Wheel loosening warning methods, devices, media and vehicles

Abstract

This application discloses a wheel loosening warning method, device, medium, and vehicle, applied in the field of vehicle control technology. The method includes: acquiring wheel images, wheel attribute data, and driving attribute data of the vehicle; obtaining target tire pressure detection information and target fastness detection information of the vehicle based on the wheel images and wheel attribute data; wherein, the target tire pressure detection information is used to indicate whether the tire pressure of the wheel is normal, and the target fastness detection information is used to indicate whether the mechanical structure of the wheel is tight; if the target tire pressure detection information indicates abnormal tire pressure, and / or the target fastness detection information indicates that the mechanical structure of the wheel is not tight, then the vehicle's wheel motion trajectory data is obtained based on the wheel images, wheel attribute data, and driving attribute data; and wheel loosening warning processing is performed on the vehicle based on the wheel motion trajectory data. This application can effectively improve the accuracy of wheel loosening warning.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a wheel loosening warning method, device, medium, and vehicle. Background Technology

[0002] Vehicles are among the most common, widespread, and frequently used modes of transportation in daily life. Loose wheels pose a significant safety hazard, affecting vehicle stability and increasing the risk of traffic accidents. Therefore, providing wheel loosening warnings is crucial for vehicle safety maintenance. Current technologies monitor tire pressure and its changes in real time while the vehicle is in motion. If a variable reaches a set threshold, a wheel loosening warning signal is issued to indicate the risk of a loose wheel. However, these technologies rely solely on tire pressure to determine wheel looseness, limiting their accuracy to a single factor. Summary of the Invention

[0003] This application provides a wheel loosening warning method, device, medium, and vehicle to improve the accuracy of wheel loosening warning.

[0004] On the one hand, embodiments of this application provide a wheel loosening warning method, including the following steps:

[0005] Acquire vehicle wheel images, wheel attribute data, and driving attribute data;

[0006] Based on the wheel image and the wheel attribute data, target tire pressure detection information and target fastness detection information of the vehicle are obtained; wherein, the target tire pressure detection information is used to indicate whether the tire pressure of the wheel is normal, and the target fastness detection information is used to indicate whether the mechanical structure of the wheel is fastened.

[0007] When the target tire pressure detection information is used to indicate abnormal tire pressure of the wheel, and / or the target fastening detection information is used to indicate that the mechanical structure of the wheel is not fastened, the wheel motion trajectory data of the vehicle is obtained based on the wheel image, the wheel attribute data and the driving attribute data.

[0008] Based on the wheel movement trajectory data, a wheel loosening warning process is performed on the vehicle.

[0009] On the other hand, embodiments of this application provide a wheel loosening warning device, including:

[0010] The acquisition module is used to acquire images of the vehicle's wheels, wheel attribute data, and driving attribute data.

[0011] The first processing module is used to obtain target tire pressure detection information and target fastness detection information of the vehicle based on the wheel image and the wheel attribute data; wherein, the target tire pressure detection information is used to indicate whether the tire pressure of the wheel is normal, and the target fastness detection information is used to indicate whether the mechanical structure of the wheel is fastened.

[0012] The second processing module is used to obtain the wheel motion trajectory data of the vehicle based on the wheel image, the wheel attribute data, and the driving attribute data when the target tire pressure detection information is used to indicate that the tire pressure of the wheel is abnormal, and / or the target fastening detection information is used to indicate that the mechanical structure of the wheel is not fastened.

[0013] The third processing module is used to perform wheel loosening warning processing on the vehicle based on the wheel movement trajectory data.

[0014] In another aspect, embodiments of this application provide a computer-readable storage medium in which a processor-executable program, when executed by the processor, is used to implement the aforementioned wheel loosening warning method.

[0015] In another aspect, embodiments of this application provide a vehicle, including:

[0016] At least one processor;

[0017] At least one memory for storing at least one program;

[0018] When the at least one program is executed by the at least one processor, the at least one processor implements the above-described wheel loosening warning method.

[0019] According to the wheel loosening warning method, device, medium, and vehicle provided in this application, firstly, wheel images, wheel attribute data, and driving attribute data of the vehicle are acquired; then, based on the wheel images and wheel attribute data, target tire pressure detection information and target fastness detection information of the vehicle are obtained; wherein, the target tire pressure detection information is used to indicate whether the tire pressure of the wheel is normal, and the target fastness detection information is used to indicate whether the mechanical structure of the wheel is tight; subsequently, if the target tire pressure detection information indicates that the tire pressure of the wheel is abnormal, and / or, the target fastness detection information indicates that the mechanical structure of the wheel is not tight, then the wheel motion trajectory data of the vehicle is obtained based on the wheel images, wheel attribute data, and driving attribute data; finally, based on the wheel motion trajectory data, wheel loosening warning processing is performed on the vehicle. According to the technical solution of this application, multi-dimensional factors such as image data and attribute data associated with the vehicle's wheels, as well as attribute data associated with vehicle driving, are fully considered, and wheel loosening warning processing is implemented based on these multi-dimensional factors. This can eliminate the interference of loosening misjudgment caused by single-dimensional factors, thereby effectively improving the accuracy of wheel loosening warning.

[0020] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description, claims and drawings. Attached Figure Description

[0021] Figure 1 This is a flowchart of a wheel loosening early warning method provided in this application;

[0022] Figure 2 yes Figure 1 A detailed flowchart of step S102;

[0023] Figure 3 yes Figure 1 Another specific flowchart of step S102;

[0024] Figure 4 yes Figure 1 A detailed flowchart of step S103;

[0025] Figure 5 yes Figure 1 A detailed flowchart of step S104;

[0026] Figure 6 This is a flowchart of the model training provided in this application;

[0027] Figure 7 This is a diagram illustrating the specific implementation process of a wheel loosening early warning method provided in this application;

[0028] Figure 8 This is a structural diagram of a wheel loosening warning device provided in this application;

[0029] Figure 9 This is an example image of a vehicle provided in this application. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0031] The present application will be further described below with reference to the accompanying drawings and specific embodiments. The described embodiments should not be considered as limitations on the present application, and all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present application.

[0032] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0034] With the rapid development of technology, vehicles are one of the most common, widespread, and frequently used modes of transportation in daily life, becoming important commuting and production tools. When a vehicle is in motion, problems with the wheels will affect its stability, potentially causing issues such as increased noise, vehicle vibration, and vehicle deviation. In severe cases, it may lead to tire blowouts or wheel detachment, increasing the risk of traffic accidents. Therefore, loose wheels are a significant safety hazard, and providing early warning of loose wheels is crucial for vehicle safety maintenance.

[0035] In related technologies, tire pressure or changes in tire pressure are monitored in real time while the vehicle is in motion. If the tire pressure or changes in tire pressure reach a set threshold, a warning signal for wheel loosening is issued to indicate the risk of wheel loosening. However, tire pressure is easily affected by factors such as temperature, load, and altitude. These technologies rely solely on tire pressure to determine wheel loosening, making them susceptible to misjudgments such as false positives, thus resulting in low accuracy in wheel loosening warnings.

[0036] In view of this, embodiments of this application provide a wheel loosening warning method, device, medium, and vehicle, which aim to monitor the tire pressure and tightness of the wheels and the vehicle's deviation status in real time, and issue corresponding wheel loosening warnings based on the monitoring results, thereby effectively improving the accuracy of wheel loosening warnings.

[0037] First, the implementation steps of a wheel loosening warning method provided in this application embodiment will be described in detail below with reference to the accompanying drawings.

[0038] This application provides a wheel loosening warning method, which can be applied to a terminal, a server, or software running on either a terminal or a server. The terminal can be a tablet, laptop, desktop computer, etc., but is not limited to these. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. Furthermore, the server can be a node server in a blockchain network, but is not limited to these. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0039] Reference Figure 1 , Figure 1 This is a flowchart of a wheel loosening warning method provided in this application, which may include the following steps S101-S104:

[0040] S101, acquire the vehicle's wheel image, wheel attribute data, and driving attribute data;

[0041] S102, Based on the wheel image and wheel attribute data, obtain the target tire pressure detection information and target fastness detection information of the vehicle; wherein, the target tire pressure detection information is used to indicate whether the tire pressure of the wheel is normal, and the target fastness detection information is used to indicate whether the mechanical structure of the wheel is fastened.

[0042] S103, when the target tire pressure detection information is used to indicate abnormal tire pressure of the wheel, and / or the target fastening detection information is used to indicate that the mechanical structure of the wheel is not fastened, the wheel motion trajectory data of the vehicle is obtained based on the wheel image, wheel attribute data and driving attribute data.

[0043] S104, based on wheel motion trajectory data, performs early warning processing for wheel loosening of vehicles.

[0044] In step S101 above, image data and attribute data associated with the vehicle's wheels are acquired before and during vehicle travel, serving as the vehicle's wheel images and wheel attribute data; and attribute data associated with vehicle travel are acquired, serving as the vehicle's driving attribute data. This allows for the detection and warning of wheel loosening in subsequent steps, using these data as a benchmark.

[0045] Here, the aforementioned wheel images may include, but are not limited to, image data associated with wheel shape before the vehicle is in motion, and image data associated with local wheel temperature during vehicle operation. The aforementioned wheel attribute data may include, but is not limited to, attribute data associated with the physical characteristics of the wheel during vehicle operation; this attribute data is numerical text data. The aforementioned driving attribute data may include, but is not limited to, attribute data associated with the physical characteristics of the vehicle during operation; this attribute data is numerical text data.

[0046] In step S102 above, during the wheel loosening warning, based on the wheel image and wheel attribute data, the tire pressure of the wheel is first checked to see if it is normal, and the mechanical structure of the wheel is checked to see if it is securely installed, thereby obtaining the vehicle's target tire pressure detection information and target tightness detection information. The target tire pressure detection information indicates whether the tire pressure of the wheel is normal, and the target tightness detection information indicates whether the mechanical structure of the wheel is secure.

[0047] Here, tire pressure is highly correlated with wheel looseness. When tire pressure is abnormally low, it indicates a tire leak, which may be caused by issues such as loose wheel bolts, damaged bearings, or deformed wheel rims, leading to wheel looseness. In other words, abnormal tire pressure can indirectly reflect wheel looseness. Therefore, checking tire pressure first in a wheel looseness warning system helps quickly identify any potential risk of wheel looseness.

[0048] Similarly, the tightness of the wheel's mechanical structure is highly correlated with wheel loosening. The tightness of the wheel's mechanical structure typically refers to the tightness of the wheel's fixing bolts, hub bolts, hub bearings, etc. When there are issues such as loose fixing bolts or bearing bolts, or deformed hub bearings, it indicates insufficient tightness in the wheel's mechanical structure. This can lead to the wheel losing its fixed constraint, resulting in wheel loosening. In other words, insufficient tightness in the wheel's mechanical structure can indirectly reflect wheel loosening. Therefore, checking the tightness of the wheel's mechanical structure first in a wheel loosening warning system helps to quickly identify the potential risk of wheel loosening in a vehicle.

[0049] In step S103 above, if the target tire pressure detection information indicates abnormal tire pressure of the wheel and / or the target fastening detection information indicates that the mechanical structure of the wheel is not fastened, it means that the tire pressure of the wheel is abnormal and / or the mechanical structure of the wheel is not fastened, and there is a potential risk of wheel loosening. At this time, the wheel's motion trajectory in the future time period is predicted based on the wheel image, wheel attribute data and driving attribute data, so as to obtain the vehicle's wheel motion trajectory data.

[0050] Here, during vehicle operation, if the wheel's trajectory is not a perfect circle, exhibits a regular curve, or shows lateral movement relative to the vehicle body, it indicates wheel misalignment; otherwise, it indicates no wheel misalignment. Wheel misalignment is highly correlated with wheel looseness. When a wheel misaligns, it indicates insufficient dynamic balance or hub displacement. For example, insufficient wheel dynamic balance will cause steering wheel vibration and wheel misalignment; similarly, hub displacement will cause lateral wheel displacement and wheel misalignment, which will lead to wheel looseness. In other words, wheel misalignment directly reflects wheel looseness. Therefore, given the potential risk of wheel looseness, detecting the vehicle's wheel trajectory data helps to quickly and accurately determine whether the wheels are loose. It should be understood that if the target tire pressure detection information indicates normal tire pressure and the target tightness detection information indicates tight mechanical structure of the wheel, it means the tire pressure is normal and the mechanical structure is tight, and there is no potential risk of wheel looseness. In this case, the process returns to step S101 to achieve cyclic detection.

[0051] In step S104 above, after determining the wheel movement trajectory data of the vehicle, the wheel movement trajectory data is used as a reference to determine whether the vehicle's wheels are loose, and a wheel loosening warning is issued accordingly.

[0052] Through the above steps S101-S104, this embodiment first detects whether the tire pressure of the wheel is normal and whether the mechanical structure of the wheel is tight based on the image data and attribute data associated with the wheel, thereby initially identifying whether there is a potential risk of wheel loosening in the vehicle. Then, if there is a potential risk of wheel loosening in the vehicle, the vehicle's wheel movement trajectory data is predicted based on the image data and attribute data associated with the vehicle's wheel and the attribute data associated with the vehicle's driving, and wheel loosening warning processing is performed accordingly. Thus, this embodiment does not simply consider single-dimensional factors, but fully considers multi-dimensional factors such as the image data and attribute data associated with the vehicle's wheel and the attribute data associated with the vehicle's driving, and realizes wheel loosening warning processing based on these multi-dimensional factors. This can eliminate the interference of loosening misjudgment caused by single-dimensional factors (tire pressure), thereby effectively improving the accuracy of wheel loosening warning, ensuring that the wheel is always in good condition, ensuring the safety of drivers and passengers, reducing the risk of traffic accidents, and helping to improve the safety, intelligence, and comfort experience of users when driving or riding in the vehicle.

[0053] In some implementations, refer to Figure 2The aforementioned wheel images may include ground contact images of the wheels before the vehicle travels and infrared images of the wheels while the vehicle is traveling; the aforementioned wheel attribute data may include first tire pressure data of the wheels before the vehicle travels, and second tire pressure data, effective radius data, and wheel hub vibration frequency data of the wheels while the vehicle is traveling; in the aforementioned step S102, obtaining the target tire pressure detection information and target fastening detection information of the vehicle based on the wheel images and wheel attribute data may include the following steps S201-S202:

[0054] S201, Based on the grounding image and the first tire pressure data, determine the tire pressure risk factor of the vehicle before driving;

[0055] S202, tire pressure detection processing is performed based on tire pressure risk coefficient, infrared image, second tire pressure data, effective radius data and wheel hub vibration frequency data to obtain the tire pressure detection information of the vehicle when it is in motion as the target tire pressure detection information.

[0056] Here, in the aforementioned wheel images, the contact patch image refers to a top-down view of the tire's contact patch shape, indicating the wheel's shape before the vehicle moves and is related to tire pressure. Under normal circumstances, the contact patch area is a uniform ellipse; if the contact patch area widens and the edges are noticeably deformed, it indicates possible insufficient tire pressure. The infrared image refers to an infrared thermal image of the wheel, indicating the changes in heat distribution as the wheel rolls during vehicle movement, and is also related to tire pressure. Under normal circumstances, the heat distribution of the wheel should be uniform during rolling; if the local temperature rises during rolling, it indicates possible repeated bending of the sidewalls, leading to insufficient tire pressure. Therefore, contact patch images and infrared images help detect abnormal tire pressure in vehicles.

[0057] Optionally, ground images can be acquired by integrating a conventional camera into the wheel arch; infrared images can be acquired by integrating an infrared camera into the wheel arch, but this is not a limitation.

[0058] Among the wheel attribute data mentioned above, tire pressure data refers to the pressure of the tires, which directly indicates the tire pressure. When the tire pressure data is lower than the normal value, it indicates insufficient tire pressure. Effective radius data refers to the equivalent radius of the tire when it actually rolls under load, and it is highly correlated with the tire pressure. Under normal circumstances, the effective radius data remains relatively constant; if the effective radius data decreases, it indicates possible insufficient tire pressure. For example, if the tire pressure of the left front wheel is insufficient, the speed of the left front wheel will be slightly higher than that of the right front wheel because the effective radius of the left front wheel is reduced, requiring it to rotate more times to maintain the same vehicle speed. Hub vibration frequency data refers to the frequency of free vibration of the wheel hub without external excitation, and it is highly correlated with the tire pressure. Under normal circumstances, the hub vibration frequency data remains relatively constant; if the hub vibration frequency data decreases, it indicates a decrease in tire stiffness, which may indicate insufficient tire pressure. Therefore, using tire pressure data, effective radius data, and hub vibration frequency data helps to detect whether the vehicle's tire pressure is abnormal.

[0059] Optionally, tire pressure data can be collected using a tire pressure sensor, and wheel vibration frequency data can be collected using a wheel vibration sensor; vehicle speed data can be obtained using a vehicle speed sensor, and wheel speed data can be obtained using a wheel speed sensor. The ratio of the vehicle speed data to the wheel speed data can be used as the effective radius data, but this is not limited to this.

[0060] In related technologies, tire pressure abnormalities are typically detected solely by the tire pressure value or its change. However, tire pressure is easily affected by factors such as temperature, load, and altitude, leading to potential misjudgments of abnormal tire pressure and a need for improved accuracy. To address this, this embodiment introduces multimodal data and employs a two-stage (dynamic and static) tire pressure detection method to improve the accuracy of tire pressure detection.

[0061] In step S201 above, tire pressure risk prediction is performed based on the ground contact image of the wheels before the vehicle is driven and the first tire pressure data, and the tire pressure risk coefficient before the vehicle is driven is obtained. This tire pressure risk coefficient can reflect the probability of abnormal tire pressure of the wheels of the vehicle before it is driven.

[0062] Here, the vehicle is stationary before driving, and the wheels are in a cold tire state. By using the ground contact image and tire pressure data of the cold tires, the probability of abnormal tire pressure in the wheels before driving is determined, thus achieving tire pressure detection in the static stage. Image modal data can effectively capture the physical deformation characteristics of the wheels in a cold tire state (such as abnormal ground contact area, irregular edges, etc.), while text modal data can effectively capture the physical tire pressure characteristics of the wheels in a cold tire state. This implementation introduces multimodal data to achieve tire pressure risk prediction, thereby effectively improving the accuracy of tire pressure detection in the static stage, quickly and accurately identifying potential situations of suspected tire pressure abnormalities, and thus helping to accelerate the efficiency of tire pressure detection.

[0063] In some embodiments, determining the tire pressure risk coefficient of a vehicle before driving based on the grounding image and the first tire pressure data may include: extracting features from the grounding image to obtain grounding image features; extracting features from the first tire pressure data to obtain first tire pressure features; and determining the tire pressure risk coefficient of a vehicle before driving based on the grounding image features and the first tire pressure features, combined with machine learning methods.

[0064] Here, in the static tire pressure detection phase, firstly, feature extraction is performed on the ground contact image to obtain ground contact image features. These features can include wheel width and edge deformation features. The width feature reflects the wheel's width, and the edge deformation feature reflects the wheel's deformation when it touches the ground, thus providing a more comprehensive picture of the wheel's characteristics when it touches the ground. Simultaneously, feature extraction is performed on the first tire pressure data to obtain the first tire pressure features. The specific implementation of feature extraction can be flexibly set according to actual conditions, and this embodiment does not impose any limitations on it. Next, the ground contact image features and the first tire pressure features are input into a pre-trained first tire pressure risk prediction model to obtain the tire pressure risk coefficient before the vehicle is driven; the risk coefficient is the predicted probability. The first tire pressure risk prediction model is a machine learning model trained using multiple first feature samples and the label information corresponding to each first feature sample. The first feature samples include ground contact image feature samples and tire pressure feature samples. The label information corresponding to each first feature sample is the tire pressure risk coefficient, which can be determined through expert annotation, historical data statistics, etc. Furthermore, the type of the first tire pressure risk prediction model can be flexibly set according to the actual situation. For example, it can be a model such as support vector machine or logistic regression, but it is not limited to this. In this way, by performing tire pressure risk prediction through machine learning methods, the superior performance of machine learning methods can effectively improve the accuracy of tire pressure risk prediction.

[0065] In some embodiments, determining the tire pressure risk coefficient of the vehicle before driving based on the grounding image and the first tire pressure data may include: predicting the tire pressure risk based on the grounding image to obtain a first risk coefficient; predicting the tire pressure risk based on the first tire pressure data to obtain a second risk coefficient; and determining the tire pressure risk coefficient of the vehicle before driving based on the first risk coefficient and the second risk coefficient.

[0066] Here, in the static tire pressure detection phase, firstly, tire pressure risk is predicted based on the grounding image and a pre-trained second tire pressure prediction model, yielding a first risk coefficient. This first risk coefficient indicates the probability that the tire pressure of the vehicle's wheels is abnormal before driving; it is the predicted probability. The second tire pressure risk prediction model is trained using multiple grounding image samples and the corresponding label information for each sample. The label information for each grounding image sample represents the risk coefficient, which can be determined through expert annotation, historical data statistics, etc. Furthermore, the type of the second tire pressure risk prediction model can be flexibly set according to actual conditions; for example, it could be a convolutional neural network, but it is not limited to this. Simultaneously, tire pressure risk is predicted based on the first tire pressure data and a pre-trained third tire pressure prediction model, yielding a second risk coefficient. This second risk coefficient indicates the probability that the tire pressure of the vehicle's wheels is abnormal before driving; it is the predicted probability. This third tire pressure prediction model is trained using multiple tire pressure data samples and the corresponding label information for each sample. The label information for each tire pressure data sample represents the risk coefficient, which can be determined through expert annotation, historical data statistics, etc. Furthermore, the type of the third tire pressure risk prediction model can be flexibly set according to the actual situation, such as support vector machines, logistic regression, etc., but is not limited to these. Next, the first and second risk coefficients are integrated to obtain the tire pressure risk coefficient before the vehicle is driven. For example, the mean of the first and second risk coefficients is calculated as the tire pressure risk coefficient before the vehicle is driven. Alternatively, the first and second risk coefficients are weighted and summed to obtain the tire pressure risk coefficient before the vehicle is driven. Thus, this embodiment performs tire pressure risk prediction from the perspective of image modality data, which can accurately determine the tire pressure risk based on physical deformation characteristics. Similarly, performing tire pressure risk prediction from the perspective of text modality data can accurately determine the tire pressure risk based on physical tire pressure characteristics. Considering that the tire pressure risks reflected by different modalities of data are different, the final tire pressure risk is determined by integrating the tire pressure risks corresponding to multiple modalities, thereby helping to further improve the accuracy of tire pressure risk prediction.

[0067] In step S202 above, based on the probability of abnormal tire pressure of the wheels before the vehicle is driven, the target tire pressure detection information is determined by using multiple factors such as infrared images of the wheels in the driving state, second tire pressure data, effective radius data and wheel hub vibration frequency data, to indicate whether the tire pressure of the wheels of the vehicle is abnormal when it is driving.

[0068] Here, on the one hand, compared to methods that only rely on tire pressure values ​​or changes in tire pressure for tire pressure detection, this embodiment fully considers multimodal data related to tire pressure height, using this multimodal data to achieve tire pressure detection in the dynamic phase. On the other hand, compared to methods that only rely on real-time data while the vehicle is in motion for tire pressure detection, this embodiment, in dynamic tire pressure detection, not only considers real-time data related to tire pressure height while the vehicle is in motion, but also considers the probability of tire pressure risk before the vehicle is in motion. Thus, this embodiment introduces multi-dimensional data into dynamic tire pressure detection, considering tire pressure conditions when the vehicle is stationary and not stationary, thereby effectively improving the comprehensiveness, accuracy, and reliability of tire pressure detection and reducing the risk of misjudgment.

[0069] In some embodiments, considering that tire pressure detection of the vehicle at the current moment is more important, the longest cycle time of the above step S202 is thirty seconds, that is, the above step S202 is executed once every thirty seconds or less (e.g., every twenty seconds), and the result of the new execution overwrites the result of the previous execution, thereby realizing real-time tire pressure detection.

[0070] In some embodiments, the above-mentioned tire pressure detection processing based on tire pressure risk coefficient, infrared image, second tire pressure data, effective radius data, and wheel hub vibration frequency data to obtain tire pressure detection information of the vehicle while driving may include: extracting features from the infrared image, second tire pressure data, effective radius data, and wheel hub vibration frequency data to obtain infrared temperature field features, second tire pressure features, effective radius features, and wheel hub vibration frequency features; and obtaining tire pressure detection information of the vehicle while driving by combining the tire pressure risk coefficient, infrared temperature field features, second tire pressure features, effective radius features, and wheel hub vibration frequency features with machine learning methods.

[0071] Here, during tire pressure detection, firstly, feature extraction is performed on the infrared image, second tire pressure data, effective radius data, and wheel hub vibration frequency data to obtain infrared temperature field features, second tire pressure features, effective radius features, and wheel hub vibration frequency features. This allows for the extraction of feature information highly correlated with tire pressure during vehicle operation. The specific implementation of feature extraction can be flexibly configured according to actual conditions, and this embodiment does not impose any limitations on it. Then, the tire pressure risk coefficient, infrared temperature field features, second tire pressure features, effective radius features, and wheel hub vibration frequency features are input into a pre-trained tire pressure detection model. The tire pressure detection model obtains the tire pressure detection information during vehicle operation. The tire pressure detection model is trained using multiple second feature samples and the corresponding label information for each second feature sample. The second feature samples include tire pressure risk coefficient samples, infrared temperature field feature samples, tire pressure feature samples, effective radius feature samples, and wheel hub vibration frequency feature samples. The label information corresponding to the second feature samples indicates whether the tire pressure is normal; it is typically represented as one or zero, where one indicates normal tire pressure and zero indicates abnormal tire pressure. Furthermore, the tire pressure monitoring model can be flexibly configured according to actual conditions, such as support vector machines, random forests, etc., but is not limited to these. Thus, by using machine learning methods to perform tire pressure monitoring, the superior performance of machine learning methods can effectively improve the accuracy of tire pressure monitoring.

[0072] In some embodiments, the above-mentioned tire pressure detection processing based on tire pressure risk coefficient, infrared image, second tire pressure data, effective radius data, and wheel hub vibration frequency data to obtain tire pressure detection information of the vehicle while driving may include: performing temperature detection based on the infrared image to obtain temperature detection information, which is used to indicate whether the vehicle's wheel temperature field is abnormal; if any one of the temperature detection information, tire pressure risk coefficient, second tire pressure data, effective radius data, or wheel hub vibration frequency data meets a first preset condition, then the tire pressure detection information of the vehicle while driving is determined to indicate abnormal tire pressure; otherwise, the tire pressure detection information of the vehicle while driving is determined to indicate normal tire pressure; wherein, the first preset condition includes: the temperature detection information indicates abnormal wheel temperature field of the vehicle, the tire pressure risk coefficient is higher than the tire pressure risk threshold, the second tire pressure data is outside the tire pressure range, the effective radius data is outside the radius range, and the wheel hub vibration frequency data is outside the first frequency range.

[0073] Here, during tire pressure detection, firstly, infrared images are input into a pre-trained temperature detection model. The model obtains temperature detection information indicating whether the vehicle's wheel temperature field is abnormal. This model is trained using multiple infrared image samples and their corresponding label information. The label information indicates whether the wheel temperature field is abnormal, typically represented as one or zero, where one indicates a normal wheel temperature field and zero indicates an abnormal one. Furthermore, the temperature detection model can be flexibly configured according to actual conditions; for example, it could be a convolutional neural network, but it is not limited to this. Next, it is determined whether any one of the following—temperature detection information, tire pressure risk coefficient, second tire pressure data, effective radius data, or wheel hub vibration frequency data—meets a first preset condition. If so, it indicates that the vehicle's tire pressure is abnormal at the current moment, and the tire pressure detection information during vehicle operation is used to indicate abnormal tire pressure. Otherwise, it indicates that the vehicle's tire pressure is normal at the current moment, and the tire pressure detection information during vehicle operation is used to indicate normal tire pressure. In this way, by converting infrared images into feature information that can be used for comparison, and realizing tire pressure detection in the dynamic stage through simple comparison operations, the accuracy of tire pressure detection can be ensured while improving the efficiency of tire pressure detection and meeting real-time requirements. Optionally, the tire pressure risk threshold, tire pressure range, radius range, and first frequency range can all be set according to actual conditions, and this embodiment does not impose specific limitations on them.

[0074] In some implementations, refer to Figure 3 The aforementioned wheel attribute data includes wheel clamping torque data, axial displacement data, and radial displacement data before the vehicle is in motion, as well as wheel driving torque data, wheel speed data, operating sound data, and wheel hub vibration frequency data during vehicle operation. In step S102, obtaining the vehicle's target tire pressure detection information and target clamping detection information based on the wheel image and wheel attribute data may include the following steps S301-S302:

[0075] S301, based on the fastening torque data, axial displacement data and radial displacement data, determine the fastening risk factor before the vehicle is driven;

[0076] S302 performs fastening detection processing based on fastening risk coefficient, drive torque data, wheel speed data, working sound data, and wheel hub vibration frequency data to obtain the fastening detection information of the vehicle while it is in motion, which is used as the target fastening detection information.

[0077] Here, in the wheel attribute data mentioned above, the tightening torque data refers to the tightening torque of the wheel nuts, which is highly correlated with the tightness of the wheel. Under normal circumstances, the tightening torque data should be higher than the standard value (e.g., 80-120 N·m for passenger cars); when the tightening torque data is lower than the standard value, it indicates that the wheel nuts are loose, and the wheel tightness may be insufficient. Axial displacement data refers to the axial displacement of the wheel, which is highly correlated with the tightness of the wheel. Under normal circumstances, the axial displacement data should be higher than the standard value (e.g., higher than 0.5 mm); when the axial displacement data is lower than the standard value, it indicates that the wheel is loose axially, and the wheel tightness may be insufficient. Radial displacement data represents the radial displacement of the wheel, which is highly correlated with the tightness of the wheel. Under normal circumstances, the radial displacement data should be higher than the standard value (e.g., higher than 0.5 mm); when the radial displacement data is lower than the standard value, it indicates that the wheel is loose radially, and the wheel tightness may be insufficient. Drive torque data refers to the drive torque of the wheel, which is highly correlated with the tightness of the wheel. When the drive torque data exceeds the preset range, it indicates an abnormal drive torque distribution and reduced wheel end resistance, potentially indicating wheel looseness or insufficient wheel tightness. Wheel speed data refers to the wheel's rotational speed and is highly correlated with wheel tightness. When the wheel speed data changes beyond the preset range, it indicates abnormal wheel speed fluctuations and changes in the contact gap between the wheel hub and brake disc, potentially indicating wheel looseness or insufficient wheel tightness. Operating sound data refers to the frequency data of the wheel during rotation and is highly correlated with wheel tightness. Abnormal operating sound data (e.g., high-frequency knocking sounds or low-frequency resonance sounds) indicates potential wheel looseness or insufficient wheel tightness. Wheel hub vibration frequency data refers to the frequency of free vibration of the wheel hub without external excitation and is highly correlated with wheel tightness. Under normal circumstances, wheel hub vibration frequency data is usually concentrated in the low frequency range (e.g., less than 200Hz). If the wheel hub vibration frequency data increases, it indicates a significant increase in the energy of the high-frequency components, suggesting conditions such as bolt knocking or friction resonance. In this case, the wheel may be loose, indicating insufficient wheel tightness. Therefore, using data such as tightening torque, axial displacement, radial displacement, drive torque, wheel speed, operating sound, and wheel hub vibration frequency can help detect whether the vehicle's wheel tightness is abnormal.

[0078] Optionally, fastening torque data can be collected using an electronic torque sensor, axial displacement data and radial displacement data can be collected using a displacement sensor, drive torque data can be collected using a torque sensor, wheel speed data can be collected using a wheel speed sensor, and working sound data can be collected using an acoustic sensor, but not limited to these.

[0079] In related technologies, the tightness of the wheels is usually only detected before the vehicle is in motion, and there are few methods to detect the tightness of the wheels while the vehicle is in motion. In response, this embodiment introduces multimodal data and adopts a two-stage dynamic and static tightness detection method, aiming to accurately detect the tightness of the wheels while the vehicle is in motion.

[0080] In step S301 above, wheel tightness risk prediction is performed based on the wheel fastening torque data, axial displacement data and radial displacement data before the vehicle is driven, and the tightness risk coefficient before the vehicle is driven is obtained. This tightness risk coefficient can reflect the probability that the vehicle's wheels are not tight enough before the vehicle is driven.

[0081] Here, the vehicle is stationary before driving, and the wheels are in a cold tire state. By using the tightening torque data, axial displacement data, and radial displacement data of the cold tires, the probability of insufficient wheel tightness before driving is determined, thus achieving wheel tightness detection in the static stage. Text-modal data such as tightening torque data, axial displacement data, and radial displacement data can effectively capture the physical characteristics associated with wheel tightness. This implementation method introduces multi-dimensional data to achieve wheel tightness risk prediction, thereby effectively improving the accuracy of wheel tightness detection in the static stage, quickly and accurately identifying potential situations of insufficient wheel tightness, and thus helping to accelerate the efficiency of wheel tightness detection.

[0082] In some embodiments, determining the vehicle's fastening risk coefficient before driving based on fastening torque data, axial displacement data, and radial displacement data may include: extracting features from the fastening torque data, axial displacement data, and radial displacement data to obtain fastening torque features, axial displacement features, and radial displacement features; and determining the vehicle's fastening risk coefficient before driving based on the fastening torque features, axial displacement features, and radial displacement features, combined with machine learning methods.

[0083] Here, in the static stage of wheel tightness detection, firstly, feature extraction is performed on the tightness torque data, axial displacement data, and radial displacement data to obtain tightness torque features, axial displacement features, and radial displacement features. This allows for the extraction of tightness characteristic information reflecting the wheel in a cold tire state. The specific implementation of feature extraction can be flexibly set according to actual conditions, and this embodiment does not impose any limitations on it. Next, the tightness torque features, axial displacement features, and radial displacement features are input into the first tightness risk prediction model to obtain the tightness risk coefficient of the vehicle before driving. The risk coefficient is the prediction probability. The first tightness risk prediction model is a model trained using multiple third feature samples and the corresponding label information for each third feature sample. The third feature samples include tightness torque feature samples, axial displacement feature samples, and radial displacement feature samples. The label information corresponding to the third feature samples is the tightness risk coefficient, which can be determined through expert annotation, historical data statistics, etc. Furthermore, the type of the first tightness risk prediction model can be flexibly set according to actual conditions, such as support vector machines, logistic regression, etc., but is not limited to these. Thus, by using machine learning to perform wheel tightness risk prediction, the superior performance of machine learning can effectively improve the accuracy of wheel tightness risk prediction.

[0084] In some embodiments, determining the vehicle's tightening risk coefficient before driving based on tightening torque data, axial displacement data, and radial displacement data may include: predicting wheel tightness risk based on tightening torque data to obtain a third risk coefficient; predicting wheel tightness risk based on axial displacement data to obtain a fourth risk coefficient; predicting wheel tightness risk based on radial displacement data to obtain a fifth risk coefficient; and determining the vehicle's tightening risk coefficient before driving based on the third, fourth, and fifth risk coefficients.

[0085] Here, in the static stage of wheel tightness detection, firstly, a third risk coefficient is obtained by predicting wheel tightness risk based on the tightening torque data and a pre-trained second tightening risk prediction model. The second tightening risk prediction model is trained using multiple tightening torque data samples and the corresponding label information for each sample. Simultaneously, a fourth risk coefficient is obtained by predicting wheel tightness risk based on the axial displacement data and a pre-trained third tightening risk prediction model. The third tightening risk prediction model is trained using multiple axial displacement data samples and the corresponding label information for each sample. Finally, a fifth risk coefficient is obtained by predicting wheel tightness risk based on the radial displacement data and a pre-trained fourth tightening risk prediction model. The fourth tightening risk prediction model is trained using multiple radial displacement data samples and the corresponding label information for each sample. It should be understood that in each of the above tightening risk prediction models, the output risk coefficient is the prediction probability, and the label information corresponding to the data samples used during training are all risk coefficients, which can be determined through expert annotation, historical data statistics, etc. Furthermore, the types of the aforementioned fastening risk prediction models can be flexibly set according to actual conditions, such as random forests, logistic regression, etc., but are not limited to these. Next, the third, fourth, and fifth risk coefficients are integrated to obtain the vehicle's fastening risk coefficient before driving. For example, the mean of the third, fourth, and fifth risk coefficients can be calculated as the vehicle's fastening risk coefficient before driving. Alternatively, the third, fourth, and fifth risk coefficients can be weighted and summed to obtain the vehicle's fastening risk coefficient before driving. In this way, fastening torque data, axial displacement data, and radial displacement data can respectively reflect the fastening risk in different physical characteristics. Considering that the fastening risks reflected by these three dimensions of data are different, the final fastening risk is determined by integrating the fastening risks corresponding to multiple dimensions, thus helping to further improve the accuracy of wheel fastening risk prediction.

[0086] In step S302 above, based on the probability that the wheels of the vehicle are not secure enough before driving, the target fastening detection information is determined by using multiple dimensions such as the driving torque data, wheel speed data, working sound data and wheel hub vibration frequency data of the wheels in the driving state, to indicate whether the mechanical structure of the wheels of the vehicle is secure when driving.

[0087] Here, on the one hand, this embodiment fully considers multi-dimensional data highly correlated with wheel tightness, using this multi-dimensional data to achieve wheel tightness detection in the dynamic phase. On the other hand, in the wheel tightness detection during the dynamic phase, this embodiment not only considers real-time data highly correlated with wheel tightness while the vehicle is in motion, but also considers the probability of wheel tightness risk before the vehicle is in motion. Thus, by introducing multi-dimensional data into the wheel tightness detection during the dynamic phase and considering the wheel tightness status when the vehicle is stationary and not stationary, this embodiment can effectively improve the comprehensiveness, accuracy, and reliability of wheel tightness detection, and reduce the risk of misjudgment.

[0088] In some embodiments, considering that the wheel tightness detection of the vehicle at the current moment is more important, the longest cycle time of the above step S302 is thirty seconds, that is, the above step S302 is executed once every thirty seconds or less (e.g., every twenty seconds), and the result of the new execution overwrites the result of the previous execution, thereby realizing real-time wheel tightness detection.

[0089] In some implementations, the aforementioned fastening detection processing based on fastening risk coefficient, drive torque data, wheel speed data, operating sound data, and wheel hub vibration frequency data to obtain fastening detection information of the vehicle during driving can include: extracting features from the drive torque data, wheel speed data, operating sound data, and wheel hub vibration frequency data to obtain drive torque features, wheel speed features, operating sound features, and wheel hub vibration frequency features; and using machine learning methods to obtain the fastening detection information of the vehicle during driving based on the fastening risk coefficient, drive torque features, wheel speed features, operating sound features, and wheel hub vibration frequency features.

[0090] Here, during wheel tightness detection, firstly, feature extraction is performed on the drive torque data, wheel speed data, operating sound data, and wheel hub vibration frequency data to obtain drive torque features, wheel speed features, operating sound features, and wheel hub vibration frequency features. This allows for the extraction of feature information highly correlated with wheel tightness during vehicle operation. The specific implementation of feature extraction can be flexibly set according to actual conditions, and this embodiment does not impose any limitations on it. Then, the tightness risk coefficient, drive torque features, wheel speed features, operating sound features, and wheel hub vibration frequency features are input into a pre-trained tightness detection model to obtain tightness detection information of the vehicle during operation. The tightness detection model is trained using multiple fourth feature samples and the corresponding label information for each fourth feature sample. The fourth feature samples include tightness risk coefficient samples, drive torque feature samples, wheel speed feature samples, operating sound feature samples, and wheel hub vibration frequency feature samples. The label information corresponding to the fourth feature sample indicates whether the wheel tightness is normal; it is typically represented as one or zero, where one indicates normal wheel tightness and zero indicates abnormal wheel tightness. Furthermore, the wheel fastening detection model can be flexibly configured according to the actual situation, such as support vector machines, random forests, etc., but is not limited to these. Thus, by using machine learning methods to perform wheel fastening detection, the superior performance of machine learning methods can effectively improve the accuracy of wheel fastening detection.

[0091] In some embodiments, the above-mentioned fastening detection processing based on the fastening risk coefficient, drive torque data, wheel speed data, working sound data, and wheel hub vibration frequency data to obtain fastening detection information of the vehicle during driving as target fastening detection information may include: performing sound detection based on the working sound data to obtain sound detection information, which is used to indicate whether the working sound of the wheel is abnormal; if any one of the fastening risk coefficient, drive torque data, wheel speed data, sound detection information, or wheel hub vibration frequency data meets a second preset condition, then the fastening detection information of the vehicle during driving is determined to indicate that the mechanical structure of the wheel is not fastened; otherwise, the fastening detection information of the vehicle during driving is determined to indicate that the mechanical structure of the wheel is fastened; wherein, the second preset condition includes: the sound detection information indicates that the working sound of the wheel is abnormal, the fastening risk coefficient is higher than the fastening risk threshold, the drive torque data is outside the drive torque range, the wheel speed data is outside the wheel speed range, and the wheel hub vibration frequency data is outside the second frequency range.

[0092] Here, during wheel tightness detection, firstly, the operating sound data is input into a pre-trained sound detection model. The sound detection model obtains sound detection information indicating whether the vehicle's wheel operating sound is abnormal. The sound detection model is trained using multiple operating sound samples and the corresponding label information for each sample. The label information indicates whether the wheel's operating sound is abnormal; it is typically represented by one or zero, where one indicates a normal wheel operating sound and zero indicates an abnormal wheel operating sound. Furthermore, the sound detection model can be flexibly configured according to actual conditions, such as support vector machines or decision trees, but is not limited to these. Next, it is determined whether any one of the following—tightness risk coefficient, drive torque data, wheel speed data, sound detection information, or wheel hub vibration frequency data—meets a second preset condition. If so, it indicates that the vehicle's wheel tightness is insufficient at the current moment, and the tightness detection information during vehicle operation is determined as indicating that the wheel's mechanical structure is not tight. Otherwise, it indicates that the vehicle's wheel tightness meets the requirements at the current moment, and the tightness detection information during vehicle operation is determined as indicating that the wheel's mechanical structure is tight. In this way, by converting the working sound data into feature information that can be used for comparison, and realizing wheel tightness detection in the dynamic stage through simple comparison operations, the accuracy of wheel tightness detection can be ensured while improving the efficiency of wheel tightness detection and meeting real-time requirements. Optionally, the tightness risk threshold, drive torque range, wheel speed range, and second frequency range can all be set according to actual conditions, and this embodiment does not impose specific limitations on them.

[0093] In some implementations, refer to Figure 4 The aforementioned wheel image may include an infrared image of the wheel while the vehicle is in motion; in step S103, obtaining the vehicle's wheel motion trajectory data based on the wheel image, wheel attribute data, and driving attribute data may include the following steps S401-S403:

[0094] S401, Based on driving attribute data and wheel attribute data, trajectory prediction processing is performed to obtain the initial wheel motion trajectory data of the vehicle.

[0095] S402, Determine the vehicle's trajectory correction coefficient based on the infrared image;

[0096] S403, The initial wheel motion trajectory data is corrected according to the trajectory correction coefficient to obtain the wheel motion trajectory data.

[0097] In step S401 above, driving attribute data and wheel attribute data are input into a pre-trained first trajectory prediction model to obtain the initial wheel motion trajectory data of the vehicle. The initial wheel motion trajectory data is presented as a line, which can include the coordinate positions of the wheel at multiple future moments in the vehicle coordinate system. The wheel attribute data input into the first trajectory prediction model can be the second tire pressure data, effective radius data, wheel hub vibration frequency data, drive torque data, wheel speed data, operating sound data, and wheel hub vibration frequency data of the wheel when the vehicle is in motion. The first trajectory prediction model can be a model trained using multiple first data samples and the corresponding wheel motion trajectory samples for each first data sample. The first data samples include driving attribute data samples and wheel attribute data samples. The type of the first trajectory prediction model can be flexibly set according to the actual situation, such as support vector machine, logistic regression, etc., but is not limited to these. Here, driving attribute data reflects the actual condition of the vehicle while it is in motion, and wheel attribute data reflects the actual condition of the wheels while the vehicle is in motion. The actual condition of the vehicle while it is in motion and the actual condition of the wheels while the vehicle is in motion together affect the trajectory of the wheels. When it is determined that there is a potential risk of wheel loosening, this implementation method can obtain the initial wheel trajectory data of the vehicle by comprehensively considering the factors of these two dimensions, thereby effectively improving the accuracy of wheel trajectory prediction.

[0098] Optionally, the driving attribute data can be flexibly set according to the actual situation, and this embodiment does not impose specific limitations on it. For example, the driving attribute data may include vehicle speed data, steering angle data, yaw rate data, lateral acceleration data, longitudinal acceleration data, braking force data, etc., but is not limited to these.

[0099] In step S402 above, since the vehicle attribute data and wheel attribute data are mostly collected by sensors, which are easily affected by environmental factors, the resulting initial wheel trajectory data may contain errors. Therefore, this embodiment determines a trajectory correction coefficient based on the infrared image of the wheels while the vehicle is in motion to correct the initial wheel trajectory data. Here, since the infrared image of the wheels while the vehicle is in motion is data obtained through an infrared camera, it is not easily affected by environmental factors and can accurately reflect the true condition of the wheels. Therefore, determining the trajectory correction coefficient using the infrared image of the wheels while the vehicle is in motion helps to accurately correct the initial wheel trajectory data.

[0100] In some embodiments, determining the vehicle trajectory correction coefficient based on the infrared image may include: extracting features from the infrared image to obtain infrared temperature field features; and searching a preset database based on the infrared temperature field features to obtain the vehicle trajectory correction coefficient.

[0101] First, feature extraction is performed on the infrared image to obtain infrared temperature field features, which allows for the extraction of feature information representing the true condition of the wheel. The specific implementation of feature extraction is not limited. In this embodiment, the infrared temperature field feature is represented by a specific numerical value, indicating the average temperature in the wheel's temperature field. Then, a preset database is searched based on the infrared temperature field features. This database pre-stores multiple infrared temperature field feature samples and their corresponding coefficient values. The coefficient values ​​corresponding to the infrared temperature field features are obtained through retrieval and used as the vehicle's trajectory correction coefficients. Here, a simple database traversal operation allows for quick retrieval of the required trajectory correction coefficients, effectively improving the efficiency of obtaining these coefficients.

[0102] In some embodiments, determining the vehicle trajectory correction coefficient based on the infrared image may include: extracting features from the infrared image to obtain infrared temperature field features; and obtaining the vehicle trajectory correction coefficient based on the infrared temperature field features and a machine learning method.

[0103] First, feature extraction is performed on the infrared image to obtain infrared temperature field features, which provides information representing the true condition of the wheel. The specific implementation of feature extraction is not limited. Then, the infrared temperature field features are input into a coefficient prediction model to obtain the vehicle's trajectory correction coefficients. This coefficient prediction model is a machine learning model trained using multiple infrared temperature field feature samples and their corresponding label information. The label information for each infrared temperature field feature sample is the trajectory correction coefficient. Furthermore, the type of coefficient prediction model can be flexibly set according to the actual situation; for example, it could be a support vector machine, logistic regression, etc., but it is not limited to these. Here, machine learning methods are used to perform the trajectory correction coefficient prediction process. Because machine learning methods have superior performance, introducing them when determining the trajectory correction coefficients can effectively improve their accuracy.

[0104] In step S403 above, after obtaining the trajectory correction coefficient, the initial wheel motion trajectory data is corrected based on it to obtain the wheel motion trajectory data, thereby improving the accuracy of the wheel motion trajectory data. Thus, given the potential risk of wheel loosening, accurately determining the vehicle's wheel motion trajectory data helps to quickly and accurately determine whether the wheels are loose.

[0105] In some embodiments, the above-mentioned correction processing of the initial wheel motion trajectory data according to the trajectory correction coefficient to obtain the wheel motion trajectory data may include: obtaining the wheel motion trajectory data by combining the trajectory correction coefficient and the initial wheel motion trajectory data with a machine learning method.

[0106] Here, machine learning is introduced. The trajectory correction coefficients and initial wheel trajectory data are input into a pre-trained second trajectory prediction model to obtain wheel trajectory data. The second trajectory prediction model is trained using multiple second data samples and their corresponding wheel trajectory samples. These second data samples can include wheel trajectory samples and trajectory correction coefficient samples. The type of the second trajectory prediction model can be flexibly set according to the actual situation; for example, it can be a support vector machine, logistic regression, etc., but is not limited to these. Here, machine learning is used to perform trajectory correction. Because machine learning has superior performance, introducing it during trajectory correction can effectively improve the accuracy of trajectory correction.

[0107] In some embodiments, the above-mentioned correction processing of the initial wheel motion trajectory data according to the trajectory correction coefficient to obtain the wheel motion trajectory data may include: multiplying the trajectory correction coefficient and the initial wheel motion trajectory data to obtain the wheel motion trajectory data.

[0108] Here, since the initial wheel trajectory data includes the wheel's coordinate positions at multiple future moments in the vehicle coordinate system, when correcting the trajectory, for each coordinate position, the trajectory correction coefficient can be multiplied by the coordinate position to obtain the new coordinate position with the assigned trajectory correction coefficient. By iterating through each coordinate position, each new coordinate position can be obtained, thus yielding the final wheel trajectory data. This method of assigning coefficients to perform trajectory correction allows for rapid correction of the initial wheel trajectory data, ensuring accuracy while accelerating the correction speed to meet real-time requirements.

[0109] In some implementations, refer to Figure 5 In step S104 above, the wheel loosening warning process for the vehicle based on wheel motion trajectory data may include the following steps S501-S502:

[0110] S501 performs deviation detection processing based on wheel motion trajectory data to obtain vehicle deviation detection information; the deviation detection information is used to indicate whether the wheel will deviate in the future time period.

[0111] S502, based on the vehicle deviation detection information, performs a wheel loosening warning.

[0112] In step S501 above, wheel misalignment detection processing is performed using wheel motion trajectory data as a reference to obtain misalignment detection information indicating whether the wheel will misalign in the future time period. Here, based on the wheel's motion trajectory data in the future time period, it is determined whether the wheel will misalign in the future time period. This can accurately determine the degree of wheel misalignment at the future moment. At the same time, considering that wheel misalignment can directly reflect wheel looseness, determining the degree of misalignment from the motion trajectory data can help to quickly and accurately determine whether the wheel is loose.

[0113] In some embodiments, the above-mentioned process of performing deviation detection based on wheel motion trajectory data to obtain vehicle deviation detection information may include: inputting wheel motion trajectory data into a deviation detection model to obtain deviation detection information.

[0114] Here, wheel trajectory data is input into a wheel deviation detection model, which identifies and detects wheel deviation. This model is trained using multiple wheel trajectory samples and their corresponding labels. The labels indicate whether a wheel is deviating from its lane; they are typically one or zero, with one indicating deviation and zero indicating no deviation. Furthermore, the type of wheel deviation detection model can be flexibly chosen based on specific needs; it can be a support vector machine, logistic regression, convolutional neural network, etc., but is not limited to these. This approach, by introducing a wheel deviation detection model, achieves automated wheel deviation detection. Due to the superior performance of this model, the above method effectively improves the accuracy of wheel deviation detection.

[0115] In step S502 above, when a wheel pulls to one side, it indicates that the wheel has insufficient dynamic balance or wheel hub displacement. For example, insufficient wheel dynamic balance will cause steering wheel vibration and wheel pull, while wheel hub displacement will cause lateral wheel displacement and wheel pull, which will lead to wheel loosening. In other words, wheel pull directly reflects wheel loosening. Therefore, using the pull detection information as a benchmark, a wheel loosening warning is issued for the vehicle.

[0116] In some implementations, step S501 above, which involves performing a deviation detection process based on wheel trajectory data to obtain vehicle deviation detection information, may include:

[0117] Determine the vehicle's expected wheel trajectory data and the similarity data between the wheel trajectory data;

[0118] If the similarity data is less than or equal to a preset threshold, the deviation detection information will be used to indicate that the wheel will deviate in the future time period; otherwise, the deviation detection information will be used to indicate that the wheel will not deviate in the future time period.

[0119] Here, in the deviation detection process, firstly, the expected wheel trajectory data of the vehicle is acquired. This data includes the expected coordinate positions of the wheels at multiple future moments in the vehicle's coordinate system. This data can be pre-stored in a preset database and can be determined through expert annotation, historical data statistics, etc. Next, the similarity data between the expected wheel trajectory data and the actual wheel trajectory data is calculated. This effectively measures the difference between the actual and expected wheel trajectories. The type of similarity can be flexibly set according to the actual situation; for example, it can be cosine similarity, Euclidean distance, etc., but is not limited to these. It should be understood that since both the expected and expected wheel trajectory data include multiple coordinate positions, they can actually be represented as a sequence of data, so the similarity between them can be directly calculated. Then, it is determined whether the similarity data is less than or equal to a preset threshold. If so, it indicates a significant difference between the actual and expected wheel trajectories, and the wheel is deviating. In this case, the deviation detection information is used to indicate wheel deviation in the future time period. If not, it indicates that the difference between the actual trajectory and the expected trajectory of the wheel is small, and the wheel has not deviated. In this case, the deviation detection information is used to indicate that the wheel will not deviate in the future. Therefore, this implementation method converts the abstract trajectory difference into a numerical index through similarity calculation, which can accurately measure the difference between the actual trajectory and the expected trajectory of the wheel. Then, based on the difference between the actual trajectory and the expected trajectory, it determines whether the wheel will deviate in the future, thus effectively improving the accuracy of deviation detection.

[0120] In some implementations, step S502 above, which involves performing a wheel loosening warning based on the vehicle's deviation detection information, may include:

[0121] If the vehicle pulls to one side information is used to indicate that the vehicle will pull to one side in the future, then a wheel loosening warning will be issued for the vehicle.

[0122] Alternatively, if the deviation detection information is used to indicate that the vehicle has not deviated from its lane in the future, then no loosening warning will be issued.

[0123] Here, if the vehicle drift detection information indicates that the vehicle will drift to one side in the future, a wheel loosening warning is issued. For example, when the body domain controller issues a wheel loosening warning, it can output a warning display signal to the cockpit domain controller. The cockpit domain controller then generates a wheel loosening warning icon based on this signal and displays it on the instrument panel to alert the driver of the potential risk of wheel loosening. If the vehicle drift detection information indicates that the vehicle will not drift to one side in the future, no loosening warning is issued. Therefore, using the vehicle drift detection information as a benchmark for wheel loosening warning further improves the accuracy of the warning.

[0124] In some embodiments, after performing a wheel loosening warning on the vehicle, the system returns to step S101 to perform cyclic detection until the vehicle drift detection information indicates that the vehicle will not drift in the future, at which point the wheel loosening warning stops. Similarly, after not performing a loosening warning, the system returns to step S101 to perform cyclic detection.

[0125] In some implementations, the models involved are all integrated into the same artificial intelligence module to form a multi-task learning model.

[0126] In some implementations, refer to Figure 6 The training process for the model may include: establishing training and testing sets; starting model training by inputting the current training set into the model; after one round of training, using the testing set to test the accuracy of the model in the current round, obtaining the accuracy of the model in the current round; if the accuracy of the model in the current round is greater than an accuracy threshold, then the model training is considered complete, and the model in the current round is output as the trained model; otherwise, proceed to the next round. Optionally, the accuracy threshold can be flexibly set according to the actual situation, for example, the accuracy threshold can be 98%, but it is not limited to this.

[0127] To facilitate understanding of the wheel loosening warning method described in this application, an example of its actual application scenario is provided below.

[0128] In this application scenario, the vehicle is a truck. Trucks, due to their purpose, frequently travel on highways, and compared to ordinary cars and SUVs, trucks are more likely to experience wheel slippage. (Refer to...) Figure 7 The method in this application embodiment performs the following loosening warning processing on each wheel of the truck:

[0129] S601, Data Source Acquisition: Acquire the ground contact image of the wheels before the vehicle travels and the infrared image of the wheels while the vehicle is traveling as the vehicle's wheel images. Acquire the first tire pressure data, fastening torque data, axial displacement data, and radial displacement data of the wheels before the vehicle travels, and the second tire pressure data, effective radius data, drive torque data, wheel speed data, operating sound data, and wheel hub vibration frequency data of the wheels while the vehicle is traveling as the vehicle's wheel attribute data. Acquire the vehicle speed data, steering angle data, yaw rate data, lateral acceleration data, longitudinal acceleration data, and braking force data while the vehicle is traveling as the vehicle's driving attribute data.

[0130] S602, Tire Pressure Detection and Tightness Detection: Based on the grounding image and the first tire pressure data, determine the tire pressure risk coefficient before the vehicle is driven. This tire pressure risk coefficient reflects the probability that the tire pressure of the vehicle's wheels is abnormal before driving. Then, perform tire pressure detection processing based on the tire pressure risk coefficient, infrared image, second tire pressure data, effective radius data, and wheel hub vibration frequency data to obtain the tire pressure detection information when the vehicle is driving as the target tire pressure detection information. The target tire pressure detection information is used to indicate whether the tire pressure of the wheels is normal.

[0131] Meanwhile, based on the fastening torque data, axial displacement data, and radial displacement data, a fastening risk coefficient is determined before the vehicle is driven. This fastening risk coefficient reflects the probability that the wheels of the vehicle are not fastened properly before driving. Subsequently, fastening detection processing is performed based on the fastening risk coefficient, drive torque data, wheel speed data, working sound data, and wheel hub vibration frequency data to obtain the fastening detection information of the vehicle during driving as the target fastening detection information. The target fastening detection information is used to indicate whether the mechanical structure of the wheel is fastened.

[0132] S603, Trajectory Detection: If the target tire pressure detection information indicates abnormal tire pressure, and / or the target fastening detection information indicates that the mechanical structure of the wheel is not fastened, it indicates a potential risk of wheel loosening. In this case, firstly, the second tire pressure data, effective radius data, wheel hub vibration frequency data, drive torque data, wheel speed data, operating sound data, wheel hub vibration frequency data, vehicle speed data, steering angle data, yaw rate data, lateral acceleration data, longitudinal acceleration data, and braking force data of the wheels during vehicle operation are input into a pre-trained first trajectory prediction model to obtain the initial wheel motion trajectory data. The initial wheel motion trajectory data is presented as a line, which can include the coordinate positions of the wheel at multiple future moments in the vehicle coordinate system. Next, based on the infrared image of the wheel during vehicle operation, a trajectory correction coefficient is determined to correct the initial wheel motion trajectory data. Finally, the initial wheel motion trajectory data is corrected based on the trajectory correction coefficient to obtain the final wheel motion trajectory data.

[0133] S604, Wheel Loosening Warning: First, determine the similarity data between the vehicle's expected wheel trajectory data and the wheel trajectory data. Then, if the similarity data is less than or equal to a preset threshold, the wheel deviation detection information is determined to indicate that the wheel will deviate from its lane in the future; otherwise, the wheel deviation detection information is determined to indicate that the wheel will not deviate from its lane in the future. Finally, if the wheel deviation detection information indicates that the vehicle will deviate from its lane in the future, a wheel loosening warning is issued; otherwise, no loosening warning is issued.

[0134] Furthermore, refer to Figure 8 This application also provides a wheel loosening warning device, which includes:

[0135] The acquisition module 701 is used to acquire vehicle wheel images, wheel attribute data, and driving attribute data;

[0136] The first processing module 702 is used to obtain target tire pressure detection information and target fastness detection information of the vehicle based on the wheel image and the wheel attribute data; wherein, the target tire pressure detection information is used to indicate whether the tire pressure of the wheel is normal, and the target fastness detection information is used to indicate whether the mechanical structure of the wheel is fastened.

[0137] The second processing module 703 is used to obtain the vehicle's wheel motion trajectory data based on the wheel image, wheel attribute data, and driving attribute data when the target tire pressure detection information is used to indicate abnormal tire pressure of the wheel, and / or the target fastening detection information is used to indicate that the mechanical structure of the wheel is not fastened.

[0138] The third processing module 704 is used to perform wheel loosening warning processing on the vehicle based on wheel motion trajectory data.

[0139] The content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0140] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to implement the aforementioned wheel loosening warning method.

[0141] The content of the above method embodiments is applicable to this medium embodiment. The specific functions implemented in this medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0142] Finally, refer to Figure 9 This application also provides a vehicle, including:

[0143] At least one processor 801;

[0144] At least one memory 802 is used to store at least one program;

[0145] When the at least one program is executed by the at least one processor 801, the at least one processor 801 implements the above-described wheel loosening warning method.

[0146] The aforementioned vehicles can be private cars, such as sedans, sport utility vehicles (SUVs), multi-purpose vehicles (MPVs), or pickup trucks, or commercial vehicles, such as vans, buses, small trucks, or large trailers, or gasoline vehicles or new energy vehicles such as hybrid or pure electric vehicles.

[0147] The aforementioned memory 802, as a non-transitory network system, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory 802 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 802 may optionally include memory 802 remotely located relative to processor 801, and these remote memories 802 can be connected to processor 801 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0148] The aforementioned memory 802 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 802 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 802 and is called and executed by the processor 801.

[0149] The processor 801 described above can be implemented using a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0150] In some embodiments, the vehicle may further include:

[0151] Input / output interfaces are used to implement information input and output;

[0152] The communication interface is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0153] The bus transmits information between various components of the device, such as the processor 801, memory 802, input / output interfaces, and communication interfaces.

[0154] The processor 801, memory 802, input / output interface, and communication interface can communicate with each other within the device via a bus.

[0155] The content of the above method embodiments is applicable to this vehicle embodiment. The specific functions implemented in this vehicle embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0156] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0157] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional technology for an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0158] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several programs to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0159] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable programs for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, a program execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can retrieve and execute a program from or in conjunction with such a program execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with a program execution system, apparatus, or device.

[0160] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0161] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0162] In the foregoing description of this specification, the references to terms such as "one embodiment," "another embodiment," or "some embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0163] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0164] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for early warning of wheel loosening, characterized in that, Includes the following steps: The system acquires vehicle wheel images, wheel attribute data, and driving attribute data. The wheel images include at least wheel ground contact images acquired before the vehicle starts moving, and wheel infrared images acquired while the vehicle is in motion. The wheel attribute data includes at least: first tire pressure data, fastening torque data, axial displacement data, and radial displacement data acquired before the vehicle starts moving; and second tire pressure data, effective radius data, wheel hub vibration frequency data, drive torque data, wheel speed data, and operating sound data acquired while the vehicle is in motion. Based on the wheel image and the wheel attribute data, target tire pressure detection information and target fastness detection information of the vehicle are obtained; wherein, the target tire pressure detection information is used to indicate whether the tire pressure of the wheel is normal, and the target fastness detection information is used to indicate whether the mechanical structure of the wheel is fastened. The step of obtaining the target tire pressure detection information of the vehicle based on the wheel image and the wheel attribute data includes: Based on the grounding image and the first tire pressure data, determine the tire pressure risk factor of the vehicle before driving; The tire pressure detection process is performed based on the tire pressure risk coefficient, the infrared image, the second tire pressure data, the effective radius data, and the wheel hub vibration frequency data to obtain the tire pressure detection information of the vehicle during driving, which is used as the target tire pressure detection information. The step of obtaining the target fastening detection information of the vehicle based on the wheel image and the wheel attribute data includes: Based on the fastening torque data, the axial displacement data, and the radial displacement data, determine the fastening risk factor of the vehicle before driving; Based on the fastening risk coefficient, the driving torque data, the wheel speed data, the working sound data, and the wheel hub vibration frequency data, fastening detection processing is performed to obtain the fastening detection information of the vehicle during driving, which is used as the target fastening detection information. When the target tire pressure detection information is used to indicate abnormal tire pressure of the wheel, and / or the target fastening detection information is used to indicate that the mechanical structure of the wheel is not fastened, the wheel motion trajectory data of the vehicle is obtained based on the wheel image, the wheel attribute data and the driving attribute data. The step of obtaining the vehicle's wheel motion trajectory data based on the wheel image, the wheel attribute data, and the driving attribute data includes: Based on the driving attribute data and the wheel attribute data, trajectory prediction processing is performed to obtain the initial wheel motion trajectory data of the vehicle. Based on the infrared image, determine the trajectory correction coefficient of the vehicle; The initial wheel motion trajectory data is corrected according to the trajectory correction coefficient to obtain the wheel motion trajectory data; Based on the wheel movement trajectory data, a wheel loosening warning process is performed on the vehicle.

2. The method according to claim 1, characterized in that, The process of providing a wheel loosening warning for the vehicle based on the wheel motion trajectory data includes: Based on the wheel motion trajectory data, a deviation detection process is performed to obtain the vehicle's deviation detection information; wherein, the deviation detection information is used to indicate whether the wheel will deviate from its proper position in the future time period; Based on the deviation detection information, a wheel loosening warning is issued for the vehicle.

3. The method according to claim 2, characterized in that, The step of performing deviation detection processing based on the wheel motion trajectory data to obtain the vehicle's deviation detection information includes: Determine the similarity data between the expected wheel trajectory data and the wheel trajectory data of the vehicle; If the similarity data is less than or equal to a preset threshold, the deviation detection information is determined to indicate that the wheel will deviate from its lane in the future time period; otherwise, the deviation detection information is determined to indicate that the wheel will not deviate from its lane in the future time period.

4. The method according to claim 2, characterized in that, The step of performing a wheel loosening warning process on the vehicle based on the deviation detection information includes: If the deviation detection information is used to indicate that the vehicle will deviate from its lane in the future, then a wheel loosening warning will be issued for the vehicle. Alternatively, if the deviation detection information is used to indicate that the vehicle has not deviated from its designated position in the future, then no loosening warning will be issued.

5. A wheel loosening warning device, characterized in that, include: The acquisition module is used to acquire wheel images, wheel attribute data, and driving attribute data of the vehicle. The wheel images include at least wheel ground contact images acquired before the vehicle is driven and wheel infrared images acquired while the vehicle is driven. The wheel attribute data includes at least: first tire pressure data, fastening torque data, axial displacement data, and radial displacement data acquired before the vehicle is driven; and second tire pressure data, effective radius data, wheel hub vibration frequency data, drive torque data, wheel speed data, and operating sound data acquired while the vehicle is driven. The first processing module is used to obtain target tire pressure detection information and target fastness detection information of the vehicle based on the wheel image and the wheel attribute data; wherein, the target tire pressure detection information is used to indicate whether the tire pressure of the wheel is normal, and the target fastness detection information is used to indicate whether the mechanical structure of the wheel is fastened. The step of obtaining the target tire pressure detection information of the vehicle based on the wheel image and the wheel attribute data includes: Based on the grounding image and the first tire pressure data, determine the tire pressure risk factor of the vehicle before driving; The tire pressure detection process is performed based on the tire pressure risk coefficient, the infrared image, the second tire pressure data, the effective radius data, and the wheel hub vibration frequency data to obtain the tire pressure detection information of the vehicle during driving, which is used as the target tire pressure detection information. The step of obtaining the target fastening detection information of the vehicle based on the wheel image and the wheel attribute data includes: Based on the fastening torque data, the axial displacement data, and the radial displacement data, determine the fastening risk factor of the vehicle before driving; Based on the fastening risk coefficient, the driving torque data, the wheel speed data, the working sound data, and the wheel hub vibration frequency data, fastening detection processing is performed to obtain the fastening detection information of the vehicle during driving, which is used as the target fastening detection information. The second processing module is used to obtain the wheel motion trajectory data of the vehicle based on the wheel image, the wheel attribute data, and the driving attribute data when the target tire pressure detection information is used to indicate that the tire pressure of the wheel is abnormal, and / or the target fastening detection information is used to indicate that the mechanical structure of the wheel is not fastened. The step of obtaining the vehicle's wheel motion trajectory data based on the wheel image, the wheel attribute data, and the driving attribute data includes: Based on the driving attribute data and the wheel attribute data, trajectory prediction processing is performed to obtain the initial wheel motion trajectory data of the vehicle. Based on the infrared image, determine the trajectory correction coefficient of the vehicle; The initial wheel motion trajectory data is corrected according to the trajectory correction coefficient to obtain the wheel motion trajectory data; The third processing module is used to perform wheel loosening warning processing on the vehicle based on the wheel movement trajectory data.

6. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to implement the wheel loosening warning method as described in any one of claims 1-4.

7. A vehicle, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the wheel loosening warning method as described in any one of claims 1-4.

Images