A tire carcass life prediction method and system based on intelligent tire technology

Abstract

The present application relates to the technical field of data processing, in particular to a kind of tire carcass life prediction method and system based on intelligent tire technology, the method comprises: obtaining tire vibration data and other multiple dimensions under tire wear related data;Based on tire vibration data, data segmentation is carried out to the distance traveled;For each segmented mileage, the wear coefficient of the segmented mileage is calculated;Based on the wear coefficient of each segmented mileage, a prediction model is constructed, and the remaining life of the tire carcass is predicted based on the prediction model.The present application embeds high-precision sensors in the tire, collects vibration and temperature data in real time, quantifies the influence of each different road section on tire wear through the vibration and temperature changes of the vehicle on different road sections, thereby achieving accurate prediction of tire wear;Solve the problem that the influence of the road conditions of different road sections on tire wear is not considered in the prior art, which leads to inaccurate prediction results.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a tire body life prediction method and system based on intelligent tire technology. BACKGROUND

[0002] Tire is a key component of a vehicle, and its performance and life have an important influence on the vehicle. The traditional tire life prediction method usually relies on laboratory tests and empirical data, which cannot reflect the actual wear condition of the tire under different road conditions in real time and accurately. Moreover, this tire wear detection method mainly relies on periodic inspection and maintenance, which has a detection blind area and cannot timely discover and handle potential safety hazards.

[0003] The intelligent tire technology in the prior art embeds sensors in the tire to monitor the pressure, temperature and other parameters of the tire in real time, which provides the possibility for tire state monitoring and life prediction. This method not only improves the service life of the tire, but also improves the driving safety of the vehicle. Although some existing intelligent tires can monitor vibration and temperature, they rarely consider the influence of different road conditions such as flat road, rugged road or slippery road on tire wear. Different road conditions have different influences on tire wear, and existing intelligent tires often cannot distinguish and quantify these influences, so the model cannot accurately predict the tire life in complex and variable actual driving environments. Therefore, the data processing and prediction model of these preliminary application intelligent tire products still needs to be further optimized to realize more accurate tire wear prediction. SUMMARY

[0004] In order to solve the above technical problems, the purpose of the present application is to provide a tire body life prediction method and system based on intelligent tire technology, and the technical solution adopted is as follows:

[0005] A tire body life prediction method based on intelligent tire technology, the method comprising:

[0006] obtaining tire vibration data and other multi-dimensional tire wear related data;

[0007] segmenting the data based on the tire vibration data according to the driving mileage;

[0008] For each segmented mileage, the tire vibration data and other dimensional data are combined to calculate the wear coefficient of the segmented mileage;

[0009] constructing a prediction model based on the wear coefficients of each segmented mileage, and predicting the remaining life of the tire body based on the prediction model.

[0010] Further, the obtaining of tire vibration data further comprises:

[0011] The triaxial acceleration sensor is used to detect the acceleration data of the vehicle tire in the X-axis, Y-axis and Z-axis directions, and the acceleration data of the Z-axis is taken as the tire vibration data corresponding to the time.

[0012] Further, the tire wear related data in the other plurality of dimensions further comprises:

[0013] Tire temperature data, tire pressure data, tire load data, vehicle speed data.

[0014] Further, the data segmentation of the travel mileage based on the tire vibration data further comprises:

[0015] For the distance between each two tire pattern depth measurements, the difference between the plurality of tire vibration data of the vehicle in the neighborhood and the average vibration when the vehicle is stationary is calculated as the real-time vibration fluctuation;

[0016] According to the real-time vibration fluctuation and the change of the vehicle speed corresponding to the distance between the vehicle runs, the travel mileage is segmented to obtain a plurality of different subintervals.

[0017] Further, the calculation of the wear coefficient of each segmented mileage combined with each data dimension further comprises:

[0018] For each segmented mileage, the data mean of each data dimension corresponding to the segmented mileage is obtained, including the tire temperature mean, the tire pressure mean, the tire load mean and the vehicle speed mean corresponding to the segmented mileage;

[0019] According to the tire vibration data of each point on the segmented mileage, the average vibration fluctuation of the segmented mileage is calculated;

[0020] According to the average vibration fluctuation corresponding to the segmented mileage and the undetermined parameter of the corresponding data dimension, the data mean of each data dimension and the undetermined parameter of the corresponding data dimension, the wear coefficient of the segmented mileage is calculated.

[0021] Further, the undetermined parameter of the data dimension is specifically: for any one data dimension, based on the actual measurement result of the segmented mileage, and the wear coefficient of the segmented mileage and the mileage of the segmented mileage, the error amount of single measurement is determined;

[0022] For multiple data measurement results, when the error amount of multiple tire pattern depth measurements is minimized, the corresponding parameter size is taken as the undetermined parameter of the corresponding data dimension. Further, the prediction of the remaining life of the tire body based on the prediction model further comprises:

[0023] The travel mileage in the future running process of the vehicle is input into the prediction model;

[0024] data partitioning is performed on the travel mileage in the future running process of the vehicle to obtain a plurality of data segments;

[0025] average vibration fluctuation and temperature mean value of each segment mileage are calculated respectively;

[0026] The wear coefficients of a plurality of segment mileages in the travel mileage in the subsequent running process of the vehicle are calculated according to the undetermined parameters determined according to the plurality of tire pattern depth measurement results of the vehicle, the average vibration fluctuation of each segment mileage, and the temperature mean value.

[0027] The total wear amount prediction value of the vehicle tire is calculated according to the wear coefficients of a plurality of segment mileages.

[0028] The tire body remaining life is calculated according to the total wear amount prediction value of the vehicle tire.

[0029] Further, the calculation of the total wear amount prediction value of the vehicle tire according to the wear coefficients of a plurality of segment mileages further comprises:

[0030] The initial total wear amount prediction value of the vehicle tire is calculated according to the wear coefficients of a plurality of segment mileages.

[0031] The measurement results of the remaining vehicles when the new tire is installed to the first tire pattern depth measurement are obtained, and the initial wear coefficient size is calculated according to the measurement results of the first time and the travel mileage.

[0032] The initial total wear amount prediction value is corrected according to the initial wear coefficient size to obtain the total wear amount prediction value.

[0033] Further, the method further comprises:

[0034] The tire body remaining life is reminded to the user in real time through the vehicle-mounted computer or the mobile terminal device.

[0035] A tire body life prediction system based on intelligent tire technology, the system comprises:

[0036] A data acquisition module for acquiring tire vibration data, determining tire vibration data based on the tire vibration data;

[0037] A model construction module for data segmentation on the travel mileage based on the tire vibration data; for each segment mileage, the wear coefficient of the segment mileage is calculated; and a prediction model is constructed based on the wear coefficients of each segment mileage;

[0038] A prediction module for predicting the tire body remaining life based on the prediction model.

[0039] The present application has the following beneficial effects: the present application obtains tire vibration data and other multi-dimensional tire wear related data; data is segmented based on tire vibration data for the distance traveled; for each segmented distance, the wear coefficient of the segmented distance is calculated; a prediction model is constructed based on the wear coefficients of each segmented distance, and the remaining life of the tire body is predicted based on the prediction model. The present application realizes accurate prediction of tire wear by embedding high-precision sensors in the tire, collecting vibration and temperature data in real time, quantifying the influence of different road sections on tire wear through vibration and temperature changes of the vehicle on different road sections, thereby realizing accurate prediction of tire wear; the prediction model of the present application divides the distance by analyzing the vibration changes on different road sections in the historical data, can accurately identify the driving situation of the vehicle on different road sections, so that the wear prediction is more targeted and accurate; the wear coefficient of each segmented distance is calculated through the tire vibration data and temperature data of each segmented distance, which improves the accuracy of wear prediction; only vibration and temperature change data are used to quantify tire wear, which simplifies the data type and complexity required for wear prediction, improves the efficiency of real-time monitoring and prediction, reduces the operating cost of the vehicle, and through the prediction model, helps users to reasonably plan the use and replacement time of the tire, prolongs the service life of the tire, reduces unnecessary replacement, reduces the operating cost of the vehicle, and at the same time, discovers and handles the seriously worn tire in advance, avoiding the safety risk caused by excessive wear of the tire. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings.

[0041] Figure 1 A flowchart of a tire body life prediction method based on intelligent tire technology provided by an embodiment of the present application;

[0042] Figure 2 A vibration curve schematic diagram provided by an embodiment of the present application;

[0043] Figure 3 A speed curve schematic diagram provided by an embodiment of the present application;

[0044] Figure 4 A schematic diagram of a tire body life prediction system based on intelligent tire technology provided by an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined object, the specific implementation, structure, features and effects of a tire body life prediction method and system based on intelligent tire technology according to the present application are described in detail as follows in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0047] During vehicle operation, tire wear mainly depends on the tread depth of the tire. As the tire is used for a long time and the mileage increases, the tire surface pattern will gradually wear thin. When the tire tread depth is less than 1.6mm, the tire and road friction is greatly reduced, and the braking distance of the car will be longer, directly increasing the driving risk by several times. According to the national standard line, the initial tire tread depth is started until it is worn to 1.6mm, and the tire life is from 100% wear to 0%.

[0048] The specific scheme of the tire body life prediction method based on intelligent tire technology provided by the present application is described in detail below in combination with the drawings.

[0049] Please refer to Figure 1 which shows a flowchart of a tire body life prediction method based on intelligent tire technology provided by one embodiment of the present application. The method comprises:

[0050] Step S110: Obtain tire vibration data and other multi-dimensional tire wear related data.

[0051] The factors affecting tire wear include tire vibration data, tire temperature data, tire load data, tire pressure data, vehicle speed data, road condition data, etc. Tire wear related data includes tire temperature data, tire pressure data, tire load data, and vehicle speed data, each corresponding to a data dimension.

[0052] The vibration, pressure and other data can be obtained by the acceleration sensor and the pressure sensor installed inside the tire. The acceleration sensor and the pressure sensor are installed inside the tire to capture the vibration signal of the tire. When the tire rolls on the road, the unevenness of the road will cause the tire to vibrate. The acceleration sensor can measure the vibration of the object in the acceleration direction, and thus understand the working state, wear degree and other conditions of the tire. The tire temperature data can be obtained according to the ideal gas equation, which is a known technology and will not be described in detail here. The tire load data can be predicted according to the vibration data. The tire load data is obtained according to the historical vibration data. The prediction method is also a known technology and will only be briefly introduced here. The vibration signal in the collected historical data is analyzed in time domain, frequency domain and time-frequency domain, and the root mean square value, peak-to-peak value, spectral energy distribution, wavelet coefficient and other key features are extracted to construct an input feature vector. A CNN model is constructed, and a mean square error loss function is used for training. The trained model is integrated into the vehicle-mounted system, and the real-time sensor data stream is combined to estimate the load to obtain the tire load data.

[0053] When using a three-axis acceleration sensor to detect the vibration of the vehicle tire, the vibration signals on the three axes, i.e., the X-axis, the Y-axis and the Z-axis, are usually considered simultaneously. The three axes represent the vibration in different directions. The road condition data can be quantified according to the tire vibration data during the driving process of the vehicle. Considering that the vertical vibration is most obvious during the driving process of the tire due to the unevenness, potholes and other reasons of the road, the concave-convex of the road will cause the tire to produce a large acceleration change in the vertical direction. Therefore, the acceleration change data of the Z-axis is used as the tire vibration data.

[0054] The tire vibration data, temperature change data and real-time vehicle speed change data are comprehensively analyzed to predict the real-time life of the subsequent tire.

[0055] It should be noted that in the present embodiment, the tire vibration data and other various kinds of tire wear related data provide a data basis for subsequent joint analysis of the wear of the tire. Each kind of tire wear related data corresponds to one dimension. At the same time, the tire vibration data also corresponds to one kind, i.e., the tire vibration data also corresponds to one data dimension. That is, the present embodiment includes tire vibration data, tire temperature data, tire pressure data, tire load data and vehicle speed data, i.e., five dimensions of monitoring data of vehicle driving.

[0056] For a single vehicle, the tire wear condition is more likely to be affected by the road surface condition of the road section. For example, when driving on a smooth straight road, the vehicle speed is relatively more stable, and the fluctuation of the vehicle tire is smaller, so the tire wear is smaller. Conversely, when driving on a rugged mountain road, the vehicle speed changes more, and because the road smoothness is poor, the vibration fluctuation is also relatively larger, and the tire wear is also larger.

[0057] Therefore, it is necessary to divide the vibration data changes of the vehicle in different operating states. When the vehicle is stationary, the vehicle speed is 0, and the tire wear in this type of time period is 0. Therefore, only the data at a speed of 0 is considered for tire life analysis during the actual tire vibration data and temperature data acquisition process. Then, according to the mileage distance (vehicle kilometers) of the vehicle operation, the mileage is divided.

[0058] Step S120: data segmentation of the travel mileage based on the tire vibration data.

[0059] In an optional embodiment, step S120 further comprises: for the distance between each two tire pattern depth measurements, the difference between the multiple tire vibration data of the vehicle in the neighborhood and the average vibration when stationary is calculated as the real-time vibration fluctuation; according to the real-time vibration fluctuation and the vehicle speed change between the corresponding distance, the travel mileage is segmented to obtain multiple different subintervals.

[0060] The tire pattern depth measurement is performed when the vehicle kilometers are , and the next tire pattern depth measurement is performed when the corresponding kilometers are . First, the data of the travel mileage is segmented according to the tire vibration data. In the interval, the vehicle will start and brake multiple times. Because the vibration change amplitude of the tire is large during starting and braking, and because of the difference in driving habits of different users, the tire wear during starting and braking is also different. Figure 2 is a schematic diagram of the vibration curve provided by an embodiment of the present application. In this embodiment, the acceleration change data of the Z-axis is the tire vibration data, Figure 2 which is a schematic diagram of the acceleration curve; Figure 3 is a schematic diagram of the speed curve provided by an embodiment of the present application; Figure 2 and Figure 3 are a process of the vehicle from starting to stopping and the corresponding tire vibration data and speed change schematic diagram, in which the speed unit is m / s. For example, Figure 2 and Figure 3As shown, when the vehicle speed changes, the vibration data changes greatly, and when the vehicle suddenly accelerates and brakes subsequently, the vibration data fluctuates greatly, so the vibration fluctuation of the vehicle at the mileage of is the following formula (1):

[0061] ; (1)

[0062] wherein the vibration fluctuation of the vehicle at the mileage of represents the size of the position neighborhood; represents the vibration size at the mileage of represents the average vibration size corresponding to the vehicle speed of 0 in the mileage interval ; wherein .

[0063] That is, the real-time vibration fluctuation is calculated by using the difference between the multiple tire vibration data of the vehicle in the neighborhood and the average vibration when the vehicle is stationary, and the fluctuation of the vibration is quantified.

[0064] After obtaining the vibration fluctuation corresponding to each different mileage, according to the vibration fluctuation and the corresponding speed change, the travel mileage is segmented, and the loss change degree at the mileage of is the following formula (2):

[0065] ; (2)

[0066] wherein represents the vibration fluctuation at the mileage of represents the first-order difference size of the speed at the mileage of is the loss change degree at the mileage of

[0067] According to the change data of , the average loss change degree at the mileage of is calculated and determined, and when , the mileage is determined as the data segmentation endpoint between the travel mileages; wherein ; according to the obtained multiple mileage data segmentation endpoints, the vehicle travel mileage is divided into multiple different subintervals.

[0068] ​​​​​​​​​Step S130: For each segment mileage, calculate the wear coefficient for that segment mileage.

[0069] In an optional implementation, step S130 further includes: for each segment mileage, obtaining the average data value under each data dimension corresponding to the segment mileage, including the average tire temperature, average tire pressure, average tire load, and average vehicle speed corresponding to the segment mileage; calculating the average vibration fluctuation of the segment mileage based on the tire vibration data at each point on the segment mileage; and calculating the wear coefficient of the segment mileage based on the average vibration fluctuation corresponding to the segment mileage, the undetermined parameters of the corresponding data dimension, the average data value under each data dimension, and the undetermined parameters of the corresponding data dimension.

[0070] Because tire wear varies across different vehicles, and driving habits differ among users, simply relying on tire vibration data from different road sections is insufficient to accurately quantify the specific wear amount and corresponding wear coefficient of different tires on various road surfaces. Therefore, for the tire being tested, step S120 above involves segmenting the mileage based on tire vibration data to obtain multiple segmented mileages. Each segmented mileage represents the mileage at which a tire tread depth measurement is performed after replacing the tire. The mileage traveled during the first tire tread depth measurement was as follows: Let the tire tread depth wear corresponding to each of the above intervals be respectively... .

[0071] The tire vibration data between every two tread depth measurements for each segment mileage is constructed into a sub-data sequence, and multiple segment mileages are constructed into multiple different sub-data sequences. Within each sub-sequence, the tire vibration data is relatively consistent, indicating that the vehicle's operating state is relatively stable under the corresponding mileage of a single sub-sequence, and the tire wear per unit distance will not change significantly. Therefore, within a single sub-sequence, the tire wear coefficient will be calculated more accurately.

[0072] Considering that tire temperature may vary across different mileage segments, and that the rubber strength of the tire surface decreases to some extent as temperature rises (temperature changes are not significant in short mileage segments, so the effect of temperature changes is not considered when dividing the mileage), the mileage segment is recorded as follows: The wear coefficient of each subsequence is Then the first The formula for calculating the wear coefficient of each segmented mileage subsequence is as follows (3):

[0073] (3)

[0074] in, Represents an exponential function; For the undetermined parameters in the v-th data dimension, This represents the undetermined parameter under the (m+1)th data dimension, which is also the undetermined parameter under the tire vibration data dimension (to be solved based on the actual wear amount). m represents the total number of other data dimensions besides the tire vibration data dimension, and the value in this embodiment is 4. Indicates the first A series of vibrational change subsequences; Indicates the first The mean of the data in the v-th data dimension corresponding to each vibration change subsequence.

[0075] The average data values ​​for each data dimension include the average tire temperature, average tire pressure, average tire load, and average vehicle speed corresponding to that mileage segment. For example, Indicates the first The average tire temperature within the mileage corresponding to each vibration change subsequence.

[0076] In one alternative implementation, the undetermined parameter is determined based on the actual wear amount. Specifically, based on the actual wear of the tire tread depth at each mileage segment, an exponential function is used to fit the wear coefficient of each mileage segment to the product of the average tire temperature and average vibration fluctuation corresponding to that mileage segment, thus obtaining the magnitude of the error for a single measurement. For multiple tire tread depth measurements, the parameter value corresponding to the minimum sum of errors from multiple measurements is determined and used as a parameter to be determined. .

[0077] Since vibration fluctuations and the relationship between temperature and road surface are not simple linear changes, the wear coefficient for each tire tread depth segment is fitted using an exponential function based on the actual wear amount at that mileage segment. The fitting relationship between the parameters corresponding to the segmented mileage is determined by first determining the magnitude of the error of a single measurement in each dimension. This embodiment takes the data dimension corresponding to tire vibration data as an example for illustration, and the formula is as follows (4).

[0078] (4)

[0079] in Indicates the first The actual wear amount measured during the first tire tread depth measurement; Indicates the first The depth of the pattern was measured to the first... The number of vibration change subsequences existing between the secondary pattern depth measurements; Indicates the first Wear coefficient of each vibration variation subsequence; denotes the mileage of the i-th sub-sequence; denotes the error size of the i-th tire pattern depth measurement; denotes the error size of the i-th tire pattern depth measurement; denotes the error size of the i-th tire pattern depth measurement;

[0080] Then, for multiple pattern depth measurement results, when the sum of the error sizes reaches the minimum, the above-mentioned to-be-determined parameters can be obtained, as shown in the following formula (5):

[0081] , ; (5)

[0082] denotes the error size of the i-th tire pattern depth measurement; denotes the error size of the i-th tire pattern depth measurement; denotes the error size of the i-th tire pattern depth measurement; denotes the error size of the i-th tire pattern depth measurement; is a to-be-determined parameter in the data dimension corresponding to the tire vibration data, which is solved according to the actual wear amount of the tire pattern depth; denotes the value of the independent variable when the function takes the minimum value, that is, denotes the value of the independent variable when the function takes the minimum value, that is, denotes the value of the independent variable when the function takes the minimum value, that is, denotes the value of the independent variable when the function takes the minimum value, that is,

[0083] According to the gradient descent method, the above-mentioned is solved.

[0084] It should be noted that, in the data dimension corresponding to the tire vibration data, the actual wear amount of the tire pattern depth is used to determine the error size of single measurement in the corresponding data dimension. In other data dimensions, the error size of single measurement in the corresponding dimension can be calculated according to the actual measurement results of single measurement in the corresponding dimension. Meanwhile, the above-mentioned k is described by taking the tire vibration data dimension as an example, and the calculation method of the above-mentioned k in each data dimension is the same, that is, the calculation method according to the formula (5) can obtain to .

[0085] Step S140: Constructing a prediction model based on the wear coefficients of each segmented mileage, and predicting the remaining life of the tire body based on the prediction model.

[0086] ​​​In an alternative embodiment, step S140 further comprises: inputting the running mileage in the future running process of the vehicle into the prediction model, performing data partition on the running mileage in the future running process of the vehicle, to obtain a plurality of data segments; calculating the average vibration fluctuation and the average temperature of each segment mileage respectively; determining the undetermined parameters according to the plurality of tire pattern depth measurement results of the vehicle, the average vibration fluctuation and the average temperature of each segment mileage, calculating the wear coefficients of a plurality of segment mileages in the running mileage in the subsequent running process of the vehicle; calculating the total wear amount prediction value of the vehicle tire according to the wear coefficients of a plurality of segment mileages; and calculating the remaining life of the tire body of the vehicle according to the total wear amount prediction value of the vehicle tire.

[0087] For a tire of a vehicle, in obtaining its historical data After the actual wear amount of the second tire pattern depth measurement, the same method is used to divide the mileage in the subsequent running process of the vehicle, and the average vibration fluctuation and the average tire temperature data of each segment mileage are calculated respectively, and the historical plurality of tire pattern depth measurement results of the vehicle are combined to obtain the value of the tire of the vehicle, and then the wear coefficients of each different road section are calculated.

[0088] Calculate the initial total wear amount prediction value of the vehicle tire The formula is formula (6) as follows:

[0089] ; (6)

[0090] wherein, represents the number of times of tire pattern depth detection; represents the wear amount of the pattern depth from the th detection to the th detection process; represents the number of segment mileages contained in the mileage change data from the th detection to the present; represents the wear coefficient of the th segment mileage; represents the mileage of the th segment; is the initial total wear amount prediction value of the vehicle tire.

[0091] Since the above analysis process is based on the existence of historical detection data; when the above If the vehicle has been in use for a long time, the initial wear amount of the tire cannot be quantified, and thus accurate estimation of the tire wear amount cannot be performed; however, since the tire wear degree is low when the tire is initially used, the initial wear amount can be quantified according to the tire measurement data of the plurality of other vehicles, although the error is relatively large, the influence on the vehicle safety is small. In an optional embodiment, the step of calculating the total wear amount prediction value of the vehicle tire according to the wear coefficients of the plurality of segmented mileages further comprises: calculating an initial total wear amount prediction value of the vehicle tire according to the wear coefficients of the plurality of segmented mileages; obtaining the measurement results of the other vehicles when the new tire is installed to the first tire pattern depth measurement, calculating the initial wear coefficient size according to the first measurement results and the travel mileage; correcting the initial total wear amount prediction value according to the initial wear coefficient size to obtain the total wear amount prediction value.

[0092] Therefore, the wear amount of the other vehicles when the new tire is installed to the first tire pattern depth measurement is obtained, and the corresponding mileage change is recorded, the measurement results of the other vehicles when the new tire is installed to the first tire pattern depth measurement are obtained, and the initial wear coefficient size is calculated according to the first measurement results and the travel mileage. Specifically, the average value of the ratio of the wear amount to the mileage when the first tire pattern depth measurement is performed is taken as the initial wear coefficient size .

[0093] Therefore, the total wear amount prediction value of the vehicle tire after correction is as follows (7):

[0094] ; (7)

[0095] wherein, is the initial total wear amount prediction value of the vehicle tire; represents the initial wear coefficient size; represents the mileage size from the beginning of the use of the tire to the present; is the total wear amount prediction value of the vehicle tire after correction.

[0096] At this point, the prediction result of the real-time tire wear amount is obtained, and the remaining life of the tire body is calculated according to the total wear amount prediction value of the vehicle tire , and the calculation formula is as follows (8):

[0097] ; (8)

[0098] wherein, represents the initial pattern depth; is the total wear amount prediction value of the vehicle tire after correction; represents the minimum value of the pattern depth, and the unit is mm.

[0099] In an optional embodiment, after the remaining life L of the tire body is calculated, the method further comprises: reminding the user in real time through the on-board computer or the mobile terminal device to prevent safety hazards caused by excessive tire wear.

[0100] By adopting the method of the embodiment, the tire vibration data and the tire wear related data in other dimensions are acquired, the travel mileage is segmented based on the tire vibration data, the wear coefficient of each segmented mileage is calculated, and the prediction model is constructed based on the wear coefficients of the segmented mileages, and the remaining life of the tire body is predicted based on the prediction model. The high-precision sensor is embedded in the tire to collect vibration and temperature data in real time, the influence of different road sections on tire wear is quantified through the vibration and temperature changes of the vehicle on different road sections, so that the tire wear condition is accurately predicted. The prediction model of the method divides the mileage by analyzing the vibration changes on different road sections in the historical data, so that the driving condition of the vehicle on different road sections can be accurately identified, and the wear prediction is more targeted and accurate. The wear coefficient of each segmented mileage is calculated through the tire vibration data and the temperature data of each segmented section, so that the accuracy of the wear prediction is improved. The vibration and temperature change data are used to quantify the tire wear, so that the data type and complexity required for wear prediction are simplified, the real-time monitoring and prediction efficiency is improved, the vehicle operation cost is reduced, the user can be helped to reasonably plan the use and replacement time of the tire, the service life of the tire is prolonged, unnecessary replacement is reduced, the vehicle operation cost is reduced, and the safety risk caused by excessive tire wear is avoided.

[0101] The specific scheme of the tire body life prediction system based on the intelligent tire technology provided by the present application is described in detail below with reference to the accompanying drawings.

[0102] Please refer to Figure 4 which shows a schematic diagram of a tire body life prediction system based on intelligent tire technology provided by an embodiment of the present application, the system comprising: a data acquisition module 510, a model construction module 520, and a prediction module 530.

[0103] The data acquisition module 510 is configured to acquire tire vibration data and tire wear related data in other dimensions.

[0104] The model construction module 520 is configured to segment the travel mileage based on the tire vibration data, calculate the wear coefficient of each segmented mileage, and construct a prediction model based on the wear coefficients of the segmented mileages.

[0105] The prediction module 530 is configured to predict the remaining life of the tire body based on the prediction model.

[0106] In an optional implementation, the data acquisition module 510 is further configured to detect acceleration data of the vehicle tire in X-axis, Y-axis and Z-axis directions respectively by using a three-axis acceleration sensor, and take the acceleration data of the Z-axis as the tire vibration data corresponding to the time.

[0107] In an optional implementation, the data acquisition module 510 is further configured to acquire the tire wear related data in other multiple dimensions, including tire temperature data, tire pressure data, tire load data and vehicle speed data.

[0108] In an optional implementation, the model construction module 520 is further configured to calculate real-time vibration fluctuation by calculating the difference between the multiple tire vibration data of the vehicle in the neighborhood and the average vibration when the vehicle is stationary for each distance interval between two tire pattern depth measurements; and perform data segmentation on the travel distance according to the real-time vibration fluctuation and the change of the vehicle speed in the corresponding distance interval, to obtain multiple different subintervals.

[0109] In an optional implementation, the model construction module 520 is further configured to acquire the average tire temperature corresponding to each segmented distance interval; calculate the average vibration fluctuation of the segmented distance interval according to the tire vibration data of each point on the segmented distance interval; and calculate the wear coefficient of the segmented distance interval according to the average tire temperature corresponding to the segmented distance interval, the average vibration fluctuation and the undetermined parameter determined according to the actual wear amount.

[0110] In an optional implementation, the undetermined parameter determined according to the actual wear amount is specifically: based on the actual wear amount of the tire pattern depth of the segmented distance interval, fitting the product of the wear coefficient of each segmented distance interval and the average tire temperature and the average vibration fluctuation corresponding to the segmented distance interval by using an exponential function to obtain the error amount of a single time; and for multiple tire pattern depth measurement results, solving the parameter size corresponding to the minimum error amount sum of multiple tire pattern depth measurements as the undetermined parameter.

[0111] In an alternative embodiment, the prediction module 530 is further configured to: input the travel mileage in the future running of the vehicle into the prediction model, perform data partitioning on the travel mileage in the future running of the vehicle to obtain a plurality of data segments; calculate the average vibration fluctuation and the temperature mean of each segment mileage respectively; calculate the wear coefficients of the plurality of segment mileages in the future running of the vehicle according to the undetermined parameters determined according to the plurality of tire pattern depth measurements of the vehicle, the average vibration fluctuation of each segment mileage, and the temperature mean; calculate the total wear amount prediction value of the tire of the vehicle according to the wear coefficients of the plurality of segment mileages; and calculate the remaining life of the tire body of the vehicle according to the total wear amount prediction value of the tire of the vehicle.

[0112] In an alternative embodiment, the prediction module 530 is further configured to: calculate the initial total wear amount prediction value of the tire of the vehicle according to the wear coefficients of the plurality of segment mileages; obtain the measurement results of the remaining vehicles when the new tire is installed to the first tire pattern depth measurement, calculate the initial wear coefficient size according to the measurement results of the first time and the travel mileage; and correct the initial total wear amount prediction value according to the initial wear coefficient size to obtain the total wear amount prediction value.

[0113] In an alternative embodiment, the prediction module 530 is further configured to: remind the user in real time through the on-board computer or the mobile terminal device about the remaining life of the tire body.

[0114] The system of the embodiment adopts high-precision sensors to collect vibration and temperature data in real time, quantifies the influence of different road sections on tire wear through the vibration and temperature changes of the vehicle on different road sections, and thus realizes accurate prediction of the tire wear condition; the prediction model of the system divides the mileage by analyzing the vibration changes on different road sections in the historical data, can accurately identify the driving condition of the vehicle on different road sections, and makes the wear prediction more targeted and accurate; the wear coefficient of each segmented mileage is calculated through the tire vibration data and temperature data of each segmented section, and the accuracy of the wear prediction is improved; only the vibration and temperature change data are used to quantify the tire wear, the data type and complexity required for wear prediction are simplified, and the efficiency of real-time monitoring and prediction is improved, which can reduce the operating cost of the vehicle; through the prediction model, the user can also reasonably plan the use and replacement time of the tire, prolong the service life of the tire, reduce unnecessary replacement, reduce the operating cost of the vehicle, and at the same time, the seriously worn tires can be found and processed in advance, avoiding the safety risks caused by excessive wear of the tire.

[0115] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0116] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments.

Claims

1. A method for predicting the life of a tire carcass based on smart tire technology, characterized in that, The method comprises: acquiring tire vibration data and other multiple dimensions of tire wear related data; segmenting the travel mileage based on the tire vibration data; for each segmented mileage, combining the tire vibration data and other each dimension data to calculate the wear coefficient of the segmented mileage; constructing a prediction model based on the wear coefficient of each segmented mileage, and predicting the remaining life of the tire body based on the prediction model; wherein the segmentation of the travel mileage based on the tire vibration data further comprises: for the distance between each two tire pattern depth measurements, the difference between the multiple tire vibration data of the vehicle in the neighborhood and the average vibration when the vehicle is stationary calculates the real-time vibration fluctuation; according to the real-time vibration fluctuation and the change of the vehicle speed corresponding to the distance between the vehicle operation, the travel mileage is segmented to obtain multiple different subintervals; the wear coefficient of the segmented mileage is calculated by combining the tire vibration data and other each dimension data further comprises: for each segmented mileage, the data mean of each data dimension corresponding to the segmented mileage is acquired, including the tire temperature mean, the tire pressure mean, the tire load mean and the vehicle speed mean corresponding to the segmented mileage; according to the tire vibration data of each point on the segmented mileage, the average vibration fluctuation of the segmented mileage is calculated; according to the average vibration fluctuation corresponding to the segmented mileage and the to-be-determined parameter of the corresponding data dimension, the data mean of each data dimension and the to-be-determined parameter of the corresponding data dimension, the wear coefficient of the segmented mileage is calculated; the to-be-determined parameter of the data dimension is specifically: for any one data dimension, based on the actual measurement results of the segmented mileage, the wear coefficient of the segmented mileage and the mileage of the segmented mileage, the error amount of single measurement is determined; for multiple data measurement results, when the error amount of multiple tire pattern depth measurements is the smallest, the corresponding parameter size is taken as the to-be-determined parameter of the corresponding data dimension.

2. A method for predicting the life of a tire carcass based on smart tire technology according to claim 1, characterized in that, the acquisition of tire vibration data further comprises: using a three-axis acceleration sensor to detect the acceleration data of the vehicle tire in X axis, Y axis and Z axis directions, and taking the acceleration data of Z axis as the tire vibration data corresponding to the time.

3. A method for predicting the life of a tire carcass based on smart tire technology according to claim 2, characterized in that, the other multiple dimensions of tire wear related data further comprise: tire temperature data, tire pressure data, tire load data and vehicle speed data.

4. A method for predicting the life of a tire carcass based on smart tire technology according to claim 1, characterized in that, the prediction of the remaining life of the tire body based on the prediction model further comprises: inputting the travel mileage in the future running process of the vehicle into the prediction model; dividing the travel mileage in the future running process of the vehicle to obtain multiple data segments; respectively calculating the average vibration fluctuation and the temperature mean of each segmented mileage; determining the to-be-determined parameter according to the multiple tire pattern depth measurement results of the vehicle, the average vibration fluctuation and the temperature mean of each segmented mileage to calculate the wear coefficient of multiple segmented mileages in the future running process of the vehicle; according to the wear coefficient of multiple segmented mileages, the total wear amount prediction value of the vehicle tire is calculated; The total wear prediction value of the vehicle tire is calculated according to the total wear prediction value of the vehicle tire.

5. A method for predicting the life of a tire carcass based on smart tire technology according to claim 4, characterized in that, The total wear prediction value of the vehicle tire is calculated according to the total wear prediction value of the vehicle tire. The total wear prediction value of the vehicle tire is calculated according to the total wear prediction value of the vehicle tire. The initial total wear prediction value of the vehicle tire is calculated according to the wear coefficient of the segmented mileage. The initial total wear prediction value is corrected according to the initial wear coefficient, and the total wear prediction value is obtained.

6. A method for predicting the life of a tire carcass based on smart tire technology according to claim 5, characterized in that, The method further comprises: The remaining life of the tire body is reminded to the user in real time through the vehicle-mounted computer or the mobile terminal device.

7. A tire carcass life prediction system based on smart tire technology, characterized in that, The system is used to realize the tire body life prediction method based on the intelligent tire technology according to any one of claims 1-6, and the system comprises: A data acquisition module is used to acquire the tire vibration data, and the tire vibration data is determined based on the tire vibration data. A model construction module is used to segment the travel mileage based on the tire vibration data, calculate the wear coefficient of each segmented mileage, and construct a prediction model based on the wear coefficients of the segmented mileages. A prediction module is used to predict the remaining life of the tire body based on the prediction model.

Images