Early warning method and device for service life of wheel, server, medium and program product

Abstract

The invention relates to the technical field of rim life monitoring, in particular to a wheel life early warning method and device, a server, a medium and a program product, and the method comprises the steps: receiving a strain signal of a wheel inner rim of the server; inputting the strain signal into a pre-trained life prediction model to output the actual residual life of the rim; and when the actual residual life is smaller than or equal to a certain threshold value, the server is controlled to carry out life early warning. Therefore, the problems that in the related technology, through wheel turning repair related data and an electrical equipment asset management system, the cracking situation caused by the fact that the rim is greatly damaged under the misuse working condition cannot be completely avoided, the safety performance of the vehicle is low, and safety accidents are likely to be caused are solved.

Description

Technical Field

[0001] The present application relates to the technical field of wheel rim life monitoring, and in particular to a wheel life early warning method, device, server, medium and program product. Background Art

[0002] In the related technology, the remaining life of the wheel can be generated based on the data related to the remaining life of the wheel using the pre-trained prediction model, and then a wheel turning and repair plan can be generated based on the wheel turning and repair related data to update the remaining life of the wheel; it is also possible to construct a health record road network electromechanical equipment asset management system that includes the identity identification and basic information of electromechanical equipment to perform identity identification and basic information transmission, so that corresponding operation and maintenance management can be carried out when abnormal conditions occur.

[0003] However, in the relevant technology, the wheel turning and repair related data and electrical equipment asset management system cannot completely prevent the wheel rim from being severely damaged and cracked under misuse conditions, which makes the vehicle's safety performance low and easily causes safety accidents, and urgently needs improvement. Summary of the Invention

[0004] The present application provides a wheel life early warning method, device, server, medium and program product to solve the problem in the related art that it is impossible to completely prevent the wheel rim from being severely damaged and cracking under misuse conditions, resulting in low vehicle safety performance and prone to safety accidents.

[0005] The first aspect of the present application provides a wheel life warning method, which includes the following steps: receiving a strain signal of the inner rim of a wheel from a server; inputting the strain signal into a pre-trained life prediction model to output the actual remaining life of the rim; and controlling the server to perform a life warning when the actual remaining life is less than or equal to a preset threshold.

[0006] Through the above technical solution, the strain signal of the wheel rim received by the server can be input into the pre-trained life prediction model, and then the actual remaining life of the rim can be output. When the actual remaining life is less than or equal to a certain threshold, the server can be controlled to issue a life warning. The actual remaining life of the wheel can be accurately calculated before the rim cracks and the tire leaks, and potential risks can be discovered in time, and the driver can be reminded to avoid serious traffic accidents.

[0007] Optionally, in one embodiment of the present application, before inputting the strain signal into a pre-trained life prediction model, it also includes: calculating the fatigue damage value of the rim based on the training strain signal, and determining the first remaining life of the rim based on the training strain signal; calculating the second remaining life of the rim using the fatigue damage value; training an initial model based on the training strain signal, at least one of the first remaining life and the second remaining life, so as to train the life prediction model.

[0008] Through the above technical solution, before the strain signal is input into the pre-trained life prediction model, the fatigue damage value of the rim can be calculated based on the training strain signal, and then the second remaining life can be calculated. The first remaining life can also be determined based on the training strain signal, so as to train the initial model to train the life prediction model. Through the parallel calculation of the first remaining life and the second remaining life, a dual verification system is constructed to improve the fault tolerance of the prediction results, multi-modal data fusion training, and improve the prediction stability, with high dynamic adaptive update capability.

[0009] Optionally, in one embodiment of the present application, the initial model is trained based on the training strain signal, at least one of the first remaining life and the second remaining life to train the life prediction model, including: determining at least one of the architecture information, number of layers information, loss function information and training information of the life prediction model based on the training strain signal; constructing the life prediction model based on the architecture information, the number of layers information, the loss function information and at least one of the training information; detecting whether the life prediction model meets a preset condition based on the first remaining life and the second remaining life; if the life prediction model does not meet the preset condition, adjusting the life prediction model until the life prediction model meets the preset condition, thereby obtaining the final life prediction model.

[0010] Through the above technical solution, the architecture information, number of layers, loss function information and training information of the life prediction model can be determined based on the training strain signal, and then the life prediction model can be constructed. The life prediction model can be detected based on the remaining life to determine whether it meets certain conditions. If it does not meet the conditions, the life prediction model can be adjusted until the conditions are met. The dynamic architecture adaptive mechanism can intelligently match the model complexity with the data characteristics, improve the inference speed while maintaining the prediction accuracy, and the dual-modal constraint training paradigm can reduce the deviation of the prediction results and enhance the interpretability of the model.

[0011] Optionally, in one embodiment of the present application, the calculating the fatigue damage value of the rim based on the training strain signal includes: determining the elastic strain value of the rim elastic strain and the plastic strain value of the rim plastic strain based on the training strain signal; obtaining the fatigue coefficient corresponding to the rim and the elastic modulus of the material used for the rim; and calculating the fatigue damage value based on at least one of the elastic strain value, the plastic strain value, the fatigue coefficient and the elastic modulus.

[0012] Through the above technical solution, the elastic strain value and plastic strain value can be determined based on the training strain signal, and the fatigue damage value can be calculated by combining the fatigue coefficient and elastic modulus. By accurately extracting the elastic strain value and plastic strain value, the prediction error is reduced, and the fatigue coefficient is introduced to improve the prediction accuracy while maintaining the prediction stability.

[0013] Optionally, in one embodiment of the present application, before inputting the strain signal into a pre-trained life prediction model, it also includes: judging whether the strain signal satisfies a preset strain condition; if the strain signal satisfies the preset strain condition, determining that the wheel rim is damaged, and allowing the strain signal to be input into the pre-trained life prediction model.

[0014] Through the above technical solution, before the strain signal is input into the pre-trained life prediction model, it can be judged whether the strain signal meets certain strain conditions. If so, it can be determined that the wheel rim is damaged and allowed to be input into the pre-trained life prediction model. Invalid strain signals can be shielded through certain strain conditions, reducing model reasoning, reducing hardware computing power requirements, improving prediction accuracy, and enhancing anti-interference capabilities.

[0015] The second aspect of the present application provides a wheel life warning device, which includes: a receiving module for receiving a strain signal of the inner rim of a wheel of a server; an output module for inputting the strain signal into a pre-trained life prediction model to output the actual remaining life of the rim; and a control module for controlling the server to perform a life warning when the actual remaining life is less than or equal to a preset threshold.

[0016] Through the above technical solution, the strain signal of the wheel rim received by the server can be input into the pre-trained life prediction model, and then the actual remaining life of the rim can be output. When the actual remaining life is less than or equal to a certain threshold, the server can be controlled to issue a life warning. The actual remaining life of the wheel can be accurately calculated before the rim cracks and the tire leaks, and potential risks can be discovered in time, and the driver can be reminded to avoid serious traffic accidents.

[0017] Optionally, in one embodiment of the present application, it also includes: a first calculation module, which is used to calculate the fatigue damage value of the rim based on the training strain signal before inputting the strain signal into the pre-trained life prediction model, and determine the first remaining life of the rim based on the training strain signal; a second calculation module, which is used to calculate the second remaining life of the rim using the fatigue damage value; and a training module, which is used to train an initial model based on the training strain signal, at least one of the first remaining life and the second remaining life, so as to train the life prediction model.

[0018] Through the above technical solution, before the strain signal is input into the pre-trained life prediction model, the fatigue damage value of the rim can be calculated based on the training strain signal, and then the second remaining life can be calculated. The first remaining life can also be determined based on the training strain signal, so as to train the initial model to train the life prediction model. Through the parallel calculation of the first remaining life and the second remaining life, a dual verification system is constructed to improve the fault tolerance of the prediction results, multi-modal data fusion training, and improve the prediction stability, with high dynamic adaptive update capability.

[0019] Optionally, in one embodiment of the present application, the training module includes: a first determination unit, used to determine at least one of the architecture information, number of layers information, loss function information and training information of the life prediction model based on the training strain signal; a construction unit, used to construct the life prediction model based on at least one of the architecture information, the number of layers information, the loss function information and the training information; a detection unit, used to detect whether the life prediction model meets a preset condition based on the first remaining life and the second remaining life; a generation unit, used to adjust the life prediction model if the life prediction model does not meet the preset condition until the life prediction model meets the preset condition, thereby obtaining the final life prediction model.

[0020] Through the above technical solution, the architecture information, number of layers, loss function information and training information of the life prediction model can be determined based on the training strain signal, and then the life prediction model can be constructed. The life prediction model can be detected based on the remaining life to determine whether it meets certain conditions. If it does not meet the conditions, the life prediction model can be adjusted until the conditions are met. The dynamic architecture adaptive mechanism can intelligently match the model complexity with the data characteristics, improve the inference speed while maintaining the prediction accuracy, and the dual-modal constraint training paradigm can reduce the deviation of the prediction results and enhance the interpretability of the model.

[0021] Optionally, in one embodiment of the present application, the first calculation module includes: a second determination unit, used to determine the elastic strain value of the rim elastic strain and the plastic strain value of the rim plastic strain based on the training strain signal; an acquisition unit, used to obtain the fatigue coefficient corresponding to the rim and the elastic modulus of the material used for the rim; and a calculation unit, used to calculate the fatigue damage value based on at least one of the elastic strain value, the plastic strain value, the fatigue coefficient and the elastic modulus.

[0022] Through the above technical solution, the elastic strain value and plastic strain value can be determined based on the training strain signal, and the fatigue damage value can be calculated by combining the fatigue coefficient and elastic modulus. By accurately extracting the elastic strain value and plastic strain value, the prediction error is reduced, and the fatigue coefficient is introduced to improve the prediction accuracy while maintaining the prediction stability.

[0023] Optionally, in one embodiment of the present application, it also includes: a judgment module, used to judge whether the strain signal meets a preset strain condition before inputting the strain signal into a pre-trained life prediction model; a judgment module, used to judge that the wheel rim is damaged when the strain signal meets the preset strain condition, and allow the strain signal to be input into the pre-trained life prediction model.

[0024] Through the above technical solution, before the strain signal is input into the pre-trained life prediction model, it can be judged whether the strain signal meets certain strain conditions. If so, it can be determined that the wheel rim is damaged and allowed to be input into the pre-trained life prediction model. Invalid strain signals can be shielded through certain strain conditions, reducing model reasoning, reducing hardware computing power requirements, improving prediction accuracy, and enhancing anti-interference capabilities.

[0025] A third aspect of the present application provides a server, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the wheel life warning method as described in the above embodiment.

[0026] A fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned wheel life warning method.

[0027] The fifth embodiment of the present application provides a computer program product, including a computer program, which implements the above-mentioned wheel life warning method when executed.

[0028] The embodiment of the present application can input the strain signal of the wheel rim received from the server into a pre-trained life prediction model, thereby outputting the actual remaining life of the wheel rim. If the actual remaining life is less than or equal to a certain threshold, the server is controlled to issue a life warning. This can accurately calculate the actual remaining life of the wheel before the rim cracks and the tire leaks, thereby promptly identifying potential risks and alerting the driver to avoid serious traffic accidents. This solves the problem in the related art that wheel repair data and electrical equipment asset management systems cannot completely prevent the cracking of the wheel rim caused by severe damage under misuse conditions, resulting in low vehicle safety performance and the susceptibility to safety accidents.

[0029] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0031] Figure 1 This is a block diagram of a wheel life warning system provided according to one embodiment of the present application;

[0032] Figure 2 This is a flow chart of a wheel life warning method provided according to an embodiment of the present application;

[0033] Figure 3 A schematic diagram of the structure of a deep learning model provided according to one embodiment of the present application;

[0034] Figure 4 This is a flow chart of the working principle of the wheel life warning method provided according to one embodiment of the present application;

[0035] Figure 5 This is a flow chart of the working principle of wheel life warning provided according to one embodiment of the present application;

[0036] Figure 6 This is a block diagram of a wheel life warning device provided according to an embodiment of the present application;

[0037] Figure 7 A schematic diagram of the structure of a server provided according to an embodiment of the present application.

[0038] Reference numerals:

[0039] 10 - Wheel life warning system; 101 - Wheel, 102 - Strain sensor, 103 - Axle joint, 104 - Wheel rim, 105 - Signal receiver, 106 - Central controller, 107 - Fatigue life calculation module, 108 - Strain signal monitoring and statistics module, 109 - Server; 20 - Wheel life warning device; 100 - Receiving module, 200 - Output module, 300 - Control module; 701 - Memory, 702 - Processor, 703 - Communication interface. DETAILED DESCRIPTION

[0040] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0041] The following describes the wheel life early warning method, device, server, medium, and program product according to an embodiment of the present application with reference to the accompanying drawings. To address the problem mentioned in the background art above that it is impossible to completely prevent the cracking of the wheel rim caused by severe damage under misuse conditions, resulting in low vehicle safety performance and a high risk of causing safety accidents, the present application provides a wheel life early warning method. In this method, the strain signal of the wheel rim received from the server can be input into a pre-trained life prediction model to output the actual remaining life of the wheel rim. When the actual remaining life is less than or equal to a certain threshold, the server is controlled to issue a life warning. This method can accurately calculate the actual remaining life of the wheel before the wheel rim cracks and tire deflation occur, thereby promptly identifying potential risks and alerting the driver to avoid serious traffic accidents. This solves the problem in the related art that wheel rim cracking caused by severe damage under misuse conditions cannot be completely prevented through wheel turning and repair data and electrical equipment asset management systems, resulting in low vehicle safety performance and a high risk of causing safety accidents.

[0042] Before introducing the wheel life warning method proposed in the embodiment of the present application, the wheel life warning system involved in the embodiment of the present application is first introduced.

[0043] Specifically, Figure 1 The figure is a block diagram of a wheel life warning system provided according to one embodiment of the present application.

[0044] like Figure 1 As shown, the wheel life warning system 10 includes a wheel 101, a strain sensor 102, an axle joint 103, a rim 104, a signal receiver 105, a central controller 106, a fatigue life calculation module 107, a strain signal monitoring and statistics module 108 and a server 109.

[0045] Among them, the embodiment of the present application can use the strain sensor 102 to collect the strain signal of the inner rim 104 of the wheel 101 in real time, and transmit it to the central controller 106 and the server 109 through the signal receiver 105, and then use the fatigue life calculation module 107 and the strain signal monitoring and statistics module 108 to calculate the corresponding actual remaining life in real time and perform life warning.

[0046] Specifically, Figure 2 The present invention provides a flowchart of a wheel life early warning method according to an embodiment of the present application.

[0047] like Figure 2 As shown, the early warning method for wheel life includes the following steps:

[0048] In step S201 , a strain signal of an inner rim of a wheel is received from a server.

[0049] It can be understood that the embodiments of the present application can monitor the strain signal of the wheel rim in real time by arranging a strain sensor at a certain position of the wheel rim, and thus detect the wheel rim cracking problem as soon as possible. Among them, the certain position can be set by technicians in this field according to actual conditions, and this application does not impose any specific restrictions.

[0050] In some embodiments, the embodiments of the present application can receive the strain signal of the inner rim of the wheel from the server in real time.

[0051] Illustratively, an embodiment of the present application can evenly arrange strain sensors on the entire circumference of the inner rim of the wheel, located on the side end face of the inner rim of the wheel, keep the strain sensors in a working state at all times, wirelessly receive strain signals collected at the rim in real time through the strain sensors, control the frequency of the received signals, and transmit the strain signals to the central controller through the strain sensors, and then transmit the strain signals to the server through the central controller.

[0052] The embodiment of the present application arranges a strain sensor at the inner rim of the wheel to directly collect the strain signal of the wheel when it is stimulated by an external load during driving, and then quickly calculates the fatigue life of the rim based on the strain signal, and promptly reminds the driver through the vehicle computer.

[0053] Optionally, in one embodiment of the present application, before inputting the strain signal into a pre-trained life prediction model, it also includes: calculating the fatigue damage value of the rim based on the training strain signal, and determining the first remaining life of the rim based on the training strain signal; calculating the second remaining life of the rim using the fatigue damage value; training the initial model based on at least one of the training strain signal, the first remaining life and the second remaining life to train the life prediction model.

[0054] In some embodiments, the embodiments of the present application may calculate the fatigue damage value of the rim based on the training strain signal, and calculate the remaining second remaining life by accumulating the fatigue damage value.

[0055] In some embodiments, the present application may determine a first remaining life of the rim based on the training strain signal.

[0056] In some embodiments, the embodiments of the present application can train an initial model through the first remaining life and the second remaining life, and then train a life prediction model.

[0057] For example, the embodiment of the present application can calculate the fatigue damage value of the rim by training the strain signal, count the cumulative damage, calculate the second remaining life, and return the second remaining life to the central controller, display it on the vehicle computer, and remind the driver to pay attention.

[0058] Furthermore, the embodiment of the present application can control the time for the server to calculate the results and the capacity of the storage medium, and automatically update the second remaining life.

[0059] Optionally, in one embodiment of the present application, the fatigue damage value of the rim is calculated based on the training strain signal, including: determining the elastic strain value of the rim elastic strain and the plastic strain value of the rim plastic strain based on the training strain signal; obtaining the fatigue coefficient corresponding to the rim and the elastic modulus of the material used for the rim; and calculating the fatigue damage value based on at least one of the elastic strain value, the plastic strain value, the fatigue coefficient and the elastic modulus.

[0060] As a possible implementation method, the embodiment of the present application can determine the elastic strain value of the rim elastic strain and the plastic strain value of the rim plastic strain based on the training strain signal, and calculate the fatigue damage value in combination with the corresponding fatigue coefficient and the elastic modulus of the material used in the rim.

[0061] For example, embodiments of the present application can locate and number the positions of different strain sensors, count and store the strain signals of each sensor by channel, and calculate the cycle life in terms of inverse numbers by embedding strain-life material curves of different wheel materials in the server. The expression for the strain-life material curve can be, but is not limited to,:

[0062]

[0063] Among them, ε a is the total strain, is the elastic strain, is the plastic strain, ε f ′ is the fatigue ductility coefficient, σ f ′is the fatigue strength coefficient, b is the fatigue strength index, c is the fatigue ductility index, 2N f is the cycle life in terms of reversal number, and E is the elastic modulus of the material.

[0064] Furthermore, the embodiment of the present application can calculate the total strain ε based on the cycle life in terms of reverse number. a Fatigue damage value D caused to the wheel rim i , its expression can be but not limited to:

[0065]

[0066] Then the second remaining life is calculated, and its expression can be but not limited to:

[0067]

[0068] Among them, N f Indicates half of the cycle life in reverse numbers, D i represents the damage caused by the i-th effective strain, represents the second remaining life of the rim, i represents the number of times the i-th effective strain signal is input, and n represents the total number of effective strains.

[0069] Optionally, in one embodiment of the present application, an initial model is trained based on at least one of the training strain signal, the first remaining life, and the second remaining life to train a life prediction model, including: determining at least one of the architecture information, number of layers information, loss function information, and training information of the life prediction model based on the training strain signal; constructing a life prediction model based on at least one of the architecture information, number of layers information, loss function information, and training information; detecting whether the life prediction model meets preset conditions based on the first remaining life and the second remaining life; and if the life prediction model does not meet the preset conditions, adjusting the life prediction model until the life prediction model meets the preset conditions to obtain a final life prediction model.

[0070] As one possible implementation, embodiments of the present application can determine at least one of the life prediction model's architecture information, number of layers, loss function information, and training information based on the training strain signal, thereby constructing a life prediction model. Based on the first remaining life and the second remaining life, the life prediction model can be tested to see if it meets certain conditions. If the life prediction model does not meet the certain conditions, the life prediction model can be adjusted until it meets the certain conditions. The certain conditions can be set by those skilled in the art based on actual circumstances and are not specifically limited in this application.

[0071] For example, the embodiment of the present application predicts the remaining life of the rim based on the strain signal with long time series, high dynamic characteristics, and strong nonlinear characteristics, and determines the corresponding deep learning model framework, the number of layers and the type of each layer, the number of neurons in each layer, the connection method between layers, the form of the training error function, the learning rate, the number of batches and other parameters. This application does not impose specific restrictions.

[0072] Furthermore, the embodiments of the present application can select life prediction models that meet certain conditions by repeatedly training, testing and verifying each deep learning model. In each deep learning model framework, the convolutional deep learning neural network (such as including convolution layers and pooling layers, etc., which are not specifically limited in this application) can obtain global information of input samples at a higher training speed to ensure that the predicted life has a higher overall prediction accuracy; the long short-term memory network layer can obtain the timing delay of the strain signal and improve the accuracy of life prediction; the residual network can improve the convergence efficiency of the multi-layer deep learning model. By combining these three deep learning frameworks, a composite deep learning model is constructed, which can improve the prediction accuracy of problems with long time series, high dynamic characteristics, and strong nonlinear characteristics. Among them, the structural diagram of the deep learning model in the embodiment of the present application is as follows: Figure 2 shown.

[0073] Optionally, in one embodiment of the present application, before inputting the strain signal into a pre-trained life prediction model, it also includes: judging whether the strain signal meets a preset strain condition; if the strain signal meets the preset strain condition, determining that the wheel rim is damaged, and allowing the strain signal to be input into the pre-trained life prediction model.

[0074] In some embodiments, before inputting the strain signal into a pre-trained life prediction model, embodiments of the present application may first determine whether the strain signal satisfies certain strain conditions. If the strain signal satisfies the certain strain conditions, the rim is determined to be damaged and the strain signal is allowed to be input into the pre-trained life prediction model. Otherwise, if the rim is not damaged, the strain signal may not be input into the pre-trained life prediction model. The certain strain conditions can be set by those skilled in the art based on actual circumstances and are not specifically limited in this application.

[0075] For example, in an embodiment of the present application, strain signal A is greater than the target threshold and satisfies certain strain conditions, while strain signal B is less than the target threshold and does not satisfy certain strain conditions. Therefore, in an embodiment of the present application, strain signal A may be input into a pre-trained life prediction model, but strain signal B may not be input into the pre-trained life prediction model.

[0076] In step S202 , the strain signal is input into a pre-trained life prediction model to output the actual remaining life of the rim.

[0077] In some embodiments, the present application may input the strain signal into a pre-trained life prediction model to output the actual remaining life of the rim.

[0078] For example, the embodiment of the present application can Figure 3 The deep learning model shown is used as a pre-trained life prediction model, and the strain signal is input into the pre-trained life prediction model to obtain the actual remaining life of the rim.

[0079] The embodiment of the present application can calculate the actual remaining life from the strain signal at the wheel rim through a deep learning model, and then quickly calculate the fatigue damage based on the strain signal, and feed back and output the remaining life.

[0080] In step S203, when the actual remaining life is less than or equal to the preset threshold, the control server issues a life warning.

[0081] As a possible implementation method, the embodiment of the present application can issue a lifespan warning when the actual remaining lifespan is less than or equal to a certain threshold. The certain threshold can be set by those skilled in the art based on actual conditions and is not specifically limited by this application.

[0082] In addition, it should be noted that, in the embodiment of the present application, the life warning can be divided into green warning, yellow warning, blue warning and red warning according to the actual remaining life.

[0083] Among them, the embodiment of the present application can perform routine inspections through green warnings; shorten the inspection cycle through yellow warnings; perform planned maintenance through blue warnings; and perform shutdown inspections through red warnings.

[0084] The working principle of the wheel life warning method proposed in the embodiments of the present application is introduced below in combination with multiple embodiments.

[0085] Example 1:

[0086] Specifically, Figure 4 The flowchart is a working principle of the wheel life early warning method provided according to one embodiment of the present application.

[0087] Step S401: collecting rim strain signals.

[0088] Step S402: Receive a strain signal.

[0089] Step S403: transmitting a strain signal.

[0090] Step S404: determining whether the strain signal satisfies certain strain conditions.

[0091] If the conditions are met, execute step 405; otherwise, execute step S401.

[0092] Step S405: inputting the strain signal into a pre-trained life prediction model.

[0093] Among them, the embodiment of the present application can output the actual remaining life of the rim through a pre-trained life prediction model.

[0094] Step S406: Perform life warning.

[0095] Among them, the embodiment of the present application can issue a life warning when the actual remaining life is less than or equal to a certain threshold.

[0096] The embodiment of the present application can output the corresponding actual remaining life based on the collected strain signal and use a pre-trained life prediction model to provide a life warning.

[0097] Example 2:

[0098] Specifically, Figure 5 The figure is a flow chart of the working principle of wheel life warning provided according to one embodiment of the present application.

[0099] Step S501: Wheel.

[0100] Step S502: collecting strain signals.

[0101] Step S503: Transmit the strain signal to the central controller.

[0102] Step S504: Transmit the strain signal to the server.

[0103] In an embodiment of the present application, a pre-trained life prediction model is stored on the server, and the actual remaining life of the rim is predicted based on the strain signal.

[0104] Step S505: Transmit the actual remaining life to the vehicle system.

[0105] Among them, the embodiment of the present application can use a strain sensor to collect the strain signal of the inner rim of the wheel in real time, and transmit the strain signal to the central controller and server, and then calculate the actual remaining life and transmit it to the vehicle system.

[0106] According to the wheel life warning method proposed in the embodiment of the present application, the strain signal of the wheel rim received from the server can be input into a pre-trained life prediction model, thereby outputting the actual remaining life of the wheel rim. When the actual remaining life is less than or equal to a certain threshold, the server is controlled to issue a life warning. This can accurately calculate the actual remaining life of the wheel before the rim cracks and the tire leaks, thereby promptly identifying potential risks and alerting the driver to avoid serious traffic accidents. This solves the problem in the related art that wheel turning and repair related data and electrical equipment asset management systems cannot completely prevent the rim from cracking due to severe damage caused by misuse, resulting in low vehicle safety performance and the susceptibility to safety accidents.

[0107] Next, the wheel life warning device proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0108] Figure 6 This is a block diagram of a wheel life warning device provided according to an embodiment of the present application.

[0109] like Figure 6 As shown, the wheel life warning device 20 includes: a receiving module 100 , an output module 200 and a control module 300 .

[0110] The receiving module 100 is used to receive the strain signal of the inner rim of the wheel from the server.

[0111] The output module 200 is used to input the strain signal into a pre-trained life prediction model to output the actual remaining life of the rim.

[0112] The control module 300 is used to control the server to issue a life warning when the actual remaining life is less than or equal to a preset threshold.

[0113] Optionally, in one embodiment of the present application, it further includes: a first calculation module, a second calculation module and a training module.

[0114] Among them, the first calculation module is used to calculate the fatigue damage value of the rim based on the training strain signal before inputting the strain signal into the pre-trained life prediction model, and determine the first remaining life of the rim based on the training strain signal.

[0115] The second calculation module is used to calculate the second remaining life of the rim using the fatigue damage value.

[0116] The training module is used to train an initial model based on at least one of the training strain signal, the first remaining life and the second remaining life, so as to train a life prediction model.

[0117] Optionally, in one embodiment of the present application, the training module includes: a first determination unit, a construction unit, a detection unit and a generation unit.

[0118] The first determination unit is used to determine at least one of the architecture information, layer number information, loss function information and training information of the life prediction model based on the training strain signal.

[0119] A construction unit is used to construct a life prediction model based on at least one of architecture information, number of layers information, loss function information and training information.

[0120] The detection unit is used to detect whether the life prediction model meets a preset condition based on the first remaining life and the second remaining life.

[0121] The generation unit is used to adjust the life prediction model when the life prediction model does not meet the preset conditions until the life prediction model meets the preset conditions to obtain the final life prediction model.

[0122] Optionally, in one embodiment of the present application, the first calculation module includes: a second determination unit, an acquisition unit and a calculation unit.

[0123] The second determining unit is configured to determine an elastic strain value of the rim elastic strain and a plastic strain value of the rim plastic strain based on the training strain signal.

[0124] The acquisition unit is used to obtain the fatigue coefficient corresponding to the rim and the elastic modulus of the material used for the rim.

[0125] The calculation unit is used to calculate the fatigue damage value based on at least one of the elastic strain value, the plastic strain value, the fatigue coefficient and the elastic modulus.

[0126] Optionally, in one embodiment of the present application, it further includes: a judgment module and a determination module.

[0127] The judgment module is used to judge whether the strain signal meets the preset strain condition before inputting the strain signal into the pre-trained life prediction model.

[0128] The determination module is used to determine whether the wheel rim is damaged when the strain signal meets the preset strain condition, and allows the strain signal to be input into a pre-trained life prediction model.

[0129] It should be noted that the above explanations of the embodiment of the wheel life warning method are also applicable to the wheel life warning device of this embodiment, and will not be repeated here.

[0130] According to the wheel life warning device proposed in the embodiment of the present application, the strain signal of the wheel rim received from the server can be input into a pre-trained life prediction model, thereby outputting the actual remaining life of the wheel rim. When the actual remaining life is less than or equal to a certain threshold, the server is controlled to issue a life warning. This can accurately calculate the actual remaining life of the wheel before the wheel rim cracks and the tire leaks, thereby promptly identifying potential risks and alerting the driver to avoid serious traffic accidents. This solves the problem in the related art that wheel turning and repair related data and electrical equipment asset management systems cannot completely prevent the wheel rim from cracking due to severe damage under misuse conditions, resulting in low vehicle safety performance and the susceptibility to safety accidents.

[0131] Figure 7 This is a schematic diagram of the structure of a server provided according to an embodiment of the present application. The server may include:

[0132] Memory 701 , processor 702 , and computer programs stored in the memory 701 and executable on the processor 702 .

[0133] When the processor 702 executes the program, the early warning method for the wheel life provided in the above embodiment is implemented.

[0134] Furthermore, the server further includes:

[0135] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0136] The memory 701 is used to store computer programs that can be run on the processor 702 .

[0137] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0138] If the memory 701, processor 702, and communication interface 703 are implemented independently, the communication interface 703, memory 701, and processor 702 can be interconnected via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 7Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0139] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0140] The processor 702 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0141] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned wheel life warning method.

[0142] An embodiment of the present application further provides a computer program product, including a computer program, which implements the above wheel life warning method when executed.

[0143] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", 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 application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0144] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0145] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0146] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Additionally, 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 by optically scanning the paper or other medium and then editing, interpreting, or otherwise processing in a suitable manner as necessary, and then storing it in a computer memory.

[0147] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, it can be implemented using any one or a combination of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0148] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above-mentioned embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0149] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a 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.

[0150] 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 application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A wheel life early warning method, characterized in that: Applied to the server, the method comprises the following steps: receiving a strain signal from the server from the inner rim of the wheel; Inputting the strain signal into a pre-trained life prediction model to output the actual remaining life of the rim; When the actual remaining lifespan is less than or equal to a preset threshold, the server is controlled to issue a lifespan warning.

2. The method according to claim 1, characterized in that Before inputting the strain signal into the pre-trained life prediction model, the method further includes: calculating a fatigue damage value of the wheel rim based on a training strain signal, and determining a first remaining life of the wheel rim based on the training strain signal; calculating a second remaining life of the wheel rim using the fatigue damage value; An initial model is trained based on at least one of the training strain signal, the first remaining life, and the second remaining life to train the life prediction model.

3. The method according to claim 2, characterized in that The step of training an initial model based on at least one of the training strain signal, the first remaining life, and the second remaining life to train the life prediction model includes: determining at least one of architecture information, number of layers information, loss function information, and training information of the life prediction model based on the training strain signal; constructing the lifespan prediction model based on at least one of the architecture information, the number of layers information, the loss function information, and the training information; Based on the first remaining life and the second remaining life, detecting whether the life prediction model meets a preset condition; In the case that the life prediction model does not meet the preset conditions, the life prediction model is adjusted until the life prediction model meets the preset conditions, thereby obtaining the final life prediction model.

4. The method according to claim 2, characterized in that The calculating the fatigue damage value of the wheel rim based on the training strain signal includes: determining an elastic strain value of the wheel rim elastic strain and a plastic strain value of the wheel rim plastic strain based on the training strain signal; Obtaining a fatigue coefficient corresponding to the wheel rim and an elastic modulus of a material used for the wheel rim; The fatigue damage value is calculated based on at least one of the elastic strain value, the plastic strain value, the fatigue coefficient, and the elastic modulus.

5. The method according to claim 1, wherein Before inputting the strain signal into the pre-trained life prediction model, the method further includes: Determining whether the strain signal meets a preset strain condition; If the strain signal satisfies the preset strain condition, it is determined that the wheel rim is damaged, and the strain signal is allowed to be input into a pre-trained life prediction model.

6. A wheel life warning device, characterized in that: Applied to a server, the device includes: A receiving module, configured to receive a strain signal from an inner wheel rim of a wheel from a server; an output module, configured to input the strain signal into a pre-trained life prediction model to output the actual remaining life of the rim; The control module is used to control the server to issue a life warning when the actual remaining life is less than or equal to a preset threshold.

7. The device according to claim 6, characterized in that Also includes: a first calculation module, configured to calculate a fatigue damage value of the rim based on a training strain signal before inputting the strain signal into a pre-trained life prediction model, and determine a first remaining life of the rim based on the training strain signal; a second calculation module, configured to calculate a second remaining life of the wheel rim using the fatigue damage value; A training module is used to train an initial model based on the training strain signal, at least one of the first remaining life and the second remaining life, so as to train the life prediction model.

8. A server, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the wheel life warning method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the wheel life warning method according to any one of claims 1 to 5.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed, is used to implement the early warning method for wheel life according to any one of claims 1 to 5.

Images