Commercial vehicle differential lock control method, system and equipment and storage medium

Abstract

The invention discloses a commercial vehicle differential lock control method, system and device and a storage medium, and the method comprises the steps: collecting images and point cloud data of a road environment in front of a commercial vehicle in real time, and processing the images and point cloud data through a deep learning algorithm; generating a digital pavement adhesion map containing the potential slip risk area and the estimated adhesion coefficient of the potential slip risk area; a future driving path of the commercial vehicle is predicted according to the road adhesion map, the current vehicle speed and the steering wheel angle, and when the predicted driving path intersects with the potential slip risk area, a pre-locking instruction of a differential lock is automatically generated before the commercial vehicle drives into the potential slip risk area; when the commercial vehicle drives into the potential slip risk area and it is detected that the slip rate of the driving wheel exceeds a set threshold value, differential lock complete locking is executed; and after the differential lock is locked, the security unlocking confidence coefficient is calculated based on the multi-factor decision model, and when the security unlocking confidence coefficient exceeds a set threshold value, differential lock unlocking is executed. Intelligent control over the commercial vehicle differential lock is achieved.

Description

Technical Field

[0001] This invention belongs to the field of automotive electronic control technology, and in particular relates to a method, system, device and storage medium for controlling differential locks in commercial vehicles. Background Technology

[0002] Differential locks are crucial equipment for commercial vehicles to improve their passability in low-traction road conditions. However, engaging and disengaging differential locks largely relies on manual operation by the driver, which has significant drawbacks: 1. Experience dependence and operational burden: Drivers need to accurately judge road conditions and slippage status, and the stressful process of getting out of trouble can lead to distraction, increasing workload and safety risks; 2. Delayed response: Manual operation is performed after slippage occurs, and power interruption may cause loss of vehicle inertia, exacerbating the risk of getting stuck; 3. The persistent problem of "forgetting to unlock": If the driver does not unlock the differential lock in time after the vehicle returns to a good road surface, it can lead to abnormal wear and burning of the differential gears, generating huge internal stress in the transmission system, causing serious mechanical failures and economic losses.

[0003] Currently, although there are attempts to automatically control differential locks by detecting wheel speed differences, such solutions are only simple reactive controls of "slippage-lock, no slippage-unlock," which have obvious shortcomings: ① They cannot cope with impending risks and lack foresight; ② On road sections with frequent changes in traction (such as intermittent icy and snowy roads), they are prone to frequent and abrupt locking / unlocking cycles, affecting driving comfort and system lifespan; ③ They cannot distinguish between slight slippage and severe getting stuck, resulting in low intelligence. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method, system, device, and storage medium for controlling differential locks in commercial vehicles. To solve the above-mentioned technical problems, the present invention is implemented using the following solution: This invention provides a method for controlling a differential lock in a commercial vehicle, comprising: Real-time acquisition of images and point cloud data of the road environment in front of commercial vehicles, and processing of the acquired images and point cloud data through deep learning algorithms to generate a digital road surface adhesion map containing potential skidding risk areas and estimated adhesion coefficients of potential skidding risk areas. Based on the road adhesion map, current vehicle speed and steering wheel angle, the driving path of the commercial vehicle is predicted within a set time in the future. When the predicted driving path intersects with a potential slippage risk area, a pre-locking or preparation command for the differential lock is automatically generated before the commercial vehicle enters the potential slippage risk area. When a commercial vehicle enters a potential slippage risk area and the drive wheel slip rate is detected to exceed a set threshold, the differential lock is fully engaged. After the differential lock is locked, the confidence level for safe unlocking is calculated based on a multi-factor decision model. When the confidence level for safe unlocking exceeds a set threshold, the differential lock is unlocked.

[0005] Furthermore, real-time acquisition of images and point cloud data of the road environment in front of commercial vehicles is achieved through onboard cameras and millimeter-wave radar.

[0006] Furthermore, the acquired image and point cloud data are processed using deep learning algorithms, including: Pixel-level semantic segmentation of the acquired images and point cloud data is performed using deep learning algorithms to identify road surface types and local risk features.

[0007] Furthermore, the differential lock pre-locking or preparation commands are automatically generated, including: Send a pre-activation signal that is not fully locked to the differential lock actuator, causing the differential lock actuator to enter a low-power standby state.

[0008] Furthermore, the multi-factor decision model is based on multiple factors including road condition confidence, wheel speed difference stability, and steering wheel angle.

[0009] Furthermore, it also includes: When the differential lock is fully engaged and a commercial vehicle is detected to be in a state of severe slippage, the peak output torque of the drive motor is limited and intermittent braking force is applied to the slipping wheels.

[0010] The present invention also provides a predictive control system for intelligent differential locks in commercial vehicles, comprising: The multi-source information perception module is used to collect images and point cloud data of the road environment in front of commercial vehicles in real time, and to process the collected images and point cloud data through deep learning algorithms to generate a digital road surface adhesion map that includes potential skidding risk areas and estimated adhesion coefficients of potential skidding risk areas. The path prediction and pre-lock decision module is used to predict the driving path of the commercial vehicle within a set time in the future based on the road adhesion map, current vehicle speed and steering wheel angle. When the predicted driving path intersects with a potential slip risk area, the module automatically generates a pre-lock or preparation command for the differential lock before the commercial vehicle enters the potential slip risk area. The adaptive precision locking module is used to fully lock the differential lock when a commercial vehicle enters a potential slip risk area and the drive wheel slip rate is detected to exceed a set threshold. The multi-factor intelligent unlocking module is used to calculate the confidence level of safe unlocking based on a multi-factor decision model after the differential lock is locked. When the confidence level of safe unlocking exceeds a set threshold, the differential lock is unlocked.

[0011] The present invention also 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 aforementioned commercial vehicle differential lock control method.

[0012] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the aforementioned commercial vehicle differential lock control method. Beneficial effects

[0013] This invention collects and processes images and point cloud data of the road environment in front of commercial vehicles in real time using deep learning algorithms to generate a digital road surface adhesion map containing potential slip risk areas and estimated adhesion coefficients for these areas. Based on the road surface adhesion map, current vehicle speed, and steering wheel angle, the future driving path of the commercial vehicle is predicted. When the predicted driving path intersects with a potential slip risk area, a pre-locking command for the differential lock is automatically generated before the commercial vehicle enters the potential slip risk area. When the commercial vehicle enters the potential slip risk area and the drive wheel slip ratio is detected to exceed a set threshold, the differential lock is fully locked. After the differential lock is locked, a safe unlocking confidence level is calculated based on a multi-factor decision model. When the safe unlocking confidence level exceeds a set threshold, the differential lock is unlocked, thus realizing intelligent control of the commercial vehicle differential lock.

[0014] This invention possesses revolutionary predictive capabilities: through a "perception-prediction-pre-action" mechanism, it achieves a leap from "passive reaction" to "active response," enabling vehicles to prepare in advance when encountering adverse road conditions, achieving smooth escape without power interruption, and greatly improving passability.

[0015] This invention possesses a high degree of intelligence: the unlocking strategy based on a multi-factor confidence model mimics the comprehensive judgment logic of an excellent driver, resulting in more accurate and smoother decision-making. It effectively avoids the mechanical feel and malfunctions of traditional automatic control, thereby improving the system's robustness and service life.

[0016] This invention provides comprehensive safety protection: it fundamentally eliminates mechanical damage to the transmission system caused by human error in forgetting to unlock the door, saving car owners significant maintenance costs, reducing the driver's workload, and improving driving safety.

[0017] This invention has good adaptability and scalability: it is especially suitable for new energy commercial vehicle platforms with fast torque response and precise control, and can be easily expanded to the coordinated control of multiple differential locks. Attached Figure Description

[0018] Figure 1 This is a flowchart of a commercial vehicle differential lock control method provided in an embodiment of the present invention; Figure 2This is a simplified flowchart of a differential lock control method for commercial vehicles provided in an embodiment of the present invention; Figure 3 This is a detailed flowchart of a commercial vehicle differential lock control method provided in an embodiment of the present invention; Figure 4 This is a framework diagram of a commercial vehicle differential lock control system provided in an embodiment of the present invention; Figure 5 This is an overall framework diagram of a commercial vehicle differential lock control system provided in an embodiment of the present invention. Detailed Implementation

[0019] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention. Example 1

[0020] like Figure 1 , Figure 2 and Figure 3 As shown, this embodiment provides a differential lock control method for commercial vehicles, including the following steps: S1. Environmental perception: Utilizes multi-sensor fusion technology such as vehicle-mounted cameras and millimeter-wave radar to collect images and point cloud data of the road environment in front of the vehicle in real time.

[0021] S2. Road Condition Modeling: Processing images and point cloud data of the road environment in front of the vehicle collected by multi-sensor fusion technology: Pixel-level semantic segmentation of the collected images and point cloud data is performed through deep learning algorithms. This not only identifies road surface types (such as asphalt, ice and snow, and mud), but also accurately identifies local risk features such as water accumulation, floating ice, and ruts, generating a digital road surface adhesion map that includes potential skidding risk areas and their estimated adhesion coefficients.

[0022] S3. Prediction and Decision: Based on the road adhesion map, the vehicle's current speed and steering wheel angle, predict the vehicle's driving path within a predetermined time (short term, such as 3-5 seconds); when the predicted path intersects with a potential slippage risk area, before the vehicle enters the area, issue a "pre-lock or prepare" command to the differential lock actuator, putting it into standby state, greatly shortening the locking action response time.

[0023] S4. Adaptive Locking: When the vehicle enters a potential slippage risk area and slippage of the drive wheels is detected to exceed the first threshold, the differential lock is immediately commanded and fully locked. In case of severe vehicle entrapment, the system can automatically intervene, limit the motor torque and work with the ESP to apply intermittent braking to the slipping wheel to achieve the best extrication effect.

[0024] S5. Intelligent unlocking: After the differential lock is locked, the safe unlocking confidence level is calculated based on a multi-factor decision model (composed of factors such as road condition confidence level, wheel speed difference stability, and driver steering intention, which can effectively avoid misunderstanding of locking and frequent actions in complex road conditions). When the safe unlocking confidence level exceeds a preset threshold (such as 95%), the differential lock unlocking command is automatically generated and executed.

[0025] In step S3, the "pre-lock or prepare" instruction refers to sending a non-fully locked pre-activation signal to the differential lock actuator, causing it to enter a low-power standby state, so as to shorten the mechanical response time of full locking to less than 100 milliseconds.

[0026] In step S5, the multi-factor decision model should consider at least the following factors: a) Road condition factor: Confidence that the vision system has identified a high-adhesion road surface; b) Dynamic factors: the duration and stability of the wheel speed difference or slip ratio between the drive wheels being below the second threshold; c) Handling factor: The size of the vehicle's steering wheel angle; d) Historical Factor: The weight of the dynamic factor is automatically increased during the period immediately after the vehicle leaves the low-traction surface.

[0027] In step S4, when it is determined that the vehicle is in a state of severe slippage, the "creep escape mode" is automatically triggered. This mode includes limiting the peak output torque of the drive motor and applying intermittent braking force to the slipping wheels.

[0028] The following is a non-limiting description of the best embodiment of the present invention, using a specific application scenario: a pure electric dump truck driving on a construction site after rain: 1. Initial state: The vehicle is driving in a dry construction site area, and the system continuously monitors it. The camera detects a dark road surface 50 meters ahead, the millimeter-wave radar detects a change in road surface smoothness, and the semantic segmentation algorithm determines that the area is a "large area of ​​water and silt accumulation," with an estimated adhesion coefficient of 0.2, and marks it on the high-risk area map.

[0029] 2. Prediction and Pre-preparation: Based on the current vehicle speed of 20km / h and straight-line driving, the ECU predicts that the vehicle will enter the area in approximately 9 seconds. When approximately 2 seconds (about 10 meters) away from the risk area, the ECU sends a low-duty-cycle PWM signal to the differential lock solenoid valve, causing its valve core to pre-move to a near-operating position (pre-lock preparation). The instrument panel displays a "Differential Lock Pre-Activation" prompt.

[0030] 3. Precise Locking and Escape: When the front wheels of the vehicle enter the mud, the left rear wheel begins to slip, with the slip ratio instantly exceeding 20%. The ECU immediately issues a full command, the solenoid valve fully opens, and the differential lock achieves complete locking in a very short time (only 50ms due to pre-preparation). At the same time, the system detects a surge in motor torque without an increase in vehicle speed, judging it as severe slippage, and automatically enters "creep escape mode," limiting the motor torque to the rated value and instructing the left rear wheel braking system to perform intermittent braking, allowing the vehicle to successfully drive out of the mud.

[0031] 4. Smart unlocking: After the vehicle drives onto a solid surface: Visual system report: 10 meters of continuous dry hard surface, 99% confidence level.

[0032] Wheel speed difference: Reduced to below 3km / h and stabilized for more than 5 seconds.

[0033] Steering wheel angle: close to 0 degrees.

[0034] The ECU calculated that the confidence level for safe unlocking reached 98%, and thus smoothly released the differential lock. The system was reset and monitoring resumed. Example 2

[0035] This embodiment provides a predictive control system for a commercial vehicle intelligent differential lock to implement the commercial vehicle differential lock control method described in Embodiment 1, including: The multi-source information perception module is used to collect images and point cloud data of the road environment in front of commercial vehicles in real time, and to process the collected images and point cloud data through deep learning algorithms to generate a digital road surface adhesion map that includes potential skidding risk areas and estimated adhesion coefficients of potential skidding risk areas. The path prediction and pre-lock decision module is used to predict the driving path of the commercial vehicle within a set time in the future based on the road adhesion map, current vehicle speed and steering wheel angle. When the predicted driving path intersects with a potential slip risk area, the module automatically generates a pre-lock or preparation command for the differential lock before the commercial vehicle enters the potential slip risk area. The adaptive precision locking module is used to fully lock the differential lock when a commercial vehicle enters a potential slip risk area and the drive wheel slip rate is detected to exceed a set threshold. The multi-factor intelligent unlocking module is used to calculate the confidence level of safe unlocking based on a multi-factor decision model after the differential lock is locked. When the confidence level of safe unlocking exceeds a set threshold, the differential lock is unlocked.

[0036] Specifically, such as Figure 4 and Figure 5 As shown, the system includes: Perception layer: Multi-sensor fusion module, with at least one camera and at least one millimeter-wave radar, for collecting environmental data; vehicle status sensors (wheel speed, steering wheel angle, IMU, etc.) for collecting vehicle speed, wheel speed, steering wheel angle and drive motor torque signals.

[0037] Decision layer: High-performance ECU (central controller) with embedded core algorithms such as road condition recognition, path prediction, and multi-factor decision-making. It is configured to run road condition recognition and modeling algorithms, path prediction algorithms, and multi-factor weighted decision-making algorithms, and generate differential lock control commands accordingly.

[0038] Execution layer: Fast-response electronic and pneumatic differential lock actuator, used to receive the control commands and drive the differential lock to perform locking or unlocking actions.

[0039] The intelligent decision-making central controller communicates with other domain controllers in the vehicle via CAN bus or Ethernet and integrates navigation path information to assist in long-distance path prediction. Example 3

[0040] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the commercial vehicle differential lock control method described in Embodiment 1. Example 4

[0041] This embodiment provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the commercial vehicle differential lock control method described in Embodiment 1.

[0042] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0043] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0044] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0045] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0046] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for controlling a differential lock in a commercial vehicle, characterized in that, include: Real-time acquisition of images and point cloud data of the road environment in front of commercial vehicles, and processing of the acquired images and point cloud data through deep learning algorithms to generate a digital road surface adhesion map containing potential skidding risk areas and estimated adhesion coefficients of potential skidding risk areas. Based on the road adhesion map, current vehicle speed and steering wheel angle, the driving path of the commercial vehicle is predicted within a set time in the future. When the predicted driving path intersects with a potential slippage risk area, a pre-locking or preparation command for the differential lock is automatically generated before the commercial vehicle enters the potential slippage risk area. When a commercial vehicle enters a potential slippage risk area and the drive wheel slip rate is detected to exceed a set threshold, the differential lock is fully engaged. After the differential lock is locked, the confidence level for safe unlocking is calculated based on a multi-factor decision model. When the confidence level for safe unlocking exceeds a set threshold, the differential lock is unlocked.

2. The commercial vehicle differential lock control method according to claim 1, characterized in that, Real-time acquisition of images and point cloud data of the road environment in front of commercial vehicles is achieved through vehicle-mounted cameras and millimeter-wave radar.

3. The commercial vehicle differential lock control method according to claim 1, characterized in that, The acquired image and point cloud data are processed using deep learning algorithms, including: Pixel-level semantic segmentation of the acquired images and point cloud data is performed using deep learning algorithms to identify road surface types and local risk features.

4. The commercial vehicle differential lock control method according to claim 1, characterized in that, Automatically generate differential lock pre-locking or preparation commands, including: Send a pre-activation signal that is not fully locked to the differential lock actuator, causing the differential lock actuator to enter a low-power standby state.

5. The commercial vehicle differential lock control method according to claim 1, characterized in that, The multi-factor decision model is based on multiple factors including road condition confidence, wheel speed difference stability, and steering wheel angle.

6. The commercial vehicle differential lock control method according to claim 1, characterized in that, Also includes: When the differential lock is fully engaged and a commercial vehicle is detected to be in a state of severe slippage, the peak output torque of the drive motor is limited and intermittent braking force is applied to the slipping wheels.

7. A predictive control system for intelligent differential locks in commercial vehicles, characterized in that, include: The multi-source information perception module is used to collect images and point cloud data of the road environment in front of commercial vehicles in real time, and to process the collected images and point cloud data through deep learning algorithms to generate a digital road surface adhesion map that includes potential skidding risk areas and estimated adhesion coefficients of potential skidding risk areas. The path prediction and pre-lock decision module is used to predict the driving path of the commercial vehicle within a set time in the future based on the road adhesion map, current vehicle speed and steering wheel angle. When the predicted driving path intersects with a potential slip risk area, the module automatically generates a pre-lock or preparation command for the differential lock before the commercial vehicle enters the potential slip risk area. The adaptive precision locking module is used to fully lock the differential lock when a commercial vehicle enters a potential slip risk area and the drive wheel slip rate is detected to exceed a set threshold. The multi-factor intelligent unlocking module is used to calculate the confidence level of safe unlocking based on a multi-factor decision model after the differential lock is locked. When the confidence level of safe unlocking exceeds a set threshold, the differential lock is unlocked.

8. 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 commercial vehicle differential lock control method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the commercial vehicle differential lock control method according to any one of claims 1 to 6.

Images