Tire wear degree determination method and device, vehicle and storage medium

Abstract

The embodiment of the invention discloses a tire wear degree determination method and device, a vehicle and a storage medium. The method comprises the steps that a sensor signal corresponding to a tire in the vehicle running process is obtained; preprocessing the sensor signal; the preprocessed sensor signals are input into a preset neural network model, and the neural network model is trained based on a sample pair formed by sensor historical signals and historical wear degrees; and determining the wear degree of the tire according to an output result of the neural network model. According to the embodiment of the invention, the wear degree of the tire can be effectively determined, the cost is saved, the popularization of tire wear degree detection is facilitated, and the driving safety is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a method and device for determining the degree of tire wear, a vehicle and a storage medium. Background Art

[0002] The existing solutions for tire wear monitoring include camera image analysis, laser-based depth camera signal acquisition, millimeter wave radar, embedded material electromagnetic field change analysis, embedded signal line analysis, and vibration frequency analysis.

[0003] However, in the prior art, for determining the degree of tire wear, the camera-based solution has better accuracy and is external, with no requirements for the tire, but the cost is too high, which is not conducive to the popularization of tire wear detection. The millimeter-wave radar-based solution is similar to the camera solution and is also too costly. The embedded type solution has the highest accuracy. However, the requirements for tire processing technology are too high, and few tire manufacturers are willing to develop such a process, which is not conducive to the popularization of tire wear detection. For the vibration type solution, the accuracy is not as good as the camera type and embedded type, but fortunately, the requirements for tires are not high and do not need to be embedded, but the difficulty lies in the later data processing and recognition, and the algorithm processing of the existing vibration solution is mainly based on traditional algorithms, such as the least squares method and the time series method. Since it is difficult to generalize to all scenarios, it is not conducive to the popularization of tire wear detection.

[0004] Therefore, how to effectively determine the degree of tire wear while saving costs has become an urgent problem to be solved. Summary of the invention

[0005] The present invention provides a tire wear degree determination method, device, vehicle and storage medium, which can effectively determine the tire wear degree, save costs, facilitate the popularization of tire wear degree detection, and improve driving safety.

[0006] According to one aspect of the present invention, a method for determining tire wear degree is provided, comprising:

[0007] Acquire sensor signals corresponding to tires during vehicle driving;

[0008] Preprocessing the sensor signal;

[0009] Inputting the preprocessed sensor signal into a preset neural network model, wherein the neural network model is trained based on sample pairs consisting of historical sensor signals and historical wear levels;

[0010] The degree of tire wear is determined based on the output result of the neural network model.

[0011] The step of acquiring the sensor signal generated during the vehicle driving process includes:

[0012] Based on the sensors built into the tires, the soundprint signals and acceleration signals generated by the vehicle during driving are acquired.

[0013] The preprocessing of the sensor signal comprises:

[0014] Performing signal processing on the acquired voiceprint signal and acceleration signal;

[0015] Determine the voiceprint signal strength according to the processed voiceprint signal, and determine the voiceprint signal waveform according to the change information of the voiceprint signal strength over time;

[0016] The acceleration signal strength is determined according to the processed acceleration signal, and the acceleration signal waveform is determined according to the information of the change of the acceleration signal strength over time.

[0017] The step of inputting the preprocessed sensor signal into a preset neural network model comprises:

[0018] Inputting the voiceprint signal strength and / or voiceprint signal waveform into a preset neural network model;

[0019] Inputting the acceleration signal strength and / or the acceleration signal waveform into a preset neural network model;

[0020] The predicted probability of the degree of wear is generated by the neural network model based on the voiceprint signal strength and / or the voiceprint signal waveform, and the acceleration signal strength and / or the acceleration signal waveform.

[0021] Determining the degree of wear of the tire according to the output result of the neural network model includes:

[0022] The degree of wear of the tire is determined according to the predicted probability of the degree of wear.

[0023] According to another aspect of the present invention, there is provided a device for determining the degree of tire wear, comprising:

[0024] An acquisition module, used to acquire sensor signals corresponding to tires during vehicle driving;

[0025] A preprocessing module, used for preprocessing the sensor signal;

[0026] An input module, used for inputting the preprocessed sensor signal into a preset neural network model, wherein the neural network model is trained based on sample pairs consisting of historical sensor signals and historical wear degrees;

[0027] The wear degree determination module is used to determine the wear degree of the tire according to the output result of the neural network model.

[0028] The acquisition module is specifically used for:

[0029] Based on the built-in sensors in the tire, the soundprint signal and acceleration signal generated by the tire during driving are obtained.

[0030] The preprocessing module is specifically used for:

[0031] Performing signal processing on the acquired voiceprint signal and acceleration signal;

[0032] Determine the voiceprint signal strength according to the processed voiceprint signal, and determine the voiceprint signal waveform according to the change information of the voiceprint signal strength over time;

[0033] The acceleration signal strength is determined according to the processed acceleration signal, and the acceleration signal waveform is determined according to the information of the change of the acceleration signal strength over time.

[0034] According to another aspect of the present invention, a vehicle is provided, the vehicle comprising:

[0035] at least one processor; and

[0036] a memory communicatively connected to the at least one processor; wherein,

[0037] The storage module stores a computer program and historical parameter data that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a tire wear degree determination method described in any embodiment of the present invention.

[0038] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a tire wear degree determination method described in any embodiment of the present invention when executed.

[0039] The technical solution of the embodiment of the present invention can obtain the sensor signal corresponding to the tire during the driving process of the vehicle; pre-process the sensor signal; input the pre-processed sensor signal into a preset neural network model; and determine the wear degree of the tire according to the output result of the neural network model. The embodiment of the present invention can effectively determine the wear degree of the tire, save costs, facilitate the popularization of tire wear degree detection, and improve driving safety.

[0040] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 is a flow chart of a method for determining the degree of tire wear provided according to Embodiment 1 of the present invention;

[0043] Figure 2 is a signal waveform scene diagram applicable to this embodiment;

[0044] Figure 3 is a flow chart of another method for determining the degree of wear provided according to the second embodiment of the present invention;

[0045] Figure 4 This is a simplified framework diagram scene diagram of an AI Core model applicable to this embodiment;

[0046] Figure 5 is a schematic structural diagram of a wear degree determination device provided according to Embodiment 3 of the present invention;

[0047] Figure 6 It is a structural schematic diagram of a vehicle that implements a method for determining the degree of wear provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0049] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or vehicle comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or vehicles.

[0050] Embodiment 1

[0051] Figure 1 This is a flowchart of a method for determining the degree of tire wear provided in the first embodiment of the present invention. This embodiment is applicable to the scene of determining the degree of tire wear. The method can be executed by a device for determining the degree of tire wear. The device for determining the degree of tire wear can be implemented in the form of hardware and / or software. The device for determining the degree of tire wear can be integrated in a vehicle. Figure 1 As shown, the method includes:

[0052] S110: Acquire sensor signals corresponding to tires during vehicle driving.

[0053] Among them, tires are one of the important parts of vehicles. Because they are in direct contact with the road surface, they bear the weight of the car and work together with the car suspension to mitigate the impact of the car when driving. Therefore, tires will have different degrees of wear during driving. Testing the degree of wear of tires can eliminate safety hazards caused by tires in time, thereby effectively avoiding traffic accidents caused by tires.

[0054] In this embodiment, the sensor signal is mainly acquired by the sensor, wherein the sensor may be a device or apparatus that converts the acquired information into a usable signal according to a certain rule and outputs the signal.

[0055] Exemplarily, acquiring sensor signals generated during the driving of the vehicle may include: acquiring a soundprint signal and an acceleration signal generated during the driving of the vehicle based on sensors built into the tires.

[0056] Among them, the sensor is placed inside the tire to collect the corresponding signals generated during the vehicle's driving process. There is no need for special processing of the tire. The sensor is low in cost and easy to install, and can be installed compatible with traditional tire pressure sensors.

[0057] Optionally, the sensor of this embodiment may be an integrated sensor, which can be used to collect four signals including temperature, air pressure, voiceprint (vibration) signal and acceleration, wherein the voiceprint signal and acceleration signal are signals required for subsequent processing in this embodiment.

[0058] S120: Preprocess the sensor signal.

[0059] Among them, preprocessing the sensor signal may be preprocessing it using an AI algorithm.

[0060] In this embodiment, since the sensor is an ultra-low power consumption component, AI calculation cannot be performed directly on the sensor. Therefore, the signal data collected by the sensor needs to be uploaded to a local host or a cloud server before AI calculation is performed.

[0061] Exemplarily, preprocessing the sensor signal may include: performing signal processing on the acquired voiceprint signal and acceleration signal; determining the voiceprint signal strength based on the processed voiceprint signal, and determining the voiceprint signal waveform based on the information of the change of the voiceprint signal strength over time; determining the acceleration signal strength based on the processed acceleration signal, and determining the acceleration signal waveform based on the information of the change of the acceleration signal strength over time.

[0062] It should be emphasized that the waveforms of the voiceprint signals and acceleration signals collected in different scenarios are different.

[0063] The steps of preprocessing the sensor signal may include: waveform preprocessing, encoding, DFT, filtering, convolution, linear transformation and intensity analysis.

[0064] The waveform of the voiceprint signal and the waveform of the acceleration signal determined in this embodiment can be as follows: Figure 2 A signal waveform scenario is shown in FIG. , wherein the Y axis is used to indicate the signal strength received by the sensor, and the X axis is used to indicate time.

[0065] S130, inputting the preprocessed sensor signal into a preset neural network model, wherein the neural network model is trained based on sample pairs consisting of historical sensor signals and historical wear degrees.

[0066] Among them, the neural network model can be an AI Core model.

[0067] In this embodiment, during the training of the neural network model, the AI ​​Core model can be trained using sample pairs consisting of historical sensor signals and historical wear levels.

[0068] Among them, the AI ​​Core model has a pooling layer and a convolution layer, and the preprocessed sensor signal can be input into the AICore model. After the AI ​​Core model performs convolution and pooling, the training result is obtained.

[0069] Exemplarily, inputting the preprocessed sensor signal into a preset neural network model may include: inputting the voiceprint signal strength and / or the voiceprint signal waveform into the preset neural network model; inputting the acceleration signal strength and / or the acceleration signal waveform into the preset neural network model; and generating a predicted probability of the degree of wear based on the voiceprint signal strength and / or the voiceprint signal waveform, and the acceleration signal strength and / or the acceleration signal waveform through the neural network model.

[0070] Among them, the predicted probability of wear degree can be generated by inputting voiceprint signal strength and acceleration signal strength; inputting voiceprint signal strength and acceleration signal waveform; inputting voiceprint signal waveform and acceleration signal strength; inputting voiceprint signal waveform and acceleration signal waveform.

[0071] S140: Determine the degree of tire wear according to the output result of the neural network model.

[0072] Exemplarily, determining the degree of wear of the tire according to the output result of the neural network model may include: determining the degree of wear of the tire according to the predicted probability of the degree of wear.

[0073] Among them, the predicted probability of the wear degree can be determined using a normalized exponential function.

[0074] In this embodiment, the degree of tire wear may be expressed in percentage.

[0075] The embodiments of the present invention can obtain sensor signals corresponding to tires during vehicle driving; preprocess the sensor signals; input the preprocessed sensor signals into a preset neural network model; and determine the degree of wear of the tires based on the output results of the neural network model, thereby effectively determining the degree of wear of the tires, saving costs, facilitating the popularization of tire wear degree detection, and improving driving safety.

[0076] Embodiment 2

[0077] Figure 3 This is a flowchart of another method for determining the degree of tire wear provided by Embodiment 2 of the present invention. This embodiment is a specific limitation of the above embodiment, and the explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 3 The tire wear degree determination method provided in this embodiment specifically includes the following steps:

[0078] S210: Acquire sensor signals.

[0079] S220, input the sensor to a waveform shaper for processing.

[0080] S230, input the signal processed by the waveform shaper to the waveform enhancer for processing.

[0081] S240, subjecting the signal processed by the waveform enhancer to DFT discrete Fourier transform processing.

[0082] S250, processing the signal processed by DFT through a Mel filter bank.

[0083] S260, input the processed signal into the AI ​​Core model.

[0084] Among them, the AI ​​Core model can be Figure 4 A simplified framework diagram of an AI Core model is shown in the scene diagram.

[0085] S270, convolve and pool the processed signal in the AI ​​Core model.

[0086] During the training of the AI ​​Core model, the array form of the processed signal can be input, such as a one-dimensional array a1, a2, a3, ..., an. The one-dimensional array can be used to represent the pre-processed sensor signal collected in the tire puncture scenario. Optionally, the scenario of this implementation can also be different scenarios such as bulges and tire scrapes, which is not specifically limited in this embodiment.

[0087] Specifically, after the above one-dimensional array is input into the AI ​​Core model, the convolution pool and pooling pool based on the AI ​​Core model will be processed and the corresponding results will be output. The AI ​​Core model can obtain a corresponding relationship and identify the one-dimensional array a1, a2, a3, …, an as tire nails.

[0088] S280: Determine the degree of wear of the tire according to the output result of the AI ​​Core model.

[0089] The embodiments of the present invention can effectively determine the degree of wear of the tire, save costs, facilitate the popularization of tire wear degree detection, and improve driving safety.

[0090] Embodiment 3

[0091] Figure 5 This is a schematic diagram of the structure of a device for determining the degree of tire wear provided by Embodiment 3 of the present invention. Figure 5 As shown, the device includes: an acquisition module 310, a preprocessing module 320, an input module 330 and a wear degree determination module 340, wherein:

[0092] An acquisition module 310 is used to acquire sensor signals corresponding to tires during vehicle driving;

[0093] A preprocessing module 320, used for preprocessing the sensor signal;

[0094] An input module 330, used to input the preprocessed sensor signal into a preset neural network model, wherein the neural network model is trained based on sample pairs consisting of historical sensor signals and historical wear levels;

[0095] The wear degree determination module is used to determine the wear degree of the tire according to the output result of the neural network model.

[0096] The technical solution of the embodiment of the present invention obtains the sensor signal corresponding to the tire during the driving process of the vehicle; pre-processes the sensor signal; inputs the pre-processed sensor signal into a preset neural network model; and determines the wear degree of the tire according to the output result of the neural network model. The embodiment of the present invention can effectively determine the wear degree of the tire, save costs, facilitate the popularization of tire wear degree detection, and improve driving safety.

[0097] Optionally, the acquisition module 310 is specifically used for:

[0098] Based on the sensors built into the tires, the soundprint signals and acceleration signals generated by the vehicle during driving are acquired.

[0099] Optionally, the preprocessing module 320 is specifically used for:

[0100] Performing signal processing on the acquired voiceprint signal and acceleration signal;

[0101] Determine the voiceprint signal strength according to the processed voiceprint signal, and determine the voiceprint signal waveform according to the change information of the voiceprint signal strength over time;

[0102] The acceleration signal strength is determined according to the processed acceleration signal, and the acceleration signal waveform is determined according to the information of the change of the acceleration signal strength over time.

[0103] Optionally, the input module 330 may include:

[0104] A voiceprint waveform input unit, used to input the voiceprint signal strength and / or voiceprint signal waveform into a preset neural network model;

[0105] An acceleration waveform input unit, used for inputting the acceleration signal strength and / or the acceleration signal waveform into a preset neural network model;

[0106] A generating unit is used to generate a predicted probability of the degree of wear based on the voiceprint signal strength and / or the voiceprint signal waveform, and the acceleration signal strength and / or the acceleration signal waveform through the neural network model.

[0107] Optionally, the wear degree determination module 340 is specifically configured to:

[0108] The degree of wear of the tire is determined according to the predicted probability of the degree of wear.

[0109] A tire wear degree determination device provided in an embodiment of the present invention can execute a tire wear degree determination method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0110] Embodiment 4

[0111] Figure 6 This is a schematic diagram of the structure of a vehicle provided by Embodiment 4 of the present invention. Figure 6 As shown, the vehicle 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the vehicle 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0112] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. When the processor 11 executes the various methods described above, it implements:

[0113] Acquire sensor signals corresponding to tires during vehicle driving;

[0114] Preprocessing the sensor signal;

[0115] Inputting the preprocessed sensor signal into a preset neural network model, wherein the neural network model is trained based on sample pairs consisting of historical sensor signals and historical wear levels;

[0116] The degree of tire wear is determined based on the output result of the neural network model.

[0117] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0118] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0119] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0120] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining the degree of tire wear, characterized in that: include: Acquire sensor signals corresponding to tires during vehicle driving; Preprocessing the sensor signal; Inputting the preprocessed sensor signal into a preset neural network model, wherein the neural network model is trained based on sample pairs consisting of historical sensor signals and historical wear levels; The degree of tire wear is determined based on the output result of the neural network model.

2. The method according to claim 1, characterized in that The step of acquiring a sensor signal generated during vehicle travel includes: Based on the sensors built into the tires, the soundprint signals and acceleration signals generated by the vehicle during driving are acquired.

3. The method according to claim 2, characterized in that The preprocessing of the sensor signal comprises: Performing signal processing on the acquired voiceprint signal and acceleration signal; Determine the voiceprint signal strength according to the processed voiceprint signal, and determine the voiceprint signal waveform according to the change information of the voiceprint signal strength over time; The acceleration signal strength is determined according to the processed acceleration signal, and the acceleration signal waveform is determined according to the information of the change of the acceleration signal strength over time.

4. The method according to claim 3, characterized in that The step of inputting the preprocessed sensor signal into a preset neural network model comprises: Inputting the voiceprint signal strength and / or voiceprint signal waveform into a preset neural network model; Inputting the acceleration signal strength and / or the acceleration signal waveform into a preset neural network model; The predicted probability of the degree of wear is generated by the neural network model based on the voiceprint signal strength and / or the voiceprint signal waveform, and the acceleration signal strength and / or the acceleration signal waveform.

5. The method according to claim 4, characterized in that Determining the degree of wear of the tire according to the output result of the neural network model includes: The degree of wear of the tire is determined according to the predicted probability of the degree of wear.

6. A device for determining the degree of tire wear, characterized in that: include: An acquisition module, used to acquire sensor signals corresponding to tires during vehicle driving; A preprocessing module, used for preprocessing the sensor signal; An input module, used for inputting the preprocessed sensor signal into a preset neural network model, wherein the neural network model is trained based on sample pairs consisting of historical sensor signals and historical wear degrees; The wear degree determination module is used to determine the wear degree of the tire according to the output result of the neural network model.

7. The device according to claim 6, characterized in that The acquisition module is specifically used for: Based on the built-in sensors in the tire, the soundprint signal and acceleration signal generated by the tire during driving are obtained.

8. The device according to claim 6, characterized in that The preprocessing module is specifically used for: Performing signal processing on the acquired voiceprint signal and acceleration signal; Determine the voiceprint signal strength according to the processed voiceprint signal, and determine the voiceprint signal waveform according to the change information of the voiceprint signal strength over time; The acceleration signal strength is determined according to the processed acceleration signal, and the acceleration signal waveform is determined according to the information of the change of the acceleration signal strength over time.

9. A vehicle, characterized in that: The vehicle comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the tire wear degree determination method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the tire wear degree determination method according to any one of claims 1 to 5 when executed.

Images