Tire damage risk prediction method and related device

Abstract

The invention discloses a tire damage risk prediction method and a related device. The method comprises the steps that a vehicle-mounted terminal uploads sensor data to a cloud; the cloud quantizes to obtain a tire prediction pressure, and calculates a tire pressure residual value; constructing a feature matrix by using the tire temperature, the vehicle speed, the actual tire pressure and the tire pressure residual value, and converting the feature matrix into a dimensionality reduction matrix by dimensionality reduction based on PCA (Principal Component Analysis); judging a tire damage risk based on the tire pressure residual value, if the tire damage risk is a tire burst risk, calculating a tire burst probability based on a tire burst risk regression model, and searching a coping strategy from a first tire burst risk library; if the risk is the air leakage risk, calculating an air leakage probability based on an air leakage risk regression model, and searching a coping strategy from an air leakage risk library; the tire burst probability regression model and the air leakage probability regression model are both in exponential correlation with the dimension reduction matrix; and returning the coping strategy to the vehicle-mounted terminal to instruct the vehicle to execute response operation. By monitoring tire pressure abnormity, efficient and reliable prediction of tire damage is realized, and cloud computing power is saved.

Description

Technical Field

[0001] This application relates to the field of vehicle safety monitoring technology, specifically to the fields of sensor data fusion and machine learning, and particularly to a method and device for predicting tire damage risk. Background Technology

[0002] As the only part of a vehicle in contact with the road surface, the tire's working condition directly affects driving safety. Tire blowouts and leaks are the most common forms of tire failure, especially at high speeds, in complex road conditions, or in extreme temperature environments. These failures can easily lead to loss of vehicle control and cause serious traffic accidents. Existing tire monitoring technologies mainly focus on tire pressure monitoring systems (TPMS), which collect tire pressure data and issue alarms when the pressure is below or above a preset threshold. However, existing technologies have the following drawbacks: 1) They rely solely on a single pressure parameter, failing to consider key influencing factors such as temperature (tire temperature, road surface temperature) and vehicle speed, resulting in low alarm accuracy and a tendency for false alarms or missed alarms; 2) They lack quantitative analysis of the correlation between pressure and temperature, making it impossible to predict potential risks in advance, and only able to issue alarms passively after a fault occurs; 3) They do not take into account the impact of road environment on tire material performance, resulting in insufficient prediction accuracy in extreme scenarios such as high-temperature roads. Therefore, there is an urgent need for a tire risk prediction technology that can integrate multi-dimensional data, quantify parameter correlation, and dynamically optimize the prediction model to improve prediction accuracy and timeliness and ensure vehicle driving safety. Summary of the Invention

[0003] This application provides a method and related device for predicting tire damage risk, in order to solve the problems of insufficient accuracy in judging tire damage, low alarm accuracy, and inability to predict damage in advance in the prior art.

[0004] The technical solution is as follows: Firstly, a method for predicting tire damage risk is provided, including: The vehicle terminal collects sensor data related to the tires during vehicle operation and uploads it to the cloud; the tire-related sensor data includes at least: tire temperature, actual tire pressure, and vehicle speed. The cloud platform quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. The cloud uses tire temperature, vehicle speed, actual tire pressure, and tire pressure residual values ​​to construct a feature matrix, and performs dimensionality reduction transformation on the feature matrix based on multi-component analysis (PCA) technology to obtain a dimensionality-reduced matrix. The cloud-based system determines the tire puncture risk based on the tire pressure residual value. If the risk is determined to be a blowout, the system calculates the blowout probability based on the blowout risk regression model and searches for corresponding response strategies in the first blowout risk database based on the blowout probability. If the risk is determined to be a leak, the system calculates the leak probability based on the leak risk regression model and searches for corresponding response strategies in the leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the dimensionality reduction matrix. The cloud will send the found response strategies to the vehicle terminal to instruct the vehicle to perform response operations related to the response strategies.

[0005] In one possible implementation, the tire-related sensor data further includes: road surface temperature; then, after calculating the tire blowout probability based on a blowout probability regression model, the method further includes: Determine if the road surface temperature is greater than the temperature threshold and the vehicle speed is greater than the speed threshold; If so, then search for the corresponding response strategy from the second tire blowout risk database based on the tire blowout probability; Otherwise, the corresponding response strategy is searched from the first tire blowout risk database based on the tire blowout probability; wherein, for the same risk level, the tire blowout probability threshold of the second tire blowout risk database is always lower than the tire blowout probability threshold of the first tire blowout risk database.

[0006] In one possible implementation, the cloud quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure, specifically including: Based on the tire temperature and vehicle speed, the cloud platform constructs the following regression equation for tire temperature and pressure: in, Predict tire pressure, For tire temperature, For vehicle speed, , , , These are the corresponding coefficients; The relationship between temperature and pressure is quantified, and the predicted tire pressure is calculated using the above equation. Calculate the tire pressure residual value based on the predicted tire pressure and the actual tire pressure: in, This is the tire pressure residual value. This refers to the actual tire pressure.

[0007] In one possible implementation, the cloud platform determines the risk of tire damage based on the tire pressure residual value, specifically including: If the cloud determines that the tire pressure residual value is greater than 0 and the absolute value of the gradient of the tire pressure residual value is greater than 0, then it is determined that there is a risk of tire blowout. If the cloud determines that the tire pressure residual value is less than 0 and the absolute value of the gradient of the tire pressure residual value is greater than 0, then it is determined that there is a risk of air leakage.

[0008] In one possible implementation, the probability of a tire blowout is calculated based on a tire blowout risk regression model, specifically including: The probability of a tire blowout is calculated using the following formula: The probability of leakage is calculated based on a leakage risk regression model, specifically including: The probability of air leakage is calculated based on the following formula: in, For the probability of a tire blowout, Let w1 be the probability of air leakage, w2 be the weight matrix corresponding to the dimensionality reduction matrix in the air leakage risk regression model, and x1_pca be the dimensionality reduction matrix.

[0009] Secondly, a tire damage risk prediction system is provided, comprising: an on-board terminal and a cloud platform; wherein, The vehicle-mounted terminal collects sensor data related to the tires during vehicle operation and uploads it to the cloud; wherein the sensor data related to the tires includes at least: tire temperature, actual tire pressure, and vehicle speed; The cloud platform quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. The cloud uses tire temperature, vehicle speed, actual tire pressure, and tire pressure residual values ​​to construct a feature matrix, and performs dimensionality reduction transformation on the feature matrix based on multi-component analysis (PCA) technology to obtain a dimensionality-reduced matrix. The cloud-based system determines the risk of tire puncture based on the tire pressure residual value. If the risk is determined to be a blowout, the system calculates the blowout probability based on the blowout probability regression model and searches for corresponding response strategies in the first blowout risk database based on the blowout probability. If the risk is determined to be a leak, the system calculates the leak probability based on the leak risk regression model and searches for corresponding response strategies in the leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the dimensionality reduction matrix. The cloud will send the found response strategies to the vehicle terminal to instruct the vehicle to perform response operations related to the response strategies.

[0010] Thirdly, a tire damage risk prediction device is provided, including: The data receiving module is used to receive sensor data related to the tires collected by the vehicle terminal during the vehicle's operation; wherein, the sensor data related to the tires includes at least: tire temperature, actual tire pressure, and vehicle speed; The residual value calculation module is used to quantify the relationship between temperature and pressure based on the tire temperature and vehicle speed, obtain the predicted tire pressure, and calculate the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. The PCA processing module is used to construct a feature matrix using tire temperature, vehicle speed, actual tire pressure, and tire pressure residual values, and to perform dimensionality reduction transformation on the feature matrix based on multi-component analysis (PCA) technology to obtain a dimensionality-reduced matrix. The strategy lookup module is used to determine the tire puncture risk based on the tire pressure residual value. If the risk is determined to be a blowout risk, the blowout probability is calculated based on the blowout probability regression model, and the corresponding response strategy is searched from the first blowout risk database based on the blowout probability. If the risk is determined to be a leak risk, the leak probability is calculated based on the leak risk regression model, and the corresponding response strategy is searched from the leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the dimensionality reduction matrix. The strategy sending module is used to send the found response strategies to the vehicle terminal to instruct the vehicle to perform response operations related to the response strategies.

[0011] Fourthly, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described above and any possible implementations.

[0012] Fifthly, a computer-readable storage medium is provided, wherein at least one instruction is stored therein, the at least one instruction being loaded and executed by a processor to implement the aspects described above and any possible implementation thereof.

[0013] In a sixth aspect, a computer program product is provided, comprising a computer program, wherein the computer program, when executed by a processor, implements the aspects and any possible implementations described above.

[0014] In a seventh aspect, an autonomous vehicle is provided, including the electronic devices described above.

[0015] The beneficial effects of the technical solution provided in this application include at least the following: As can be seen from the above technical solution, the embodiments of this application collect tire-related sensor data such as tire temperature, actual tire pressure, and vehicle speed through an in-vehicle terminal and upload them to the cloud. The cloud quantifies the relationship between temperature and pressure based on tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. A feature matrix is ​​constructed using tire temperature, vehicle speed, actual tire pressure, and the tire pressure residual value, and the feature matrix is ​​dimensionality-reduced based on multi-component analysis (PCA) to obtain a dimensionality-reduced matrix. The tire pressure residual value is used to determine the tire puncture risk. If the risk is determined to be a blowout risk, the blowout probability is calculated based on a blowout risk regression model, and a corresponding response strategy is searched from a first blowout risk database based on the blowout probability. If the risk is determined to be a leak risk, the leak probability is calculated based on a leak risk regression model, and a corresponding response strategy is searched from a leak risk database based on the leak probability. The blowout probability regression model and the leak probability regression model are both exponentially correlated with the dimensionality-reduced matrix. The cloud sends the found response strategies to the in-vehicle terminal to instruct the vehicle to perform response operations related to the response strategies. This application can monitor abnormal tire pressure using PCA technology and logistic regression, enabling efficient and reliable prediction of tire damage while saving cloud computing power.

[0016] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram illustrating the steps of a tire damage risk prediction method provided in an embodiment of this application.

[0019] Figure 2 This is a schematic diagram illustrating the steps of another tire damage risk prediction method of this application.

[0020] Figure 3 This is a schematic diagram of the structure of a tire damage risk prediction system provided in an embodiment of this application.

[0021] Figure 4 This is a structural block diagram of a tire damage risk prediction device provided in another embodiment of this application.

[0022] Figure 5 This is a block diagram of an electronic device used to implement the tire damage risk prediction method of the embodiments of this application. Detailed Implementation

[0024] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These embodiments should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0025] Obviously, the described embodiments are only some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0026] It should be noted that the terminal devices involved in the embodiments of this application may include, but are not limited to, smart devices such as mobile phones, personal digital assistants (PDAs), wireless handheld devices, and tablet computers; the display devices may include, but are not limited to, personal computers, televisions, and other devices with display functions.

[0027] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0028] Given the insufficient accuracy of tire damage assessment, low alarm accuracy, and inability to predict damage in advance in existing technologies, this application proposes a tire damage risk prediction scheme. The main inventive concept is as follows: an on-board terminal collects tire-related sensor data such as tire temperature, actual tire pressure, and vehicle speed, and uploads it to the cloud; the cloud quantifies the relationship between temperature and pressure based on tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure; a feature matrix is ​​constructed using tire temperature, vehicle speed, actual tire pressure, and the tire pressure residual value, and the feature matrix is ​​analyzed using multi-component analysis (PCA) technology. The system performs a dimensionality reduction transformation to obtain a reduced-dimensional matrix. Based on the tire pressure residual value, the risk of tire damage is assessed. If a blowout risk is identified, the probability of a blowout is calculated using a blowout risk regression model, and a corresponding response strategy is retrieved from a first blowout risk database based on the blowout probability. If a leak risk is identified, the probability of a leak is calculated using a leak risk regression model, and a corresponding response strategy is retrieved from a leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the reduced-dimensional matrix. The cloud sends the retrieved response strategies to the vehicle terminal to instruct the vehicle to execute the corresponding response operations. This application utilizes PCA technology and logistic regression to monitor abnormal tire pressure, achieving efficient and reliable prediction of tire damage while saving cloud computing power.

[0029] Reference Figure 1 The diagram shown illustrates the steps of a tire damage risk prediction method provided in this embodiment of the application. This tire damage risk prediction method utilizes a vehicle-mounted terminal on the target vehicle in conjunction with a cloud-based system to achieve early prediction of tire damage risk.

[0030] like Figure 1 As shown, the tire damage risk prediction method may include the following steps: Step 102: The vehicle terminal collects sensor data related to the tires during vehicle operation and uploads it to the cloud; the sensor data related to the tires includes at least: tire temperature, actual tire pressure, and vehicle speed.

[0031] In this application, the target vehicle is equipped with pressure sensors on the wheel hubs to calculate and collect tire pressure via the valve core; simultaneously, tire temperature sensors are also installed to collect tire temperature data. Additionally, infrared temperature sensors can be selectively installed at the bottom of the vehicle body or the underside of the front of the vehicle to detect road surface temperature in real time. Thus, through these various sensors, the actual tire pressure and tire temperature (as well as road surface temperature) are collected and transmitted to the onboard terminal. The onboard terminal then combines this sensor data with the vehicle speed as tire-related sensor data and uploads it to the cloud.

[0032] Step 104: The cloud quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure.

[0033] Optionally, the cloud quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure. When calculating the tire pressure residual value based on the predicted tire pressure and the actual tire pressure, the following regression equation between tire temperature and pressure can be constructed based on the tire temperature and vehicle speed: in, Predict tire pressure, For tire temperature, For vehicle speed, , , , These are the corresponding coefficients; then, the relationship between temperature and pressure is quantified, and the predicted tire pressure is calculated using the above equation; the tire pressure residual is calculated based on the predicted tire pressure and the actual tire pressure. in, This is the tire pressure residual value. This refers to the actual tire pressure.

[0034] In this application, It is actually a constant term. This is the coefficient for tire temperature. This is the coefficient of the square of the tire temperature. These are coefficients representing the product of tire temperature and vehicle speed. These coefficients can be adjusted based on different vehicle models and driving environments, and are generally determined based on empirical data.

[0035] Step 106: The cloud uses tire temperature, vehicle speed, actual tire pressure, and tire pressure residual values ​​to construct a feature matrix, and performs dimensionality reduction transformation on the feature matrix based on multi-component analysis (PCA) technology to obtain a dimensionality-reduced matrix.

[0036] In this application, the cloud can use tire-related sensor data and the tire pressure residual value determined in step 106 above to construct a PCA feature matrix x=[ , , , Then, using MATLAB tools, the data is standardized and dimensionality reduced. For example, the PCA feature matrix x is standardized: x_standardized = zscore(x); and the standardized x_standardized is then reduced using PCA: [coeff, score,latent] = pca(x_standardized). Here, coeff is the eigenvector, with each column representing an eigenvector, sorted by eigenvalue from largest to smallest; score is the new data representation, similar to x; and latent is the eigenvalue. The number of principal components retaining 95% variance is calculated: n_components = find(explained_var>= 0.95, 1). The resulting dimensionality-reduced matrix is: reduced_data = score(x, 1:min(3, n_components)), which is x1_pca in the subsequent model. In score(x, 1:min(3, n_components)), x represents the selected sample rows, i.e. feature evidence, ":" represents all sample rows, and 1:min(3, n_components) represents selecting the top 3 or n (only the minimum value among 3 and n) principal components, i.e. the 3 or n components with the largest variance.

[0037] Step 108: The cloud platform determines the tire puncture risk based on the tire pressure residual value. If the risk is determined to be a blowout risk, the probability of a blowout is calculated based on the blowout risk regression model, and a corresponding response strategy is searched from the first blowout risk database based on the blowout probability. If the risk is determined to be a leak risk, the probability of a leak is calculated based on the leak risk regression model, and a corresponding response strategy is searched from the leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the dimensionality reduction matrix.

[0038] Optionally, when the cloud determines the risk of tire damage based on the tire pressure residual value, it can specifically determine that if the tire pressure residual value is greater than 0 and the absolute value of the gradient of the tire pressure residual value is greater than 0, then it is determined that there is a risk of tire blowout; if the cloud determines that the tire pressure residual value is less than 0 and the absolute value of the gradient of the tire pressure residual value is greater than 0, then it is determined that there is a risk of air leakage.

[0039] In this application, the least squares method can be used to calculate and optimize the parameters, and the tire pressure residual value determined after regression is used as a key feature input into the subsequent model. >0 and >0: A risk of tire blowout is considered. When <0 and >0: There is a risk of gas leakage.

[0040] Furthermore, for situations where a tire blowout risk is confirmed, the probability of a blowout can be calculated using the following formula: After calculating the probability of a tire blowout, the calculated probability of a tire blowout can be determined from the first tire blowout risk database, the corresponding risk level can be matched, and the corresponding response strategy can be found and called.

[0041] First Tire Blowout Risk Database For situations where a leak risk is confirmed, the probability of a leak can be calculated using the following formula: in, For the probability of a tire blowout, Let w1 be the probability of air leakage, w2 be the weight matrix corresponding to the dimensionality reduction matrix in the air leakage risk regression model, and x1_pca be the dimensionality reduction matrix.

[0042] Similarly, once the leakage probability is calculated, the leakage probability threshold range can be determined from the following leakage risk database, the corresponding risk level can be matched, and the corresponding response strategy can be found and invoked.

[0043] First Leakage Risk Database Step 110: The cloud sends the found response strategy to the vehicle terminal to instruct the vehicle to perform response operations related to the response strategy.

[0044] After finding and retrieving a response strategy that matches the risk level in the cloud, the response strategy can be sent to the vehicle's onboard terminal, so that the target vehicle can send the response strategy to the corresponding controller to execute the corresponding control operation.

[0045] Optionally, the tire-related sensor data further includes: road surface temperature; then, referring to Figure 2 The schematic diagram shown below illustrates another method for predicting tire damage risk according to this application, mainly including: Step 202: The vehicle terminal collects sensor data related to the tires during vehicle operation and uploads it to the cloud; the sensor data related to the tires includes at least: tire temperature, actual tire pressure, and vehicle speed.

[0046] Step 204: The cloud quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure.

[0047] Step 206: The cloud uses tire temperature, vehicle speed, actual tire pressure, and tire pressure residual value to construct a feature matrix, and performs dimensionality reduction transformation on the feature matrix based on multi-component analysis (PCA) technology to obtain a dimensionality-reduced matrix.

[0048] Step 208: The cloud platform determines the risk of tire damage based on the tire pressure residual value.

[0049] Step 210: If the risk of tire blowout is determined, calculate the probability of tire blowout based on the tire blowout risk regression model.

[0050] Step 212: Determine whether the road surface temperature is greater than the temperature threshold and the vehicle speed is greater than the speed threshold.

[0051] Considering the impact of road surface temperature on the material of vehicle tires during high-speed driving, the predicted tire blowout probability can be optimized: when If the temperature is >50℃ and the speed is >50km / h, proceed to step 214; otherwise, proceed to step 216.

[0052] If yes, proceed to step 214; otherwise, proceed to step 216.

[0053] Step 214: Search for the corresponding response strategy in the second tire blowout risk database based on the tire blowout probability.

[0054] After calculating the probability of a tire blowout, the calculated probability of a tire blowout can be determined from the second tire blowout risk database, the corresponding risk level can be matched, and the corresponding response strategy can be found and called.

[0055] Second tire blowout risk database Step 216: Search for the corresponding response strategy in the first tire blowout risk database based on the tire blowout probability.

[0056] Among them, the tire blowout probability threshold of the second tire blowout risk library is always lower than the tire blowout probability threshold of the first tire blowout risk library within the same risk level.

[0057] Step 218: If a gas leak risk is identified, calculate the gas leak probability based on the gas leak risk regression model, and search for the corresponding response strategy from the gas leak risk database based on the gas leak probability.

[0058] The tire blowout probability regression model and the air leakage probability regression model are both exponentially correlated with the dimensionality reduction matrix.

[0059] Step 220: The cloud sends the found response strategy to the vehicle terminal to instruct the vehicle to perform response operations related to the response strategy.

[0060] It should be understood that Figure 2 For the specific implementation of the relevant steps in the tire damage risk prediction scheme shown, please refer to... Figure 1 The proposed solution will not be elaborated upon here.

[0061] As described in the above technical solution, the vehicle terminal collects tire-related sensor data such as tire temperature, actual tire pressure, and vehicle speed, and uploads it to the cloud. The cloud quantifies the relationship between temperature and pressure based on tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. A feature matrix is ​​constructed using tire temperature, vehicle speed, actual tire pressure, and the tire pressure residual value, and a dimensionality reduction matrix is ​​obtained using multi-component analysis (PCA). The tire pressure residual value is used to determine the tire puncture risk. If the risk is determined to be a blowout risk, the blowout probability is calculated based on a blowout risk regression model, and a corresponding response strategy is retrieved from a first blowout risk database based on the blowout probability. If the risk is determined to be a leak risk, the leak probability is calculated based on a leak risk regression model, and a corresponding response strategy is retrieved from a leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the dimensionality reduction matrix. The cloud sends the found response strategies to the vehicle terminal to instruct the vehicle to perform the corresponding response operations. This application can monitor abnormal tire pressure using PCA technology and logistic regression, enabling efficient and reliable prediction of tire damage while saving cloud computing power.

[0062] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0063] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0064] Figure 3The diagram shown is a structural schematic of a tire damage risk prediction system provided in an embodiment of this application. The tire damage risk prediction system 300 may include: an on-board terminal 301 and a cloud platform 302; wherein the on-board terminal 301 is integrated and installed on the target vehicle 303, and the target vehicle 303 is also equipped with various sensors, such as tire temperature sensors for collecting tire temperature, infrared temperature sensors for collecting road surface temperature, and tire pressure sensors for collecting tire pressure, etc. These are not labeled here.

[0065] The vehicle terminal 301 collects tire-related sensor data from the vehicle during driving and uploads it to the cloud; wherein the tire-related sensor data includes at least: tire temperature, actual tire pressure, and vehicle speed. The cloud 302 quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. The cloud-based 302 uses tire temperature, vehicle speed, actual tire pressure, and tire pressure residual values ​​to construct a feature matrix, and performs dimensionality reduction transformation on the feature matrix based on multi-component analysis (PCA) technology to obtain a dimensionality-reduced matrix. The cloud-based 302 determines the tire puncture risk based on the tire pressure residual value. If the risk is determined to be a blowout, the blowout probability is calculated based on the blowout probability regression model, and a corresponding response strategy is retrieved from the first blowout risk database based on the blowout probability. If the risk is determined to be a leak, the leak probability is calculated based on the leak risk regression model, and a corresponding response strategy is retrieved from the leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the dimensionality reduction matrix. The cloud 302 sends the found response strategy to the vehicle terminal 301 to instruct the vehicle to perform response operations related to the response strategy.

[0066] Figure 4 This invention provides a structural block diagram of a tire damage risk prediction device according to an embodiment of the present application. Figure 4As shown. The tire damage risk prediction device 400 of this embodiment may include a data receiving module 401, a residual value calculation module 402, a PCA processing module 403, a strategy lookup module 404, and a strategy sending module 405. The data receiving module 401 receives tire-related sensor data collected by the vehicle terminal during vehicle operation; the tire-related sensor data includes at least: tire temperature, actual tire pressure, and vehicle speed. The residual value calculation module 402 quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. The PCA processing module 403 constructs a feature matrix using tire temperature, vehicle speed, actual tire pressure, and the tire pressure residual value, and performs dimensionality reduction transformation on the feature matrix based on multi-component analysis (PCA) technology to obtain a dimensionality-reduced matrix. The strategy lookup module 404 is used to determine the tire puncture risk based on the tire pressure residual value. If the risk is determined to be a blowout risk, the blowout probability is calculated based on the blowout probability regression model, and a corresponding response strategy is searched from the first blowout risk database based on the blowout probability. If the risk is determined to be a leak risk, the leak probability is calculated based on the leak risk regression model, and a corresponding response strategy is searched from the leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the dimensionality reduction matrix. The strategy sending module 405 is used to send the found response strategies to the vehicle terminal to instruct the vehicle to perform response operations related to the response strategies.

[0067] It should be noted that the tire damage risk prediction device in this embodiment is a processing engine located in the network-side server, or it can also be a distributed system located in the network side, such as a processing engine or distributed system in the network-side autonomous driving platform, etc. This embodiment does not make any special limitations on this.

[0068] Optionally, in one possible implementation of this embodiment, the tire-related sensor data further includes: road surface temperature; then, after calculating the tire blowout probability based on the tire blowout probability regression model, the strategy lookup module 404 is further used to determine whether the road surface temperature is greater than a temperature threshold and the vehicle speed is greater than a speed threshold; if so, the corresponding coping strategy is searched from the second tire blowout risk database according to the tire blowout probability; otherwise, the corresponding coping strategy is searched from the first tire blowout risk database according to the tire blowout probability; wherein, in the same risk level, the tire blowout probability threshold of the second tire blowout risk database is always less than the tire blowout probability threshold of the first tire blowout risk database.

[0069] Optionally, in one possible implementation of this embodiment, when the residual value calculation module 402 quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure, it is specifically used to construct the following regression equation between tire temperature and pressure based on the tire temperature and vehicle speed: in, Predict tire pressure, For tire temperature, For vehicle speed, , , , These are the corresponding coefficients; the relationship between temperature and pressure is quantified, and the predicted tire pressure is calculated using the above equation; the tire pressure residual is calculated based on the predicted tire pressure and the actual tire pressure. in, This is the tire pressure residual value. This refers to the actual tire pressure.

[0070] Optionally, in one possible implementation of this embodiment, when the strategy lookup module 404 determines the risk of tire damage based on the tire pressure residual value, it is specifically used to determine that if the tire pressure residual value is greater than 0 and the absolute value of the gradient of the tire pressure residual value is greater than 0, then it is determined that there is a risk of tire blowout; if the tire pressure residual value is less than 0 and the absolute value of the gradient of the tire pressure residual value is greater than 0, then it is determined that there is a risk of air leakage.

[0071] Optionally, in one possible implementation of this embodiment, the strategy lookup module 404, when calculating the probability of a tire blowout based on the tire blowout risk regression model, specifically calculates the probability of a tire blowout based on the following formula: Furthermore, when calculating the leakage probability based on the leakage risk regression model, the strategy lookup module 404 specifically calculates the leakage probability based on the following formula: in, For the probability of a tire blowout, Let w1 be the probability of air leakage, w2 be the weight matrix corresponding to the dimensionality reduction matrix in the air leakage risk regression model, and x1_pca be the dimensionality reduction matrix.

[0072] In this embodiment, tire-related sensor data such as tire temperature, actual tire pressure, and vehicle speed can be collected through the vehicle terminal and uploaded to the cloud. The cloud quantifies the relationship between temperature and pressure based on tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. A feature matrix is ​​constructed using tire temperature, vehicle speed, actual tire pressure, and the tire pressure residual value, and the feature matrix is ​​dimensionality-reduced using multi-component analysis (PCA) to obtain a dimensionality-reduced matrix. The tire pressure residual value is used to determine the tire puncture risk. If the risk is determined to be a blowout risk, the blowout probability is calculated based on the blowout risk regression model, and the corresponding response strategy is searched from the first blowout risk database based on the blowout probability. If the risk is determined to be a leak risk, the leak probability is calculated based on the leak risk regression model, and the corresponding response strategy is searched from the leak risk database based on the leak probability. The blowout probability regression model and the leak probability regression model are both exponentially correlated with the dimensionality-reduced matrix. The cloud sends the found response strategies to the vehicle terminal to instruct the vehicle to perform response operations related to the response strategies. This application can monitor abnormal tire pressure using PCA technology and logistic regression, enabling efficient and reliable prediction of tire damage while saving cloud computing power.

[0073] One embodiment of this application provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the method for predicting tire damage risk as described above.

[0074] One embodiment of this application provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the tire damage risk prediction method as described above.

[0075] One embodiment of this application provides an autonomous driving vehicle, including the electronic devices described above. Specifically, the autonomous driving vehicle can be a Level 2 or higher vehicle.

[0076] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0077] Figure 5A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of this application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0078] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. The RAM 503 may also store various programs and data required for the operation of the electronic device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0079] Multiple components in electronic device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows electronic device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0080] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the tire puncture risk prediction method. For example, in some embodiments, the tire puncture risk prediction method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the tire puncture risk prediction method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the tire puncture risk prediction method by any other suitable means (e.g., by means of firmware).

[0081] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, at least one input device, and at least one output device.

[0082] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0083] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0084] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0085] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0086] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0087] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0088] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for predicting tire damage risk, characterized in that, include: The vehicle terminal collects sensor data related to the tires during vehicle operation and uploads it to the cloud; the tire-related sensor data includes at least: tire temperature, actual tire pressure, and vehicle speed. The cloud platform quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. The cloud uses tire temperature, vehicle speed, actual tire pressure, and tire pressure residual values ​​to construct a feature matrix, and performs dimensionality reduction transformation on the feature matrix based on multi-component analysis (PCA) technology to obtain a dimensionality-reduced matrix. The cloud-based system determines the tire puncture risk based on the tire pressure residual value. If the risk is determined to be a blowout, the system calculates the blowout probability based on the blowout risk regression model and searches for corresponding response strategies in the first blowout risk database based on the blowout probability. If the risk is determined to be a leak, the system calculates the leak probability based on the leak risk regression model and searches for corresponding response strategies in the leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the dimensionality reduction matrix. The cloud will send the found response strategies to the vehicle terminal to instruct the vehicle to perform response operations related to the response strategies.

2. The method as described in claim 1, characterized in that, The tire-related sensor data also includes: road surface temperature; therefore, after calculating the tire blowout probability based on the blowout probability regression model, the method further includes: Determine if the road surface temperature is greater than the temperature threshold and the vehicle speed is greater than the speed threshold; If so, then search for the corresponding response strategy from the second tire blowout risk database based on the tire blowout probability; Otherwise, the corresponding response strategy is searched from the first tire blowout risk database based on the tire blowout probability; wherein, for the same risk level, the tire blowout probability threshold of the second tire blowout risk database is always lower than the tire blowout probability threshold of the first tire blowout risk database.

3. The method as described in claim 1 or 2, characterized in that, The cloud-based system quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure. It then calculates the tire pressure residual based on the predicted tire pressure and the actual tire pressure, specifically including: Based on the tire temperature and vehicle speed, the cloud platform constructs the following regression equation for tire temperature and pressure: in, Predict tire pressure, For tire temperature, For vehicle speed, , , , These are the corresponding coefficients; The relationship between temperature and pressure is quantified, and the predicted tire pressure is calculated using the above equation. Calculate the tire pressure residual value based on the predicted tire pressure and the actual tire pressure: in, This is the tire pressure residual value. This refers to the actual tire pressure.

4. The method as described in claim 3, characterized in that, The cloud-based system determines the risk of tire damage based on the tire pressure residual value, specifically including: If the cloud determines that the tire pressure residual value is greater than 0 and the absolute value of the gradient of the tire pressure residual value is greater than 0, then it is determined that there is a risk of tire blowout. If the cloud determines that the tire pressure residual value is less than 0 and the absolute value of the gradient of the tire pressure residual value is greater than 0, then it is determined that there is a risk of air leakage.

5. The method as described in claim 3, characterized in that, The probability of a tire blowout is calculated based on a tire blowout risk regression model, specifically including: The probability of a tire blowout is calculated using the following formula: The probability of leakage is calculated based on a leakage risk regression model, specifically including: The probability of air leakage is calculated based on the following formula: in, For the probability of a tire blowout, Let w1 be the probability of air leakage, w2 be the weight matrix corresponding to the dimensionality reduction matrix in the air leakage risk regression model, and x1_pca be the dimensionality reduction matrix.

6. A tire damage risk prediction system, characterized in that, include: In-vehicle terminals and the cloud; among them, The vehicle-mounted terminal collects sensor data related to the tires during vehicle operation and uploads it to the cloud; wherein the sensor data related to the tires includes at least: tire temperature, actual tire pressure, and vehicle speed; The cloud platform quantifies the relationship between temperature and pressure based on the tire temperature and vehicle speed to obtain the predicted tire pressure, and calculates the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. The cloud uses tire temperature, vehicle speed, actual tire pressure, and tire pressure residual values ​​to construct a feature matrix, and performs dimensionality reduction transformation on the feature matrix based on multi-component analysis (PCA) technology to obtain a dimensionality-reduced matrix. The cloud-based system determines the risk of tire puncture based on the tire pressure residual value. If the risk is determined to be a blowout, the system calculates the blowout probability based on the blowout probability regression model and searches for corresponding response strategies in the first blowout risk database based on the blowout probability. If the risk is determined to be a leak, the system calculates the leak probability based on the leak risk regression model and searches for corresponding response strategies in the leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the dimensionality reduction matrix. The cloud will send the found response strategies to the vehicle terminal to instruct the vehicle to perform response operations related to the response strategies.

7. A tire damage risk prediction device, characterized in that, include: The data receiving module is used to receive sensor data related to the tires collected by the vehicle terminal during the vehicle's operation; wherein, the sensor data related to the tires includes at least: tire temperature, actual tire pressure, and vehicle speed; The residual value calculation module is used to quantify the relationship between temperature and pressure based on the tire temperature and vehicle speed, obtain the predicted tire pressure, and calculate the tire pressure residual value based on the predicted tire pressure and the actual tire pressure. The PCA processing module is used to construct a feature matrix using tire temperature, vehicle speed, actual tire pressure, and tire pressure residual values, and to perform dimensionality reduction transformation on the feature matrix based on multi-component analysis (PCA) technology to obtain a dimensionality-reduced matrix. The strategy lookup module is used to determine the tire puncture risk based on the tire pressure residual value. If the risk is determined to be a blowout risk, the blowout probability is calculated based on the blowout probability regression model, and the corresponding response strategy is searched from the first blowout risk database based on the blowout probability. If the risk is determined to be a leak risk, the leak probability is calculated based on the leak risk regression model, and the corresponding response strategy is searched from the leak risk database based on the leak probability. Both the blowout probability regression model and the leak probability regression model are exponentially correlated with the dimensionality reduction matrix. The strategy sending module is used to send the found response strategies to the vehicle terminal to instruct the vehicle to perform response operations related to the response strategies.

8. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-5.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.

Images