Tire foreign matter monitoring method, electronic equipment, storage medium and vehicle

Abstract

The invention discloses a tire foreign matter monitoring method, an electronic device, a storage medium and a vehicle, the tire foreign matter monitoring method comprises the following steps: obtaining output information of at least one tire foreign matter identification model, the tire foreign matter identification model taking tire detection data as input; and obtaining a tire foreign matter detection result according to the output information of the at least one tire foreign matter recognition model. By adopting the method, the accuracy of tire foreign matter detection can be improved, so that the problem of misjudgment of tire foreign matter detection is avoided, and the robustness of the tire foreign matter recognition model is high.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicles, and in particular to a method for monitoring foreign matter in a tire, an electronic device, a storage medium and a vehicle. Background Art

[0002] In the related art, the judgment standard for determining whether there is a foreign object in the tire is relatively simple. In the case of environmental interference, even if a foreign object is inserted into the tire, the tire will be judged as free of foreign objects, which may lead to the possibility of misjudgment of tire foreign object detection. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, one purpose of the present invention is to provide a method for monitoring tire foreign matter, which can improve the accuracy of tire foreign matter detection, thereby avoiding the problem of misjudgment of tire foreign matter detection, and the tire foreign matter recognition model has high robustness.

[0004] A second objective of the present invention is to provide an electronic device.

[0005] A third objective of the present invention is to provide a computer-readable storage medium.

[0006] A fourth object of the present invention is to provide a vehicle.

[0007] In order to solve the above problems, a first aspect of the present invention provides a method for monitoring foreign objects in a tire, comprising: obtaining output information of at least one tire foreign object recognition model, wherein the tire foreign object recognition model takes tire detection data as input; and obtaining a tire foreign object detection result according to the output information of the at least one tire foreign object recognition model.

[0008] According to the method for monitoring foreign objects in tires according to an embodiment of the present invention, at least one tire foreign object recognition model obtains corresponding output information by analyzing tire detection data, so as to identify whether there are foreign objects in the tire through the output information. Therefore, compared with the method of determining whether there are foreign objects in the tire through the intensity threshold of the pulse signal and the tire vibration signal in the prior art, in the present application, the output information of at least one tire foreign object recognition model is used to determine whether there are foreign objects in the tire. The model can process a large amount of data in real time with the help of artificial intelligence technology, and the recognition result is fast, accurate and efficient. Moreover, the tire foreign object recognition model is built through training of a large amount of sample data, and no longer detects tire foreign objects for a single threshold, thereby improving the accuracy of tire foreign object detection, thereby avoiding the problem of misjudgment of tire foreign object detection, and the model has high robustness.

[0009] In some embodiments, the output information includes first-category information and second-category information, the first-category information corresponds to the absence of foreign matter on the tire, and the second-category information corresponds to the presence of foreign matter on the tire.

[0010] In some embodiments, the second type of information further includes a plurality of classification information corresponding to a plurality of different types of foreign matter present on the tire.

[0011] In some embodiments, the plurality of classification information includes first classification information and second classification information, the first classification information corresponds to foreign objects pierced into the tire, and the second classification information corresponds to foreign objects embedded in the tread of the tire.

[0012] In some embodiments, the tire foreign object recognition model takes a variety of tire detection data as input.

[0013] In some embodiments, the plurality of tire detection data includes tire vibration data and tire audio data.

[0014] In some embodiments, the output information is obtained based on the time domain features and frequency features extracted from the tire vibration data and the time domain features and frequency domain features extracted from the tire audio data by the tire foreign object recognition model.

[0015] In some embodiments, obtaining output information of at least one tire foreign object recognition model includes: obtaining multiple output information of multiple tire foreign object recognition models, wherein the multiple tire foreign object recognition models use the tire detection data of the same time period as input.

[0016] In some embodiments, the tire detection data in the same time period is tire detection data collected within one or more data collection time windows.

[0017] In some embodiments, the data collection time window is determined based on the cycle time of one rotation of the tire; the cycle time of one rotation of the tire is determined based on the frequency of one rotation of the tire, and the frequency of one rotation of the tire is obtained based on wheel speed information.

[0018] In some embodiments, a tire foreign object detection result is obtained based on the output information of the at least one tire foreign object recognition model, including: when the proportion or number of times that the multiple output information is the second type of information reaches a first threshold, the tire foreign object detection result is that there is a foreign object on the tire; or, when the proportion or number of times that the multiple output information is the first type of information reaches a second threshold, the tire foreign object detection result is that there is no foreign object on the tire.

[0019] In some embodiments, the method further includes: when the tire foreign object detection result indicates that there is a foreign object on the tire, issuing an alarm prompt.

[0020] A second aspect of the present invention provides an electronic device, comprising: at least one processor; a memory communicatively connected to at least one of the processors; wherein the memory stores a computer program executable by at least one of the processors, and when at least one of the processors executes the computer program, the method for monitoring foreign matter in a tire as described in the above embodiment is implemented.

[0021] The electronic device according to the embodiment of the present invention can improve the accuracy of tire foreign object detection and avoid the problem of misjudgment of tire foreign object detection by executing the method of monitoring tire foreign object of the above embodiment, and the tire foreign object recognition model has high robustness.

[0022] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed, the method for monitoring foreign matter in a tire as described in the above embodiment is implemented.

[0023] A fourth aspect of the present invention provides a vehicle, the vehicle includes the electronic device described in the above embodiment; or the vehicle includes: a detection device for collecting tire detection information; a data processing device, the data processing device is configured with at least one tire foreign object recognition model, connected to the detection device, and used to execute the method for monitoring tire foreign objects described in the above embodiment.

[0024] According to the vehicle of the embodiment of the present invention, the accuracy of tire foreign object detection can be improved, the problem of misjudgment of tire foreign object detection can be avoided, and the tire foreign object recognition model has high robustness.

[0025] In some embodiments, the detection device includes: a tire vibration detection module for detecting tire vibration data; and a tire audio detection module for detecting tire audio data.

[0026] In some embodiments, the tire vibration detection module is an accelerometer in a tire pressure monitoring system of the vehicle or an accelerometer in an active noise reduction system of the vehicle.

[0027] In some embodiments, the tire audio detection module is a microphone of an active noise reduction system of the vehicle.

[0028] In some embodiments, the data processing device includes at least one of a micro control unit, a central domain control, and a vehicle computer.

[0029] In some embodiments, the vehicle further includes: a prompting device, which is connected to the data processing device and is used to display and / or alarm when there is a foreign object on the tire.

[0030] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 is a flow chart of a method for monitoring foreign matter in a tire according to an embodiment of the present invention; Figure 2 is a flow chart of a method for monitoring foreign matter in a tire according to another embodiment of the present invention; Figure 3 is a structural block diagram of an electronic device according to an embodiment of the present invention; Figure 4 is a structural block diagram of a vehicle according to an embodiment of the present invention; Figure 5 is a structural block diagram of a vehicle according to another embodiment of the present invention; Figure 6 is a schematic diagram of a vehicle according to one embodiment of the present invention; Figure 7 is a structural block diagram of a vehicle according to another embodiment of the present invention; Figure 8 is a structural block diagram of a vehicle according to another embodiment of the present invention; Fig. 9 is a structural block diagram of a vehicle according to another embodiment of the present invention.

[0032] Reference numerals: Vehicle 100; electronic device 10; Processor 1; memory 2; detection device 3; data processing device 4; prompt device 5; tire 6; chassis 7; micro control unit 41; central domain control 42; vehicle computer 43; data processing unit 44; instrument panel 51; vehicle multimedia device 52. DETAILED DESCRIPTION

[0033] Embodiments of the present invention are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. Embodiments of the present invention are described in detail below.

[0034] In order to solve the above problems, a first aspect of the present invention provides a method for monitoring tire foreign matter. The method can improve the accuracy of tire foreign matter detection, avoid the problem of misjudgment of tire foreign matter detection, and the tire foreign matter recognition model has high robustness.

[0035] Reference below Figure 1 A method for monitoring foreign matter in a tire according to an embodiment of the present invention is described as follows: Figure 1As shown, the method includes: step S1-step S2.

[0036] Step S1, obtaining output information of at least one tire foreign object recognition model, wherein the tire foreign object recognition model takes tire detection data as input.

[0037] Among them, the tire foreign body recognition model is an artificial intelligence model, and the tire foreign body recognition model is a model trained by sample data so that the model learns the characteristics of the presence of foreign bodies in the tire and the absence of foreign bodies in the tire, so as to be able to recognize whether there are foreign bodies in the tire. The tire foreign body recognition model can be a support vector machine (SVM), logistic regression (LR), K-nearest neighbor algorithm (KNN), various tree-based decision models, neural network-based deep learning models, iterative reinforcement learning models, and clustering models based on unsupervised learning. Various tree-based decision models include AdaBoost, XGBoost, and LightGBM. Deep learning models based on neural networks include convolutional one-dimensional convolutional neural networks, two-dimensional convolutional neural networks, loop-based recurrent neural networks, long short-term memory networks, and various neural network models based on attention mechanisms. There is no specific restriction on the number of tire foreign body recognition models, and the number can be 1 or more. Tire detection data can be understood as detection data that can reflect whether there is foreign matter in the tire. The tire detection data at least includes size data, wear data, air pressure data, vibration data or noise data, etc., and there is no specific limitation on this.

[0038] Specifically, the tire detection data is input into at least one tire foreign body recognition model, and at least one tire foreign body recognition model processes and analyzes the tire detection data to obtain output information corresponding to at least one tire foreign body recognition model, wherein the output information is information related to whether there is foreign matter in the tire. Therefore, the tire foreign body recognition model in the present application can process a large amount of tire detection data in real time, and the recognition result is fast, accurate and efficient. In addition, the output information of the tire foreign body recognition model can be information on the type of tire foreign matter.

[0039] Step S2, obtaining a tire foreign object detection result according to output information of at least one tire foreign object recognition model.

[0040] Specifically, according to the output information of at least one tire foreign object recognition model, that is, according to the analysis result of the tire detection data by one tire foreign object recognition model, or by comparing the analysis results of the tire detection data by multiple tire foreign object recognition models, the tire foreign object detection result is determined, wherein the tire foreign object detection result can be the presence of foreign objects in the tire or the absence of foreign objects in the tire. Therefore, compared with the method of determining whether there is a foreign object in the tire by the intensity threshold of the pulse signal and the tire vibration signal in the prior art, in the present application, the presence of foreign objects in the tire is determined by the output information of the tire foreign object recognition model, and the tire foreign objects are detected by the tire foreign object recognition model trained by the sample data, instead of detecting the tire foreign objects for a single threshold value, which improves the accuracy of the tire foreign object detection, thereby avoiding the problem of misjudgment of the tire foreign object detection, and the model has high robustness. In addition, determining whether there is a foreign object in the tire by the output information of multiple tire foreign object recognition models can further improve the accuracy of the tire foreign object detection, thereby avoiding the problem of misjudgment of the tire foreign object detection.

[0041] Exemplarily, the number of tire foreign body recognition models is one, and if the output information of the tire foreign body recognition model is information that foreign bodies exist in the tire, then the tire foreign body detection result is that foreign bodies exist in the tire; if the output information of the tire foreign body recognition model is information that foreign bodies do not exist in the tire, then the tire foreign body detection result is that foreign bodies do not exist in the tire. The number of tire foreign body recognition models is multiple, and if the output information of multiple tire foreign body recognition models is all information that foreign bodies exist in the tire, or if the output information of most of the multiple tire foreign body recognition models is information that foreign bodies exist in the tire, then the tire foreign body detection result is that foreign bodies exist in the tire; if the output information of multiple tire foreign body recognition models is information that foreign bodies do not exist in the tire, then the tire foreign body detection result is that foreign bodies do not exist in the tire.

[0042] According to the method for monitoring foreign objects in tires according to an embodiment of the present invention, at least one tire foreign object recognition model obtains corresponding output information by analyzing tire detection data, so as to recognize whether there are foreign objects in the tire through the output information. Therefore, compared with the method of determining whether there are foreign objects in the tire through the intensity threshold of the pulse signal and the tire vibration signal in the prior art, in the present application, the output information of at least one tire foreign object recognition model is used to determine whether there are foreign objects in the tire. The model can process a large amount of data in real time with the help of artificial intelligence technology, and the recognition result is fast, accurate and efficient. Moreover, the tire foreign object recognition model is built through training with a large amount of sample data, and no longer detects tire foreign objects based on a single threshold, thereby improving the accuracy of tire foreign object detection, thereby avoiding the problem of misjudgment of tire foreign object detection, and the model has high robustness.

[0043] In some embodiments, the output information includes first-type information and second-type information, the first-type information corresponds to the absence of foreign matter on the tire, and the second-type information corresponds to the presence of foreign matter on the tire.

[0044] Specifically, the tire detection data is input into at least one tire foreign object recognition model to obtain output information corresponding to the at least one tire foreign object recognition model, wherein the output information includes first-category information and second-category information. If the output information is the first-category information, the tire foreign object detection result is that there is no foreign object on the tire; if the output information is the second-category information, the tire foreign object detection result is that there is a foreign object on the tire. Therefore, in the present application, the output information of at least one tire foreign object recognition model is used to determine whether there is a foreign object in the tire, thereby improving the accuracy of tire foreign object detection, thereby avoiding the problem of misjudgment of tire foreign object detection, and the model has high robustness.

[0045] In some embodiments, the second category of information also includes multiple classification information, and the multiple classification information corresponds to multiple different types of foreign objects present on the tire. The classification information can be nails, stones, screws, wires, glass fragments, etc.; or, the classification information can be metal, non-metal or composite; or, the classification information can be puncture type or wear type.

[0046] Specifically, the existing tire foreign body detection method cannot identify the tire foreign body category. In order to solve this problem, in this application, the tire foreign body recognition model is trained by sample data containing various types of foreign bodies, so that the tire foreign body recognition model can recognize different types of foreign bodies and extract tire detection data features of different types of foreign bodies. Based on this, the tire detection data is input into at least one tire foreign body recognition model to obtain the second type of information corresponding to at least one tire foreign body recognition model to determine the tire foreign body detection result. For example, if the second type of information is a nail, the tire foreign body detection result is a nail; if the second type of information is a stone, the tire foreign body detection result is a stone; if the second type of information is a metal, the tire foreign body detection result is a metal. Therefore, in this application, at least one tire foreign body recognition model can accurately identify the type of tire foreign body, so that the user can take corresponding measures according to the type of tire foreign body, improve the accuracy of tire foreign body detection, and thus avoid the problem of misjudgment of tire foreign body detection.

[0047] In some embodiments, the plurality of classification information includes first classification information and second classification information, the first classification information corresponds to foreign objects pierced into the tire, and the second classification information corresponds to foreign objects embedded in the tread of the tire.

[0048] Specifically, in the present application, a tire foreign object recognition model is trained by using sample data of foreign objects including various existence modes of foreign objects on tires, so that the tire foreign object recognition model can recognize the existence modes of foreign objects on tires and extract tire detection data features of different existence modes of foreign objects on tires. Based on this, the tire detection data is input into at least one tire foreign object recognition model to obtain first classification information or second classification information corresponding to at least one tire foreign object recognition model. If the output information is the first classification information, the tire foreign object detection result is a foreign object pierced into the tire; if the output information is the second classification information, the tire foreign object detection result is a foreign object embedded in the tread of the tire. Therefore, in the present application, at least one tire foreign object recognition model can accurately recognize the existence mode of foreign objects in the tire, so that users can take corresponding measures according to the existence mode of foreign objects in the tire, thereby improving the accuracy of tire foreign object detection and avoiding the problem of misjudgment of tire foreign object detection.

[0049] In some embodiments, the tire foreign object recognition model uses a variety of tire detection data as input, so that the tire foreign object recognition model can accurately identify foreign objects on the tire, providing strong support for the safe use and maintenance of the tire.

[0050] Among them, the various tire detection data include size data, wear data, air pressure data, vibration data or noise data, etc.

[0051] In some embodiments, the various tire detection data include tire vibration data and tire audio data.

[0052] Specifically, when there is a foreign object in the tire, the foreign object interacts with the ground. For example, when a vehicle tire is pierced by metal or a stone or other foreign object is embedded in the tire pattern, the protruding part of the foreign object interacts with the ground, causing tire vibration and tire noise, i.e., periodic changes in tire audio. Therefore, the presence of a foreign object in the tire can be determined through tire vibration data and tire audio data. However, the tire vibration signal has a single feature. In order to better reflect the presence of foreign objects in the tire, tire foreign objects are identified through tire audio data and tire vibration signals. The two types of information complement each other and increase the accuracy of identifying tire foreign objects.

[0053] Based on this, at least one tire foreign object recognition model is inputted through tire vibration data and tire audio data to obtain output information of at least one tire foreign object recognition model, thereby realizing tire foreign object detection. In addition, the tire foreign object recognition model can also be further trained through tire vibration data and tire audio data, so that the tire foreign object recognition model learns tire vibration characteristics and tire audio characteristics, and the tire foreign object recognition model can distinguish tire vibration characteristics and tire audio characteristics of tires with foreign objects and characteristics of tires without foreign objects, thereby improving the decision accuracy of tire foreign object recognition.

[0054] In some embodiments, the output information of the model is obtained by extracting the time domain features and frequency features of the tire vibration data and the time domain features and frequency domain features of the tire audio data according to the tire foreign object recognition model.

[0055] Exemplarily, the tire vibration data and the tire audio data are preprocessed, and the preprocessed tire vibration data and the tire audio data are subjected to feature extraction to extract feature information that can reflect the tire status. The time domain features include the amplitude, frequency, fluctuation or variance of the vibration, and the frequency domain features include the spectrum distribution and Mel cepstral coefficients. These features can provide richer and more accurate information to help the tire foreign object recognition model better understand the tire status. In addition, since the tire detection data has many characteristic frequency bands, the tire foreign object recognition model is not restricted by the driving or parking environment of the car, and has richer application scenarios and is suitable for a variety of driving environments.

[0056] Among them, preprocessing includes operations such as data alignment and data cropping. The cropped data mainly contains normal driving characteristic signals, audio characteristic information and vibration characteristic information of foreign objects piercing the tire or stones embedded in the tire pattern. Therefore, by preprocessing the tire vibration data and tire audio data, clearer, more accurate and representative data can be obtained, providing a basis for subsequent feature extraction and model calculation. Data alignment is to unify different data to the same time node. Data cropping is to crop the data to the same time length.

[0057] In some embodiments, obtaining output information of at least one tire foreign object recognition model includes: obtaining multiple output information of multiple tire foreign object recognition models, where the multiple tire foreign object recognition models use tire detection data of the same time period as input.

[0058] Specifically, tire detection data of the same time period is input into multiple tire foreign object recognition models to obtain output information corresponding to the multiple tire foreign object recognition models, and the output information corresponding to the multiple tire foreign object recognition models is compared, that is, the analysis results of the multiple tire foreign object recognition models on the tire detection data are compared to determine the tire foreign object detection result. Therefore, in the present application, determining whether there is a foreign object in the tire through the output information of multiple tire foreign object recognition models can further improve the accuracy of tire foreign object detection, thereby avoiding the problem of misjudgment of tire foreign object detection.

[0059] In some embodiments, the tire detection data of the same time period is tire detection data collected within one or more data collection time windows, and the same time period may be 10s or 20s, without limitation.

[0060] In some embodiments, the data collection time window is determined based on the cycle time of one tire rotation; the cycle time of one tire rotation is determined based on the frequency of one tire rotation, and the frequency of one tire rotation is obtained based on wheel speed information.

[0061] Exemplarily, the cycle time T of one rotation of the tire is determined based on the frequency f of one rotation of the tire, that is, the cycle time T of one rotation of the tire is calculated by the frequency f of one rotation of the tire, where T=1 / f, and the frequency f of one rotation of the tire is obtained based on the wheel speed information V, where f=V / 2πR, R is the radius of the tire, and the circumference of the tire is 2πR. Then, the minimum data acquisition time window required to capture data once is determined based on the cycle time T of one rotation of the tire.

[0062] In some embodiments, a tire foreign object detection result is obtained based on the output information of at least one tire foreign object recognition model, including: when the proportion or number of times that multiple output information is the second type of information reaches a first threshold, the tire foreign object detection result is that there is foreign object on the tire; or, when the proportion or number of times that multiple output information is the first type of information reaches a second threshold, the tire foreign object detection result is that there is no foreign object on the tire.

[0063] The first threshold and the second threshold may be determined according to the number of tire foreign object recognition models.

[0064] Specifically, when the proportion or number of times that multiple output information is the second type of information reaches a first threshold, wherein the first threshold is used to determine whether the proportion or number of times that the second type of information reaches a sufficiently high proportion or number, then it means that the possibility of the presence of foreign matter in the tire is extremely high, and the tire foreign matter detection result is that there is foreign matter on the tire; or, when the proportion or number of times that multiple output information is the first type of information reaches a second threshold, wherein the first threshold is used to determine whether the proportion or number of times that the first type of information reaches a sufficiently high proportion or number, then it means that the possibility of the presence of foreign matter in the tire is very small, and the tire foreign matter detection result is that there is no foreign matter on the tire. Therefore, in the present application, determining whether there is foreign matter in the tire through the output information of multiple tire foreign matter recognition models can further improve the accuracy of tire foreign matter detection, thereby avoiding the problem of misjudgment of tire foreign matter detection.

[0065] In some embodiments, when the tire foreign object detection result indicates that there is a foreign object on the tire, the tire foreign object detection result is alarmed, and the tire foreign object detection result includes the type of tire foreign object. For example, the tire foreign object detection result is displayed on the dashboard, and an alarm is given through voice, text, or pictures, such as a text indicating that there is a metal nail on the left front tire, so that the user can know in time that there is a foreign object on the tire and take corresponding measures. Exemplarily, if the proportion or number of output information of the second type of information reaches a first threshold, the vehicle feeds back the tire foreign object detection result to the driver and passengers.

[0066] In the embodiment, in order to prevent false alarms as much as possible, the tire foreign object detection result confirmed by the output information of a single tire foreign object recognition model will not be directly fed back to the driver and passengers through the vehicle.

[0067] Reference below Figure 2 The method for monitoring foreign matter in a tire according to an embodiment of the present invention is described as follows. The specific contents are as follows.

[0068] Step S3, start.

[0069] Step S4, obtaining tire detection data, where the tire detection data includes tire vibration data and tire audio data.

[0070] Step S5, preprocessing the tire detection data.

[0071] Step S6, calculating the time domain characteristics of the tire vibration data and the frequency domain characteristics of the tire audio data, and then inputting the time domain characteristics of the tire vibration data and the frequency domain characteristics of the tire audio data into the tire foreign object recognition model for recognition to determine the tire foreign object detection result.

[0072] Step S7, determine whether there is foreign matter on the tire, if yes, execute step S8, otherwise, execute step S4.

[0073] Step S8, outputting classification information of foreign matter.

[0074] Step S9, end.

[0075] A second aspect of the present invention provides an electronic device, such as Figure 3 As shown, the electronic device 10 includes: at least one processor 1 and a memory 2 communicatively connected to the at least one processor 1 .

[0076] The memory 2 stores a computer program that can be executed by at least one processor 1 , and when the at least one processor 1 executes the computer program, the method for monitoring foreign matter in a tire according to the above embodiment is implemented.

[0077] It should be noted that the specific implementation of the electronic device of the embodiment of the present invention is similar to the specific implementation of the method for monitoring tire foreign matter in any of the above embodiments of the present invention. Please refer to the description of the method part for details. In order to reduce redundancy, it will not be repeated here.

[0078] The electronic device according to the embodiment of the present invention can improve the accuracy of tire foreign object detection and avoid the problem of misjudgment of tire foreign object detection by executing the method of monitoring tire foreign object of the above embodiment, and the tire foreign object recognition model has high robustness.

[0079] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, the method for monitoring foreign matter in a tire according to the above embodiment is implemented.

[0080] A fourth aspect of the present invention provides a vehicle 100, such as Figure 4 As shown, the vehicle 100 includes the electronic device 10 of the above embodiment; or Figure 5 As shown, the vehicle 100 includes: a detection device 3 and a data processing device 4 .

[0081] The detection device 3 is used to collect tire detection information; the data processing device 4 is configured with at least one tire foreign body recognition model, connected to the detection device 3, and used to execute the method for monitoring tire foreign bodies of the above embodiment.

[0082] It should be noted that the specific implementation method of the vehicle in the embodiment of the present invention is similar to the specific implementation method of the method for monitoring foreign matter in the tire in any of the above embodiments of the present invention. Please refer to the description of the method part for details. In order to reduce redundancy, it will not be repeated here.

[0083] According to the vehicle of the embodiment of the present invention, the accuracy of tire foreign object detection can be improved, the problem of misjudgment of tire foreign object detection can be avoided, and the tire foreign object recognition model has high robustness.

[0084] In some embodiments, the detection device includes: a tire vibration detection module and a tire audio detection module.

[0085] The tire vibration detection module is used to detect tire vibration data; the tire audio detection module is used to detect tire audio data. Figure 6 As shown, the detection devices 3 are distributed near the four tires.

[0086] In some embodiments, the tire vibration detection module is an accelerometer in the tire pressure monitoring system of the vehicle or an accelerometer in the active noise reduction system of the vehicle. The accelerometers are distributed near the four tires, and the tire vibration data is not easily disturbed by the environment, making the tire vibration data more accurate. In addition, the existing accelerometers of the vehicle are used to collect data, so there is no need to increase the vehicle hardware, and there is no need to add new vehicle mechanical structures to accommodate the corresponding hardware, thereby reducing the design complexity, improving the utilization rate of the vehicle hardware, and reducing costs.

[0087] In some embodiments, the tire audio detection module is a microphone of the vehicle's active noise reduction system. The microphones are distributed near the four tires, and the tire audio data is not easily affected by environmental interference, making the tire audio data more accurate. In addition, the vehicle's existing microphones are used to collect data, so there is no need to increase vehicle hardware or add new vehicle mechanical structures to accommodate the corresponding hardware, thereby reducing design complexity, improving the utilization rate of vehicle hardware, and reducing costs.

[0088] In some embodiments, Figure 7 As shown, the data processing device 4 includes at least one of a micro control unit 41 , a central domain control 42 and a vehicle computer 43 .

[0089] Specifically, there are multiple other options for the hardware related to data processing of tire detection data and deployment of tire foreign body recognition models. Processors in the vehicle that support the required data storage and computing capacity can be used as alternatives. For example, the microcontroller unit, central domain control, and vehicle computer can be used as processors to identify tire foreign bodies. The microcontroller unit has powerful data processing and analysis capabilities and can process and analyze data in real time.

[0090] In some embodiments, Figure 7 As shown, the data processing device 4 includes a micro control unit 41 , a central domain control 42 and a vehicle computer 43 .

[0091] Among them, the micro control unit 41 is connected to the central domain control 42, and the central domain control 42 is connected to the vehicle computer 43; any one of the micro control unit 41, the central domain control 42 and the vehicle computer 43 is configured with a tire foreign body recognition model.

[0092] Specifically, the tire foreign body recognition model is configured in the micro control unit 41, the central domain control 42 and the vehicle computer 43, so that the micro control unit 41, the central domain control 42 and the vehicle computer 43 can recognize the tire foreign body through the tire foreign body recognition model. Figure 6 As shown, the micro control unit 41 is disposed on the chassis 6 of the vehicle 100. Before configuring the tire foreign object recognition model to the micro control unit 41, the central domain control 42 and the vehicle computer 43, the tire foreign object recognition model needs to be pre-trained through the collected database.

[0093] In the embodiment, the micro control unit 41 as the data processing device 4 executes the method for monitoring tire foreign matter in the above embodiment, such as Figure 7As shown, the detection device 3 collects tire detection information and sends the tire detection information to the micro control unit 41, the micro control unit 41 sends the tire detection information to the data processing unit, the data processing unit 44 pre-processes the tire detection information, and then sends the pre-processed tire detection information to the micro control unit 41, the micro control unit 41 analyzes the tire detection information through the tire foreign body recognition model to obtain the output information of the tire foreign body recognition model. The micro control unit 41 then sends the tire foreign body detection result to the central domain control 42, and the central domain control 42 then sends the tire foreign body detection result to the instrument panel 51 and the vehicle-mounted multimedia device 52, so that the instrument panel 51 and the vehicle-mounted multimedia device 52 can prompt according to the tire foreign body detection result.

[0094] In addition, the data transmission between the micro control unit 41 and the data processing unit 44 is wireless or wired.

[0095] In the embodiment, the central domain control 42 as the data processing device 4 executes the method for monitoring tire foreign matter in the above embodiment, such as Figure 8 As shown, the detection device 3 collects tire detection information and sends the tire detection information to the micro control unit 41, the micro control unit 41 then sends the tire detection information to the central domain control 42, the central domain control 42 sends the tire detection information to the data processing unit 44, the data processing unit 44 pre-processes the tire detection information, and then sends the pre-processed tire detection information to the central domain control 42, the central domain control 42 analyzes the tire detection information through the tire foreign object recognition model to obtain the output information of the tire foreign object recognition model, and the central domain control 42 sends the tire foreign object detection result to the instrument panel 51 and the vehicle-mounted multimedia device 52, so that the instrument panel 51 and the vehicle-mounted multimedia device 52 can prompt according to the tire foreign object detection result.

[0096] In the embodiment, the vehicle computer 43 is used as a data processing device to execute the method for monitoring tire foreign matter in the above embodiment, such as Fig. 9 As shown, the detection device 3 collects tire detection information and sends the tire detection information to the micro control unit 41, the micro control unit 41 then sends the tire detection information to the central domain control 42, the central domain control 42 then forwards the tire detection information to the vehicle computer 43, the vehicle computer 43 sends the tire detection information to the data processing unit 44, the data processing unit 44 pre-processes the tire detection information, and then sends the pre-processed tire detection information to the vehicle computer 43, the vehicle computer 43 analyzes the tire detection information through the tire foreign body recognition model to obtain the output information of the tire foreign body recognition model. The central domain control 42 sends the tire foreign body detection result to the instrument panel 51, so that the instrument panel 51 prompts according to the tire foreign body detection result. The vehicle computer 43 sends the tire foreign body detection result to the vehicle multimedia device 52, so that the vehicle multimedia device 52 prompts according to the tire foreign body detection result.

[0097] In some embodiments, Figure 5 As shown, the vehicle 100 further includes: a prompting device 5 .

[0098] Among them, the prompt device 5 is connected to the data processing device 4, and is used to display and / or alarm when there is foreign matter on the tire, for example, by displaying text or symbols or prompt boxes through the vehicle-mounted multimedia device or by alarming through voice, or by displaying or warning with special symbols or text of different colors through the instrument or display screen, or by simultaneously displaying prompt information and making voice alarms through the instrument or vehicle-mounted multimedia, so as to prompt the user in a timely, intuitive and obvious manner so that the user can take corresponding measures in time, such as replacing or removing foreign matter, to ensure driving safety.

[0099] For example, in some embodiments, Figure 7 As shown, the prompting device 5 includes a dashboard 51 and a vehicle-mounted multimedia device 52. The dashboard 51 is connected to the central domain control 42 and the vehicle-mounted multimedia device 52, and the vehicle-mounted multimedia device 52 is connected to the vehicle-mounted multimedia device 43, so that the user can know in time that there are foreign objects on the tire and take corresponding measures to improve safety.

[0100] In the description of this specification, any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code including one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0101] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0102] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0103] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0104] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0105] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

[0106] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example.

[0107] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A method for monitoring foreign matter in a tire, characterized in that: include: Obtaining output information of at least one tire foreign object recognition model, wherein the tire foreign object recognition model takes tire detection data as input; A tire foreign object detection result is obtained according to output information of the at least one tire foreign object recognition model.

2. The method according to claim 1, characterized in that: The output information includes first-category information and second-category information, wherein the first-category information corresponds to the absence of foreign matter on the tire, and the second-category information corresponds to the presence of foreign matter on the tire.

3. The method according to claim 2, characterized in that The second type of information also includes a plurality of classification information, and the plurality of classification information corresponds to a plurality of different types of foreign matter existing on the tire.

4. The method according to claim 3, characterized in that The plurality of classification information includes first classification information and second classification information, the first classification information corresponds to foreign matter pierced into the tire, and the second classification information corresponds to foreign matter embedded in the tread of the tire.

5. The method according to any one of claims 1 to 4, characterized in that: The tire foreign object recognition model takes a variety of tire detection data as input.

6. The method according to claim 5, characterized in that The plurality of tire detection data includes tire vibration data and tire audio data.

7. The method according to claim 6, characterized in that The output information is obtained based on the time domain features and frequency features extracted from the tire vibration data and the time domain features and frequency domain features extracted from the tire audio data by the tire foreign matter recognition model.

8. The method according to any one of claims 2 to 4, characterized in that: The obtaining of output information of at least one tire foreign object recognition model includes: obtaining multiple output information of multiple tire foreign object recognition models, wherein the multiple tire foreign object recognition models use the tire detection data of the same time period as input.

9. The method according to claim 8, characterized in that The tire detection data in the same time period is tire detection data collected within one or more data collection time windows.

10. The method according to claim 9, characterized in that The data acquisition time window is determined according to the cycle time of one rotation of the tire; The period of one rotation of the tire is determined according to the frequency of one rotation of the tire, and the frequency of one rotation of the tire is obtained according to wheel speed information.

11. The method according to claim 8, characterized in that Obtaining a tire foreign object detection result according to output information of the at least one tire foreign object recognition model includes: When the proportion or number of the plurality of output information being the second type of information reaches a first threshold, the tire foreign matter detection result is that a foreign matter exists on the tire; Alternatively, when the proportion or number of the plurality of output information being the first type of information reaches a second threshold, the tire foreign object detection result is that there is no foreign object on the tire.

12. The method according to claim 11, characterized in that The method further comprises: When the tire foreign matter detection result indicates that there is foreign matter on the tire, an alarm is issued.

13. An electronic device, characterized in that: include: at least one processor; a memory communicatively coupled to at least one of the processors; The memory stores a computer program executable by at least one of the processors, and when at least one of the processors executes the computer program, the method for monitoring foreign matter in a tire according to any one of claims 1 to 12 is implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method for monitoring foreign matter in a tire according to any one of claims 1 to 12 is implemented.

15. A vehicle, characterized in that: The vehicle comprises the electronic device of claim 13; Alternatively, the vehicle comprises: Testing equipment, used to collect tire testing information; A data processing device, wherein the data processing device is configured with at least one tire foreign body recognition model, is connected to the detection device, and is used to execute the method for monitoring tire foreign bodies according to any one of claims 1 to 12.

16. The vehicle according to claim 15, characterized in that The detection equipment comprises: A tire vibration detection module, used to detect tire vibration data; The tire audio detection module is used to detect tire audio data.

17. The vehicle according to claim 16, characterized in that The tire vibration detection module is an accelerometer in a tire pressure monitoring system of the vehicle or an accelerometer in an active noise reduction system of the vehicle.

18. The vehicle according to claim 16, characterized in that The tire audio detection module is a microphone of the active noise reduction system of the vehicle.

19. The vehicle according to claim 15, characterized in that The data processing device includes at least one of a micro control unit, a central domain control and a vehicle computer.

20. The vehicle according to claim 15, characterized in that The vehicle further comprises: A prompting device is connected to the data processing device and is used for displaying and / or alarming when foreign matter exists on the tire.

Images