A tire wear detection and early warning method, device and medium for new energy vehicles

Abstract

The present application discloses a tire wear detection and early warning method, device and medium for new energy vehicles, which relate to the field of computer technology. The method comprises: determining vehicle parameters of the vehicle, and obtaining the driving habits of the driver through a preset sensor group; standardizing the vehicle data and driving habits to obtain training data, and training a neural network model according to the training data to obtain a tire wear prediction model; obtaining real-time driving data through the sensor group, and inputting the real-time driving data into the tire wear prediction model to determine the predicted wear condition of the tire and the predicted time corresponding to the predicted wear condition, wherein the predicted wear condition includes the tire wear type and the tire wear degree; detecting the tire according to the predicted time to obtain the actual wear condition of the tire, and comparing the actual wear condition with the predicted wear condition. If the actual wear condition is consistent with the predicted wear condition, the driver is warned.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a tire wear detection and early warning method, device and medium for new energy vehicles. Background Art

[0002] New energy electric vehicles are vehicles that use batteries as energy storage power sources. They use batteries as energy storage power sources, provide electricity to the motor through the battery, drive the motor to operate, and thus drive the vehicle. Compared with traditional fuel vehicles, the battery pack of new energy electric vehicles occupies a considerable space at the bottom of the vehicle and is heavier. This uneven weight distribution causes the center of gravity of the vehicle to move downward and to one side, so that during driving, especially when accelerating, braking and turning, the load and stress on the tires are unevenly distributed, accelerating local wear of the tires. The power output characteristics of electric vehicles are different from those of traditional fuel vehicles. The electric motor can provide high torque instantly. This instant power response may cause the tires to generate greater friction with the ground when starting or accelerating sharply, exacerbating wear. Electric vehicles are generally equipped with a regenerative braking system, which converts part of the kinetic energy into electrical energy and stores it back in the battery when the vehicle decelerates or brakes. However, this braking method may increase the slip rate between the tire and the road, especially on slippery roads or in emergency braking situations, thereby accelerating tire wear.

[0003] The most intuitive manifestation of tire wear is uneven wear on the tire surface, which may be manifested as one side or a specific area wearing much more than other areas, forming an obvious "bald spot" or "feather-like" wear. Uneven wear will change the rolling radius and shape of the tire, which in turn affects the vehicle's driving stability and handling, such as increasing the risk of skidding during steering and reducing braking performance. The reduction in handling and braking performance may make the vehicle difficult to control in an emergency, increasing the risk of accidents. Increased tire wear will lead to increased rolling resistance, which in turn increases the vehicle's energy consumption and reduces the cruising range. Uneven wear also directly leads to the tire reaching the replacement standard ahead of schedule, increasing the vehicle's operating costs. In addition, when the above-mentioned uneven wear occurs, if the driver does not discover it in time, it will increase the risk of traffic accidents and create safety hazards. Summary of the invention

[0004] In order to solve the above problems, the present application proposes a tire wear detection and early warning method for new energy vehicles, including: determining vehicle parameters of the vehicle, the vehicle parameters including but not limited to vehicle structure, tire dynamic data, and power output characteristics, and obtaining the driver's driving habits through a pre-set sensor group, the driving habits including but not limited to historical driving conditions, turning speed, and number of emergency brakes; standardizing the vehicle data and the driving habits to obtain training data, and training a neural network model based on the training data to obtain a tire wear prediction model; obtaining real-time driving data through the sensor group, and inputting the real-time driving data into the tire wear prediction model to determine the predicted wear condition of the tire and the predicted time corresponding to the predicted wear condition, the predicted wear condition including tire wear type and tire wear degree; detecting the tire according to the predicted time to obtain the actual wear condition of the tire, comparing the actual wear condition with the predicted wear condition, and if the actual wear condition is consistent with the predicted wear condition, then warning the driver.

[0005] In one example, a neural network model is trained based on the training data, and the method further includes: determining a driving condition point based on the standardized driving habits, and determining a tire wear type corresponding to the driving condition point; determining historical tire dynamic data based on the standardized vehicle parameters, and determining a degree of wear corresponding to the driving condition point based on the historical tire dynamic data; performing feature extraction on the degree of wear to determine a wear weight corresponding to the tire wear type, and determining the tire wear prediction model based on the wear weight; determining a pre-set prediction time, and setting a prediction period of the tire wear prediction model based on the prediction time.

[0006] In one example, the method also includes: if the actual wear condition is inconsistent with the predicted wear condition, determining a degree difference value based on the actual wear condition and the predicted wear condition; determining the tire wear type corresponding to the degree difference value, and adjusting the wear weight corresponding to the tire wear type according to the degree difference value to update the tire wear prediction model; counting the number of inconsistencies between the actual wear condition and the predicted wear condition, and reducing the prediction time by a multiple according to the number to update the tire wear prediction model.

[0007] In one example, the method further includes: collecting environmental information of the vehicle when it is traveling, the environmental information including but not limited to weather data and road condition information; and adjusting the wear weight corresponding to the tire wear type according to the environmental information.

[0008] In one example, the method further includes: determining a sensor group at the tire, acquiring dynamic data of the tire through the sensor group, the dynamic data of the tire including but not limited to tire pressure and temperature, and determining actual wear condition of the tire based on the real-time data.

[0009] In one example, the method also includes: determining a prediction report based on the actual wear condition and the predicted wear condition, and uploading the prediction report to a predetermined cloud platform; obtaining multiple prediction reports of multiple vehicles through the cloud platform, determining the vehicle type, and determining the tire wear condition corresponding to the vehicle type based on the multiple prediction reports, so as to determine the tire maintenance plan corresponding to the vehicle type based on the tire wear condition, the tire maintenance plan including but not limited to tire replacement time, tire quality inspection cycle, tire parameter adjustment suggestions, and driving habit adjustment suggestions; sending the tire maintenance plan to the driver so that the driver can repair the tires according to the tire maintenance plan.

[0010] In one example, the method further includes: determining the accuracy of the tire wear prediction model based on the multiple prediction reports, and comparing the accuracy with a preset threshold; if the accuracy is less than the threshold, determining the corresponding vehicle type, and determining the corresponding tire production plan based on the vehicle type, the tire production plan including but not limited to a tire type selection plan and factory parameter adjustment; sending the tire production plan to a vehicle manufacturer corresponding to the vehicle type, so that the vehicle manufacturer can make production adjustments to the vehicle according to the tire production plan.

[0011] In one example, the method further includes: determining a visual interactive interface pre-set in the vehicle, obtaining the prediction report and the tire maintenance plan through the visual interactive interface, and displaying the prediction report and the tire maintenance plan.

[0012] On the other hand, the present application also proposes a tire wear detection and warning device for a new energy vehicle, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the tire wear detection and warning device for the new energy vehicle can perform: determining vehicle parameters of the vehicle, the vehicle parameters including but not limited to vehicle structure, tire dynamic data, power output characteristics, obtaining the driver's driving habits through a pre-set sensor group, the driving habits including but not limited to historical driving conditions, turning speed, number of emergency brakes; and processing the vehicle data and The driving habits are standardized to obtain training data, and a neural network model is trained according to the training data to obtain a tire wear prediction model; real-time driving data is acquired through the sensor group, and the real-time driving data is input into the tire wear prediction model to determine the predicted wear condition of the tire and the predicted time corresponding to the predicted wear condition, wherein the predicted wear condition includes the tire wear type and the tire wear degree; the tire is tested according to the predicted time to obtain the actual wear condition of the tire, and the actual wear condition is compared with the predicted wear condition. If the actual wear condition is consistent with the predicted wear condition, the driver is warned.

[0013] On the other hand, the present application also proposes a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to: determine vehicle parameters of a vehicle, wherein the vehicle parameters include but are not limited to vehicle structure, tire dynamic data, and power output characteristics, and obtain the driver's driving habits through a pre-set sensor group, wherein the driving habits include but are not limited to historical driving conditions, turning speed, and number of emergency brakes; standardize the vehicle data and the driving habits to obtain training data, and train a neural network model based on the training data to obtain a tire wear prediction model; obtain real-time driving data through the sensor group, and input the real-time driving data into the tire wear prediction model to determine the predicted wear condition of the tire and the predicted time corresponding to the predicted wear condition, wherein the predicted wear condition includes the tire wear type and the tire wear degree; detect the tire according to the predicted time to obtain the actual wear condition of the tire, and compare the actual wear condition with the predicted wear condition. If the actual wear condition is consistent with the predicted wear condition, the driver is warned.

[0014] This application uses a neural network model for accurate prediction and achieves early warning of tire wear. It not only improves the accuracy of tire wear detection, but also ensures the continued effectiveness of the prediction model through real-time data feedback and model optimization mechanisms. At the same time, combined with environmental information and cloud platform big data analysis, it provides drivers with personalized tire maintenance plans, and promotes vehicle manufacturers to optimize and adjust tire production plans, further improving the safety and economy of vehicle driving. It allows drivers to intuitively understand the tire status and maintenance recommendations, enhancing the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 This is a flow chart of a tire wear detection and early warning method for a new energy vehicle in an embodiment of the present application;

[0017] Figure 2 This is a schematic diagram of a tire wear detection and warning device for a new energy vehicle in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0019] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0020] like Figure 1 As shown, in order to solve the above problems, an embodiment of the present application provides a tire wear detection and early warning method for a new energy vehicle, the method comprising:

[0021] S101. Determine vehicle parameters of the vehicle, including but not limited to vehicle structure, tire dynamic data, and power output characteristics, and obtain the driver's driving habits through a pre-set sensor group, including but not limited to historical driving conditions, turning speed, and number of emergency brakes.

[0022] The vehicle parameters collect the structural features of the vehicle in detail, such as vehicle model, vehicle weight, wheelbase, etc.; dynamic data of tires, such as tire pressure, tire temperature, tire speed, wear, etc.; and power output characteristics of the vehicle, such as engine or motor power, torque output, etc. Among them, when judging the wear of the tire, a high-definition camera is set at the tire to take a clear image of the tire. The captured color image is converted into a grayscale image to reduce the computational complexity and speed of feature extraction. The median filter and other methods are used to remove noise in the image and improve the image quality. The edge detection algorithms such as gradient operators are used to detect the edge of the tire tread texture and identify the contour and wear area of ​​the tire pattern. The Watershed method, active contour method and other regional detection methods are used to divide and identify the area of ​​the tire tread texture. By detecting the grayscale, texture and other features of different areas, the degree and type of tire wear are determined. The grayscale threshold of the tire image is processed using algorithms such as iterative threshold method and Otsu method to obtain the grayscale features of the tire wear area. Combined with morphological analysis methods, the tire wear area is labeled and quantified. Through the steps of template design, region detection, region tracking and region quantification, the area, perimeter, centroid and other characteristic quantities of the wear area are obtained. In view of the fact that the initial characteristics of tire texture wear are not obvious, the wavelet transform analysis method is adopted. By selecting appropriate wavelet functions and thresholds, the grayscale change mutation points are extracted as edges, and the adhesion and discontinuity of the contour are reduced. A model-assisted analysis system for tire wear is constructed, including functions such as object modeling, wear analysis, data pool and data management. By analyzing tire wear images and sequence images, the change process of tire wear is grasped and the future wear trend is predicted. According to the extracted tire wear characteristic quantities, such as the area and depth of the wear area, the degree of tire wear is judged. Usually, when the tire tread depth is lower than the minimum value recommended by the manufacturer, such as 1.6 mm, the tire needs to be replaced. According to the morphology and distribution characteristics of tire wear, the type of tire wear is judged. Common tire wear types include tire outer tread wear, tire middle tread wear, tire inner tread wear, etc.

[0023] The sensor group pre-installed on the vehicle can capture and record the driver's driving habits in real time. These driving habit data are particularly important for predicting tire wear, as they directly reflect the driver's preferences and style when operating the vehicle. Specifically, historical driving conditions, such as road type and road quality, will affect the tire wear rate; the speed of cornering and the number of emergency brakes are directly related to the lateral wear and brake wear of the tire.

[0024] In one embodiment, tire pressure sensors, temperature sensors, vibration sensors, etc. are installed at the tire. The tire pressure sensor measures the pressure inside the tire in real time. Tire pressure is one of the key factors affecting tire wear and performance. Too low or too high tire pressure will accelerate tire wear. The temperature sensor monitors the temperature inside the tire. The tire will heat up due to friction and compression during driving. Excessive temperature will affect the performance and life of the tire material, thereby affecting the wear condition. The vibration sensor can detect the side slip, bumps, etc. of the tire, so as to more comprehensively evaluate the wear condition of the tire.

[0025] S102, standardizing the vehicle data and the driving habits to obtain training data, and training a neural network model according to the training data to obtain a tire wear prediction model.

[0026] Clean the vehicle data and driving habits, remove missing values, outliers, etc., to ensure the integrity and accuracy of the data. Scale the numerical range of the data to between 0 and 1, or between -1 and 1, to eliminate the impact of different dimensions on model training. Adjust the mean of the data to 0 and the standard deviation to 1 so that the data conforms to the standard normal distribution. Calculate its mean and standard deviation (or maximum and minimum values), and then transform it according to the selected standardization method. Divide the standardized training data into a training set and a test set. The training set is used to train the neural network model, and the test set is used to evaluate the performance of the model.

[0027] In one embodiment, cluster analysis, pattern recognition and other methods are used to perform standardized driving habit data to divide driving behaviors into different driving condition points. Each driving condition point represents a specific driving mode and road condition. The tire wear type corresponding to each driving condition point is determined. For example, frequent sudden braking may lead to increased wear of the tire braking surface, and high-speed turning may lead to wear of the tire sidewall. Through data analysis methods, such as time series analysis, regression analysis, etc., combined with historical tire dynamic data, the tire wear degree corresponding to each driving condition point is evaluated, for example, the reduction in tire tread depth, the uniformity of tread wear and other indicators are calculated. Feature extraction is performed on the wear degree data to identify characteristic parameters closely related to the tire wear type. The characteristic parameters include wear speed, uniformity of wear distribution, wear amount in a specific area, etc. Based on the extracted characteristic parameters, the wear parameters corresponding to each tire wear type are determined according to expert advice. A tire wear prediction model is constructed based on the wear parameters and driving condition point data using machine learning or deep learning algorithms, such as neural networks. The model is trained using historical data, and the model parameters are adjusted to optimize the prediction performance. The pre-set prediction time is determined according to actual needs and application scenarios. This time can be a fixed period, such as weekly or monthly, or it can be triggered based on specific conditions, such as reaching a certain mileage. According to the prediction time, set the prediction cycle of the tire wear prediction model. Ensure that the model can predict according to the set cycle and update the prediction results in time for decision-making reference.

[0028] S103. Acquire real-time driving data through the sensor group, and input the real-time driving data into the tire wear prediction model to determine the predicted wear condition of the tire and the predicted time corresponding to the predicted wear condition, wherein the predicted wear condition includes the tire wear type and the tire wear degree.

[0029] The sensor group collects various data of the vehicle in real time and pre-processes the collected real-time driving data. The pre-processed real-time driving data is input into the tire wear prediction model. The tire wear prediction model calculates and infers the input real-time driving data to obtain the predicted wear of the tire. The prediction results include the tire wear type and tire wear degree. The predicted wear condition is associated with its corresponding prediction time to form a complete prediction report.

[0030] S104, inspecting the tire according to the predicted time to obtain actual wear conditions of the tire, comparing the actual wear conditions with the predicted wear conditions, and issuing an early warning to the driver if the actual wear conditions are consistent with the predicted wear conditions.

[0031] When the preset prediction time is reached, the sensor is automatically triggered by the preset controller to perform tire detection, and the actual wear data obtained during the detection process is recorded in detail, including the actual wear type and actual wear degree. The actual wear condition is compared and analyzed with the predicted wear condition, focusing on the consistency of tire wear type, wear degree and wear distribution. According to actual needs and technical requirements, a reasonable threshold range is set to determine whether the actual wear condition is consistent or close to the predicted wear condition. If the actual wear condition and the predicted wear condition are within the set threshold range, they are considered to be consistent or close. If the judgment result shows that the actual wear condition is consistent or close to the predicted wear condition, an early warning to the driver is triggered. The early warning content should include the current wear condition of the tire, the predicted wear condition, the recommended maintenance or replacement measures, and possible safety risks. The early warning can be sent to the driver through a variety of methods such as a visual on-board display, a mobile phone APP, text messages, and emails.

[0032] In one embodiment, if the actual wear condition is inconsistent with the predicted wear condition, the difference between the actual wear condition and the predicted wear condition is quantified, including the difference in the degree of wear and the difference in the type of wear. First, the degree difference value of the wear degree is determined, and then the type of wear to which the degree difference value corresponds is determined. The wear weight corresponding to the tire wear type is determined, and the wear weight is adjusted according to the degree difference value. For example, the prediction error of a certain wear type is large, and the weight of this type in the model needs to be increased to improve its prediction accuracy. The number of inconsistencies between the actual wear condition and the predicted wear condition is recorded. According to the number of inconsistencies, the prediction time is reduced by multiples. For example, if an inconsistency occurs frequently, the prediction time is reduced by half so that the tire condition can be detected more frequently and the prediction results can be updated.

[0033] In one embodiment, the current weather data, such as temperature, humidity, precipitation, road icing, etc., are obtained in real time through vehicle-mounted meteorological sensors, GPS positioning combined with external meteorological services or mobile phone APPs. The current road condition information, such as road type (asphalt road, cement road, gravel road, etc.), road condition (dry, slippery, muddy, potholes, etc.), traffic flow, speed limit, etc., is obtained by using technologies such as vehicle-mounted navigation systems and traffic information centers. Under different weather conditions, the friction coefficient between the tire and the road surface, the thermal expansion coefficient of the tire material, etc. will change, thereby affecting the wear of the tire. For example, a slippery road surface on rainy days may cause increased tire side slip and accelerate tire edge wear; in hot weather, the tire material softens and the wear rate may increase. Different road conditions also have a significant impact on tire wear. For example, gravel roads or potholes will increase the impact and vibration of the tire, causing the tire to wear faster; while the smooth road surface on the highway will relatively reduce the wear of the tire. According to the results of the environmental information analysis, the main environmental factors affecting the tire wear type and their degree of influence are determined as the basis for adjusting the wear weight. In the tire wear prediction model, an adjustable wear weight is set for each wear type. Dynamically adjust these weights based on the influencing factors of environmental information. For example, when driving in rainy days, increase the weight of side slip wear; when driving on gravel roads, increase the weight of impact wear. Apply the adjusted wear weights to the tire wear prediction model in real time, so that the model can more accurately reflect the tire wear under current environmental conditions. Combine environmental information with historical wear data to further optimize the prediction model's algorithms and parameters and improve the model's long-term prediction capabilities.

[0034] In one embodiment, a detailed prediction report is prepared based on the actual wear and predicted wear of the tire. The report contains information such as the current wear state of the tire, the predicted wear trend, and the prediction accuracy evaluation. The prediction report is uploaded to a predetermined cloud platform. The cloud platform should have the ability to store, process and analyze data so that the multi-vehicle data can be subsequently integrated and analyzed. Multiple prediction reports of multiple vehicles are collected through the cloud platform. These reports should cover a variety of situations such as different vehicle types, different driving conditions, and different usage habits. According to the brand, model, year and other information of the vehicle, the collected prediction reports are classified according to the vehicle type. For each vehicle type, the prediction reports of all its vehicles are integrated to analyze the tire wear of the vehicle of this type, including the analysis of wear speed, wear type, wear distribution and other aspects. According to the tire wear corresponding to the vehicle type, a targeted tire maintenance plan is formulated. The maintenance plan should include the tire replacement time, tire quality inspection cycle, tire parameter adjustment suggestions, driving habit adjustment suggestions, etc. Among them, the tire parameter adjustment suggestion is to propose suggestions for adjusting parameters such as tire pressure and balance based on the wear of the tire to optimize the wear pattern and performance of the tire. Driving habit adjustment suggestions analyze the impact of driving habits on tire wear based on tire wear conditions, and provide drivers with suggestions for adjusting driving habits to reduce unnecessary tire wear. The formulated tire maintenance plan is sent to the corresponding drivers through the cloud platform or other communication methods to ensure that they can understand the content of the maintenance plan and perform tire maintenance in accordance with the plan requirements.

[0035] In one embodiment, based on the comparison between the actual wear conditions and the predicted wear conditions in multiple prediction reports, the ratio of the number of correctly predicted reports to the total number of reports is statistically calculated to calculate the accuracy of the tire wear prediction model. A reasonable accuracy threshold is pre-set based on business needs, industry standards or historical data, and the calculated accuracy is compared with the preset threshold to determine whether the performance of the model meets the requirements. If the accuracy is less than the threshold, it is necessary to further determine which vehicle types have large deviations in the prediction results. Formulate a tire production plan and select the appropriate tire type based on the characteristics of the vehicle type and usage requirements. For example, for vehicles that often travel on harsh road conditions, it may be necessary to select tires with stronger wear resistance. Adjust the factory parameters of the tire, such as air pressure, hardness, tread depth, etc., to adapt to different vehicle types and usage conditions. Send the tire production plan to the vehicle manufacturer so that the vehicle manufacturer can make production adjustments to the vehicle according to the tire production plan.

[0036] In one embodiment, a visual interactive interface pre-set in the vehicle is determined, a prediction report and a tire maintenance plan are obtained through the visual interactive interface, and the prediction report and the tire maintenance plan are displayed.

[0037] like Figure 2As shown, the embodiment of the present application also provides a tire wear detection and warning device for a new energy vehicle, including:

[0038] at least one processor; and,

[0039] a memory communicatively connected to at least one processor; wherein,

[0040] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable a tire wear detection and warning device for a new energy vehicle to perform:

[0041] Determine vehicle parameters of the vehicle, including but not limited to vehicle structure, tire dynamic data, power output characteristics, and obtain the driver's driving habits through a pre-set sensor group, including but not limited to historical driving conditions, turning speed, and number of emergency brakes;

[0042] The vehicle data and the driving habits are standardized to obtain training data, and a neural network model is trained according to the training data to obtain a tire wear prediction model;

[0043] Acquire real-time driving data through the sensor group, and input the real-time driving data into the tire wear prediction model to determine a predicted tire wear condition and a predicted time corresponding to the predicted wear condition, wherein the predicted wear condition includes a tire wear type and a tire wear degree;

[0044] The tire is inspected according to the predicted time to obtain the actual wear condition of the tire, and the actual wear condition is compared with the predicted wear condition. If the actual wear condition is consistent with the predicted wear condition, the driver is warned.

[0045] The embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows:

[0046] Determine vehicle parameters of the vehicle, including but not limited to vehicle structure, tire dynamic data, power output characteristics, and obtain the driver's driving habits through a pre-set sensor group, including but not limited to historical driving conditions, turning speed, and number of emergency brakes;

[0047] The vehicle data and the driving habits are standardized to obtain training data, and a neural network model is trained according to the training data to obtain a tire wear prediction model;

[0048] Acquire real-time driving data through the sensor group, and input the real-time driving data into the tire wear prediction model to determine a predicted tire wear condition and a predicted time corresponding to the predicted wear condition, wherein the predicted wear condition includes a tire wear type and a tire wear degree;

[0049] The tire is inspected according to the predicted time to obtain the actual wear condition of the tire, and the actual wear condition is compared with the predicted wear condition. If the actual wear condition is consistent with the predicted wear condition, the driver is warned.

[0050] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0051] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0052] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0053] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0054] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0055] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0056] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0057] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0058] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0059] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0060] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0061] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0062] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0063] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0064] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A tire wear detection and early warning method for new energy vehicles, characterized in that: include: Determine vehicle parameters of the vehicle, including but not limited to vehicle structure, tire dynamic data, power output characteristics, and obtain the driver's driving habits through a pre-set sensor group, including but not limited to historical driving conditions, turning speed, and number of emergency brakes; The vehicle parameters and the driving habits are standardized to obtain training data, and a neural network model is trained according to the training data to obtain a tire wear prediction model; Acquire real-time driving data through the sensor group, and input the real-time driving data into the tire wear prediction model to determine a predicted tire wear condition and a predicted time corresponding to the predicted wear condition, wherein the predicted wear condition includes a tire wear type and a tire wear degree; Testing the tire according to the predicted time to obtain actual wear of the tire, comparing the actual wear with the predicted wear, and issuing a warning to the driver if the actual wear is consistent with the predicted wear; Determine a driving condition point according to the standardized driving habit, and determine a tire wear type corresponding to the driving condition point; Determine historical tire dynamic data according to the standardized vehicle parameters, and determine the wear degree corresponding to the driving condition point according to the historical tire dynamic data; Extracting features of the wear degree to determine a wear weight corresponding to the tire wear type, and determining the tire wear prediction model according to the wear weight; Determining a preset prediction time, and setting a prediction period of the tire wear prediction model according to the prediction time; If the actual wear condition is inconsistent with the predicted wear condition, determining a degree difference value according to the actual wear condition and the predicted wear condition; Determining the tire wear type corresponding to the degree difference value, and adjusting the wear weight corresponding to the tire wear type according to the degree difference value, so as to update the tire wear prediction model; Counting the number of inconsistencies between the actual wear condition and the predicted wear condition, and reducing the prediction time by a multiple according to the number of inconsistencies, so as to update the tire wear prediction model; Collecting environmental information of the vehicle when it is traveling, including but not limited to weather data and road condition information; The wear weight corresponding to the tire wear type is adjusted according to the environmental information.

2. The method according to claim 1, characterized in that The method further comprises: A sensor group at the tire is determined, and dynamic data of the tire is acquired through the sensor group. The dynamic data of the tire includes but is not limited to tire pressure and temperature, and actual wear of the tire is determined according to the dynamic data of the tire.

3. The method according to claim 1, characterized in that The method further comprises: Determine a prediction report according to the actual wear condition and the predicted wear condition, and upload the prediction report to a predetermined cloud platform; Obtain multiple prediction reports of multiple vehicles through the cloud platform to determine the vehicle type, determine the tire wear corresponding to the vehicle type according to the multiple prediction reports, and determine the tire maintenance plan corresponding to the vehicle type according to the tire wear, wherein the tire maintenance plan includes but is not limited to tire replacement time, tire quality inspection cycle, tire parameter adjustment suggestions, and driving habit adjustment suggestions; The tire repair plan is sent to the driver, so that the driver repairs the tire according to the tire repair plan.

4. The method according to claim 3, characterized in that The method further comprises: Determining the accuracy of the tire wear prediction model according to the multiple prediction reports, and comparing the accuracy with a preset threshold; If the accuracy rate is less than the threshold, the corresponding vehicle type is determined, and a corresponding tire production plan is determined according to the vehicle type, wherein the tire production plan includes but is not limited to a tire type selection plan and factory parameter adjustment; The tire production plan is sent to a vehicle manufacturer corresponding to the vehicle type, so that the vehicle manufacturer adjusts the production of the vehicle according to the tire production plan.

5. The method according to claim 3, characterized in that: The method further comprises: Determine a visual interactive interface pre-set in the vehicle, obtain the prediction report and the tire maintenance plan through the visual interactive interface, and display the prediction report and the tire maintenance plan.

6. A tire wear detection and warning device for new energy vehicles, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the tire wear detection and warning device for a new energy vehicle to perform: Determine vehicle parameters of the vehicle, including but not limited to vehicle structure, tire dynamic data, power output characteristics, and obtain the driver's driving habits through a pre-set sensor group, including but not limited to historical driving conditions, turning speed, and number of emergency brakes; The vehicle parameters and the driving habits are standardized to obtain training data, and a neural network model is trained according to the training data to obtain a tire wear prediction model; Acquire real-time driving data through the sensor group, and input the real-time driving data into the tire wear prediction model to determine a predicted tire wear condition and a predicted time corresponding to the predicted wear condition, wherein the predicted wear condition includes a tire wear type and a tire wear degree; Testing the tire according to the predicted time to obtain actual wear of the tire, comparing the actual wear with the predicted wear, and issuing a warning to the driver if the actual wear is consistent with the predicted wear; Determine a driving condition point according to the standardized driving habit, and determine a tire wear type corresponding to the driving condition point; Determine historical tire dynamic data according to the standardized vehicle parameters, and determine the wear degree corresponding to the driving condition point according to the historical tire dynamic data; Extracting features of the wear degree to determine a wear weight corresponding to the tire wear type, and determining the tire wear prediction model according to the wear weight; Determining a preset prediction time, and setting a prediction period of the tire wear prediction model according to the prediction time; If the actual wear condition is inconsistent with the predicted wear condition, determining a degree difference value according to the actual wear condition and the predicted wear condition; Determining the tire wear type corresponding to the degree difference value, and adjusting the wear weight corresponding to the tire wear type according to the degree difference value, so as to update the tire wear prediction model; Counting the number of inconsistencies between the actual wear condition and the predicted wear condition, and reducing the prediction time by a multiple according to the number of inconsistencies, so as to update the tire wear prediction model; Collecting environmental information of the vehicle when it is traveling, including but not limited to weather data and road condition information; The wear weight corresponding to the tire wear type is adjusted according to the environmental information.

7. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Determine vehicle parameters of the vehicle, including but not limited to vehicle structure, tire dynamic data, power output characteristics, and obtain the driver's driving habits through a pre-set sensor group, including but not limited to historical driving conditions, turning speed, and number of emergency brakes; The vehicle parameters and the driving habits are standardized to obtain training data, and a neural network model is trained according to the training data to obtain a tire wear prediction model; Acquire real-time driving data through the sensor group, and input the real-time driving data into the tire wear prediction model to determine a predicted tire wear condition and a predicted time corresponding to the predicted wear condition, wherein the predicted wear condition includes a tire wear type and a tire wear degree; Testing the tire according to the predicted time to obtain actual wear of the tire, comparing the actual wear with the predicted wear, and issuing a warning to the driver if the actual wear is consistent with the predicted wear; Determine a driving condition point according to the standardized driving habit, and determine a tire wear type corresponding to the driving condition point; Determine historical tire dynamic data according to the standardized vehicle parameters, and determine the wear degree corresponding to the driving condition point according to the historical tire dynamic data; Extracting features of the wear degree to determine a wear weight corresponding to the tire wear type, and determining the tire wear prediction model according to the wear weight; Determining a preset prediction time, and setting a prediction period of the tire wear prediction model according to the prediction time; If the actual wear condition is inconsistent with the predicted wear condition, determining a degree difference value according to the actual wear condition and the predicted wear condition; Determining the tire wear type corresponding to the degree difference value, and adjusting the wear weight corresponding to the tire wear type according to the degree difference value, so as to update the tire wear prediction model; Counting the number of inconsistencies between the actual wear condition and the predicted wear condition, and reducing the prediction time by a multiple according to the number of inconsistencies, so as to update the tire wear prediction model; Collecting environmental information of the vehicle when it is traveling, including but not limited to weather data and road condition information; The wear weight corresponding to the tire wear type is adjusted according to the environmental information.

Images