Real-time sensing and active control method and system for wind resistance coefficient of pickup truck container

Abstract

The invention discloses a pickup truck container wind resistance coefficient real-time sensing and active control method and system. The method comprises the steps that operation state parameters in the driving process of a pickup truck are obtained in real time; according to the operation state parameters, characteristic indexes used for representing the airflow separation and backflow state of the container area are obtained through calculation through a pneumatic estimation model operating in a vehicle control unit; based on the characteristic indexes and the operation state parameters, aiming at optimizing the pneumatic performance of the whole truck, solving by adopting a model prediction control algorithm to obtain a control instruction for controlling a pneumatic actuator on the pickup truck; according to the control instruction, the pneumatic actuator is driven to be adjusted to the target state, and the pneumatic appearance of the periphery of the pickup truck container is changed through the pneumatic actuator. The peripheral airflow of the pickup truck container in the driving process of the pickup truck is sensed in real time and is actively and cooperatively regulated, so that the wind resistance in the driving process can be effectively reduced, and the driving stability is synchronously improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, specifically to a method and system for real-time sensing and active control of the drag coefficient of a pickup truck cargo box. Background Technology

[0002] With the global automotive industry's increasing emphasis on energy conservation and emission reduction, vehicle aerodynamic optimization has become a key technological path to improve fuel economy and the driving range of electric vehicles. Pickup trucks, due to their unique structure where the cab and open cargo bed are separated, are prone to significant airflow separation and vortices in the cargo bed area at high speeds, resulting in a drag coefficient much higher than that of streamlined passenger vehicles, leading to additional energy consumption. Therefore, effectively reducing the drag coefficient of pickup trucks has significant practical importance and economic value for achieving environmental goals.

[0003] Currently, the mainstream technical solutions in the industry mainly fall into two categories: one is to use fixed pneumatic auxiliary devices, such as adding cargo box covers and side skirts, to passively improve airflow by changing the geometric shape; the other is to develop simple trigger-based active control solutions, such as automatically opening and closing cargo box covers or adjusting the angle of deflectors based on vehicle speed signals.

[0004] However, whether it's a fixed component or an active control system triggered by simple rules, its operational logic relies on pre-calibrated operating conditions and cannot perceive the real-time airflow conditions around the cargo box. This inherent deficiency of lacking real-time airflow feedback makes it impossible to perceive and respond to dynamic driving conditions such as crosswinds, lane changes, or load variations. This makes the aerodynamic optimization effect highly dependent on the initial calibration environment, resulting in severely insufficient adaptability in real, changing road environments, and unstable and very limited optimization effects. Summary of the Invention

[0005] In view of the shortcomings of the prior art, the purpose of this invention is to provide a method and system for real-time sensing and active control of the drag coefficient of a pickup truck cargo box, which aims to solve the above-mentioned problems described in the prior art.

[0006] The first aspect of the present invention is to provide a method for real-time sensing and active control of the drag coefficient of a pickup truck cargo box, the method comprising: Real-time acquisition of operational status parameters of pickup trucks during driving, including near-wall airflow parameters of the pickup truck bed collected by distributed airflow sensors, as well as vehicle speed, yaw rate and lateral acceleration; Based on the operating state parameters, a characteristic index for characterizing the airflow separation and recirculation state in the cargo box area is calculated using an aerodynamic estimation model running in the vehicle controller; wherein, the characteristic index is at least one of the estimated recirculation intensity value and the vortex indication value determined based on the near-wall airflow parameters. Based on the aforementioned characteristic indicators and the aforementioned operating state parameters, with the goal of optimizing the overall vehicle aerodynamic performance, a model predictive control algorithm is used to obtain the control commands for controlling the pneumatic actuators on the pickup truck. According to the control command, the pneumatic actuator is driven to adjust to the target state, so as to change the aerodynamic shape of the pickup truck bed through the pneumatic actuator.

[0007] According to one aspect of the above technical solution, the step of calculating characteristic indicators for characterizing the airflow separation and recirculation state in the cargo box area using an aerodynamic estimation model running in the vehicle controller, based on the operating state parameters, includes: The near-wall airflow parameters are preprocessed to obtain denoised and spatiotemporally aligned standardized airflow data; The standardized airflow data is fused with the vehicle speed, yaw rate, and lateral acceleration to obtain the input vector of the aerodynamic estimation model; The input vector is input into the aerodynamic estimation model to calculate and output characteristic indicators that characterize the airflow separation and recirculation state in the cargo box area.

[0008] According to one aspect of the above technical solution, the step of fusing the standardized airflow data with the vehicle speed, yaw rate, and lateral acceleration to obtain the input vector of the aerodynamic estimation model includes: Based on a unified timestamp, the standardized airflow data is aligned and combined with the vehicle speed, yaw rate, and lateral acceleration at the same time. The combined multi-channel data are spliced ​​together in a predetermined order to form the input vector of fixed length.

[0009] According to one aspect of the above technical solution, based on the characteristic indicators and the operating state parameters, and with the goal of optimizing the overall vehicle aerodynamic performance, the step of using a model predictive control algorithm to obtain control commands for controlling the pneumatic actuators on the pickup truck includes: The optimization objective of the aerodynamic shape is set as the predicted value of the drag coefficient to be minimized by mapping the characteristic index with the vehicle speed, and the travel stroke constraint and motion rate constraint of the pneumatic actuator on the pickup truck are set. Within the set prediction time domain, using the morphological parameters of the pneumatic actuator as optimization variables, the optimization objective is solved by rolling optimization based on the model predictive control algorithm to obtain the optimal morphological parameter sequence; The first timing value in the optimal morphological parameter sequence is converted into a control command to drive the pneumatic actuator.

[0010] According to one aspect of the above technical solution, within a set prediction time domain, using the morphological parameters of the pneumatic actuator as optimization variables, and based on the model predictive control algorithm, performing rolling optimization to solve the optimization objective and obtain the optimal morphological parameter sequence, the step includes: The current vehicle state is obtained as the initial state of the model predictive control algorithm, and the vehicle state includes the feature index and the operating state parameters; Based on the initial state and the prediction model characterizing the relationship between aerodynamic shape and aerodynamic performance, the optimization that satisfies the running stroke constraint and motion rate constraint is solved in the prediction time domain to obtain a series of morphological parameters in the future time domain, and thus obtain the optimal morphological parameter sequence.

[0011] According to one aspect of the above technical solution, based on the initial state and the prediction model characterizing the relationship between aerodynamic shape and aerodynamic performance, the step of solving for optimizations that satisfy the running stroke constraints and motion rate constraints within the prediction time domain to obtain a series of morphological parameters in the future time domain, and obtaining the optimal morphological parameter sequence, includes: Construct an initial objective function, which includes integrating the predicted drag coefficient over the prediction time domain and adding a penalty term for changes in control commands; The travel distance constraint and the motion rate constraint are expressed as inequality constraints in an optimization problem. A numerical optimization algorithm is used to solve the constrained optimization problem, and the morphological parameter sequence that minimizes the objective function is obtained as the morphological parameter sequence.

[0012] According to one aspect of the above technical solution, the airflow sensor includes at least the outer side of the upper edge of the pickup truck bed, the front section of the side wall, and the rear section of the side wall. The pneumatic actuator includes at least two of the following: a retractable side skirt, an adjustable roof deflector, and a segmented cargo box cover.

[0013] A second aspect of the present invention is to provide a real-time sensing and active control system for the drag coefficient of a pickup truck bed, applied to the method described in the above-mentioned technical solution, the system comprising: The parameter acquisition module is used to acquire the operating status parameters of the pickup truck in real time, including the near-wall airflow parameters of the pickup truck bed collected by distributed airflow sensors, as well as vehicle speed, yaw rate and lateral acceleration. The feature calculation module is used to calculate, based on the operating state parameters and through an aerodynamic estimation model running in the vehicle controller, a feature index characterizing the airflow separation and recirculation state in the cargo box area; wherein, the feature index is at least one of the estimated recirculation intensity value and the vorticity indication value determined based on the near-wall airflow parameters. The instruction generation module is used to obtain control instructions for controlling the pneumatic actuators on the pickup truck by using a model predictive control algorithm based on the feature indicators and the operating state parameters, with the goal of optimizing the aerodynamic performance of the whole vehicle. The pneumatic actuator module is used to drive the pneumatic actuator to adjust to the target state according to the control command, so as to change the pneumatic shape of the pickup truck bed through the pneumatic actuator.

[0014] A third aspect of the present invention is to provide a readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method described in the above-described technical solution.

[0015] A fourth aspect of the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method described in the above technical solutions.

[0016] Compared with existing technologies, the advantages of the real-time sensing and active control method and system for the drag coefficient of pickup truck cargo boxes shown in this invention are as follows: The method described in this invention uses a distributed sensor array to perceive the local micro-flow field information of the cargo box in real time and convert it into quantifiable aerodynamic characteristic indicators. This transforms the control objective from an indirect and ambiguous vehicle speed signal to a direct and precise demand for wind resistance and stability, laying a solid foundation for closed-loop control. Based on this, a model predictive control algorithm is employed to predict future short-term aerodynamic changes based on the current state, thereby proactively calculating the optimal coordinated action commands for multiple pneumatic actuators. This not only overcomes the limitations of independent control of a single component but also enables the system to smoothly and proactively adapt to dynamic conditions such as crosswinds and lane changes, rather than responding with lag. Ultimately, this ensures that the vehicle's aerodynamic shape can continuously and dynamically self-optimize, significantly reducing wind resistance at high speeds and effectively improving driving stability under complex airflow disturbances. Attached Figure Description

[0017] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a flowchart illustrating the real-time sensing and active control method for the drag coefficient of a pickup truck cargo box provided in an embodiment of the present invention. Figure 2 The structural block diagram of the real-time sensing and active control system for the drag coefficient of a pickup truck cargo box provided in the embodiments of the present invention is shown. Detailed Implementation

[0018] To make the objectives, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of the present invention will be more thorough and complete.

[0019] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0021] Example 1 Please see Figure 1 The first embodiment of the present invention provides a method for real-time sensing and active control of the drag coefficient of a pickup truck cargo box, the method comprising steps S10-S40: Step S10: Real-time acquisition of the operating status parameters of the pickup truck during its driving process, including the near-wall airflow parameters of the pickup truck cargo box collected by distributed airflow sensors, as well as vehicle speed, yaw rate and lateral acceleration.

[0022] Specifically, in this embodiment, the distributed airflow sensors are preferably biomimetic flexible micro-airflow sensor units with millisecond-level response speed, and are arranged in an array with a spacing of 50-100 mm. These arrays are precisely attached to key locations such as the outer edge of the upper edge of the pickup truck bed, the front section of the side wall, and the rear section of the side wall, so as to obtain the near-wall airflow parameters during the driving process of the pickup truck through the airflow sensors.

[0023] Meanwhile, during vehicle operation, vehicle speed information is acquired in real time via the vehicle's CAN bus, and high-precision yaw rate and lateral acceleration data are obtained via an inertial measurement unit installed near the vehicle's center of gravity.

[0024] Step S20: Based on the operating state parameters, the characteristic index used to characterize the airflow separation and recirculation state in the cargo box area is calculated by the aerodynamic estimation model running in the vehicle controller.

[0025] The characteristic index is at least one of the estimated backflow intensity and the vorticity indication value determined based on the near-wall airflow parameters.

[0026] In this embodiment, the step of calculating characteristic indicators to characterize the airflow separation and recirculation state in the cargo box area based on the operating state parameters and through the aerodynamic estimation model running in the vehicle controller includes: The near-wall airflow parameters are preprocessed to obtain denoised and spatiotemporally aligned standardized airflow data; The standardized airflow data is fused with the vehicle speed, yaw rate, and lateral acceleration to obtain the input vector of the aerodynamic estimation model; The input vector is input into the aerodynamic estimation model to calculate and output characteristic indicators that characterize the airflow separation and recirculation state in the cargo box area.

[0027] The step of fusing the standardized airflow data with the vehicle speed, yaw rate, and lateral acceleration to obtain the input vector of the aerodynamic estimation model includes: Based on a unified timestamp, the standardized airflow data is aligned and combined with the vehicle speed, yaw rate, and lateral acceleration at the same time. The combined multi-channel data are spliced ​​together in a predetermined order to form the input vector of fixed length.

[0028] Specifically, in this embodiment, the core of step S20 is to transform the raw data collected in step S10, i.e., the operating state parameters, into characteristic indicators that can directly and quantitatively characterize the complex airflow structure of the cargo box area. It uses an aerodynamic estimation model for calculation and processing. This aerodynamic estimation model is a data-driven model deployed in the vehicle controller (VCU) and jointly trained with a large number of wind tunnel tests and computational fluid dynamics simulation data, such as deep neural networks or gradient boosting decision trees.

[0029] The input to the aforementioned aerodynamic estimation model is a standardized input vector after preprocessing and fusion. By mining the nonlinear relationships in high-dimensional data, it accurately calculates characteristic indicators related to wind resistance. In this embodiment, these include backflow intensity estimates and vorticity indicators. The backflow intensity estimate quantifies the size and intensity of the backflow zone at the rear of the cargo box. A larger value indicates more severe airflow separation and greater pressure drag, which is a direct factor affecting the drag coefficient. The vorticity indicator reflects the intensity of airflow rotation and can sensitively capture vortices generated at the corners and sides of the cargo box.

[0030] In this embodiment, by outputting the above two characteristic indicators with clear physical meaning, a measurable and understandable digital expression of the abstract aerodynamic state is achieved.

[0031] Step S30: Based on the characteristic indicators and the operating state parameters, with the goal of optimizing the aerodynamic performance of the whole vehicle, the model predictive control algorithm is used to solve for the control commands to control the pneumatic actuators on the pickup truck.

[0032] Specifically, in this embodiment, the purpose of step S30 is to transform the quantified aerodynamic state characteristics output in step S20 into precise and coordinated control commands for the aerodynamic shape. This process employs a Model Predictive Control (MPC) algorithm for calculation and solution.

[0033] More specifically, the MPC controller has a built-in predictive model that can characterize the dynamic relationship between the pneumatic actuator morphological parameters and the aerodynamic performance of the whole vehicle. In each control cycle, such as 50-100 milliseconds, the MPC controller uses the characteristic index and vehicle operating state parameters corresponding to the current moment as the initial state. Based on the predictive model, it solves the constrained optimization problem in a rolling manner in a short time domain in the future.

[0034] The objective function of the optimization problem is set to minimize the estimated drag coefficient within the prediction domain, while also taking into account lateral forces to improve stability. Simultaneously, the optimization process is strictly constrained by physical limitations, including the travel limits, motion rates, and acceleration limits of each actuator, to ensure system safety and passenger comfort.

[0035] By solving the above problem, the MPC controller outputs a series of optimal actuator configuration sequences in the future time domain. The first immediate control command in this sequence is then issued to the pneumatic actuator ultimately used for aerodynamic shape adjustment in the pickup truck bed area. This not only responds to the current airflow state but also predicts future state changes, thereby achieving coordinated, smooth, and optimal control of multiple actuators, effectively overcoming the lag and local optimization defects of traditional control methods.

[0036] Step S40: According to the control command, drive the pneumatic actuator to adjust to the target state so as to change the pneumatic shape of the pickup truck bed through the pneumatic actuator.

[0037] The pneumatic actuator includes at least two of the following: a retractable side skirt, an adjustable roof deflector, and a segmented cargo box cover.

[0038] Specifically, the aforementioned pneumatic actuator is a collaborative system that mainly includes: a cargo box side skirt telescopic mechanism, an active roof deflector, a segmented cargo box cover, and a small transition winglet between the cab and the leading edge of the cargo box. All of these pneumatic actuators are equipped with high-precision drive motors and posture feedback sensors.

[0039] When the vehicle controller issues a control command, each pneumatic actuator operates synchronously according to the control command. For example, the side skirts extend precisely to guide the airflow at the bottom and sides and suppress the generation of vortices; the roof deflector rotates to the optimal angle to improve the upstream flow of the cargo box; the segmented cargo box cover adjusts its opening and closing degree to control the volume of the return cavity; and the leading edge winglets actuate to suppress airflow separation at the gap between the cab and the cargo box.

[0040] In this embodiment, the flow field around the pickup truck bed can be actively shaped by the coordinated deformation of the pneumatic actuator. The core of this is to control the position of the airflow separation point, stabilize the shear layer and promote pressure recovery, thereby fundamentally reducing the pressure difference drag and induced drag around the pickup truck bed during the driving process.

[0041] Compared with existing technologies, the real-time sensing and active control method for the drag coefficient of pickup truck cargo boxes shown in this embodiment has the following advantages: The method described in this embodiment uses a distributed sensor array to perceive the local micro-flow field information of the cargo box in real time and convert it into quantifiable aerodynamic characteristic indicators. This transforms the control objective from an indirect and ambiguous vehicle speed signal to a direct and precise demand for wind resistance and stability, laying a solid foundation for closed-loop control. Based on this, a model predictive control algorithm is employed, which can predict future short-term aerodynamic changes based on the current state. This allows for the proactive calculation of optimal coordinated action commands for multiple pneumatic actuators, overcoming the limitations of independent control of a single component. Furthermore, it enables the system to smoothly and proactively adapt to dynamic conditions such as crosswinds and lane changes, rather than responding with lag. Ultimately, this ensures that the vehicle's aerodynamic shape can continuously and dynamically self-optimize, significantly reducing wind resistance at high speeds and effectively improving driving stability under complex airflow disturbances.

[0042] Example 2 The second embodiment of the present invention also provides a method for real-time sensing and active control of the drag coefficient of a pickup truck cargo box. The method shown in this embodiment is basically similar to the method shown in the first embodiment, except that: In this embodiment, based on the characteristic indicators and the operating state parameters, and with the goal of optimizing the overall vehicle aerodynamic performance, the steps of using a model predictive control algorithm to obtain control commands for controlling the pneumatic actuators on the pickup truck include: The optimization objective of the aerodynamic shape is set as the predicted value of the drag coefficient to be minimized by mapping the characteristic index with the vehicle speed, and the travel stroke constraint and motion rate constraint of the pneumatic actuator on the pickup truck are set. Within the set prediction time domain, using the morphological parameters of the pneumatic actuator as optimization variables, the optimization objective is solved by rolling optimization based on the model predictive control algorithm to obtain the optimal morphological parameter sequence; The first timing value in the optimal morphological parameter sequence is converted into a control command to drive the pneumatic actuator.

[0043] Specifically, in this embodiment, the optimization objective is set as minimizing the predicted drag coefficient obtained by mapping characteristic indicators to vehicle speed. Simultaneously, a penalty term is added for changes in control commands, which effectively avoids frequent and violent actuator movements, ensuring ride comfort and system durability. Furthermore, expressing the actuator's travel distance and speed as inequality constraints directly embeds the hardware's physical limits and safety requirements into the optimization problem, mathematically guaranteeing the engineering feasibility of the solution.

[0044] The step of performing rolling optimization on the optimization objective within a set prediction time domain, using the morphological parameters of the pneumatic actuator as optimization variables, and obtaining the optimal morphological parameter sequence based on the model predictive control algorithm, includes: The current vehicle state is obtained as the initial state of the model predictive control algorithm, and the vehicle state includes the feature index and the operating state parameters; Based on the initial state and the prediction model characterizing the relationship between aerodynamic shape and aerodynamic performance, the optimization that satisfies the running stroke constraint and motion rate constraint is solved in the prediction time domain to obtain a series of morphological parameters in the future time domain, and thus obtain the optimal morphological parameter sequence.

[0045] Specifically, obtaining the current vehicle state as the initial state means that the optimization solution is initiated based on the latest and most accurate system state, forming real-time feedback that allows the control to continuously correct model errors and external disturbances. Furthermore, optimizing based on the predictive model in the future time domain enhances predictive capabilities. For example, when sensors detect early signs of increasing crosswind, the algorithm can calculate the optimal actuator adjustment sequence in advance to suppress the impending increase in lateral force, rather than waiting until the vehicle's attitude has significantly deviated before responding, thereby significantly improving the timeliness and stability of the control.

[0046] The steps of obtaining the optimal morphological parameter sequence, based on the initial state and the prediction model characterizing the relationship between aerodynamic shape and aerodynamic performance, and solving for optimizations that satisfy the travel distance constraints and motion speed constraints within the prediction time domain to obtain a series of morphological parameters in the future time domain, include: Construct an initial objective function, which includes integrating the predicted drag coefficient over the prediction time domain and adding a penalty term for changes in control commands; The travel distance constraint and the motion rate constraint are expressed as inequality constraints in an optimization problem. A numerical optimization algorithm is used to solve the constrained optimization problem, and the morphological parameter sequence that minimizes the objective function is obtained as the morphological parameter sequence.

[0047] Specifically, by constructing an objective function that includes integral and penalty terms, and combining it with constraints to form a standard constrained optimization problem, mature numerical algorithms such as quadratic programming can be applied. After optimization, this algorithm can reliably find a feasible solution that satisfies all constraints and minimizes the objective function, i.e., the optimal morphological parameter sequence, within milliseconds, under the limited computing power of automotive-grade VCUs.

[0048] Example 3 Please see Figure 2 The third embodiment of the present invention provides a real-time sensing and active control system for the drag coefficient of a pickup truck bed, applied to the method described in any of the above embodiments, the system comprising: The parameter acquisition module is used to acquire the operating status parameters of the pickup truck in real time, including the near-wall airflow parameters of the pickup truck bed collected by distributed airflow sensors, as well as vehicle speed, yaw rate and lateral acceleration. The feature calculation module is used to calculate, based on the operating state parameters and through an aerodynamic estimation model running in the vehicle controller, a feature index characterizing the airflow separation and recirculation state in the cargo box area; wherein, the feature index is at least one of the estimated recirculation intensity value and the vorticity indication value determined based on the near-wall airflow parameters. The instruction generation module is used to obtain control instructions for controlling the pneumatic actuators on the pickup truck by using a model predictive control algorithm based on the feature indicators and the operating state parameters, with the goal of optimizing the aerodynamic performance of the whole vehicle. The pneumatic actuator module is used to drive the pneumatic actuator to adjust to the target state according to the control command, so as to change the pneumatic shape of the pickup truck bed through the pneumatic actuator.

[0049] Example 4 A fourth embodiment of the present invention provides a readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method described in any of the above embodiments.

[0050] Example 5 A fifth embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method described in any of the above embodiments.

[0051] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0052] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A method for real-time sensing and active control of the drag coefficient of a pickup truck cargo box, characterized in that, The method includes: Real-time acquisition of operational status parameters of pickup trucks during driving, including near-wall airflow parameters of the pickup truck bed collected by distributed airflow sensors, as well as vehicle speed, yaw rate and lateral acceleration; Based on the operating state parameters, a characteristic index for characterizing the airflow separation and recirculation state in the cargo box area is calculated using an aerodynamic estimation model running in the vehicle controller; wherein, the characteristic index is at least one of the estimated recirculation intensity value and the vortex indication value determined based on the near-wall airflow parameters. Based on the aforementioned characteristic indicators and the aforementioned operating state parameters, with the goal of optimizing the overall vehicle aerodynamic performance, a model predictive control algorithm is used to obtain the control commands for controlling the pneumatic actuators on the pickup truck. According to the control command, the pneumatic actuator is driven to adjust to the target state, so as to change the aerodynamic shape of the pickup truck bed through the pneumatic actuator.

2. The method for real-time sensing and active control of the drag coefficient of a pickup truck cargo box according to claim 1, characterized in that, Based on the operating state parameters, the steps for calculating characteristic indicators to characterize the airflow separation and recirculation state in the cargo box area using an aerodynamic estimation model running in the vehicle controller include: The near-wall airflow parameters are preprocessed to obtain denoised and spatiotemporally aligned standardized airflow data; The standardized airflow data is fused with the vehicle speed, yaw rate, and lateral acceleration to obtain the input vector of the aerodynamic estimation model; The input vector is input into the aerodynamic estimation model to calculate and output characteristic indicators that characterize the airflow separation and recirculation state in the cargo box area.

3. The method for real-time sensing and active control of the drag coefficient of a pickup truck cargo box according to claim 2, characterized in that, The step of fusing the standardized airflow data with the vehicle speed, yaw rate, and lateral acceleration to obtain the input vector of the aerodynamic estimation model includes: Based on a unified timestamp, the standardized airflow data is aligned and combined with the vehicle speed, yaw rate, and lateral acceleration at the same time. The combined multi-channel data are spliced ​​together in a predetermined order to form the input vector of fixed length.

4. The method for real-time sensing and active control of the drag coefficient of a pickup truck cargo box according to claim 1, characterized in that, Based on the aforementioned characteristic indicators and the aforementioned operating state parameters, and with the goal of optimizing the overall vehicle aerodynamic performance, the steps of obtaining control commands for controlling the pneumatic actuators on the pickup truck using a model predictive control algorithm include: The optimization objective of the aerodynamic shape is set as the predicted value of the drag coefficient to be minimized by mapping the characteristic index with the vehicle speed, and the travel stroke constraint and motion rate constraint of the pneumatic actuator on the pickup truck are set. Within the set prediction time domain, using the morphological parameters of the pneumatic actuator as optimization variables, the optimization objective is solved by rolling optimization based on the model predictive control algorithm to obtain the optimal morphological parameter sequence; The first timing value in the optimal morphological parameter sequence is converted into a control command to drive the pneumatic actuator.

5. The method for real-time sensing and active control of the drag coefficient of a pickup truck cargo box according to claim 4, characterized in that, Within a set prediction time domain, using the morphological parameters of the pneumatic actuator as optimization variables, and based on the model predictive control algorithm, performing rolling optimization to solve the optimization objective and obtain the optimal morphological parameter sequence includes: The current vehicle state is obtained as the initial state of the model predictive control algorithm, and the vehicle state includes the feature index and the operating state parameters; Based on the initial state and the prediction model characterizing the relationship between aerodynamic shape and aerodynamic performance, the optimization that satisfies the running stroke constraint and motion rate constraint is solved in the prediction time domain to obtain a series of morphological parameters in the future time domain, and thus obtain the optimal morphological parameter sequence.

6. The method for real-time sensing and active control of the drag coefficient of a pickup truck cargo box according to claim 5, characterized in that, Based on the initial state and the prediction model characterizing the relationship between aerodynamic shape and aerodynamic performance, the steps of solving for optimizations that satisfy the travel distance constraints and motion speed constraints within the prediction time domain to obtain a series of morphological parameters in the future time domain and obtaining the optimal morphological parameter sequence include: Construct an initial objective function, which includes integrating the predicted drag coefficient over the prediction time domain and adding a penalty term for changes in control commands; The travel distance constraint and the motion rate constraint are expressed as inequality constraints in an optimization problem. A numerical optimization algorithm is used to solve the constrained optimization problem, and the morphological parameter sequence that minimizes the objective function is obtained as the morphological parameter sequence.

7. The method for real-time sensing and active control of the drag coefficient of a pickup truck cargo box according to any one of claims 1-6, characterized in that, The airflow sensor includes at least the outer side of the upper edge of the pickup truck bed, the front section of the side wall, and the rear section of the side wall; The pneumatic actuator includes at least two of the following: a retractable side skirt, an adjustable roof deflector, and a segmented cargo box cover.

8. A real-time sensing and active control system for the drag coefficient of a pickup truck cargo box, characterized in that, The system, applicable to the method of any one of claims 1-7, comprises: The parameter acquisition module is used to acquire the operating status parameters of the pickup truck in real time, including the near-wall airflow parameters of the pickup truck bed collected by distributed airflow sensors, as well as vehicle speed, yaw rate and lateral acceleration. The feature calculation module is used to calculate, based on the operating state parameters and through an aerodynamic estimation model running in the vehicle controller, a feature index characterizing the airflow separation and recirculation state in the cargo box area; wherein, the feature index is at least one of the estimated recirculation intensity value and the vorticity indication value determined based on the near-wall airflow parameters. The instruction generation module is used to obtain control instructions for controlling the pneumatic actuators on the pickup truck by using a model predictive control algorithm based on the feature indicators and the operating state parameters, with the goal of optimizing the aerodynamic performance of the whole vehicle. The pneumatic actuator module is used to drive the pneumatic actuator to adjust to the target state according to the control command, so as to change the pneumatic shape of the pickup truck bed through the pneumatic actuator.

9. A readable storage medium having computer instructions stored thereon, characterized in that, When executed by the processor, this instruction implements the steps of the method as described in any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method as described in any one of claims 1-7.

Images