Snow tire life prediction method, device, equipment and storage medium

Abstract

The invention discloses a snow tire life prediction method, device and equipment and a storage medium, and the method comprises the steps: obtaining the historical use data of a snow tire of a current vehicle, and extracting a target feature having an influence on the life of the tire from the historical use data; establishing a tire life prediction model according to the target characteristics; and obtaining current tire use data of the snow tire, inputting the current tire use data into the tire life prediction model, and obtaining the remaining service life of the snow tire of the current vehicle, so that the accuracy of predicting the remaining service life of the snow tire can be remarkably improved, a vehicle owner is helped to reasonably arrange tire replacement time, and the service life of the snow tire is prolonged. Waste caused by too early replacement or safety risks caused by too late replacement are avoided, the prediction time is saved, the speed and efficiency of snow tire life prediction are improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle manufacturing, and in particular to a snow tire life prediction method, device, equipment and storage medium. Background Art

[0002] Traditional tire life prediction methods are mainly based on factors such as tire material, design, and mileage, but these methods have limitations when facing seasonal tire replacement (such as snow tires); especially in the Northeast and Northwest regions, since snow tires are needed in winter to enhance driving safety, and the life of snow tires often exceeds one winter, conventional methods are difficult to accurately predict the remaining life of used snow tires; this causes car owners to replace tires too early or too late, which not only increases the economic burden but also may affect driving safety. Summary of the invention

[0003] The main purpose of the present invention is to provide a snow tire life prediction method, device, equipment and storage medium, aiming to solve the technical problem in the prior art that the snow tire life prediction is not accurate, resulting in the owner being unable to replace the tires at the right time, which not only increases the economic burden but also may affect driving safety.

[0004] In a first aspect, the present invention provides a method for predicting the life of a snow tire, the method comprising the following steps:

[0005] Acquire historical usage data of snow tires of the current vehicle, and extract target features that have an impact on tire life from the historical usage data;

[0006] Establishing a tire life prediction model according to the target characteristics;

[0007] Current tire usage data of the snow tire is obtained, and the current tire usage data is input into the tire life prediction model to obtain the remaining service life of the snow tire of the current vehicle.

[0008] Optionally, the acquiring historical usage data of the snow tire of the current vehicle and extracting target features that have an impact on the tire life from the historical usage data includes:

[0009] Acquire vehicle driving data of the current vehicle, tire parameters of the snow tires of the current vehicle, weather data during the driving time of the current vehicle, and road surface data corresponding to the driving route of the current vehicle;

[0010] Using the vehicle driving data, the tire parameters, the weather data and the road surface data as historical usage data of the snow tire;

[0011] Target features that have an impact on tire life are extracted from the historical usage data.

[0012] Optionally, extracting target features that have an impact on tire life from the historical usage data includes:

[0013] Performing data preprocessing on the historical usage data to obtain target usage data;

[0014] Acquire basic tire information of the snow tire, and acquire characteristic data matching the basic tire information from the target usage data;

[0015] Feature extraction is performed on the feature data to obtain target features that have an impact on tire life.

[0016] Optionally, the performing data preprocessing on the historical usage data to obtain target usage data includes:

[0017] Performing data cleaning on the historical usage data to remove duplicate data, invalid data and abnormal values ​​in the historical usage data to obtain cleaned usage data;

[0018] Normalizing the cleaned usage data to obtain normalized data of the same dimension;

[0019] Missing value processing is performed on the normalized data to obtain target usage data.

[0020] Optionally, the extracting features from the feature data to obtain target features that affect tire life includes:

[0021] Feature extraction is performed on the feature data to obtain temperature and humidity data, precipitation data, snowfall data, tire driving data, tire wear data, and tire current status data, and the temperature and humidity data, the precipitation data, the snowfall data, the tire driving data, the tire wear data, and the tire current status data are used as target features that affect tire life.

[0022] Optionally, establishing a tire life prediction model according to the target feature includes:

[0023] Dividing the data corresponding to the target feature into a training set and a test set;

[0024] The initial tire prediction model is trained and optimized according to the preset machine learning model, the training set and the test set to generate a tire life prediction model.

[0025] Optionally, the training and optimizing the initial tire prediction model according to the preset machine learning model, the training set and the test set to generate the tire life prediction model includes:

[0026] Training the initial tire prediction model according to the preset machine learning model, the training set and the test set, adjusting the model parameters, and evaluating the prediction performance of the trained and optimized prediction model in real time;

[0027] When the prediction performance meets the preset performance index, the training is determined to be up to standard, and the prediction model that meets the standard is used as the tire life prediction model.

[0028] In a second aspect, in order to achieve the above-mentioned purpose, the present invention further proposes a snow tire life prediction device, the snow tire life prediction device comprising:

[0029] A feature extraction module, used to obtain historical usage data of the snow tire of the current vehicle, and extract target features that have an impact on the tire life from the historical usage data;

[0030] A model building module, used to build a tire life prediction model according to the target characteristics;

[0031] The life prediction module is used to obtain the current tire usage data of the snow tire, input the current tire usage data into the tire life prediction model, and obtain the remaining service life of the snow tire of the current vehicle.

[0032] In a third aspect, in order to achieve the above-mentioned purpose, the present invention also proposes a snow tire life prediction device, which includes: a memory, a processor, and a snow tire life prediction program stored in the memory and executable on the processor, and the snow tire life prediction program is configured to implement the steps of the snow tire life prediction method as described above.

[0033] In a fourth aspect, in order to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a snow tire life prediction program is stored, and when the snow tire life prediction program is executed by a processor, the steps of the snow tire life prediction method as described above are implemented.

[0034] The snow tire life prediction method proposed in the present invention obtains historical usage data of the snow tires of the current vehicle, extracts target features that affect the tire life from the historical usage data; establishes a tire life prediction model based on the target features; obtains current tire usage data of the snow tires, inputs the current tire usage data into the tire life prediction model, and obtains the remaining service life of the snow tires of the current vehicle. The method can significantly improve the accuracy of the remaining service life prediction of the snow tires, help car owners to reasonably arrange the tire replacement time, avoid waste caused by premature replacement or safety risks caused by late replacement, save prediction time, improve the speed and efficiency of snow tire life prediction, and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention;

[0036] Figure 2 It is a schematic flow chart of a first embodiment of a method for predicting the life of a snow tire according to the present invention;

[0037] Figure 3 It is a schematic flow chart of a second embodiment of a method for predicting the life of a snow tire according to the present invention;

[0038] Figure 4 It is a schematic flow chart of a third embodiment of a method for predicting the life of a snow tire according to the present invention;

[0039] Figure 5 A schematic flow chart of a fourth embodiment of a snow tire life prediction method according to the present invention;

[0040] Figure 6 This is a functional module diagram of the first embodiment of the snow tire life prediction device of the present invention.

[0041] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0042] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0043] The solution of the embodiment of the present invention is mainly: by obtaining the historical usage data of the snow tires of the current vehicle, the target features that affect the tire life are extracted from the historical usage data; a tire life prediction model is established according to the target features; the current tire usage data of the snow tires is obtained, and the current tire usage data is input into the tire life prediction model to obtain the remaining service life of the snow tires of the current vehicle. The accuracy of the remaining service life prediction of the snow tires can be significantly improved, and the car owners can reasonably arrange the tire replacement time to avoid the waste caused by premature replacement or the safety risks caused by late replacement, save prediction time, improve the speed and efficiency of snow tire life prediction, and improve user experience. The technical problem that the snow tire life prediction in the prior art is not accurate, resulting in the car owners being unable to change tires at the right time, which not only increases the economic burden but also may affect driving safety.

[0044] Reference Figure 1 , Figure 1 The figure is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention.

[0045] like Figure 1As shown, the device may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory, or it may be a stable memory (Non-Volatile Memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0046] Those skilled in the art will understand that Figure 1 The device structure shown in the figure does not constitute a limitation of the device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0047] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating device, a network communication module, a user interface module, and a snow tire life prediction program.

[0048] The device of the present invention calls the snow tire life prediction program stored in the memory 1005 through the processor 1001, and performs the following operations:

[0049] Acquire historical usage data of snow tires of the current vehicle, and extract target features that have an impact on tire life from the historical usage data;

[0050] Establishing a tire life prediction model according to the target characteristics;

[0051] Current tire usage data of the snow tire is obtained, and the current tire usage data is input into the tire life prediction model to obtain the remaining service life of the snow tire of the current vehicle.

[0052] The device of the present invention calls the snow tire life prediction program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0053] Acquire vehicle driving data of the current vehicle, tire parameters of the snow tires of the current vehicle, weather data during the driving time of the current vehicle, and road surface data corresponding to the driving route of the current vehicle;

[0054] Using the vehicle driving data, the tire parameters, the weather data and the road surface data as historical usage data of the snow tire;

[0055] Target features that have an impact on tire life are extracted from the historical usage data.

[0056] The device of the present invention calls the snow tire life prediction program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0057] Performing data preprocessing on the historical usage data to obtain target usage data;

[0058] Acquire basic tire information of the snow tire, and acquire characteristic data matching the basic tire information from the target usage data;

[0059] Feature extraction is performed on the feature data to obtain target features that have an impact on tire life.

[0060] The device of the present invention calls the snow tire life prediction program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0061] Performing data cleaning on the historical usage data to remove duplicate data, invalid data and abnormal values ​​in the historical usage data to obtain cleaned usage data;

[0062] Normalizing the cleaned usage data to obtain normalized data of the same dimension;

[0063] Missing value processing is performed on the normalized data to obtain target usage data.

[0064] The device of the present invention calls the snow tire life prediction program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0065] Feature extraction is performed on the feature data to obtain temperature and humidity data, precipitation data, snowfall data, tire driving data, tire wear data, and tire current status data, and the temperature and humidity data, the precipitation data, the snowfall data, the tire driving data, the tire wear data, and the tire current status data are used as target features that affect tire life.

[0066] The device of the present invention calls the snow tire life prediction program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0067] Dividing the data corresponding to the target feature into a training set and a test set;

[0068] The initial tire prediction model is trained and optimized according to the preset machine learning model, the training set and the test set to generate a tire life prediction model.

[0069] The device of the present invention calls the snow tire life prediction program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0070] Training the initial tire prediction model according to the preset machine learning model, the training set and the test set, adjusting the model parameters, and evaluating the prediction performance of the trained and optimized prediction model in real time;

[0071] When the prediction performance meets the preset performance index, the training is determined to be up to standard, and the prediction model that meets the standard is used as the tire life prediction model.

[0072] This embodiment adopts the above scheme, by obtaining the historical usage data of the snow tires of the current vehicle, extracting the target features that affect the tire life from the historical usage data; establishing a tire life prediction model according to the target features; obtaining the current tire usage data of the snow tires, inputting the current tire usage data into the tire life prediction model, and obtaining the remaining service life of the snow tires of the current vehicle, which can significantly improve the accuracy of the remaining service life prediction of the snow tires, help car owners to reasonably arrange the tire replacement time, avoid the waste caused by premature replacement or the safety risks caused by late replacement, save prediction time, improve the speed and efficiency of snow tire life prediction, and improve user experience.

[0073] Based on the above hardware structure, an embodiment of a snow tire life prediction method of the present invention is proposed.

[0074] Reference Figure 2 , Figure 2 It is a schematic flow chart of the first embodiment of the snow tire life prediction method of the present invention.

[0075] In a first embodiment, the snow tire life prediction method comprises the following steps:

[0076] Step S10: Obtain historical usage data of the snow tire of the current vehicle, and extract target features that have an impact on the tire life from the historical usage data.

[0077] It should be noted that the historical usage data is the usage data of the snow tires of the current vehicle for which tire life prediction is required within a historical period of time, and target features that have an impact on tire life can be extracted from the historical usage data.

[0078] Step S20: establishing a tire life prediction model according to the target characteristics.

[0079] It should be understood that after the target features are obtained, a tire life prediction model for predicting tire life can be established based on the target features.

[0080] Step S30: obtaining current tire usage data of the snow tire, inputting the current tire usage data into the tire life prediction model, and obtaining the remaining service life of the snow tire of the current vehicle.

[0081] It can be understood that the current tire usage data is for the snow tire. The current tire usage data of the snow tire is obtained, and then the current tire usage data is input into the tire life prediction model. The model outputs the life prediction result, thereby determining the remaining service life of the snow tire of the current vehicle.

[0082] This embodiment adopts the above scheme, by obtaining the historical usage data of the snow tires of the current vehicle, extracting the target features that affect the tire life from the historical usage data; establishing a tire life prediction model according to the target features; obtaining the current tire usage data of the snow tires, inputting the current tire usage data into the tire life prediction model, and obtaining the remaining service life of the snow tires of the current vehicle, which can significantly improve the accuracy of the remaining service life prediction of the snow tires, help car owners to reasonably arrange the tire replacement time, avoid the waste caused by premature replacement or the safety risks caused by late replacement, save prediction time, improve the speed and efficiency of snow tire life prediction, and improve user experience.

[0083] Further, Figure 3 FIG. 2 is a flow chart of a second embodiment of a snow tire life prediction method according to the present invention. Figure 3 As shown, a second embodiment of the snow tire life prediction method of the present invention is proposed based on the first embodiment. In this embodiment, the step S10 specifically includes the following steps:

[0084] Step S11, obtaining vehicle driving data of the current vehicle, tire parameters of the snow tires of the current vehicle, weather data during the driving time of the current vehicle, and road surface data corresponding to the driving route of the current vehicle.

[0085] It should be noted that before performing data extraction and analysis, the vehicle driving data of the current vehicle, the tire parameters of the snow tires of the current vehicle, the weather data of the current vehicle during the driving time, and the road surface data corresponding to the driving route of the current vehicle can be obtained.

[0086] In a specific implementation, the vehicle driving data includes but is not limited to: mileage and driving speed, etc. The mileage, i.e., driving distance data, is the mileage recorded and stored for each driving, which can generally be obtained through the vehicle's odometer or on-board diagnostics system (OBD);

[0087] Tire parameters include but are not limited to: tire pressure, tire temperature, tire brand, model, production date and size, etc.

[0088] Weather data includes but is not limited to: temperature, humidity, precipitation, snowfall, etc.

[0089] Road surface data includes but is not limited to: dry, wet, and icy.

[0090] Understandably, this data can be obtained through on-board sensors, meteorological departments or third-party data providers, and this information is crucial to understanding the basic performance and life characteristics of tires.

[0091] Step S12: using the vehicle driving data, the tire parameters, the weather data and the road surface data as historical usage data of the snow tire.

[0092] It is understandable that after obtaining these data, the vehicle driving data, the tire parameters, the weather data and the road surface data can be used as historical usage data of the snow tire. Generally, after obtaining the historical usage data, the historical usage data can be stored through a data storage module.

[0093] Step S13: extracting target features that have an impact on tire life from the historical usage data.

[0094] It should be understood that, through data analysis, target features that have an impact on tire life can be extracted from the historical usage data.

[0095] This embodiment adopts the above scheme to obtain the vehicle driving data of the current vehicle, the tire parameters of the snow tires of the current vehicle, the weather data of the current vehicle during the driving time, and the road surface data corresponding to the driving route of the current vehicle; the vehicle driving data, the tire parameters, the weather data and the road surface data are used as the historical usage data of the snow tire; the target features that affect the tire life are extracted from the historical usage data; the target features can be quickly screened out from the historical data, the accuracy of the snow tire remaining life prediction is significantly improved, and the speed and efficiency of the snow tire life prediction are improved.

[0096] Further, Figure 4 FIG. 1 is a flow chart of a third embodiment of a snow tire life prediction method according to the present invention. Figure 4 As shown, a third embodiment of the snow tire life prediction method of the present invention is proposed based on the second embodiment. In this embodiment, the step S13 specifically includes the following steps:

[0097] Step S131: pre-process the historical usage data to obtain target usage data.

[0098] It should be noted that after data preprocessing is performed on the historical usage data, some useless data can be filtered out, thereby obtaining data for feature extraction, that is, target usage data.

[0099] Furthermore, the step S131 specifically includes the following steps:

[0100] Performing data cleaning on the historical usage data to remove duplicate data, invalid data and abnormal values ​​in the historical usage data to obtain cleaned usage data;

[0101] Normalizing the cleaned usage data to obtain normalized data of the same dimension;

[0102] Missing value processing is performed on the normalized data to obtain target usage data.

[0103] It can be understood that data cleaning is to remove duplicate data, invalid data and outliers in the historical usage data. Through normalization, data of different dimensions can be converted into the same dimension for comparison and analysis. Generally, missing value processing can use interpolation, mean filling or deletion to process missing data, so as to obtain target usage data.

[0104] Step S132: Obtain basic tire information of the snow tire, and obtain feature data matching the basic tire information from the target usage data.

[0105] It is understandable that after obtaining the basic tire information of the snow tire, which includes but is not limited to tire brand, model, production date, size, etc., feature data matching the basic tire information can be obtained from the target usage data.

[0106] Step S133: extracting features from the feature data to obtain target features that have an impact on tire life.

[0107] It should be understood that after targeted feature extraction is performed on the feature data, target features that have an impact on tire life can be obtained.

[0108] Furthermore, the step S133 specifically includes the following steps:

[0109] Feature extraction is performed on the feature data to obtain temperature and humidity data, precipitation data, snowfall data, tire driving data, tire wear data, and tire current status data, and the temperature and humidity data, the precipitation data, the snowfall data, the tire driving data, the tire wear data, and the tire current status data are used as target features that affect tire life.

[0110] It is understandable that by extracting the feature data, temperature and humidity data, precipitation data, snowfall data, tire driving data, tire wear data, and tire current status data can be obtained, and these parameters can be used as target features that affect tire life.

[0111] In a specific implementation, factors that have a significant impact on tire life can be selected from driving weather data, such as temperature (too high or too low temperature will accelerate tire aging), humidity (too high humidity may cause corrosion on the tire surface), precipitation (precipitation may increase the slipperiness of the road surface and affect tire grip), etc.; features such as cumulative mileage and average driving speed can be extracted from driving distance data; features of tire wear images, such as texture features and color features, can be extracted using image processing technology; physical parameters such as the width-depth product, pattern saturation, and Akron wear of the tire can also be calculated using measuring equipment, and this is not limited in this embodiment.

[0112] Through the above scheme, this embodiment obtains target usage data by preprocessing the historical usage data; obtains basic tire information of the snow tire, and obtains feature data matching the basic tire information from the target usage data; performs feature extraction on the feature data to obtain target features that affect tire life, and can quickly obtain target features, significantly improve the accuracy of snow tire remaining life prediction, improve the speed and efficiency of snow tire life prediction, and improve user experience.

[0113] Further, Figure 5 FIG. 4 is a flow chart of a fourth embodiment of a snow tire life prediction method according to the present invention. Figure 5 As shown, a fourth embodiment of the snow tire life prediction method of the present invention is proposed based on the first embodiment. In this embodiment, the step S20 specifically includes the following steps:

[0114] Step S21, dividing the data corresponding to the target feature into a training set and a test set.

[0115] It should be noted that, before training, the data corresponding to the target features may be locked, and then the data may be divided into a training set and a test set.

[0116] Step S22: training and optimizing the initial tire prediction model according to the preset machine learning model, the training set and the test set to generate a tire life prediction model.

[0117] It is understandable that the initial tire prediction model can be trained and optimized according to the preset machine learning model, the training set and the test set, so that after the training optimization is completed, a tire life prediction model is obtained.

[0118] Furthermore, the step S22 specifically includes the following steps:

[0119] Training the initial tire prediction model according to the preset machine learning model, the training set and the test set, adjusting the model parameters, and evaluating the prediction performance of the trained and optimized prediction model in real time;

[0120] When the prediction performance meets the preset performance index, the training is determined to be up to standard, and the prediction model that meets the standard is used as the tire life prediction model.

[0121] In the specific implementation, you can consider using machine learning models such as decision trees, random forests, support vector machines (SVM), neural networks, etc.; these models can handle complex nonlinear relationships and have high prediction accuracy; in the model training process, the preprocessed data can be divided into training sets and test sets; use the training set data to train the model and adjust the model parameters to optimize the prediction performance; use the test set data to verify the model's prediction accuracy and generalization ability.

[0122] It should be understood that during the model optimization process, the model can be optimized through methods such as cross-validation and grid search to improve prediction accuracy and stability; at the same time, strategies such as adding regularization terms and adjusting the learning rate can be considered to prevent model overfitting.

[0123] It is understandable that after the model is trained, indicators such as accuracy, recall, and F1 score can be used to evaluate the model's prediction performance. Tools such as confusion matrix and receiver operating characteristic curve (ROC) curve can also be considered to more intuitively display the model's prediction results. Generally, the accuracy of the model can be verified by comparing the model's prediction results with the actual tire life data. The holdout method, cross-validation method, and other methods can be considered to evaluate the model's stability and reliability.

[0124] In specific implementation, model application can be to deploy the trained model to actual application scenarios, such as vehicle management system, tire monitoring system, etc.; collect tire usage data in real time and input the model for prediction, so as to replace aging tires in time;

[0125] Feedback and optimization can also be performed, such as collecting user feedback based on actual application results, and continuously improving and optimizing the model. In addition, new features or algorithms can be considered to improve the prediction accuracy and generalization ability of the model.

[0126] Of course, an intuitive user interface can also be provided to facilitate users to check tire status, thereby enhancing users' participation and satisfaction in vehicle maintenance and improving user experience.

[0127] Through the above scheme, this embodiment divides the data corresponding to the target features into a training set and a test set; trains and optimizes the initial tire prediction model according to the preset machine learning model, the training set and the test set to generate a tire life prediction model; can significantly improve the accuracy of the remaining life prediction of snow tires, help car owners to reasonably arrange tire replacement time, avoid waste caused by premature replacement or safety risks caused by late replacement, save prediction time, improve the speed and efficiency of snow tire life prediction, and improve user experience.

[0128] Accordingly, the present invention further provides a snow tire life prediction device.

[0129] Reference Figure 6 , Figure 6 This is a functional module diagram of the first embodiment of the snow tire life prediction device of the present invention.

[0130] In a first embodiment of the snow tire life prediction device of the present invention, the snow tire life prediction device comprises:

[0131] The feature extraction module 10 is used to obtain the historical usage data of the snow tire of the current vehicle and extract the target features that have an impact on the tire life from the historical usage data.

[0132] The model building module 20 is used to build a tire life prediction model according to the target characteristics.

[0133] The life prediction module 30 is used to obtain the current tire usage data of the snow tire, input the current tire usage data into the tire life prediction model, and obtain the remaining service life of the snow tire of the current vehicle.

[0134] The feature extraction module 10 is also used to obtain vehicle driving data of the current vehicle, tire parameters of the snow tires of the current vehicle, weather data of the current vehicle during the driving time, and road surface data corresponding to the driving route of the current vehicle; use the vehicle driving data, the tire parameters, the weather data and the road surface data as historical usage data of the snow tire; and extract target features that affect tire life from the historical usage data.

[0135] The feature extraction module 10 is also used to perform data preprocessing on the historical usage data to obtain target usage data; obtain basic tire information of the snow tire, and obtain feature data matching the basic tire information from the target usage data; perform feature extraction on the feature data to obtain target features that affect tire life.

[0136] The feature extraction module 10 is also used to perform data cleaning on the historical usage data, clean up duplicate data, invalid data and outliers in the historical usage data, and obtain cleaned usage data; normalize the cleaned usage data to obtain normalized data of the same dimension; and perform missing value processing on the normalized data to obtain target usage data.

[0137] The feature extraction module 10 is also used to extract features from the feature data to obtain temperature and humidity data, precipitation data, snowfall data, tire driving data, tire wear data, and tire current status data, and use the temperature and humidity data, the precipitation data, the snowfall data, the tire driving data, the tire wear data, and the tire current status data as target features that affect tire life.

[0138] The model building module 20 is also used to divide the data corresponding to the target feature into a training set and a test set; train and optimize the initial tire prediction model according to the preset machine learning model, the training set and the test set to generate a tire life prediction model.

[0139] The model building module 20 is also used to train the initial tire prediction model according to the preset machine learning model, the training set and the test set, and adjust the model parameters to evaluate the prediction performance of the prediction model after training optimization in real time; when the prediction performance meets the preset performance indicators, the training is determined to be qualified, and the qualified prediction model is used as the tire life prediction model.

[0140] Among them, the steps implemented by each functional module of the snow tire life prediction device can refer to the various embodiments of the snow tire life prediction method of the present invention, and will not be repeated here.

[0141] In addition, an embodiment of the present invention further provides a storage medium, on which a snow tire life prediction program is stored. When the snow tire life prediction program is executed by a processor, the following operations are implemented:

[0142] Acquire historical usage data of snow tires of the current vehicle, and extract target features that have an impact on tire life from the historical usage data;

[0143] Establishing a tire life prediction model according to the target characteristics;

[0144] Current tire usage data of the snow tire is obtained, and the current tire usage data is input into the tire life prediction model to obtain the remaining service life of the snow tire of the current vehicle.

[0145] Furthermore, when the snow tire life prediction program is executed by the processor, the following operations are also implemented:

[0146] Acquire vehicle driving data of the current vehicle, tire parameters of the snow tires of the current vehicle, weather data during the driving time of the current vehicle, and road surface data corresponding to the driving route of the current vehicle;

[0147] Using the vehicle driving data, the tire parameters, the weather data and the road surface data as historical usage data of the snow tire;

[0148] Target features that have an impact on tire life are extracted from the historical usage data.

[0149] Furthermore, when the snow tire life prediction program is executed by the processor, the following operations are also implemented:

[0150] Performing data preprocessing on the historical usage data to obtain target usage data;

[0151] Acquire basic tire information of the snow tire, and acquire characteristic data matching the basic tire information from the target usage data;

[0152] Feature extraction is performed on the feature data to obtain target features that have an impact on tire life.

[0153] Furthermore, when the snow tire life prediction program is executed by the processor, the following operations are also implemented:

[0154] Performing data cleaning on the historical usage data to remove duplicate data, invalid data and abnormal values ​​in the historical usage data to obtain cleaned usage data;

[0155] Normalizing the cleaned usage data to obtain normalized data of the same dimension;

[0156] Missing value processing is performed on the normalized data to obtain target usage data.

[0157] Furthermore, when the snow tire life prediction program is executed by the processor, the following operations are also implemented:

[0158] Feature extraction is performed on the feature data to obtain temperature and humidity data, precipitation data, snowfall data, tire driving data, tire wear data, and tire current status data, and the temperature and humidity data, the precipitation data, the snowfall data, the tire driving data, the tire wear data, and the tire current status data are used as target features that affect tire life.

[0159] Furthermore, when the snow tire life prediction program is executed by the processor, the following operations are also implemented:

[0160] Dividing the data corresponding to the target feature into a training set and a test set;

[0161] The initial tire prediction model is trained and optimized according to the preset machine learning model, the training set and the test set to generate a tire life prediction model.

[0162] Furthermore, when the snow tire life prediction program is executed by the processor, the following operations are also implemented:

[0163] Training the initial tire prediction model according to the preset machine learning model, the training set and the test set, adjusting the model parameters, and evaluating the prediction performance of the trained and optimized prediction model in real time;

[0164] When the prediction performance meets the preset performance index, the training is determined to be up to standard, and the prediction model that meets the standard is used as the tire life prediction model.

[0165] Those skilled in the art will appreciate that all or part of the steps in the above-mentioned implementation method can be accomplished by instructing related hardware through a program, and the program is stored in a storage medium, including a number of instructions for enabling a device (which may be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each implementation method of the present application; and the aforementioned storage medium is a computer-readable storage medium, including: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0166] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0167] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0168] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for predicting the life of a snow tire, characterized in that: The snow tire life prediction method comprises: Acquire historical usage data of snow tires of the current vehicle, and extract target features that have an impact on tire life from the historical usage data; Establishing a tire life prediction model according to the target characteristics; The current tire usage data of the snow tire is obtained, and the current tire usage data is input into the tire life prediction model to obtain the remaining service life of the snow tire of the current vehicle.

2. The snow tire life prediction method according to claim 1, characterized in that: The step of obtaining historical usage data of the snow tire of the current vehicle and extracting target features that have an impact on the tire life from the historical usage data includes: Acquire vehicle driving data of the current vehicle, tire parameters of the snow tires of the current vehicle, weather data during the driving time of the current vehicle, and road surface data corresponding to the driving route of the current vehicle; Using the vehicle driving data, the tire parameters, the weather data and the road surface data as historical usage data of the snow tire; Target features that have an impact on tire life are extracted from the historical usage data.

3. The snow tire life prediction method according to claim 2, characterized in that: The extracting target features that have an impact on tire life from the historical usage data includes: Performing data preprocessing on the historical usage data to obtain target usage data; Acquire basic tire information of the snow tire, and acquire characteristic data matching the basic tire information from the target usage data; Feature extraction is performed on the feature data to obtain target features that have an impact on tire life.

4. The snow tire life prediction method according to claim 3, characterized in that: The performing data preprocessing on the historical usage data to obtain target usage data includes: Performing data cleaning on the historical usage data to remove duplicate data, invalid data and abnormal values ​​in the historical usage data to obtain cleaned usage data; Normalizing the cleaned usage data to obtain normalized data of the same dimension; Missing value processing is performed on the normalized data to obtain target usage data.

5. The snow tire life prediction method according to claim 3, characterized in that: The feature extraction of the feature data to obtain target features that affect tire life includes: Feature extraction is performed on the feature data to obtain temperature and humidity data, precipitation data, snowfall data, tire driving data, tire wear data, and tire current status data, and the temperature and humidity data, the precipitation data, the snowfall data, the tire driving data, the tire wear data, and the tire current status data are used as target features that affect tire life.

6. The snow tire life prediction method according to claim 1, characterized in that: The step of establishing a tire life prediction model according to the target characteristics comprises: Dividing the data corresponding to the target feature into a training set and a test set; The initial tire prediction model is trained and optimized according to the preset machine learning model, the training set and the test set to generate a tire life prediction model.

7. The snow tire life prediction method according to claim 6, characterized in that: The training and optimization of the initial tire prediction model according to the preset machine learning model, the training set and the test set to generate a tire life prediction model includes: Training the initial tire prediction model according to the preset machine learning model, the training set and the test set, adjusting the model parameters, and evaluating the prediction performance of the trained and optimized prediction model in real time; When the prediction performance meets the preset performance index, the training is determined to be up to standard, and the prediction model that meets the standard is used as the tire life prediction model.

8. A snow tire life prediction device, characterized in that: The snow tire life prediction device comprises: A feature extraction module, used to obtain historical usage data of the snow tire of the current vehicle, and extract target features that have an impact on the tire life from the historical usage data; A model building module, used to build a tire life prediction model according to the target characteristics; The life prediction module is used to obtain the current tire usage data of the snow tire, input the current tire usage data into the tire life prediction model, and obtain the remaining service life of the snow tire of the current vehicle.

9. A snow tire life prediction device, characterized in that: The snow tire life prediction device includes: a memory, a processor, and a snow tire life prediction program stored in the memory and executable on the processor, wherein the snow tire life prediction program is configured to implement the steps of the snow tire life prediction method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a snow tire life prediction program, which, when executed by a processor, implements the steps of the snow tire life prediction method according to any one of claims 1 to 7.

Images