Intelligent tire regulation and control method and system based on environmental perception

Abstract

The invention provides an intelligent tire regulation and control method and system based on environment perception, and belongs to the technical field of vehicle tires, and the method comprises the steps: collecting the real-time environment information of the environment where a vehicle is located in real time, and obtaining the real-time working parameters of the vehicle tires in real time; analyzing the real-time environment information and the real-time working parameters to determine a parameter feature vector and an optimal parameter vector of a vehicle tire and a real-time prediction risk category; determining a real-time regulation and control instruction of the vehicle tire based on the parameter feature vector, the optimal parameter vector and the real-time prediction risk category; and real-time working parameters of the vehicle tires are adjusted based on the real-time adjusting and controlling instruction, and intelligent adjusting and controlling of the vehicle tires are achieved. According to the method, the tire regulation and control precision and real-time performance can be improved, the hysteresis quality and limitation of a static regulation and control mode are avoided, the risk change in a complex environment is quickly responded, it is ensured that the tire is always in the optimal working state under the changeable driving environment, and an efficient and accurate parameter regulation and control solution is provided for the intelligent driving technology.

Description

Technical Field

[0001] The present invention relates to the field of vehicle tire technology, and in particular to an intelligent tire control method and system based on environmental perception. Background Art

[0002] With the rapid development of the automotive industry, intelligent driving and vehicle safety have become research focuses, and tires, as the only part of the vehicle in contact with the ground, play a key role in driving safety and stability. However, traditional tire control methods mainly rely on static design, which often lags behind or is not flexible enough when dealing with complex and dynamic driving environments.

[0003] In recent years, the development of sensor technology, the Internet of Things and data processing technology has made it possible for vehicles to perceive the environment and tire status in real time. For example, the tire pressure monitoring system (TPMS) can collect tire pressure data in real time, but its function is limited to alarm prompts and cannot perform further intelligent regulation.

[0004] Therefore, the present invention provides an intelligent tire control method and system based on environmental perception. Summary of the invention

[0005] The present invention provides an intelligent tire control method and system based on environmental perception, which determines the parameter feature vector, optimal parameter vector and real-time predicted risk category of the vehicle tire by analyzing the collected real-time environmental information and real-time working parameters, determines the real-time control instructions of the vehicle tire and executes them, and realizes the intelligent control of the vehicle tire. It can improve the accuracy and real-time performance of tire control, avoid the lag and limitations of static control methods, and quickly respond to risk changes in complex environments, ensuring that the tires are always in the best working state in a changeable driving environment, and providing an efficient and accurate parameter control solution for intelligent driving technology.

[0006] In one aspect, the present invention provides an intelligent tire control method based on environment perception, comprising: 101: real-time collection of real-time environmental information of the environment in which the vehicle is located, and real-time acquisition of real-time working parameters of the vehicle tires; 102: Analyze the real-time environmental information and the real-time working parameters to determine the parameter feature vector, the optimal parameter vector and the real-time prediction risk category of the vehicle tire; 103: Determine a real-time control instruction of a vehicle tire based on the parameter feature vector, the optimal parameter vector, and the real-time predicted risk category; 104: Adjust the real-time working parameters of the vehicle tires based on the real-time control instructions to achieve intelligent control of the vehicle tires.

[0007] According to an intelligent tire control method based on environment perception provided by the present invention, real-time environmental information of the environment in which the vehicle is located is collected in real time, and real-time working parameters of the vehicle tires are obtained in real time, including: Based on a first sensor group installed in the vehicle, real-time environmental information of the environment in which the vehicle is located within a specified time period is collected, wherein the real-time environmental information includes real-time road information and real-time climate information; The real-time operating parameters of the vehicle tires within a specified time period are collected based on a second sensor group installed on the vehicle, wherein the real-time operating parameters include vehicle driving parameters and vehicle tire parameters.

[0008] According to an intelligent tire control method based on environmental perception provided by the present invention, real-time environmental information and real-time working parameters are analyzed to determine parameter feature vectors and optimal parameter vectors of vehicle tires, including: Preprocess the real-time environmental information and real-time working parameters respectively; Extracting features of the real-time road surface information in the preprocessed real-time environmental information, determining a road surface feature vector, and determining a road surface category during vehicle driving based on the road surface feature vector and a road surface mapping table; Extracting features of the real-time climate information in the preprocessed real-time environmental information, determining a climate feature vector, and determining a climate category during vehicle driving based on the climate feature vector and a climate mapping table; Extracting features of vehicle driving parameters in the preprocessed real-time working parameters, determining a driving feature vector, and determining a driving category of the vehicle during driving based on the driving feature vector and a driving mapping table; Extracting features of vehicle tire parameters in the preprocessed real-time working parameters to determine parameter feature vectors; The road surface category, climate category, driving category and parameter feature vector during vehicle driving are input into the parameter decision model. The parameter decision model adjusts the parameter feature vector based on the road surface category, climate category and driving category, and determines the optimal parameter vector of the vehicle tire based on the output result of the parameter decision model.

[0009] According to an intelligent tire control method based on environmental perception provided by the present invention, real-time environmental information and real-time working parameters are analyzed to determine the real-time predicted risk category of vehicle tires, including: The road surface feature vector, road surface category, climate feature vector and climate category during vehicle driving are input into the environmental risk prediction model, and the existence of environmental risk and the environmental risk category when environmental risk exists are determined based on the output result of the environmental classification prediction model; Inputting the driving feature vector, driving category and parameter feature vector of the vehicle during driving into the behavior risk prediction model, and determining whether there is a behavior risk and the behavior risk category when there is a behavior risk based on the output result of the behavior classification prediction model; Determine the real-time predicted risk category based on whether there is an environmental risk, the environmental risk category when there is an environmental risk, whether there is a behavioral risk, and the behavioral risk category when there is a behavioral risk;

[0010] in, represents the real-time prediction risk category, Indicates that the real-time predicted risk category is empty. Indicates the existence value of environmental risk, Indicates the existence value of behavioral risk, Indicates that there is an environmental risk. Indicates that there is no environmental risk. Indicates behavioral risk. Indicates that there is no behavioral risk. represents the ath environmental risk category, represents the bth behavioral risk category, Represents the ath environmental risk category - the bth behavioral risk category.

[0011] According to an intelligent tire control method based on environmental perception provided by the present invention, a real-time control instruction of a vehicle tire is determined based on a parameter feature vector, an optimal parameter vector and a real-time predicted risk category, including: Determine a deviation characteristic vector during vehicle driving based on the parameter characteristic vector and the optimal parameter vector; Determine whether each eigenvalue in the deviation eigenvector is within the corresponding eigenvalue range. If all eigenvalues ​​in the deviation eigenvector are within the corresponding eigenvalue range and the real-time prediction risk category is empty, no real-time control instruction is issued. otherwise, determining a control sub-instruction for each parameter of the vehicle tire based on the deviation feature vector, the parameter feature vector, and the real-time predicted risk category; The real-time control instructions of the vehicle tires are determined based on the control sub-instructions of all parameters of the vehicle tires.

[0012] According to an intelligent tire control method based on environmental perception provided by the present invention, a control sub-instruction for each parameter of a vehicle tire is determined based on a deviation feature vector, a parameter feature vector and a real-time predicted risk category, including: in, represents the control sub-command of the jth parameter of the vehicle tire, represents the eigenvalue of the jth parameter in the parameter eigenvector, represents the deviation value of the jth parameter in the deviation feature vector, Indicates the real-time risk correction factor for a specified time period. represents the comprehensive correction value of all parameters in the deviation feature vector to the jth parameter, N2 represents the number of parameters in the deviation feature vector, represents the correction factor of the control sub-instruction of the kth parameter to the jth parameter in the deviation feature vector, represents the correction value of the control sub-instruction of the kth parameter to the jth parameter in the deviation feature vector, represents the membership factor of the jth parameter to the real-time prediction risk category, They represent the instantaneous weights of the ath environmental risk category and the bth behavioral risk category, respectively. represents the risk sensitivity coefficient of the ath environmental risk category, represents the behavioral sensitivity coefficient of the bth behavioral risk category, They represent the historical weights of the ath environmental risk category and the bth behavioral risk category, respectively. N1 represents the number of historical specified time periods. represents the historical forecast risk category of the i-th historical specified time period, It indicates that the historical forecast risk category of the i-th historical specified time period is the a-th environmental risk category and takes the value of 1. It indicates that the historical forecast risk category of the i-th historical specified time period is the b-th behavioral risk category and takes the value of 1. represents the time decay factor of the ath environmental risk category and the bth behavioral risk category, represents the historical risk correction factor for the i-th historical specified time period, represents the instantaneous weight of the ath environmental risk category - the bth behavioral risk category, represents the risk sensitivity coefficient of the ath environmental risk category - the bth behavioral risk category, represents the historical weight of the a-th environmental risk category - the b-th behavioral risk category, represents the time decay factor of the ath environmental risk category - the bth behavioral risk category, It indicates that the value is 1 when the historical predicted risk category of the i-th historical specified time period is the a-th environmental risk category - the b-th behavioral risk category.

[0013] According to an intelligent tire control method based on environment perception provided by the present invention, real-time working parameters of vehicle tires are adjusted based on real-time control instructions to achieve intelligent control of vehicle tires, including: Transmitting each control sub-instruction in the real-time control instruction to a parameter control center; The parameter control center receives and analyzes all control sub-instructions, executes all analyzed control sub-instructions, and realizes intelligent control of vehicle tires.

[0014] On the other hand, the present invention also provides an intelligent tire control system based on environmental perception, comprising: Acquisition module: collects the real-time environmental information of the vehicle's environment and obtains the real-time working parameters of the vehicle's tires in real time; Analysis module: Analyzes real-time environmental information and real-time working parameters to determine the parameter feature vector, optimal parameter vector and real-time prediction risk category of vehicle tires; Determination module: determining the real-time control instructions of the vehicle tire based on the parameter feature vector, the optimal parameter vector and the real-time predicted risk category; Control module: adjusts the real-time working parameters of the vehicle tires based on real-time control instructions to achieve intelligent control of the vehicle tires.

[0015] Compared with the prior art, the present invention has the following beneficial effects: By analyzing the collected real-time environmental information and real-time working parameters, the parameter feature vector, optimal parameter vector and real-time predicted risk category of the vehicle tire are determined, the real-time control instructions of the vehicle tire are determined and executed, and the intelligent control of the vehicle tire is realized. This can improve the accuracy and real-time performance of tire control, avoid the lag and limitations of static control methods, and quickly respond to risk changes in complex environments, ensuring that the tires are always in the best working condition in a changing driving environment, providing an efficient and accurate parameter control solution for intelligent driving technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of an intelligent tire control method based on environmental perception provided by an embodiment of the present invention.

[0018] Figure 2 It is a structural schematic diagram of an intelligent tire control system based on environmental perception provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Embodiment 1: The embodiment of the present invention provides an intelligent tire control method based on environment perception, such as Figure 1 As shown, including: 101: real-time collection of real-time environmental information of the environment in which the vehicle is located, and real-time acquisition of real-time working parameters of the vehicle tires; 102: Analyze the real-time environmental information and the real-time working parameters to determine the parameter feature vector, the optimal parameter vector and the real-time prediction risk category of the vehicle tire; 103: Determine a real-time control instruction of a vehicle tire based on the parameter feature vector, the optimal parameter vector, and the real-time predicted risk category; 104: Adjust the real-time working parameters of the vehicle tires based on the real-time control instructions to achieve intelligent control of the vehicle tires.

[0021] In this embodiment, environmental information of the vehicle's environment is collected in real time through sensors, including temperature, humidity, road conditions (such as dry, wet or snowy), etc. At the same time, real-time operating parameters of the vehicle's tires are collected, such as tire pressure, tire temperature, friction coefficient, wear, etc. These data directly reflect the current operating status of the tires.

[0022] In this embodiment, a real-time control instruction is generated based on the parameter feature vector, the optimal parameter vector and the real-time predicted risk category. The real-time control instruction is an adjustment strategy for all tire parameters, and specifies the control sub-instructions for each tire parameter (such as tire pressure and tire temperature).

[0023] In this embodiment, the real-time control instructions are transmitted to the parameter control center, and the actual working parameters of the tire are adjusted by the actuator (such as the tire pressure regulator, the heating device). Through dynamic adjustment, the tire operating state is brought close to the optimal parameter vector, thereby realizing intelligent and adaptive control of the tire.

[0024] The beneficial effects of the above technical solution are as follows: by analyzing the collected real-time environmental information and real-time working parameters, the parameter characteristic vector, optimal parameter vector and real-time predicted risk category of the vehicle tire are determined, the real-time control instructions of the vehicle tire are determined and executed, and the intelligent control of the vehicle tire is realized. The accuracy and real-time performance of tire control can be improved, the lag and limitations of static control methods can be avoided, and the risk changes in complex environments can be quickly responded to, ensuring that the tires are always in the best working state in a changing driving environment, providing an efficient and accurate parameter control solution for intelligent driving technology.

[0025] Embodiment 2: The embodiment of the present invention provides an intelligent tire control method based on environment perception, which collects real-time environmental information of the environment in which the vehicle is located in real time and obtains real-time working parameters of the vehicle tires in real time, including: Based on a first sensor group installed in the vehicle, real-time environmental information of the environment in which the vehicle is located within a specified time period is collected, wherein the real-time environmental information includes real-time road information and real-time climate information; The second sensor group installed on the vehicle collects real-time operating parameters of the vehicle tires within a specified time period, wherein the real-time operating parameters include vehicle driving parameters and vehicle tire parameters.

[0026] In this embodiment, the first sensor group is responsible for collecting real-time information about the environment in which the vehicle is located, covering the environmental status within a specified time period.

[0027] In this embodiment, the real-time road surface information includes the road surface's wetness, roughness, icing conditions, slope changes, etc., and these data reflect the current road conditions.

[0028] In this embodiment, the real-time climate information includes external meteorological data such as temperature, humidity, rainfall, snowfall, wind speed, etc., which helps to determine the impact of weather on driving and tire performance.

[0029] In this embodiment, the second sensor group collects the operating status of the vehicle within the same time period, which is divided into two categories: vehicle driving parameters: such as vehicle speed, acceleration, steering wheel angle, braking force, driving force, etc., which characterize the current driving status of the vehicle; vehicle tire parameters: including tire pressure, temperature, degree of wear, tire contact area, rotation speed, etc., which are used to describe the instantaneous operating status of the tire. These parameters together reflect the interaction between the vehicle and the environment.

[0030] The beneficial effects of the above technical solution are as follows: determining real-time environmental information and real-time working parameters can provide data basis for determining parameter feature vectors, optimal parameter vectors and real-time prediction of risk categories, thereby improving the optimization level of tire performance.

[0031] Embodiment 3: The embodiment of the present invention provides an intelligent tire control method based on environmental perception, which analyzes real-time environmental information and real-time working parameters to determine parameter feature vectors and optimal parameter vectors of vehicle tires, including: Preprocess the real-time environmental information and real-time working parameters respectively; Extracting features of the real-time road surface information in the preprocessed real-time environmental information, determining a road surface feature vector, and determining a road surface category during vehicle driving based on the road surface feature vector and a road surface mapping table; Extracting features of the real-time climate information in the preprocessed real-time environmental information, determining a climate feature vector, and determining a climate category during vehicle driving based on the climate feature vector and a climate mapping table; Extracting features of vehicle driving parameters in the preprocessed real-time working parameters, determining a driving feature vector, and determining a driving category of the vehicle during driving based on the driving feature vector and a driving mapping table; Extracting features of vehicle tire parameters in the preprocessed real-time working parameters to determine parameter feature vectors; The road surface category, climate category, driving category and parameter feature vector during vehicle driving are input into the parameter decision model. The parameter decision model adjusts the parameter feature vector based on the road surface category, climate category and driving category, and determines the optimal parameter vector of the vehicle tire based on the output result of the parameter decision model.

[0032] In this embodiment, the collected real-time environmental information and real-time working parameters are preprocessed, mainly including steps such as data cleaning, denoising, and normalization to ensure the quality and availability of the data.

[0033] In this embodiment, after feature extraction of real-time road surface information, a road surface feature vector is generated. The vector represents the multi-dimensional features of the current road condition, including wetness, roughness, inclination, etc. Combined with a road surface mapping table, the road surface type encountered during the current driving process (e.g., dry, wet, icy, etc.) is determined by comparing the road surface feature vector with the data in the mapping table.

[0034] In this embodiment, feature extraction is performed on real-time climate information to generate a climate feature vector for representing current meteorological conditions (including temperature, humidity, wind speed, etc.). Based on a climate mapping table, the climate category (such as sunny, rainy, snowy, etc.) of the current driving process is determined by matching the climate feature vector with the table content.

[0035] In this embodiment, feature extraction is performed on the vehicle's driving parameters (including vehicle speed, acceleration, braking force, etc.) to generate a driving feature vector representing the vehicle's driving state. Combined with a driving mapping table, the driving category (such as high-speed driving, low-speed driving, sudden acceleration, etc.) in the current driving process is determined based on the driving feature vector.

[0036] In this embodiment, feature extraction is performed on vehicle tire parameters (including tire pressure, tire temperature, etc.) to obtain a parameter feature vector for representing the instantaneous state of the tire.

[0037] In this embodiment, the road surface category, climate category, driving category and parameter feature vector are input into the parameter decision model. The parameter decision model adjusts and optimizes the tire parameter feature vector by comprehensively considering factors such as the road surface, climate, and driving conditions to determine the optimal parameter vector.

[0038] The beneficial effects of the above technical solution are as follows: analyzing real-time environmental information and real-time working parameters to determine the parameter feature vector and optimal parameter vector of the vehicle tire can provide intelligent decision support for tire control, optimize the vehicle's driving performance and safety, and ensure that the tire is always in the best working condition in a changing driving environment.

[0039] Embodiment 4: The embodiment of the present invention provides an intelligent tire control method based on environmental perception, which analyzes real-time environmental information and real-time working parameters to determine the real-time predicted risk category of vehicle tires, including: The road surface feature vector, road surface category, climate feature vector and climate category during vehicle driving are input into the environmental risk prediction model, and the existence of environmental risk and the environmental risk category when environmental risk exists are determined based on the output result of the environmental classification prediction model; Inputting the driving feature vector, driving category and parameter feature vector of the vehicle during driving into the behavior risk prediction model, and determining whether there is a behavior risk and the behavior risk category when there is a behavior risk based on the output result of the behavior classification prediction model; Determine the real-time predicted risk category based on whether there is an environmental risk, the environmental risk category when there is an environmental risk, whether there is a behavioral risk, and the behavioral risk category when there is a behavioral risk; in, represents the real-time prediction risk category, Indicates that the real-time predicted risk category is empty. Indicates the existence value of environmental risk, Indicates the existence value of behavioral risk, Indicates that there is an environmental risk. Indicates that there is no environmental risk. Indicates behavioral risk. Indicates that there is no behavioral risk. represents the ath environmental risk category, represents the bth behavioral risk category, Represents the ath environmental risk category - the bth behavioral risk category.

[0040] In this embodiment, the road surface feature vector (multidimensional data reflecting the current road surface conditions) and road surface category (such as slippery, icy, etc.) during the vehicle's driving process are input into the environmental risk prediction model. At the same time, combined with the climate feature vector (such as temperature, humidity, precipitation, etc.) and climate category (such as sunny, rainy, snowy, etc.), the environmental risk prediction model analyzes these inputs to comprehensively determine whether there are potential risks in the vehicle's current environment (such as low adhesion, snow cover, etc.).

[0041] In this embodiment, if an environmental risk is detected, the environmental risk category (such as slippery road risk, icy road risk, low visibility, etc.) is further output to clarify the specific environmental risk type.

[0042] In this embodiment, the vehicle's driving feature vector (such as vehicle speed, acceleration, steering wheel angle, etc.), driving category (such as sudden acceleration, sudden braking, etc.) and parameter feature vector (such as tire pressure, tire temperature, etc.) are input into the behavioral risk prediction model. The behavioral risk prediction model comprehensively analyzes these input data to determine whether the current driving behavior has potential risks (such as rollover risk caused by turning too quickly, loss of control risk caused by improper braking, etc.). If a behavioral risk is detected, the behavioral risk category (such as speeding risk, sudden braking risk, tire overheating risk, etc.) is further output to clarify the specific behavioral risk type.

[0043] In this embodiment, the output results of the environmental risk prediction model and the behavioral risk prediction model are combined to determine whether the current environment is at risk and whether the behavior is at risk, and the risk categories of the environment and behavior are clarified. Based on the above information, a comprehensive judgment is made to determine the real-time predicted risk category during vehicle driving, such as "slippery road surface" or "icy and snowy road surface + speeding risk".

[0044] The beneficial effects of the above technical solution are as follows: by analyzing real-time environmental information and real-time working parameters to determine the real-time predicted risk category of vehicle tires, the risk category in complex driving scenarios can be accurately identified, the accuracy and timeliness of risk prediction can be improved, and a more intelligent risk warning mechanism and driving safety assurance capability can be provided for the vehicle.

[0045] Embodiment 5: The embodiment of the present invention provides an intelligent tire control method based on environment perception, which determines the real-time control instructions of the vehicle tire based on the parameter feature vector, the optimal parameter vector and the real-time predicted risk category, including: Determine a deviation characteristic vector during vehicle driving based on the parameter characteristic vector and the optimal parameter vector; Determine whether each eigenvalue in the deviation eigenvector is within the corresponding eigenvalue range. If all eigenvalues ​​in the deviation eigenvector are within the corresponding eigenvalue range and the real-time prediction risk category is empty, no real-time control instruction is issued. otherwise, determining a control sub-instruction for each parameter of the vehicle tire based on the deviation feature vector, the parameter feature vector, and the real-time predicted risk category; The real-time control instructions of the vehicle tires are determined based on the control sub-instructions of all parameters of the vehicle tires.

[0046] In this embodiment, the parameter feature vector (describing the current tire parameter status, such as tire pressure, tire temperature, etc.) during vehicle driving is compared with the optimal parameter vector (the optimal tire working state output by the parameter decision model) to generate a deviation feature vector.

[0047] In this embodiment, the deviation feature vector represents the difference between the current parameter and the optimal parameter, and each feature value corresponds to a specific deviation value (such as tire pressure deviation, tire temperature deviation, etc.).

[0048] In this embodiment, each eigenvalue in the deviation eigenvector is checked in turn to determine whether it is within a preset characteristic deviation range, where the characteristic deviation range represents the allowable deviation limit (eg, the tire pressure deviation allowable range is ±0.2 bar).

[0049] In this embodiment, if all characteristic values ​​are within the corresponding characteristic deviation range and the real-time predicted risk category is empty (i.e., the current environment and behavior are risk-free), it means that the vehicle operation state is close to the ideal state, and no real-time control instructions need to be issued.

[0050] In this embodiment, if there is a characteristic value in the deviation characteristic vector that exceeds the allowable range, or the real-time predicted risk category is not empty, it is necessary to generate a tire control sub-instruction.

[0051] In this embodiment, all control sub-instructions are integrated to form an overall real-time control instruction, which is used to guide the real-time control operation of the vehicle tire parameters. The real-time control instruction includes an adjustment strategy for all tire parameters to ensure that the vehicle can quickly respond to risks and return to the optimal state in complex driving environments.

[0052] The beneficial effects of the above technical solution are as follows: by determining the real-time control instructions of the vehicle tires based on the parameter feature vector, the optimal parameter vector and the real-time predicted risk category, efficient and accurate tire parameter control can be achieved, the pertinence, real-time nature and effectiveness of the control instructions are improved, and the stability and safety of vehicle operation are improved.

[0053] Embodiment 6: The embodiment of the present invention provides an intelligent tire control method based on environmental perception, which determines the control sub-instruction of each parameter of the vehicle tire based on the deviation feature vector, the parameter feature vector and the real-time predicted risk category, including: in, represents the control sub-command of the jth parameter of the vehicle tire, represents the eigenvalue of the jth parameter in the parameter eigenvector, represents the deviation value of the jth parameter in the deviation feature vector, Indicates the real-time risk correction factor for a specified time period. represents the comprehensive correction value of all parameters in the deviation feature vector to the jth parameter, N2 represents the number of parameters in the deviation feature vector, represents the correction factor of the control sub-instruction of the kth parameter to the jth parameter in the deviation feature vector, represents the correction value of the control sub-instruction of the kth parameter to the jth parameter in the deviation feature vector, represents the membership factor of the jth parameter to the real-time prediction risk category, They represent the instantaneous weights of the ath environmental risk category and the bth behavioral risk category, respectively. represents the risk sensitivity coefficient of the ath environmental risk category, represents the behavioral sensitivity coefficient of the bth behavioral risk category, They represent the historical weights of the ath environmental risk category and the bth behavioral risk category, respectively. N1 represents the number of historical specified time periods. represents the historical forecast risk category of the i-th historical specified time period, It indicates that the historical forecast risk category of the i-th historical specified time period is the a-th environmental risk category and takes the value of 1. It indicates that the historical forecast risk category of the i-th historical specified time period is the b-th behavioral risk category and takes the value of 1. represents the time decay factor of the ath environmental risk category and the bth behavioral risk category, represents the historical risk correction factor for the i-th historical specified time period, represents the instantaneous weight of the ath environmental risk category - the bth behavioral risk category, represents the risk sensitivity coefficient of the ath environmental risk category - the bth behavioral risk category, represents the historical weight of the a-th environmental risk category - the b-th behavioral risk category, represents the time decay factor of the ath environmental risk category - the bth behavioral risk category, It indicates that the value is 1 when the historical predicted risk category of the i-th historical specified time period is the a-th environmental risk category - the b-th behavioral risk category.

[0054] In this embodiment, specific adjustment suggestions are made for each parameter of the tire (such as tire pressure, tire temperature, etc.) by analyzing the deviation feature vector (indicating the current parameter deviation), the parameter feature vector (indicating the current state) and the real-time predicted risk category (reflecting the current risk factors).

[0055] The beneficial effects of the above technical solution are as follows: determining the control sub-instructions for each parameter of the vehicle tire based on the deviation characteristic vector, the parameter characteristic vector and the real-time predicted risk category can provide a basis for determining the real-time control instructions to achieve efficient and accurate tire control.

[0056] Embodiment 7: The embodiment of the present invention provides an intelligent tire control method based on environment perception, which adjusts the real-time working parameters of the vehicle tires based on the real-time control instructions to realize the intelligent control of the vehicle tires, including: Transmitting each control sub-instruction in the real-time control instruction to a parameter control center; The parameter control center receives and analyzes all control sub-instructions, executes all analyzed control sub-instructions, and realizes intelligent control of vehicle tires.

[0057] In this embodiment, after the real-time control instruction is generated, each control sub-instruction (specific adjustment suggestion for a single parameter of the tire) therein is transmitted to the parameter control center.

[0058] In this embodiment, the parameter control center receives all transmitted control sub-instructions and parses the content of each instruction one by one. The parsing process includes identifying the control object (such as the tire pressure parameter of the front left tire) and the corresponding target adjustment value.

[0059] In this embodiment, the parameter control center converts the parsed instructions into specific operation instructions so as to execute the adjustment operation of the tire parameters.

[0060] In this embodiment, the parameter control center executes each control sub-instruction one by one through the vehicle's actuators (such as a tire inflation device, a heating system, etc.) according to the analysis results to achieve intelligent tire control. For example, if the control sub-instruction requires an increase in tire pressure, the parameter control center will instruct the tire inflation device to perform precise inflation until the tire pressure reaches the target value.

[0061] The beneficial effects of the above technical solution are: adjusting the real-time working parameters of the vehicle tires based on the real-time control instructions to realize the intelligent control of the vehicle tires, which can realize the efficient transmission and precise execution of the instructions, improve the intelligence level of tire parameter control, enhance the adaptability and safety performance of the vehicle in a dynamic environment, and provide an efficient parameter control system for intelligent driving.

[0062] Embodiment 8: The embodiment of the present invention provides an intelligent tire control system based on environment perception, such as Figure 2 As shown, including: Acquisition module: collects the real-time environmental information of the vehicle's environment and obtains the real-time working parameters of the vehicle's tires in real time; Analysis module: Analyzes real-time environmental information and real-time working parameters to determine the parameter feature vector, optimal parameter vector and real-time prediction risk category of vehicle tires; Determination module: determining the real-time control instructions of the vehicle tire based on the parameter feature vector, the optimal parameter vector and the real-time predicted risk category; Control module: adjusts the real-time working parameters of the vehicle tires based on real-time control instructions to achieve intelligent control of the vehicle tires.

[0063] The beneficial effects of the above technical solution are as follows: by analyzing the collected real-time environmental information and real-time working parameters, the parameter characteristic vector, optimal parameter vector and real-time predicted risk category of the vehicle tire are determined, the real-time control instructions of the vehicle tire are determined and executed, and the intelligent control of the vehicle tire is realized. The accuracy and real-time performance of tire control can be improved, the lag and limitations of static control methods can be avoided, and the risk changes in complex environments can be quickly responded to, ensuring that the tires are always in the best working state in a changing driving environment, providing an efficient and accurate parameter control solution for intelligent driving technology.

[0064] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0065] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent tire control method based on environmental perception, characterized in that: include: 101: real-time collection of real-time environmental information of the environment in which the vehicle is located, and real-time acquisition of real-time working parameters of the vehicle tires; 102: Analyze the real-time environmental information and the real-time working parameters to determine the parameter feature vector, the optimal parameter vector and the real-time prediction risk category of the vehicle tire; 103: Determine a real-time control instruction of a vehicle tire based on the parameter feature vector, the optimal parameter vector, and the real-time predicted risk category; 104: Adjust the real-time working parameters of the vehicle tires based on the real-time control instructions to achieve intelligent control of the vehicle tires.

2. The intelligent tire control method based on environment perception according to claim 1, characterized in that: Collect the real-time environmental information of the vehicle's environment in real time, and obtain the real-time working parameters of the vehicle's tires in real time, including: Based on a first sensor group installed in the vehicle, real-time environmental information of the environment in which the vehicle is located within a specified time period is collected, wherein the real-time environmental information includes real-time road information and real-time climate information; The real-time operating parameters of the vehicle tires within a specified time period are collected based on a second sensor group installed on the vehicle, wherein the real-time operating parameters include vehicle driving parameters and vehicle tire parameters.

3. The intelligent tire control method based on environment perception according to claim 1, characterized in that: Analyze real-time environmental information and real-time working parameters to determine the parameter feature vector and optimal parameter vector of the vehicle tire, including: Preprocess the real-time environmental information and real-time working parameters respectively; Extracting features of the real-time road surface information in the preprocessed real-time environmental information, determining a road surface feature vector, and determining a road surface category during vehicle driving based on the road surface feature vector and a road surface mapping table; Extracting features of the real-time climate information in the preprocessed real-time environmental information, determining a climate feature vector, and determining a climate category during vehicle driving based on the climate feature vector and a climate mapping table; Extracting features of vehicle driving parameters in the preprocessed real-time working parameters, determining a driving feature vector, and determining a driving category of the vehicle during driving based on the driving feature vector and a driving mapping table; Extracting features of vehicle tire parameters in the preprocessed real-time working parameters to determine parameter feature vectors; The road surface category, climate category, driving category and parameter feature vector during vehicle driving are input into the parameter decision model. The parameter decision model adjusts the parameter feature vector based on the road surface category, climate category and driving category, and determines the optimal parameter vector of the vehicle tire based on the output result of the parameter decision model.

4. The intelligent tire control method based on environment perception according to claim 3, characterized in that: Analyze real-time environmental information and real-time operating parameters to determine the real-time predicted risk category of vehicle tires, including: The road surface feature vector, road surface category, climate feature vector and climate category during vehicle driving are input into the environmental risk prediction model, and the existence of environmental risk and the environmental risk category when environmental risk exists are determined based on the output result of the environmental classification prediction model; Inputting the driving feature vector, driving category and parameter feature vector of the vehicle during driving into the behavior risk prediction model, and determining whether there is a behavior risk and the behavior risk category when there is a behavior risk based on the output result of the behavior classification prediction model; Determine the real-time predicted risk category based on whether there is an environmental risk, the environmental risk category when there is an environmental risk, whether there is a behavioral risk, and the behavioral risk category when there is a behavioral risk; in, represents the real-time prediction risk category, Indicates that the real-time predicted risk category is empty. Indicates the existence value of environmental risk, Indicates the existence value of behavioral risk, Indicates that there is an environmental risk. Indicates that there is no environmental risk. Indicates behavioral risk. Indicates that there is no behavioral risk. represents the ath environmental risk category, represents the bth behavioral risk category, Represents the ath environmental risk category - the bth behavioral risk category.

5. The intelligent tire control method based on environment perception according to claim 4, characterized in that: Determine the real-time control instructions of the vehicle tire based on the parameter feature vector, the optimal parameter vector and the real-time predicted risk category, including: Determine a deviation characteristic vector during vehicle driving based on the parameter characteristic vector and the optimal parameter vector; Determine whether each eigenvalue in the deviation eigenvector is within the corresponding eigenvalue range. If all eigenvalues ​​in the deviation eigenvector are within the corresponding eigenvalue range and the real-time prediction risk category is empty, no real-time control instruction is issued. otherwise, determining a control sub-instruction for each parameter of the vehicle tire based on the deviation feature vector, the parameter feature vector, and the real-time predicted risk category; The real-time control instructions of the vehicle tires are determined based on the control sub-instructions of all parameters of the vehicle tires.

6. The intelligent tire control method based on environment perception according to claim 5, characterized in that: The control sub-instructions for each parameter of the vehicle tire are determined based on the deviation feature vector, the parameter feature vector and the real-time predicted risk category, including: in, represents the control sub-command of the jth parameter of the vehicle tire, represents the eigenvalue of the jth parameter in the parameter eigenvector, represents the deviation value of the jth parameter in the deviation feature vector, Indicates the real-time risk correction factor for a specified time period. represents the comprehensive correction value of all parameters in the deviation feature vector to the jth parameter, N2 represents the number of parameters in the deviation feature vector, represents the correction factor of the control sub-instruction of the kth parameter to the jth parameter in the deviation feature vector, represents the correction value of the control sub-instruction of the kth parameter to the jth parameter in the deviation feature vector, represents the membership factor of the jth parameter to the real-time prediction risk category, They represent the instantaneous weights of the ath environmental risk category and the bth behavioral risk category, respectively. represents the risk sensitivity coefficient of the ath environmental risk category, represents the behavioral sensitivity coefficient of the bth behavioral risk category, They represent the historical weights of the ath environmental risk category and the bth behavioral risk category, respectively. N1 represents the number of historical specified time periods. represents the historical forecast risk category of the i-th historical specified time period, It indicates that the historical forecast risk category of the i-th historical specified time period is the a-th environmental risk category and takes the value of 1. It indicates that the historical forecast risk category of the i-th historical specified time period is the b-th behavioral risk category and takes the value of 1. represents the time decay factor of the ath environmental risk category and the bth behavioral risk category, represents the historical risk correction factor for the i-th historical specified time period, represents the instantaneous weight of the ath environmental risk category - the bth behavioral risk category, represents the risk sensitivity coefficient of the ath environmental risk category - the bth behavioral risk category, represents the historical weight of the a-th environmental risk category - the b-th behavioral risk category, represents the time decay factor of the ath environmental risk category - the bth behavioral risk category, It indicates that the value is 1 when the historical predicted risk category of the i-th historical specified time period is the a-th environmental risk category - the b-th behavioral risk category.

7. The intelligent tire control method based on environment perception according to claim 1, characterized in that: Adjust the real-time working parameters of the vehicle tires based on the real-time control instructions to achieve intelligent control of the vehicle tires, including: Transmitting each control sub-instruction in the real-time control instruction to a parameter control center; The parameter control center receives and analyzes all control sub-instructions, executes all analyzed control sub-instructions, and realizes intelligent control of vehicle tires.

8. An intelligent tire control system based on environmental perception, characterized in that: include: Acquisition module: collects the real-time environmental information of the vehicle's environment and obtains the real-time working parameters of the vehicle's tires in real time; Analysis module: Analyzes real-time environmental information and real-time working parameters to determine the parameter feature vector, optimal parameter vector and real-time prediction risk category of vehicle tires; Determination module: determining the real-time control instructions of the vehicle tire based on the parameter feature vector, the optimal parameter vector and the real-time predicted risk category; Control module: adjusts the real-time working parameters of the vehicle tires based on real-time control instructions to achieve intelligent control of the vehicle tires.

Images