Off-road driving mode adaptive adjustment method and system based on intelligent tire sensing

Abstract

The application provides an off-road driving mode adaptive adjustment method and system based on intelligent tire sensing, and belongs to the technical field of vehicle engineering. The application installs a tactile sensor in a tire, collects three-axis acceleration data in real time, and after pre-processing, feature extraction and road condition type identification by a data processing unit, a driving mode controller maps the road condition type to a corresponding driving mode and generates a control instruction, a vehicle control system dynamically adjusts engine / motor output, gearbox gear, suspension system and tire air pressure and other parameters accordingly, and a user interface displays relevant information and supports manual intervention. The application adopts the above-mentioned off-road driving mode adaptive adjustment method and system based on intelligent tire sensing, can monitor the dynamic characteristics of the tire and the road condition in real time, can quickly identify complex road conditions, can automatically switch the driving mode, can improve the driving safety, and can optimize the driving performance.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicle engineering, and particularly to an off-road driving mode adaptive adjustment method and system based on intelligent tire sensing. BACKGROUND

[0002] When off-road vehicles travel in complex and variable road conditions, such as mud, sand, rocks, ice and snow, etc., the driving mode needs to be adjusted according to different road conditions to optimize the passability and maneuverability of the vehicle. Traditional driving mode adjustment usually relies on the experience of the driver to manually switch, or through the electronic control system of the vehicle to make limited automatic adjustment according to the preset sensor data.

[0003] However, these methods have the following shortcomings:

[0004] (1) Limitations of manual switching: the driver may not be able to accurately judge the current road conditions in time, resulting in delayed or inaccurate driving mode switching.

[0005] (2) Deficiencies of existing automatic adjustment systems: traditional automatic adjustment systems usually rely on the vehicle's suspension sensors, steering angle sensors, etc., and cannot directly sense the contact state and dynamic characteristics of the tires and road conditions, with limited adjustment accuracy and adaptability.

[0006] (3) Lack of real-time feedback: existing systems cannot monitor the dynamic changes of the tires (such as tire pressure, tire wear, tire slip, etc.) in real time, making it difficult to respond quickly to unexpected situations. SUMMARY

[0007] The purpose of the present application is to provide an off-road driving mode adaptive adjustment method and system based on intelligent tire sensing, which automatically identifies the current road conditions by monitoring the acceleration signals of the tires in real time, in combination with the driving state of the vehicle, and automatically switches the driving mode according to the road conditions, optimizing the driving performance and safety of the vehicle.

[0008] To achieve the above purpose, the present application provides an off-road driving mode adaptive adjustment system based on intelligent tire sensing, comprising:

[0009] A data acquisition module including tactile sensors installed inside the tires for real-time acquisition of three-axis acceleration data of the tires, including longitudinal, lateral and vertical acceleration;

[0010] A data processing unit connected to the tactile sensors for pre-processing, feature extraction and road condition type identification of the acceleration data;

[0011] A driving mode controller that maps to the corresponding driving mode and generates control instructions according to the road condition type output by the data processing unit;

[0012] Vehicle control system, executing control instructions, dynamically adjusting engine / motor output, transmission gear, suspension system and tire pressure;

[0013] User interface, displaying current road condition type, driving mode and adjustment parameters, and supporting user manual intervention mode switching.

[0014] Preferably, the data processing unit comprises:

[0015] Data preprocessing module, low-pass filtering, normalizing and time synchronizing acceleration data;

[0016] Feature extraction module, extracting peak value, mean value, variance, frequency distribution and correlation of acceleration signals in different directions;

[0017] Road condition type identification module, classifying the extracted features based on machine learning model to identify different road conditions.

[0018] Preferably, the feature extraction module further calculates: tire slip ratio, tire side slip angle, road surface friction coefficient, road surface roughness.

[0019] Preferably, the driving mode controller comprises:

[0020] Road condition type and driving mode mapping module, defining the correspondence between road condition type and driving mode;

[0021] Mode switching logic module, ensuring smooth transition of vehicle parameters during mode switching, and user manual mode priority higher than automatic switching.

[0022] Preferably, the correspondence between road condition type and driving mode includes:

[0023] Muddy road condition is mapped to muddy mode, adjustment parameters include: engine / motor output is reduced to 60% of maximum torque, transmission is switched to 1st gear, suspension travel is increased to 80% of maximum travel, tire pressure is reduced to 80% of standard pressure;

[0024] Sand road condition is mapped to sand mode, adjustment parameters include: engine / motor output is maintained to 70% of maximum torque, transmission is switched to 1st gear, suspension travel is increased to 70% of maximum travel, tire pressure is reduced to 60% of standard pressure;

[0025] Rocky road condition is mapped to rocky mode, adjustment parameters include: engine / motor output is increased to 90% of maximum torque, transmission is switched to 1st gear, suspension travel is increased to 90% of maximum travel, tire pressure is maintained to 70% of standard pressure;

[0026] Ice / snow road condition is mapped to ice / snow mode, and the adjustment parameters include: engine / motor output is reduced to 50% of maximum torque, gearbox is switched to 1st gear, suspension stroke is increased to 80% of maximum stroke, and electronic stability system is enabled;

[0027] Normal road condition is mapped to normal mode, and the adjustment parameters include: engine / motor output is maintained to 80% of maximum torque, gearbox is switched to automatic gear mode, suspension system is adjusted to comfort mode, and tire air pressure is maintained to standard air pressure.

[0028] The application also provides an off-road driving mode adaptive adjustment method based on intelligent tire sensing, comprising the following steps:

[0029] The data acquisition module acquires real-time three-axis acceleration data through the internal tactile sensor of the tire;

[0030] The data preprocessing module performs filtering, normalization and time synchronization processing on the acceleration data;

[0031] The feature extraction module extracts acceleration features and further calculates tire slip ratio, tire side slip angle, road surface friction coefficient, road surface roughness, and a road condition type recognition module identifies the road condition type based on a machine learning model;

[0032] The driving mode controller switches to the corresponding driving mode according to the road condition type according to the mapping relationship, and dynamically adjusts the engine output, gearbox gear, suspension system and tire air pressure through the vehicle control system;

[0033] The current road condition type, driving mode and adjustment parameters are fed back through the user interface, and the user is allowed to manually intervene.

[0034] Preferably, the slip ratio calculation formula is as follows:

[0035] ;

[0036] wherein, represents the actual speed of the vehicle, represents the linear speed of the tire.

[0037] Preferably, the side slip angle calculation formula is as follows:

[0038] ;

[0039] wherein, represents the side slip angle, represents the lateral acceleration of the tire.

[0040] Preferably, the sampling frequency of the tactile sensor of the data acquisition module is at least 1000 Hz, and the collected acceleration signals are sent to the data processing unit of the vehicle through wireless transmission technology.

[0041] Preferably, the user interface is also used to receive user feedback on the suitability of the current driving mode, the system optimizes the mode switching logic based on user feedback, and provides a system optimization upgrade interface for regular updates of the machine learning model.

[0042] Therefore, the present application adopts the above-mentioned off-road driving mode adaptive adjustment method and system based on intelligent tire sensing, and has the following beneficial technical effects:

[0043] (1) Improve driving safety: By real-time monitoring of the dynamic characteristics of the tire and the road conditions, the present application can quickly identify potential dangerous road conditions and automatically switch to the most suitable driving mode, significantly improving the driving safety of the vehicle in complex road conditions.

[0044] (2) Optimize driving performance: Automatically adjust the engine / motor output, suspension system, tire pressure and other parameters of the vehicle according to different road conditions, optimize the passability and handling of the vehicle, and improve the driving experience.

[0045] (3) Reduce the burden on the driver: Automatic driving mode switching reduces the operational burden on the driver, especially in complex and variable off-road conditions, improving the convenience and comfort of driving.

[0046] (4) Enhance system adaptability: Through machine learning algorithms and multi-sensor data fusion technology, the present application can adapt to a variety of complex road conditions and driving scenarios, with high robustness and adaptability. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 is a structural diagram of the off-road driving mode adaptive adjustment system based on intelligent tire sensing of the present application;

[0048] Figure 2 is a flowchart of the off-road driving mode adaptive adjustment method based on intelligent tire sensing of the present application. DETAILED DESCRIPTION

[0049] The technical solutions of the present application are further described below through the drawings and examples.

[0050] Unless otherwise defined, the technical terms or scientific terms used in the present application shall have their usual meanings understood by those skilled in the art to which the present application belongs.

[0051] Example 1

[0052] As shown in Figure 1 , the off-road driving mode adaptive adjustment system based on intelligent tire sensing includes:

[0053] (1) Data acquisition module, including tactile sensor (three-axis acceleration sensor, installation position is located in the center of the tire liner, one is installed in each tire) installed inside the tire, its core function is to collect real-time three-axis acceleration data of the tire, covering longitudinal, lateral and vertical acceleration information. In order to accurately capture the subtle dynamic changes of the tire under different road conditions, the sampling frequency is set to at least 1000Hz. The collected acceleration signal is transmitted in real time and stably to the vehicle's data processing unit through wireless transmission technology, ensuring the timeliness and accuracy of the data.

[0054] (2) Data processing unit, connected to the tactile sensor, used for pre-processing, feature extraction and road type recognition of acceleration data.

[0055] Specifically, the data processing unit includes:

[0056] Data preprocessing module, low-pass filtering, normalization and time synchronization of acceleration data;

[0057] Among them, the filter processing: the collected acceleration signal is low-pass filtered, the filter frequency is set to 400Hz, the high-frequency noise is removed, and the useful low-frequency signal is retained.

[0058] Normalization processing: normalize the acceleration signal to the range of -1 to 1.

[0059] Time synchronization: ensure the time synchronization of tactile sensor data and other vehicle sensors (such as speed sensor, steering angle sensor, etc.), with an error of less than 1ms.

[0060] Feature extraction module, extracting peak value, mean value, variance, frequency distribution and correlation of acceleration signals in different directions; the feature extraction module further calculates:

[0061] Tire slip ratio, the calculation formula is:

[0062] ;

[0063] Among them, represents the actual speed of the vehicle, represents the linear speed of the tire.

[0064] Tire side slip angle, the calculation formula is:

[0065] ;

[0066] Among them, represents the side slip angle, represents the lateral acceleration of the tire.

[0067] Road surface friction coefficient: By analyzing the longitudinal and lateral acceleration signals of the tire, combined with tire dynamics models (such as Magic Formula, Brush Model, UniTire Model, SWIFT Model, etc.), the road surface friction coefficient is estimated using the least squares method or Kalman filter algorithm.

[0068] Road roughness: By analyzing the frequency distribution and amplitude variation of the vertical acceleration signal of the tire, the characteristics of road roughness are extracted using the Fast Fourier Transform (FFT) algorithm. The power spectral density (PSD) and root mean square value (RMS) of road roughness are calculated.

[0069] Road condition type recognition module, based on machine learning models (LSTM, etc. Convolutional Neural Networks, other machine learning models such as Support Vector Machines), classifies the extracted features to identify different road conditions.

[0070] The above parameters can also use three-axis acceleration signals collected by sensors installed on the tire (such as three-axis acceleration sensors) as input data. By constructing a labeled data set (i.e. a data pair containing sensor signals and corresponding real parameter values), a machine learning model (such as a spatio-temporal convolutional neural network or a neural network embedded with physical constraints) can be trained to directly estimate tire slip ratio, side slip angle, road surface friction coefficient and road roughness. This data-driven approach aims to utilize the powerful feature extraction and nonlinear fitting capabilities of machine learning to complement or replace traditional physical model methods, improving the robustness and generalization ability of parameter estimation.

[0071] Road condition classification as shown in Table 1:

[0072] Table 1 Road condition classification

[0073] ;

[0074] Additional explanation: The typical value intervals listed in Table 1 are based on ISO 8608 and GB / T 7031 standards, and are preliminarily determined by combining large-scale road test data and manual annotation results. They can be used as a reference for the current stage; further verification and dynamic revision are still needed.

[0075] (3) Driving mode controller, according to the road condition type output by the data processing unit, maps to the corresponding driving mode and generates control instructions.

[0076] The driving mode controller includes:

[0077] Road condition type and driving mode mapping module, defines the correspondence between road condition type and driving mode, wherein:

[0078] Muddy road conditions map to Muddy mode, with parameters adjusted to include: engine / motor output reduced to 60% of maximum torque, transmission shifted to 1st gear, suspension travel increased to 80% of maximum travel, tire pressure reduced to 80% of standard pressure;

[0079] Sand road conditions map to Sand mode, with parameters adjusted to include: engine / motor output maintained at 70% of maximum torque, transmission shifted to 1st gear, suspension travel increased to 70% of maximum travel, tire pressure reduced to 60% of standard pressure;

[0080] Rocky road conditions map to Rocky mode, with parameters adjusted to include: engine / motor output increased to 90% of maximum torque, transmission shifted to 1st gear, suspension travel increased to 90% of maximum travel, tire pressure maintained at 70% of standard pressure;

[0081] Ice / snow road conditions map to Ice / snow mode, with parameters adjusted to include: engine / motor output reduced to 50% of maximum torque, transmission shifted to 1st gear, suspension travel increased to 80% of maximum travel, and electronic stability system enabled;

[0082] Normal road conditions map to Normal mode, with parameters adjusted to include: engine / motor output maintained at 80% of maximum torque, transmission shifted to automatic gear mode, suspension system adjusted to comfort mode, tire pressure maintained at standard pressure;

[0083] Mode switching logic module ensures smooth transition of vehicle parameters during mode switching, with user manual mode priority higher than automatic switching.

[0084] Smooth transition: During mode switching, the driving mode controller ensures smooth transition of vehicle parameters, avoiding discomfort to the vehicle and passengers. For example, the adjustment of engine / motor torque adopts gradual adjustment to avoid sudden changes.

[0085] (4) Vehicle control system, executing control instructions, dynamically adjusting engine / motor output, transmission gear, suspension system and tire pressure.

[0086] (5) User interface, for displaying current road condition type, driving mode and vehicle parameter adjustment information, allowing users to understand the vehicle status at any time. At the same time, users can feedback the applicability of the current driving mode through the interface, and the system optimizes the mode switching logic according to user feedback. In addition, a system optimization upgrade interface is provided to regularly update the machine learning model and optimize the road condition recognition algorithm and driving mode switching strategy according to new driving data.

[0087] Example Two

[0088] As Figure 2As shown, a cross-country driving mode adaptive adjustment method based on intelligent tire tactile perception includes the following steps:

[0089] The data acquisition module collects real-time three-axis acceleration data through the internal tactile sensor of the tire.

[0090] The data preprocessing module filters, normalizes and time synchronizes the acceleration data.

[0091] The feature extraction module extracts acceleration features and further calculates tire slip rate, tire side slip angle, road surface friction coefficient, road surface roughness, and road condition type recognition module based on machine learning model to identify road condition type.

[0092] The driving mode controller switches to the corresponding driving mode according to the mapping relationship based on the road condition type, and dynamically adjusts the engine output, gearbox gear, suspension system and tire pressure through the vehicle control system.

[0093] The user interface is used to display the current road condition type, driving mode and vehicle parameter adjustment information, so that the user can always know the vehicle state. At the same time, the user can feed back the applicability of the current driving mode through the interface, and the system optimizes the mode switching logic according to the user feedback. In addition, the system optimization upgrade interface is provided, and the machine learning model is updated regularly to optimize the road condition recognition algorithm and driving mode switching strategy according to new driving data.

[0094] It is worth noting that the contents not elaborated in the present application are all prior art and are well known to those skilled in the art.

[0095] Therefore, the present application adopts the above-mentioned cross-country driving mode adaptive adjustment method and system based on intelligent tire perception, which automatically identifies the current road condition by monitoring the acceleration signal of the tire in real time, and automatically switches the driving mode according to the road condition, thereby optimizing the driving performance and safety of the vehicle.

[0096] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application and not to limit them, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that: it can still modify or equivalently replace the technical solutions of the present application, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present application.

Claims

1. An off-road driving mode adaptive adjustment system based on intelligent tire sensing, characterized in that, include: The data acquisition module includes a tactile sensor installed inside the tire for real-time acquisition of the tire's triaxial acceleration data, including longitudinal, lateral, and vertical acceleration. The data processing unit, connected to the tactile sensor, is used for preprocessing acceleration data, feature extraction, and road condition type identification. The driving mode controller maps the road condition type output by the data processing unit to the corresponding driving mode and generates control commands. The vehicle control system executes control commands and dynamically adjusts engine / motor output, transmission gears, suspension system, and tire pressure. The user interface displays the current road condition type, driving mode, and adjustment parameters, and supports manual intervention in mode switching. The driving mode controller includes: The road condition type and driving mode mapping module defines the correspondence between road condition types and driving modes; The mode switching logic module ensures a smooth transition of vehicle parameters during mode switching, and the user's manual mode has a higher priority than automatic switching. The correspondence between road condition types and driving modes includes: The muddy road conditions are mapped to Mud Mode, and the adjusted parameters include: engine / motor output reduced to 60% of maximum torque, transmission switched to 1st gear, suspension travel increased to 80% of maximum travel, and tire pressure reduced to 80% of standard tire pressure; Sandy terrain is mapped to Sand Mode, with the following adjustments: engine / motor output is maintained at 70% of maximum torque, transmission is switched to 1st gear, suspension travel is increased to 70% of maximum travel, and tire pressure is reduced to 60% of standard tire pressure. Rock conditions are mapped to Rock Mode, with the following adjustments: engine / motor output increased to 90% of maximum torque, transmission switched to 1st gear, suspension travel increased to 90% of maximum travel, and tire pressure maintained at 70% of standard pressure. When mapping icy and snowy road conditions to Ice and Snow Mode, the parameters are adjusted as follows: engine / motor output is reduced to 50% of maximum torque, the transmission is switched to 1st gear, the suspension travel is increased to 80% of maximum travel, and the electronic stability system is activated. Normal road conditions are mapped to normal mode, and the adjusted parameters include: engine / motor output is maintained at 80% of maximum torque, the transmission is switched to automatic mode, the suspension system is adjusted to comfort mode, and the tire pressure is maintained at standard pressure.

2. The off-road driving mode adaptive adjustment system based on intelligent tire perception according to claim 1, characterized in that, The data processing unit includes: The data preprocessing module performs low-pass filtering, normalization, and time synchronization on the acceleration data; The feature extraction module extracts the peak value, mean, variance, frequency distribution, and correlation of acceleration in different directions of the acceleration signal. The road condition type identification module classifies extracted features based on a machine learning model to identify different road condition types.

3. The off-road driving mode adaptive adjustment system based on intelligent tire perception according to claim 2, characterized in that, The feature extraction module further calculates: tire slip ratio, tire slip angle, road friction coefficient, and road roughness.

4. An adaptive adjustment method for off-road driving modes based on intelligent tire perception, characterized in that, The off-road driving mode adaptive adjustment system based on intelligent tire sensing as described in any one of claims 1-3 includes the following steps: The data acquisition module collects triaxial acceleration data in real time through tactile sensors inside the tire; The data preprocessing module performs filtering, normalization, and time synchronization processing on the acceleration data; The feature extraction module extracts acceleration features and further calculates tire slip ratio, tire slip angle, road friction coefficient, and road roughness. The road condition type identification module identifies road condition types based on a machine learning model. The driving mode controller switches to the corresponding driving mode according to the road conditions and mapping relationship, and dynamically adjusts the engine output, transmission gear, suspension system and tire pressure through the vehicle control system. The user interface provides feedback on the current road condition type, driving mode, and adjustment parameters, and allows users to intervene manually.

5. The off-road driving mode adaptive adjustment method based on intelligent tire perception according to claim 4, characterized in that, The formula for calculating slip ratio is as follows: ； in, Indicates the vehicle's actual speed. This indicates the linear velocity of the tire.

6. The off-road driving mode adaptive adjustment method based on intelligent tire perception according to claim 4, characterized in that, The formula for calculating the sideslip angle is as follows: ； in, Indicates the sideslip angle. This indicates the lateral acceleration of the tire.

7. The off-road driving mode adaptive adjustment method based on intelligent tire perception according to claim 4, characterized in that, The tactile sensor of the data acquisition module has a sampling frequency of at least 1000Hz, and the acquired acceleration signal is transmitted to the vehicle's data processing unit via wireless transmission technology.

8. The off-road driving mode adaptive adjustment method based on intelligent tire perception according to claim 4, characterized in that, The user interface is also used to receive user feedback on the suitability of the current driving mode. The system optimizes the mode switching logic based on user feedback, provides a system optimization and upgrade interface, and updates the machine learning model regularly.

Images