trained, thereby obtaining the control effect evaluation model under different driving styles.

[0168] In some embodiments, for the first driving style, the state data sample and the control effect label of the first driving style are taken as a training data pair, and the first evaluation model for the first driving style is trained.

[0169] In some embodiments, the first evaluation model corresponding to the first driving style is used for evaluating the vehicle state data of the vehicle of the first driving style.

[0170] For example, according to the sample X and the label, an evaluation model is trained for each style, and the performance evaluation of the evaluation model is completed.

[0171] In some embodiments, training the control effect evaluation model based on the state data sample and the control effect label can be learning the mapping relationship between the state data sample and the control effect label using a neural network model, adjusting the parameters of each network layer in the neural network model through a set loss function and an optimizer based on forward propagation and backward propagation, and obtaining the control effect evaluation model when the number of iterations or the loss function is minimized.

[0172] In some embodiments, the neural network model can be a convolutional neural network-recurrent neural network CNN-RNN series model, a Transformer model, a CNN-Transformer model, a graph neural network GNN model, a multilayer perceptron MLP, etc., which are not limited by the present disclosure.

[0173] Further, any future neural network model can also be used for training the control effect evaluation model.

[0174] In some embodiments, the optimizer is any one of Adam, AdaGrad, RMSProp, etc., which are not limited by the present disclosure.

[0175] In the above embodiments, by training a dedicated control effect evaluation model for different driving styles and applying it to the parameter adjustment or parameter calibration process of the corresponding driving style vehicle, the effect of individualized adaptive optimization can be achieved.

[0176] Further, the method proposed by the present disclosure makes parameter adjustment no longer dependent on a unified comfort standard, but can dynamically fit the driving stability preference of aggressive drivers or the smoothness preference of moderate drivers, thereby significantly improving the subjective ride satisfaction and driving experience of different users while ensuring the basic safety and performance of the chassis system. Not only does it solve the inherent problem of a single calibration strategy being difficult to accommodate multiple preferences, but it also guides the convergence of vehicle control parameters to more personalized optimal solutions through precise evaluation of different models, ultimately achieving intelligent chassis performance that caters to different users.

[0177] Figure 4 Another vehicle chassis control adjustment method for the embodiments of the present disclosure is shown in the method flowchart. Based on the embodiment shown in Figures 1-3 Figure 4 Further explanation is given to step 302 in Figure 3 Figure 4 As shown in the embodiment shown in

[0178] Step 401, determine the weight coefficients of the multiple evaluation indexes of the control effect evaluation model.

[0179] In some embodiments, the control effect evaluation model is obtained by training for different driving styles, and the weight coefficients of different evaluation indexes can be personalized for different driving styles.

[0180] In some embodiments, the principle of setting the weight coefficients under different driving styles can be to differentially allocate the decision-making influence of each performance index according to the core demands of the style.

[0181] For example, the comfort style will significantly bias the weight to the vibration and stability indexes directly perceived by the human body (such as vertical acceleration and seat vibration), at the expense of part of the control response, to pursue extreme flexibility; the sports style will allocate the weight to the body dynamic response and attitude control indexes (such as yaw response, roll angle, and tire ground contact) on the acceptable comfort bottom line, to improve the driving participation and cornering performance; the aggressive style will further extremely focus the weight on the extreme control response and road information feedback indexes (such as steering wheel linearity, yaw convergence speed, and tire cornering property), and even allow some comfort indexes to have negative weight to clearly prioritize the pursuit of the sharpness of vehicle performance boundaries and driving feedback in order to obtain more direct road communication.

[0182] For example, each style (comfort, sports, sports+ / aggressive) is designed with a set of weight coefficients (N indexes, each index corresponding to a weight coefficient); each set of weight coefficients needs to have a certain tendency and good consistency with the style.

[0183] ​​At step 402, a control effect label is determined based on the score of each evaluation index in the state data sample and the weight coefficient.

[0184] In some embodiments, the control effect label corresponding to the historical state data can be determined by synthesizing calculation based on the score and the weight coefficient corresponding to each evaluation index. The score corresponding to the evaluation index can be multiplied by the weight coefficient corresponding to the evaluation index to obtain a product value, and the product values corresponding to all evaluation indexes can be added to obtain the control effect label.

[0185] For example, for each driving style, the corresponding weight coefficient w is used to calculate the comprehensive score S = w1*s1 +... + wN*sN, respectively. For example, the same set of calibration parameters is used to calculate the scores corresponding to the three driving styles, where S is the comprehensive score, N is the number of evaluation indexes, w1 is the weight coefficient corresponding to the evaluation index 1, s1 is the score corresponding to the evaluation index 1, wN is the weight coefficient corresponding to the evaluation index N, and sN is the score corresponding to the evaluation index N.

[0186] For example, for the same set of calibration parameters, the corresponding state data and scores under the three driving styles can be obtained, and the weight coefficients corresponding to the three driving styles can be obtained, and then the scores corresponding to the three driving styles can be calculated, respectively.

[0187] In some embodiments, interval division can be further performed based on the result obtained by addition to obtain a control effect label indicating an evaluation result.

[0188] For example, according to the final calculated comprehensive score, S>80 is considered good, and S<60 is considered bad. The control effect label corresponding to good is Y = 1, and the control effect label corresponding to bad is Y = 0.

[0189] In the above embodiments, by configuring different weight coefficients with clear inclination for different driving styles, and calculating the control effect label based on the weighted sum mechanism, the precise quantitative evaluation of the same set of chassis control parameters under different style dimensions is realized. The subjective driving style preference is objectified and indexed, and the abstract concepts such as "comfort" and "sport" are converted into calculable and comparable numerical scores, so that it can be intelligently identified which style orientation the current parameter setting is more suitable for.

[0190] Further, a clear direction guide is provided for parameter adjustment (for example, it is clear whether the handling score or the comfort score should be improved), and the vehicle can automatically switch to the most matched evaluation system for parameter adjustment based on the style selected by the driver or recognized by the system, and ultimately achieve the personalized adaptive chassis performance of "one set of hardware, multiple personalities". In engineering, the problem of difficult manual setting of weights in multi-objective optimization is solved, and the scientificity and efficiency of the adjustment or calibration process are improved.

[0191] In summary, the vehicle chassis control adjustment method proposed in the present disclosure realizes the automation of the closed loop from parameter adjustment, performance simulation to intelligent evaluation by fusing multi-source sensor data to construct dynamic characteristics and forming a virtual tuning environment based on vehicle simulation and control effect evaluation model. By replacing artificial subjective evaluation with model, the development efficiency and cost-effectiveness are significantly improved, and the personalized weight configuration realizes the adaptive matching of the chassis performance for "thousands of people with thousands of faces".

[0192] Further, under the premise of ensuring the safety boundary, the vehicle dynamic performance can accurately match the diversified driving preferences and complex working condition requirements.

[0193] The following is a specific embodiment of a vehicle chassis CDC damping tuning proposed in the present disclosure.

[0194] Figure 5 A flowchart of a vehicle chassis CDC damping tuning. It includes an objective evaluation model stage and an intelligent calibration stage.

[0195] 1. Objective evaluation model stage.

[0196] Each style (comfort, sport, sport+) corresponds to an evaluation model.

[0197] Dynamic data collection: for each style (comfort, sport, sport+), use multiple sets of calibration parameters with good and poor tuning, use different speeds, run different roads, collect evaluation model input data, and complete subjective evaluation scoring, and get N scores for each road (each road evaluation needs to meet consistency, otherwise it needs to be evaluated in segments); dynamic data is raw data collection, scored through subjective evaluation details.

[0198] Subjective evaluation scoring: develop N (such as N=10) subjective evaluation indicators (control accuracy, response speed, damping softness, body roll and shaking, etc. comfort, etc.), each indicator corresponds to 1-5 points.

[0199] Comprehensive score calculation: design a set of weight coefficients (N indicators, each indicator corresponds to a weight coefficient) for each driving style (comfort, sport, sport+); each set of weight coefficients needs to have a certain tendency and has good consistency with the driving style; for each driving style, use the corresponding weight coefficient to calculate the comprehensive score S = w1*s1 +...+ wN*sN; for example, the same set of calibration parameters can calculate the scores corresponding to the three styles; where S is the comprehensive score, w1 is the weight coefficient corresponding to the evaluation indicator 1, s1 is the score corresponding to the evaluation indicator 1, wN is the weight coefficient corresponding to the evaluation indicator N, and sN is the score corresponding to the evaluation indicator N.

[0200] Sample Label: Calculate sample Lable, according to the final score, S>80 is good, S<60 is bad; Good: Y = 1, Bad: Y = 0.

[0201] Feature Engineering: Calculate sample X, according to a set of 1-second length signal time series raw data, including 3 vertical accelerations, vehicle speed, CDC speed, roll angle, pitch angle, yaw angle, etc., complete feature engineering, and calculate the input feature X vehicle state data of the evaluation model.

[0202] Model Training: According to sample X and Label, train an evaluation model for each style, and complete the performance evaluation of the evaluation model.

[0203] Evaluation Model: According to any set of raw data, calculate the feature X_new, the model prediction result Y, and get the evaluation result: good / bad. The evaluation model can output objective evaluation.

[0204] 2. Intelligent calibration stage.

[0205] Intelligent calibration based on reinforcement learning includes: taking the vehicle body posture data as the input of reinforcement learning, according to the vehicle body posture data, initializing parameters, selecting actions, and through vehicle simulation, combining the evaluation model to calculate the reward, which is used for policy update to update the result of action selection. Until the result of the evaluation model meets the expectation, the calibrated damping force parameter table is obtained.

[0206] Objective function: maximize expected cumulative reward.

[0207] The optimization method can be RL reinforcement learning.

[0208] Precondition: dependent on an accurate objective evaluation model.

[0209] The iteration process includes the following steps: (1) Initialize the lookup table parameters (solenoid damping force value table) and set the initial vehicle state (vehicle speed, vehicle body posture angular velocity, etc.); (2) The agent selects an action (adjusts one or more parameters) according to the current state; (3) According to the new parameters, use the 7-DOF vehicle simulation model + evaluation model to get the reward value (performance good or bad quantitative score); (4) Update the reinforcement learning strategy (such as DQN, policy gradient, etc.) using the reward feedback; (5) Repeat steps (2)-(4) multiple times to gradually optimize the parameter adjustment strategy; (6) Training is completed, and the best damping force parameter table is exported.

[0210] In summary, the above-mentioned vehicle chassis CDC tuning scheme improves the chassis calibration efficiency, and the overall performance of the optimized parameters is better than the manual calibration result. Further, a significant effect of reducing cost is achieved.

[0211] Figure 6 A structural schematic diagram of a vehicle chassis control adjustment device 600 according to an embodiment of the present disclosure is shown in FIG. 6. As shown in the figure, the vehicle chassis control adjustment device includes a determination module 610, an acquisition module 620, an evaluation module 630, and an adjustment module 640. Figure 6

[0212] The vehicle chassis control adjustment device proposed by the present disclosure has wide platform adaptability and can be deployed in on-board domain controllers or embedded ECUs of pure electric, hybrid, and fuel passenger cars, commercial vehicles, and special vehicles, and supports running on edge computing units, cloud service platforms, and mobile terminals. It is compatible with vehicle-grade operating systems such as Linux and QNX and mainstream simulation development environments, can realize vehicle-cloud collaborative parameter tuning through CAN, Ethernet, and 4G / 5G networks, and is suitable for full-scene applications from single-vehicle real-time optimization to cloud-based vehicle fleet intelligent management.

[0213] In some embodiments, the vehicle types to which the vehicle chassis control adjustment device can be applied include power types such as pure electric, hybrid, fuel cell, and fuel vehicles, and vehicle forms such as passenger cars, commercial vehicles, special operation vehicles, and unmanned vehicles.

[0214] In some embodiments, the processing platforms to which the vehicle chassis control adjustment device can be applied are, for example, on-board computing platforms or edge computing units.

[0215] In some embodiments, the server and cloud systems to which the vehicle chassis control adjustment device can be applied are, for example, cloud service platforms or data analysis platforms.

[0216] In some embodiments, the electronic devices and hardware to which the vehicle chassis control adjustment device can be applied are, for example, mobile terminals and Internet of Things devices.

[0217] In some embodiments, the computer systems to which the vehicle chassis control adjustment device can be applied can be any operating system, development environment, simulation system, etc.

[0218] The determination module is configured to determine a chassis control scheme to be adjusted in response to a vehicle chassis adjustment trigger event; The acquisition module is configured to acquire vehicle state data for the chassis control scheme to be adjusted; The evaluation module is configured to evaluate a control effect strategy determined based on historical state data for the vehicle state data, and determine an adjustment value that satisfies a target control effect, the adjustment value being used to represent adjustment content of a control parameter corresponding to the chassis control scheme to be adjusted.​ The adjusting module is configured to adjust the control parameter of the to-be-adjusted chassis control scheme according to the adjustment value.

[0219] In some embodiments, the determining module is configured to determine, based on the vehicle chassis adjustment trigger event, the to-be-adjusted chassis control scheme in at least one driving style and / or at least one working condition indicated by the vehicle chassis adjustment trigger event.

[0220] In some embodiments, the determining module is configured to determine the to-be-adjusted chassis damping force parameter corresponding to the to-be-adjusted chassis control scheme in at least one driving style and / or at least one working condition.

[0221] In some embodiments, the obtaining module is configured to obtain vehicle state data corresponding to the to-be-adjusted chassis damping force parameter by performing vehicle simulation according to the to-be-adjusted chassis damping force parameter corresponding to the to-be-adjusted chassis control scheme.

[0222] In some embodiments, the evaluation module is configured to perform feature extraction on the vehicle state data to determine state data feature values, analyze the state data feature values based on the control effect strategy to obtain a control effect evaluation corresponding to the vehicle state data, determine an adjustment scheme for adjusting the to-be-adjusted chassis damping force parameter to the target control effect based on the control effect evaluation and the target control effect, and determine an adjustment value of the to-be-adjusted chassis damping force parameter according to the adjustment scheme.

[0223] In some embodiments, the evaluation module is further configured to determine the control effect evaluation based on the state data feature values by analyzing a control effect evaluation model corresponding to the control effect strategy, the control effect evaluation model being used to implement the control effect strategy determined based on historical state data.

[0224] In some embodiments, the evaluation module is configured to determine an adjustment scheme for adjusting the to-be-adjusted chassis damping force parameter based on the control effect evaluation and the target control effect, determine an adjustment value of the to-be-adjusted chassis damping force parameter based on the vehicle state data and the adjustment scheme, and if the adjustment value does not meet the target control effect, update the adjustment scheme according to a control effect evaluation corresponding to the adjusted vehicle state data, and determine the adjustment value again based on the updated adjustment scheme until the target control effect is met and the adjustment scheme is determined.

[0225] In some embodiments, the adjusting module is configured to update the chassis damping force parameter adjusted based on the adjustment value to the to-be-adjusted chassis control scheme.

[0226] In some embodiments, the device further comprises a training module configured to perform feature extraction on an actual running state of the vehicle to determine a state data sample of the vehicle, determine a control effect label of the state data sample based on the state data sample, and train a control effect evaluation model based on the state data sample and the control effect label.

[0227] In some embodiments, the training module is configured to: determine time sequence original data of the actual running state of the vehicle based on a preset sampling duration; pre-process and convert the data format of the time sequence original data to obtain processed data; and perform at least one of time domain feature extraction, frequency domain feature extraction, signal interaction feature extraction, and dynamics feature extraction on the processed data to determine a state data sample of the vehicle, the state data sample including historical state data of the vehicle and scores of a plurality of evaluation indexes corresponding to the historical state data.

[0228] In some embodiments, the training module is configured to: determine weight coefficients of a plurality of evaluation indexes of the control effect evaluation model; and determine the control effect label based on the scores of each evaluation index in the state data sample and the weight coefficients.

[0229] To sum up, the vehicle chassis control adjustment device provided by the present disclosure combines vehicle simulation and a control effect evaluation model to evaluate the control parameters adjusted based on the adjustment strategy, iteratively adjusts the parameters of the adjustment strategy, and realizes the adjustment of the vehicle control parameters, thereby avoiding the inefficiency and high cost of subjective evaluation by humans and realizing efficient calibration of the control parameters related to the damping force of the vehicle chassis, further reducing the cost.

[0230] Figure 7 FIG. 7 is a structural schematic diagram of an electronic device 700 for implementing the vehicle chassis control adjustment method according to an example embodiment.

[0231] Referring to Figure 7 , the electronic device 700 can include one or more of the following components: a processing component 702, a memory 704, a power supply component 706, a multimedia component 708, an audio component 710, an input / output (I / O) interface 712, a sensor component 714, and a communication component 716.

[0232] The processing component 702 usually controls overall operations of the electronic device 700, such as operations associated with displaying, making phone calls, data communications, camera operations, and recording operations. The processing component 702 can include one or more processors 720 to execute instructions to complete all or part of the steps of the methods described above. In addition, the processing component 702 can include one or more modules to facilitate the interaction between the processing component 702 and other components. For example, the processing component 702 can include a multimedia module to facilitate the interaction between the multimedia component 708 and the processing component 702.

[0233] The memory 704 is configured to store various types of data to support operations of the electronic device 700. Examples of these data include instructions for any application programs or methods operating on the electronic device 700, contact data, phonebook data, messages, pictures, videos, etc. The memory 704 can be implemented by any type of volatile or nonvolatile memory, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disc, or optical disc.

[0234] The power supply component 706 supplies power for various components of the electronic device 700. The power supply component 706 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 700.

[0235] The multimedia component 708 includes a screen providing an output interface between the electronic device 700 and a user. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes the touch panel, the screen can be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense a touch, a slide, and a gesture on the touch panel. The touch sensor can not only sense a boundary of a touching or a sliding action, but also detect duration and pressure related to the touching or sliding action. In some embodiments, the multimedia component 708 includes a front camera and / or a back camera. The front camera and / or the back camera can receive external multimedia data when the electronic device 700 is in an operating mode, such as a photographing mode or a video mode. Each of the front camera and the back camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0236] The audio component 710 is configured to output and / or input an audio signal. For example, the audio component 710 includes a microphone (MIC) configured to receive an external audio signal when the electronic device 700 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 704 or transmitted via the communication component 716. In some embodiments, the audio component 710 also includes a speaker for outputting an audio signal.

[0237] The I / O interface 712 provides an interface between the processing component 702 and peripheral interface modules, which can be a keypad, a click wheel, buttons, etc. The buttons can include, but are not limited to, a home button, a volume button, a start button, and a lock button.

[0238] The sensor component 714 includes one or more sensors for providing status assessments for various aspects of the electronic device 700. For example, the sensor component 714 can detect an open / closed position of the electronic device 700, relative positioning of components, such as a display and a keypad of the electronic device 700, a change in position of the electronic device 700 or a component of the electronic device 700, presence or absence of user contact with the electronic device 700, orientation or acceleration / deceleration / g-force and temperature of the electronic device 700. The sensor component 714 can include an optical sensor for detecting ambient light, a proximity sensor configured to detect proximity of an object, a motion sensor configured to detect movement of the electronic device 700, a position sensor configured to detect position of the electronic device 700, a temperature sensor configured to detect temperature of the electronic device 700, an acceleration sensor configured to detect acceleration of the electronic device 700, a gyroscope sensor configured to detect orientation of the electronic device 700, an air quality sensor configured to detect air quality, a pressure sensor configured to detect pressure, and / or a humidity sensor configured to detect humidity.

[0239] The communication component 716 is configured to facilitate wired or wireless communication between the electronic device 700 and other devices. The electronic device 700 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G LTE, 5G NR (New Radio), or a combination thereof. In an example embodiment, the communication component 716 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an example embodiment, the communication component 716 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technology.

[0240] In an example embodiment, the electronic device 700 can be implemented using one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic elements, for performing the above-described methods.

[0241] In an example embodiment, a non-transitory computer-readable storage medium including instructions, such as the memory 704 including instructions, is also provided, which can be executed by the processor 720 of the electronic device 700 to complete the above-described methods. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disc, and an optical data storage device, etc.

[0242] In some embodiments, the electronic device is configured to perform the vehicle chassis control adjustment method described above, or the electronic device comprises the vehicle chassis control adjustment apparatus described above.

[0243] In some embodiments, the electronic device can be a vehicle, a cloud server, or also a terminal device or a cloud device used solely for performing the vehicle chassis control adjustment method, etc., which is not limited by the present disclosure.

[0244] Figure 8 is a block diagram of a vehicle 800 according to an exemplary embodiment. For example, the vehicle 800 can be a hybrid vehicle, or a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle 800 can be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0245] Referring to Figure 8 , the vehicle 800 can include various subsystems, such as an infotainment system 810, a perception system 820, a decision control system 830, a drive system 840, and a computing platform 850. The vehicle 800 can include more or fewer subsystems, and each subsystem can include multiple components. In addition, each subsystem of the vehicle 800 and each component can be interconnected by wired or wireless means.

[0246] In some embodiments, the infotainment system 810 can include a communication system, an entertainment system, a navigation system, etc.

[0247] The perception system 820 can include several sensors for sensing information about the environment surrounding the vehicle 800. For example, the perception system 820 can include a global positioning system (which can be a GPS system, a Beidou system, or other positioning systems), an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera.

[0248] The decision control system 830 can include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0249] The drive system 840 can include components that provide power motion for the vehicle 800. In one embodiment, the drive system 840 can include an engine, an energy source, a transmission system, and wheels. The engine can be one or a combination of an internal combustion engine, an electric motor, an air compression engine. The engine can convert the energy provided by the energy source into mechanical energy.

[0250] Some or all of the functionality of the vehicle 800 is controlled by the computing platform 850. The computing platform 850 can include at least one processor 851 and a memory 852, the processor 851 can execute instructions 853 stored in the memory 852.

[0251] The processor 851 can be any conventional processor, such as commercially available CPUs. The processor can also include a graphics processing unit (GPU), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), or a combination thereof.

[0252] The memory 852 can be implemented by any type of volatile or nonvolatile storage devices or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic storage, flash memory, magnetic or optical disk.

[0253] In addition to the instructions 853, the memory 852 can also store data, such as road maps, route information, the position, direction, speed, and the like of the vehicle. The data stored in the memory 852 can be used by the computing platform 850.

[0254] In the embodiments of the present disclosure, the processor 851 can execute the instructions 853 to complete all or part of the steps of the vehicle chassis control adjustment method described above.

[0255] The embodiments of the present disclosure also propose a computer readable storage medium having computer instructions stored therein, wherein the computer instructions are used to make the computer execute the vehicle chassis control adjustment method described in the above embodiments of the present disclosure.

[0256] The embodiments of the present disclosure also propose a computer program product, including a computer program, the computer program being executed by the processor to execute the vehicle chassis control adjustment method described in the above embodiments of the present disclosure.

[0257] Figure 9 FIG. 9 is a structural schematic diagram of a chip 900 for implementing the vehicle chassis control adjustment method described above according to an exemplary embodiment. Referring to FIG. 9, the chip 900 can include a processor 901 and a memory 902, the processor 901 can execute instructions 903 stored in the memory 902. Figure 9The chip 900 comprises at least one communication interface 901 and a processor 902, the communication interface 901 is used for receiving a signal input into the chip 900 or outputting a signal from the chip 900, and the processor 902 is in communication with the communication interface 901 and realizes the vehicle chassis control adjustment method described in the above embodiments of the present disclosure through a logic circuit or executing code instructions.

[0258] It should be noted that the terms "first", "second", and the like in the description of the present disclosure and claims and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0259] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "exemplary embodiment", "example", "specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiments or examples are included in at least one embodiment or example of the present disclosure. In the present specification, the exemplary description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0260] Any process or method descriptions in flow charts or otherwise described herein can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for performing specific logic functions or steps in the process, and that the various embodiments of the preferred implementations of the present disclosure include the use of one or more application specific integrated circuits (ASICs) or other hardware equivalents for performing some or all of the steps, and that the functions can be performed by any number of hardware configurations and equivalents in software. The processes described in the specification can be performed by one or more processing circuits.

[0261] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of instructions to implement logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processing module, or other systems that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a computer- readable storage medium or a computer-readable signal medium. The computer-readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include the following: an electrical connection having one or more wires (control method), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CD-ROM). In addition, the computer-readable medium can even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via the optical scanner of a device or device, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and stored in a computer memory.

[0262] It should be understood that parts of the embodiments of the present disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and as in another embodiment, any one or a combination of the following technologies known in the art can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits (ASICs) having appropriate combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0263] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-described embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer-readable storage medium. When the programs are executed, they include one or a combination of the steps of the method embodiments.

[0264] In addition, each functional unit in various embodiments of the present disclosure can be integrated in one processing module, or each unit can exist physically separately, or two or more units can be integrated in one module. The integrated module can be realized in the form of hardware, or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium. The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0265] Although the embodiments of the present disclosure have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for adjusting vehicle chassis control, characterized in that, The method includes: In response to a vehicle chassis adjustment trigger event, determine the chassis control scheme to be adjusted; Obtain vehicle status data for the chassis control scheme to be adjusted; The control effect strategy determined based on the vehicle status data and historical status data is evaluated to determine the adjustment value that meets the target control effect. The adjustment value is used to represent the adjustment content of the control parameters corresponding to the chassis control scheme to be adjusted. The control parameters of the chassis control scheme to be adjusted are adjusted according to the adjustment value.

2. The method according to claim 1, characterized in that, The step of responding to a vehicle chassis adjustment trigger event and determining the chassis control scheme to be adjusted includes: Based on the vehicle chassis adjustment trigger event, determine the chassis control scheme to be adjusted under at least one driving style and / or at least one operating condition indicated by the vehicle chassis adjustment trigger event.

3. The method according to claim 2, characterized in that, The process of determining the chassis control scheme to be adjusted also includes: Determine the chassis damping force parameters to be adjusted corresponding to the chassis control scheme to be adjusted under at least one driving style and / or at least one operating condition.

4. The method according to claim 1, characterized in that, The acquisition of vehicle status data for the chassis control scheme to be adjusted includes: Vehicle simulation is performed based on the chassis damping force parameters to be adjusted corresponding to the chassis control scheme to be adjusted, and vehicle state data corresponding to the chassis damping force parameters to be adjusted is obtained.

5. The method according to claim 4, characterized in that, The evaluation of the control effect strategy determined based on the vehicle state data and historical state data, and the determination of the adjustment value that meets the target control effect, includes: Feature extraction is performed on the vehicle status data to determine the status data feature values; Based on the control effect strategy determined by the historical state data, the characteristic values ​​of the state data are analyzed to obtain the control effect evaluation corresponding to the vehicle state data. Based on the control effect evaluation and the target control effect, an adjustment scheme is determined to adjust the chassis damping force parameter to the target control effect; The adjustment value of the chassis damping force parameter to be adjusted is determined according to the adjustment scheme.

6. The method according to claim 5, characterized in that, The control effect strategy determined based on historical state data analyzes the feature values ​​of the state data to obtain a control effect evaluation corresponding to the vehicle state data, including: Based on the state data feature values, the control effect evaluation is determined by analyzing the control effect strategy corresponding to the control effect evaluation model. The control effect evaluation model is used to implement the control effect strategy determined by the historical state data.

7. The method according to claim 5, characterized in that, The adjustment scheme for adjusting the chassis damping force parameter to the target control effect, based on the control effect evaluation and the target control effect, includes: Based on the control effect evaluation and the target control effect, an adjustment scheme for adjusting the chassis damping force parameters is determined; Based on the vehicle status data and the adjustment plan, the adjustment value of the chassis damping force parameter to be adjusted is determined; If the adjustment value does not meet the target control effect, the adjustment scheme is updated based on the control effect evaluation corresponding to the adjusted vehicle status data, and the adjustment value is re-determined based on the updated adjustment scheme until the target control effect is met, and the adjustment scheme is determined.

8. The method according to claim 7, characterized in that, The step of adjusting the control parameters of the chassis control scheme to be adjusted according to the adjustment value includes: The chassis damping force parameters, adjusted based on the aforementioned adjustment values, are then updated in the chassis control scheme to be adjusted.

9. The method according to any one of claims 1 to 8, characterized in that, The control effect strategy determined based on historical state data includes: Obtain the control effect evaluation model corresponding to the control effect strategy from the cloud server; or The control effect evaluation model corresponding to the control effect strategy is obtained locally from the vehicle.

10. The method according to any one of claims 1 to 8, characterized in that, The control effect strategy determined based on historical state data includes: Feature extraction is performed on the actual operating state of the vehicle to determine the state data sample of the vehicle; Based on the state data sample, determine the control effect label of the state data sample; Based on the state data samples and the control effect labels, a control effect evaluation model is trained.

11. The method according to claim 10, characterized in that, The step of extracting features from the actual operating state of the vehicle to determine the vehicle's state data samples includes: Based on a preset sampling duration, the time-series raw data of the actual operating status of the vehicle are determined; The original time-series data is preprocessed and its data format is converted to obtain the processed data; The processed data is subjected to at least one of time-domain feature extraction, frequency-domain feature extraction, signal interaction feature extraction, and dynamic feature extraction to determine the state data sample of the vehicle. The state data sample includes the historical state data of the vehicle and the scores of multiple evaluation indicators corresponding to the historical state data.

12. The method according to claim 10, characterized in that, The step of determining the control effect label of the state data sample based on the state data sample includes: Determine the weight coefficients of multiple evaluation indicators in the control effect evaluation model; The control effect label is determined based on the score of each evaluation indicator and the weight coefficient in the state data sample.

13. A vehicle chassis control and adjustment device, characterized in that, The device includes: a determining module, an acquiring module, an evaluating module, and an adjusting module. The determining module is used to determine the chassis control scheme to be adjusted in response to a vehicle chassis adjustment trigger event; The acquisition module is used to acquire vehicle status data for the chassis control scheme to be adjusted; The evaluation module is used to evaluate the control effect strategy determined by the vehicle status data based on historical status data, and determine the adjustment value that meets the target control effect. The adjustment value is used to represent the adjustment content of the control parameters corresponding to the chassis control scheme to be adjusted. The adjustment module is used to adjust the control parameters of the chassis control scheme to be adjusted according to the adjustment value.

14. The apparatus according to claim 13, characterized in that, The determining module is used for: Based on the vehicle chassis adjustment trigger event, determine the chassis control scheme to be adjusted under at least one driving style and / or at least one operating condition indicated by the vehicle chassis adjustment trigger event.

15. The apparatus according to claim 14, characterized in that, The determining module is used for: Determine the chassis damping force parameters to be adjusted corresponding to the chassis control scheme to be adjusted under at least one driving style and / or at least one operating condition.

16. The apparatus according to claim 13, characterized in that, The acquisition module is used for: Vehicle simulation is performed based on the chassis damping force parameters to be adjusted corresponding to the chassis control scheme to be adjusted, and vehicle state data corresponding to the chassis damping force parameters to be adjusted is obtained.

17. The apparatus according to claim 16, characterized in that, The evaluation module is used for: Feature extraction is performed on the vehicle status data to determine the status data feature values; Based on the control effect strategy determined by the historical state data, the characteristic values ​​of the state data are analyzed to obtain the control effect evaluation corresponding to the vehicle state data. Based on the control effect evaluation and the target control effect, an adjustment scheme is determined to adjust the chassis damping force parameter to the target control effect; The adjustment value of the chassis damping force parameter to be adjusted is determined according to the adjustment scheme.

18. The apparatus according to claim 17, characterized in that, The evaluation module is also used for: Based on the state data feature values, the control effect evaluation is determined by analyzing the control effect strategy corresponding to the control effect evaluation model. The control effect evaluation model is used to implement the control effect strategy determined by the historical state data.

19. The apparatus according to claim 17, characterized in that, The evaluation module is used for: Based on the control effect evaluation and the target control effect, an adjustment scheme for adjusting the chassis damping force parameters is determined; Based on the vehicle status data and the adjustment plan, the adjustment value of the chassis damping force parameter to be adjusted is determined; If the adjustment value does not meet the target control effect, the adjustment scheme is updated based on the control effect evaluation corresponding to the adjusted vehicle status data, and the adjustment value is re-determined based on the updated adjustment scheme until the target control effect is met, and the adjustment scheme is determined.

20. The apparatus according to claim 19, characterized in that, The adjustment module is used for: The chassis damping force parameters, adjusted based on the aforementioned adjustment values, are then updated in the chassis control scheme to be adjusted.

21. The apparatus according to any one of claims 13 to 20, characterized in that, The device further includes a training module for: Feature extraction is performed on the actual operating state of the vehicle to determine the state data sample of the vehicle; Based on the state data sample, determine the control effect label of the state data sample; Based on the state data samples and the control effect labels, a control effect evaluation model is trained.

22. An electronic device, characterized in that, The electronic device is configured to perform the vehicle chassis control adjustment method according to any one of claims 1 to 12, or the electronic device includes the apparatus according to any one of claims 13 to 21.

23. A computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 12.

24. A program product, characterized in that, Includes computer instructions for causing a computer to perform the method of any one of claims 1 to 12.

Images