Intelligent monitoring method and device for tire wear of autonomous vehicle

Abstract

The invention discloses an intelligent monitoring method and device for tire wear of an automatic driving vehicle. The method comprises the steps that road environment data, driving behavior data and tire data are collected through a vehicle sensor; building tire loss characteristics according to the road environment data, the driving behavior data and the tire data; judging whether the road environment data or the driving behavior data is changed or not, and if yes, obtaining the running time of the vehicle under the tire loss characteristics; and obtaining a tire loss value through a preset loss model according to the tire loss characteristics and the running time. Therefore, when the road environment data or the driving behavior data of the vehicle change in the driving process, the corresponding tire loss value is obtained through the loss model according to the tire loss characteristics and the running time of the vehicle in the unchanged tire loss characteristics, so that the tire loss can be accurately evaluated after the vehicle passes through the road section.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and particularly to an intelligent monitoring method and device for tire wear of autonomous driving vehicles. Background Art

[0002] The safe operation of tires is one of the core keys to ensuring the safe driving of vehicles. In traditional manual driving scenarios, the tire status of vehicles is usually judged by manual inspection. However, it is difficult for autonomous driving vehicles to effectively inspect the tire status before driving due to no one operating. At the same time, the wear of tires is closely related to the road type, environmental conditions, driving behavior data, etc. of vehicle driving. Monitoring methods such as traditional tire pressure monitoring systems (TPMS) cannot comprehensively consider these factors. Summary of the Invention

[0003] The technical problem to be solved by the present invention is: to provide an intelligent monitoring method and device for tire wear of autonomous driving vehicles, and to realize real-time analysis and prediction of tire wear.

[0004] In order to solve the above technical problem, the technical solution adopted by the present invention is: An intelligent monitoring method for tire wear of autonomous driving vehicles, comprising: Collecting road environment data, driving behavior data and tire data through vehicle sensors; Constructing tire wear characteristics according to the road environment data, driving behavior data and tire data; Judging whether the road environment data or the driving behavior data changes. If so, obtaining the running time of the vehicle under the tire wear characteristics; Obtaining a tire wear value according to the tire wear characteristics and the running time through a preset wear model.

[0005] In order to solve the above technical problem, another technical solution adopted by the present invention is: An intelligent monitoring device for tire wear of autonomous driving vehicles, comprising a memory, a processor and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, each step in the above-mentioned intelligent monitoring method for tire wear of autonomous driving vehicles is realized.

[0006] The beneficial effects of the present invention are as follows: By collecting road environment data information, driving behavior data, and tire data during vehicle driving, and constructing the collected data into tire wear characteristics; when the road environment data or driving behavior data changes during vehicle driving, it indicates that the driving process has changed significantly. At this time, the corresponding tire wear value is obtained through the wear model according to the tire wear characteristics and the running time of the vehicle in the unchanged tire wear characteristics, so as to achieve an accurate assessment of tire wear after the vehicle has passed through a section of the road. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a flowchart of the steps of an intelligent monitoring method for tire wear of an autonomous vehicle in an embodiment of the present invention; Figure 2 is another flowchart of the steps of an intelligent monitoring method for tire wear of an autonomous vehicle in an embodiment of the present invention; Figure 3 is a schematic structural diagram of an intelligent monitoring device for tire wear of an autonomous vehicle in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0008] To describe in detail the technical content, achieved objectives, and effects of the present invention, the following is described in conjunction with the embodiments and with reference to the accompanying drawings.

[0009] An intelligent monitoring method for tire wear of an autonomous vehicle includes: Collecting road environment data, driving behavior data, and tire data through vehicle sensors; Constructing tire wear characteristics according to the road environment data, driving behavior data, and tire data; Judging whether the road environment data or driving behavior data changes. If so, obtaining the running time of the vehicle under the tire wear characteristics; Obtaining the tire wear value through a preset wear model according to the tire wear characteristics and the running time.

[0010] As can be seen from the above description, the beneficial effects of the present invention are as follows: By collecting road environment data information, driving behavior data, and tire data during vehicle driving, and constructing the collected data into tire wear characteristics; when the road environment data or driving behavior data changes during vehicle driving, it indicates that the driving process has changed significantly. At this time, the corresponding tire wear value is obtained through the wear model according to the tire wear characteristics and the running time of the vehicle in the unchanged tire wear characteristics, so as to achieve an accurate assessment of tire wear after the vehicle has passed through a section of the road.

[0011] Furthermore, it further includes: Obtaining the target driving section at a preset distance after the current driving path through the navigation system; Obtain the target road section data corresponding to the target driving road section, and the historical road section data related to the target driving road section; Predict the predicted tire wear corresponding to the target driving road section based on the target road section data and the historical road section data.

[0012] As can be seen from the above description, after obtaining the target driving road section that the vehicle is about to drive through the navigation system, by obtaining the target road section data corresponding to the target driving road section and the relevant historical road section data, the corresponding predicted tire wear can be accurately predicted based on the target road section data and the historical road section data.

[0013] Further, after obtaining the predicted tire wear corresponding to the target driving road section, it further includes: Optimize the driving behavior data according to the predicted tire wear.

[0014] As can be seen from the above description, by optimizing the driving behavior data after obtaining the predicted tire wear corresponding to the target driving road section that the vehicle is about to drive, for example, when entering a low-wear road section, appropriately increase the vehicle speed to improve the driving efficiency; while in a high-wear road section, reduce the vehicle speed to reduce wear, so as to realize optimizing the vehicle's driving strategy by using the wear prediction result.

[0015] Further, it further includes: Obtain at least two different to-be-driven road sections after the current driving path through the navigation system; Predict the predicted tire wear corresponding to all the to-be-driven road sections respectively; Take the to-be-driven road section with the lowest predicted tire wear as the target driving road section.

[0016] As can be seen from the above description, after obtaining multiple selectable to-be-driven road sections through the navigation system, predict the predicted tire wear corresponding to each to-be-driven road section respectively, and select the to-be-driven road section with the lowest predicted tire wear as the target driving road section, so as to realize optimizing the path selection by using the wear prediction result, thereby reducing the wear of the tires during driving.

[0017] Further, it further includes: Obtain the tire status inspection data after the vehicle is driven; Compare the tire status inspection data with the tire wear value to obtain a comparison result; Optimize the wear model according to the comparison result.

[0018] As can be seen from the above description, by obtaining the tire status inspection data after the vehicle is driven and optimizing the wear model according to the comparison result between the tire status inspection data and the tire wear value, the accuracy of the wear model in subsequent prediction tasks can be improved.

[0019] Further, the road environment data is collected by a lidar and a camera, expressed as: X road = [R(t), S(t)]; wherein, X road represents the road environment data, R(t) represents the road surface type, and S(t) represents the road condition characteristics.

[0020] Further, the acceleration, braking intensity, and turning angle are obtained by a vehicle electronic control unit as the driving behavior data, expressed as: X drive = [A(t), B(t), θ(t)]; wherein, X drive represents the driving behavior data, the acceleration is A(t), the braking intensity is B(t), and the turning angle is .

[0021] Further, the tire pressure, temperature, and vibration characteristics are obtained from a wheel hub sensor and a tire pressure monitoring system as the tire data, expressed as: X tire = [P(t), T(t), V(t)]; wherein, the tire data is X tire , the tire pressure is P(t), the temperature is T(t), and the vibration characteristics are V(t).

[0022] Further, the obtaining of the tire wear value according to the tire wear characteristics and the running time through a preset loss model includes: Predicting the tire wear during each driving process:

[0023] wherein, represents the running time of the target section; then the total tire wear is expressed as:

[0024] wherein, D(t) represents the tire wear characteristics, which is the degree of tire wear per unit time; H new represents the updated tire health score, and H old represents the tire health score before update.

[0025] Another embodiment of the present invention provides an intelligent monitoring device for tire wear of an autonomous vehicle, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, each step in the above-mentioned intelligent monitoring method for tire wear of an autonomous vehicle is implemented.

[0026] The intelligent monitoring method and device for tire wear of autonomous vehicles provided by the present invention can be applied to the control scenarios of autonomous vehicles, which will be described below through specific embodiments: Currently, autonomous vehicles are equipped with a rich variety of sensors. Through these sensors, the vehicle can fully understand the state of road environment data, which makes it possible to accurately analyze tire wear. By collecting multi-modal environmental information and dynamic response data during vehicle driving, the tire wear can be accurately estimated, and the tire health status model can be updated after each driving and synchronized with the cloud. At the same time, during vehicle driving, according to the planned path of the next vehicle driving combined with historical data and real-time feedback, the tire wear prediction can be further corrected, providing a decision-making basis for optimizing driving strategies and vehicle maintenance. The specific embodiments are as follows: Embodiment 1 Please refer to Figure 1 and Figure 2 , an intelligent monitoring method for tire wear of autonomous vehicles, including: S1. Collect road environment data, driving behavior data, and tire data through vehicle sensors; for example, for road environment data, identify road surface types such as asphalt, sand, gravel, etc., and road condition characteristics such as wet, potholed, etc. through lidar and cameras, which is expressed as: X road =[R(t), S(t)]; wherein, R(t) represents the road surface type, and S(t) represents the road condition characteristics.

[0027] For driving behavior data, obtain information such as acceleration A(t), braking intensity B(t), and turning angle etc. through the vehicle ECU (Electronic Control Unit) as driving behavior data, which is expressed as: X drive =[A(t), B(t), θ(t)].

[0028] For tire data, obtain information such as tire pressure P(t), temperature T(t), and vibration characteristics V(t) from the wheel hub sensor and tire pressure monitoring system as tire data, which is expressed as: X tire =[P(t), T(t), V(t)].

[0029] S2. Construct tire wear characteristics based on the road environment data, driving behavior data, and tire data; for example, if the tire wear characteristics are represented in the form of a vector, then we get: X total =[X road , Xdrive , X tire ; And use a loss model f based on deep learning loss to predict tire wear, expressed as: D(t) = f loss (X total ); where D(t) represents the degree of tire wear per unit time.

[0030] S3. Determine whether the road environment data or driving behavior data has changed. If so, obtain the running time of the vehicle under the tire wear characteristics. That is, during the vehicle driving process, the system will dynamically update the wear prediction model according to real-time data. When it detects road surface changes such as transitioning from an asphalt road surface to sandy or gravel, or driving behavior changes such as changing from going straight to turning, or the vehicle speed input exceeds the change threshold, such as the vehicle speed changes by more than ±10 km / h within a short time during stable driving, indicating that there is an acceleration or deceleration change in the vehicle currently. At this time, obtain the duration T of the tire wear characteristics drive , that is, the duration of the vehicle in the previous road environment data and driving behavior, and then evaluate the tire wear during the duration based on the duration and tire wear characteristics. At the same time, generate new tire wear characteristics according to the changed road environment data or driving behavior data for predicting and calculating the tire wear in the next duration.

[0031] S4. Obtain the tire wear value according to the tire wear characteristics and running time through a preset loss model. For example, by combining the current driving behavior and road surface type with historical data, predict the tire wear in each driving process:

[0032] where represents the running time of the target section; then the total tire wear is expressed as:

[0033] where D(t) represents the tire wear characteristics, which is the degree of tire wear per unit time; H new represents the updated tire health score, H oldIndicates the tire health score before the update. In actual applications, when a new tire is replaced, the initial state parameters of the tire are recorded and the system is adaptively calibrated to ensure the accuracy of the basic evaluation model. For example, it includes recording core data such as tire pressure, temperature, tread thickness, and wear amount. The initial calibration also involves measuring vehicle dynamic parameters such as vehicle load and steering sensitivity, and enabling the evaluation system to have high-precision state monitoring capabilities through adaptive calibration methods. At the same time, a tire state acquisition and dynamic wear evaluation system is constructed for autonomous vehicles, that is, the tire wear during each driving process and the total tire wear are predicted through the above wear model. And during the model prediction process, it is judged whether the tire wear estimation system is operating normally. When the tire wear estimation system is abnormal, a maintenance alarm is triggered, and the abnormal source is located through multi-dimensional log analysis and dynamic adjustment is implemented.

[0034] When the tire wear estimation system is operating normally, a combination of model scenarios and field tests is used to verify the robustness of the system. For example, the simulation scenario test includes complex road conditions and obstacle settings such as potholes and slippery roads, and the field test focuses on the authenticity of dynamic data and the accuracy of sensors to evaluate the reliability of the system. Further, when the evaluated tire wear data is normal, the model is combined with the driving path and historical data to achieve real-time evaluation of tire wear. When the evaluated tire wear data is abnormal, a comprehensive diagnosis of the system operation log is performed, the sensor status and the data collected by it are checked, and whether there are abnormal deviations in the data is analyzed. For the detected abnormal data, precise correction and optimization are implemented.

[0035] After the vehicle has completed driving, obtain the tire state inspection data after the vehicle has driven, such as wear amount, pressure change, etc. data; then compare the tire state inspection data with the tire wear value to obtain a comparison result, and optimize the wear model according to the comparison result:

[0036] Among them, is a correction factor. At the same time, during driving, tire state data is collected in real time, and the wear model is dynamically adjusted to improve the real-time prediction ability. And the accumulated driving history data is used to regularly train the wear model to enhance the generalization ability of the model.

[0037] In an optional implementation manner, during the driving of the vehicle, the target driving section at a preset distance after the current driving path is also obtained through the navigation system, and the target section data corresponding to the target driving section and the historical section data related to the target driving section are obtained; then the predicted tire wear corresponding to the target driving section is predicted according to the target section data and the historical section data; that is, the system will predict the tire wear D of the future section according to the real-time navigation data next; For example, if the target road segment data includes road segment types R such as asphalt, sand, gravel, etc., road condition features V such as slope, congestion, traffic lights, and driving behavior B such as turning angle, etc., then we get:

[0038] Among them, is the path loss of the i-th predicted path, is the type and state of the i-th road surface, is the road condition feature of the i-th road segment, B i is the driving behavior of the i-th segment.

[0039] By integrating the predictions of each segment, the total predicted loss is obtained:

[0040] In another alternative implementation, it further includes obtaining at least two different to-be-driven road segments after the current driving path through a navigation system, and respectively predicting the predicted tire losses corresponding to all the to-be-driven road segments, and then taking the to-be-driven road segment with the lowest predicted tire loss as the target driving road segment. The specific formula is expressed as:

[0041] Among them, is the optimized path, is the set of all feasible paths, R j , V j , B j are the road surface type, road condition feature, and driving behavior of each segment on the path.

[0042] Meanwhile, after obtaining the predicted tire loss corresponding to the target driving road segment, the driving behavior data is further optimized according to the predicted tire loss. The specific driving strategy optimization is as follows: (1) Acceleration optimization: For example, when it is predicted that the vehicle is about to enter a low-loss road segment such as a flat asphalt road surface, the vehicle speed V can be appropriately increased to improve the driving efficiency; on the contrary, when in a high-loss road segment such as sand or gravel, the vehicle speed is reduced to reduce wear:

[0043] Among them, is the optimized vehicle speed.

[0044] (2) Braking optimization: When it is predicted that there is congestion or a traffic light section, the system reduces tire wear by gently braking in advance instead of braking suddenly, and adjusts the braking intensity to optimize the loss:

[0045] Among them, is the optimized braking strength.

[0046] (3) Turn optimization: On the turning section, by reducing the speed during turning and optimizing the steering angle , reduce the wear of the tire caused by the lateral force:

[0047] Among them, the optimized steering angle, the optimized vehicle speed during turning, the driving behavior during turning.

[0048] Embodiment 2 Please refer to Figure 3 , an intelligent monitoring device for tire wear of an autonomous vehicle, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: S1. Collect road environment data, driving behavior data, and tire data through vehicle sensors; S2. Construct tire wear characteristics based on the road environment data, driving behavior data, and tire data; S3. Determine whether the road environment data or driving behavior data changes. If so, obtain the running time of the vehicle under the tire wear characteristics; S4. Obtain the tire wear value according to the tire wear characteristics and the running time through a preset wear model. After the vehicle completes driving, the tire status inspection data after vehicle driving is also obtained, and after comparing the tire status inspection data with the tire wear value to obtain a comparison result, the wear model is optimized according to the comparison result.

[0049] At the same time, during the driving of the vehicle, the target driving section at a preset distance after the current driving path is also obtained through the navigation system, and the target section data corresponding to the target driving section, as well as the historical section data related to the target driving section, are obtained; then the predicted tire wear corresponding to the target driving section is predicted according to the target section data and the historical section data. Further, the driving behavior data can be optimized according to the predicted tire wear.

[0050] Among them, after obtaining at least two different sections to be driven after the current driving path through the navigation system, the predicted tire wear corresponding to all the sections to be driven can be predicted respectively, and the section to be driven with the lowest predicted tire wear is used as the target driving section.

[0051] In summary, the intelligent monitoring method and device for tire wear of the autonomous driving vehicle provided by the present invention evaluate the tire wear by combining road environment, driving behavior and tire status data, and update the wear model after driving to improve the accuracy of tire wear evaluation and prediction. Moreover, the autonomous driving vehicle can dynamically evaluate the operating status of the vehicle tires, and then combine information such as the planned travel road conditions to accurately evaluate whether the vehicle tires are competent for the travel task, and optimize the path selection and driving strategy by using the wear prediction results during driving, reduce the tire wear and maintenance costs, so as to comprehensively improve the perception and management ability of the autonomous driving vehicle for the tire status, enhance the driving safety and extend the service life of the tires.

[0052] The above are only the embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in the relevant technical fields, shall be included in the patent protection scope of the present invention by the same token.

Claims

1. An intelligent monitoring method for tire wear of an autonomous driving vehicle, characterized in that: include: Collect road environment data, driving behavior data and tire data through vehicle sensors; Constructing tire wear characteristics according to the road environment data, driving behavior data and tire data; Determine whether the road environment data or driving behavior data has changed, and if so, obtain the running time of the vehicle under the tire wear characteristics; Obtaining a tire wear value according to the tire wear characteristics and the operating time through a preset wear model; The method of obtaining the tire wear value according to the tire wear characteristics and the running time by using a preset wear model includes: Predict tire wear during each driving session: in, Indicates the target road section running time; The total tire loss is expressed as: Where D(t) represents the tire wear characteristic, which is the degree of tire wear per unit time; H new Represents the updated tire health score, H old Indicates the tire health score before updating.

2. The method for intelligent tire wear monitoring of an autonomous driving vehicle according to claim 1, characterized in that: Also includes: Obtaining a target driving section of a preset distance after the current driving route through a navigation system; Acquire target section data corresponding to the target driving section, and historical section data related to the target driving section; The predicted tire loss corresponding to the target driving section is predicted based on the target section data and the historical section data.

3. The method for intelligent tire wear monitoring of an autonomous driving vehicle according to claim 2, characterized in that: After obtaining the predicted tire loss corresponding to the target driving section, the following step further includes: The driving behavior data is optimized based on the predicted tire wear.

4. The method for intelligently monitoring tire wear of an autonomous driving vehicle according to claim 2, characterized in that: Also includes: Obtaining at least two different sections of road to be traveled after the current travel route through the navigation system; Respectively predicting the predicted tire wear corresponding to all the road sections to be traveled; The road section to be traveled with the lowest predicted tire loss is used as the target travel section.

5. The method for intelligently monitoring tire wear of an autonomous driving vehicle according to claim 1, characterized in that: Also includes: Obtain tire status inspection data after driving the vehicle; Comparing the tire status inspection data with the tire wear value to obtain a comparison result; The loss model is optimized according to the comparison result.

6. The method for intelligently monitoring tire wear of an autonomous driving vehicle according to claim 1, characterized in that: The collecting of road environment data by vehicle sensors includes: The road environment data is collected by laser radar and camera, which is expressed as: X road =[R(t),S(t)]; Among them, X road Represents road environment data and is stored in array form; R(t) represents the road surface type, and S(t) represents the road condition characteristics.

7. The method for intelligently monitoring tire wear of an autonomous driving vehicle according to claim 1, characterized in that: The collecting of road environment data by vehicle sensors includes: The acceleration, braking intensity, and turning angle are obtained through the vehicle electronic control unit as the driving behavior data, which is expressed as: X drive =[A(t),B(t),θ(t)]; Among them, X drive Represents driving behavior data and is stored in an array; the acceleration is A(t), the braking intensity is B(t), and the turning angle is .

8. The method for intelligently monitoring tire wear of an autonomous driving vehicle according to claim 1, characterized in that: The collecting of road environment data by vehicle sensors includes: The tire pressure, temperature and vibration characteristics are obtained from the wheel hub sensor and the tire pressure monitoring system as the tire data, which is expressed as: X tire =[P(t),T(t),V(t)]; Among them, X tire is tire data and is stored in array form; tire pressure is P(t), temperature is T(t), and vibration characteristics is V(t).

9. An intelligent tire wear monitoring device for an autonomous driving vehicle, 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 computer program, each step of the method for intelligent monitoring of tire wear of an autonomous driving vehicle as described in any one of claims 1-8 is implemented.

Images