Vehicle chassis remaining service life prediction method, vehicle, electronic equipment, storage medium and program product

Abstract

The invention discloses a vehicle chassis remaining service life prediction method, a vehicle, electronic equipment, a storage medium and a program product, and belongs to the technical field of computers. The method comprises the steps that chassis operation data of a target vehicle are acquired and cached; inputting the chassis operation data into a trained chassis health state prediction model to obtain a predicted remaining service life output by the chassis health state prediction model; wherein the chassis health state prediction model is trained by the following steps: acquiring first chassis operation data based on a whole vehicle fatigue endurance test, and acquiring second chassis operation data based on multi-body dynamics simulation analysis; constructing a target training database based on the first chassis operation data and the second chassis operation data; and training the target prediction model based on the target training database to obtain a chassis health state prediction model. According to the method for predicting the remaining service life of the vehicle chassis disclosed by the invention, the real-time performance and intelligence of the calculation of the remaining service life of the vehicle chassis are improved.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and in particular relates to a method for predicting the remaining useful life of a vehicle chassis, a vehicle, an electronic device, a storage medium, and a program product. Background Art

[0002] Monitoring and evaluating the health of a vehicle's chassis is a core element of a smart car's safety system, and its importance is self-evident. The durability of chassis components directly determines the reliability of the vehicle throughout its lifecycle. Typically, multi-body dynamics simulation technology is used to calculate the remaining useful life of various chassis components.

[0003] However, traditional offline simulation technology calculations have a certain lag, which makes it difficult to meet the real-time and intelligent requirements of vehicle chassis health detection. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art. To this end, this application proposes a vehicle chassis remaining useful life prediction method, vehicle, electronic device, storage medium, and program product to improve the real-time and intelligent calculation of the vehicle chassis remaining useful life.

[0005] In a first aspect, the present application provides a method for predicting the remaining useful life of a vehicle chassis, the method comprising:

[0006] Acquiring chassis operating data of a target vehicle and caching the chassis operating data; the chassis operating data includes at least one of acceleration, vibration, temperature, and load of a target component in the chassis of the target vehicle itself, where the number of the target component is at least one;

[0007] The chassis operation data is input into the trained chassis health status prediction model to obtain the predicted remaining service life of the target component output by the chassis health status prediction model. The chassis health status prediction model is trained in the following way:

[0008] Obtaining first chassis operation data based on a vehicle fatigue endurance test, and obtaining second chassis operation data based on a multi-body dynamics simulation analysis;

[0009] Building a target training database based on the first chassis operation data and the second chassis operation data;

[0010] Based on the target training database, the target prediction model is trained to obtain the chassis health status prediction model.

[0011] According to the vehicle chassis remaining service life prediction method of the present application, the predicted remaining service life of the target component output by the chassis health status prediction model is obtained based on the chassis operation data of the target vehicle through a trained chassis health status prediction model, and the chassis health status prediction model is obtained by obtaining first chassis operation data based on a whole vehicle fatigue endurance test and second chassis operation data based on a multi-body dynamics simulation analysis; a target training database is constructed based on the first chassis operation data and the second chassis operation data; and a target prediction model is trained and obtained based on the target training database, and the predicted remaining service life of the target component is obtained through the chassis health status prediction model to improve the real-time and intelligent detection of the health status of the target vehicle's own chassis.

[0012] According to one embodiment of the present application, obtaining chassis operation data of a target vehicle and caching the chassis operation data include:

[0013] When the target vehicle is in a first load scenario, obtaining chassis operation data of the target vehicle based on a first sampling method;

[0014] or

[0015] When the target vehicle is in the second load scenario, chassis operation data of the target vehicle is acquired based on the second sampling method.

[0016] According to one embodiment of the present application, obtaining chassis operation data of a target vehicle and caching the chassis operation data include:

[0017] Get the cache space occupancy ratio;

[0018] When the cache space occupancy ratio is greater than or equal to the preset occupancy ratio, the target historical chassis operation data in the cache space is cleared based on a first-in-first-out mechanism, and the chassis operation data is cached in the cache space.

[0019] According to one embodiment of the present application, constructing a target training database based on the first chassis operation data and the second chassis operation data includes:

[0020] Based on the second chassis operating data, target damage data is obtained based on finite element transient analysis;

[0021] A target training database is constructed based on the first chassis operation data and the target damage data.

[0022] According to one embodiment of the present application, after inputting chassis operating data into a trained chassis health prediction model to obtain a predicted remaining service life output by the chassis health prediction model, the method includes:

[0023] Obtaining driving change data, maintenance data, and actual remaining service life and predicted remaining service life of target components of the target vehicle;

[0024] The chassis health status prediction model is optimized and updated based on driving change data, maintenance data, and the actual and predicted remaining service life of target components.

[0025] According to one embodiment of the present application, a chassis health status prediction model is optimized and updated based on driving change data, maintenance data, and the actual remaining service life and predicted remaining service life of the target component, including:

[0026] Determine whether the target component is damaged based on maintenance data and predicted remaining service life;

[0027] In the event of damage to a target component, determining whether the target vehicle has encountered an extreme driving scenario based on driving change data;

[0028] When the target vehicle does not encounter extreme driving scenarios, the chassis health status prediction model is optimized and updated based on the predicted remaining service life and the actual remaining service life.

[0029] According to one embodiment of the present application, the chassis health status prediction model is optimized and updated based on the predicted remaining service life and the actual remaining service life, including:

[0030] When the difference between the predicted remaining service life and the actual remaining service life is greater than the target difference, the structural parameters of the chassis health status prediction model are adjusted to optimize and update the chassis health status prediction model; the structural parameters include the number of input and output time delays, the number of perception layers, and the number of nodes in each perception layer.

[0031] According to one embodiment of the present application, after inputting chassis operating data into a trained chassis health prediction model to obtain a predicted remaining service life output by the chassis health prediction model, the method includes:

[0032] Based on the predicted remaining service life of each target component, the target component and the health status information corresponding to the target component are rendered and displayed.

[0033] According to one embodiment of the present application, based on the predicted remaining service life corresponding to each target component, rendering and displaying the target component and the health status information corresponding to the target component includes:

[0034] When the predicted remaining service life of the target component is greater than or equal to a first health threshold, the target vehicle renders the target component based on the first identifier and displays the health information status of the target component based on a first drawing mode;

[0035] or

[0036] When the predicted remaining useful life of the target component is less than a first health threshold and greater than or equal to a second health threshold, the target vehicle renders the target component based on the first identifier and displays the health information status of the target component based on the second drawing mode; the second health threshold is less than the first health threshold;

[0037] or

[0038] When the predicted remaining service life of the target component is less than the second health threshold and greater than or equal to the third health threshold, the target vehicle renders the target component based on the second identifier and displays the health information status of the target component based on the second drawing mode; the third health threshold is less than the second health threshold;

[0039] or

[0040] When the predicted remaining service life of the target component is less than a third health threshold, the target vehicle renders the target component based on the third identifier and displays the health information status of the target component based on the second drawing mode.

[0041] In a second aspect, the present application provides a vehicle, which is used to execute the steps of the vehicle chassis remaining service life prediction method as described in the first aspect.

[0042] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for predicting the remaining useful life of a vehicle chassis as described in the first aspect above are implemented.

[0043] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for predicting the remaining useful life of a vehicle chassis as described in the first aspect above.

[0044] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for predicting the remaining useful life of a vehicle chassis as described in the first aspect above.

[0045] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0047] Figure 1This is one of the flow charts of the method for predicting the remaining useful life of a vehicle chassis provided in an embodiment of the present application;

[0048] Figure 2 Schematic diagram of the training process of the chassis health status prediction model provided in the embodiment of the present application;

[0049] Figure 3 Schematic diagram of the target prediction model provided in the embodiment of the present application;

[0050] Figure 4 This is the second flow chart of the method for predicting the remaining useful life of a vehicle chassis provided in an embodiment of the present application;

[0051] Figure 5 This is the third flow chart of the method for predicting the remaining useful life of a vehicle chassis provided in an embodiment of the present application;

[0052] Figure 6 This is a schematic diagram of the process of obtaining and caching chassis operation data provided by an embodiment of the present application;

[0053] Figure 7 This is a schematic diagram of the process of updating the chassis health status prediction model provided by an embodiment of the present application;

[0054] Figure 8 This is a schematic diagram of the process of rendering and displaying a target component provided by an embodiment of the present application;

[0055] Figure 9 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0057] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0058] Below, in conjunction with the accompanying drawings, the vehicle chassis remaining useful life prediction method, vehicle, electronic device, storage medium and program product provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0059] The vehicle chassis remaining useful life prediction method may be applied to a terminal, and may be specifically executed by hardware or software in the terminal.

[0060] The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet computer having a touch-sensitive surface (e.g., a touch screen display and / or a touch pad). It should also be understood that, in some embodiments, the terminal may not be a portable communication device, but a desktop computer having a touch-sensitive surface (e.g., a touch screen display and / or a touch pad).

[0061] In the following embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse, and a joystick.

[0062] The embodiment of the present application provides a method for predicting the remaining useful life of a vehicle chassis. The execution subject of the method can be an electronic device or a functional module or functional entity in the electronic device that can implement the method for predicting the remaining useful life of a vehicle chassis. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras and wearable devices, etc. The method for predicting the remaining useful life of a vehicle chassis provided in the embodiment of the present application is explained below using an electronic device as an example of the execution subject.

[0063] The present application embodiment provides a method for predicting the remaining useful life of a vehicle chassis. Figure 1 As shown, the method for predicting the remaining useful life of a vehicle chassis includes: step 110 and step 120.

[0064] Step 110: Acquire chassis operation data of the target vehicle and cache the chassis operation data; the chassis operation data includes at least one of acceleration, vibration, temperature and load of target components in the chassis of the target vehicle itself, and the number of target components is at least one.

[0065] In some embodiments, the target vehicle can obtain chassis operating data of its own chassis. In some embodiments, the target vehicle can obtain chassis operating data based on various sensors installed on its own chassis. For example, the target vehicle can obtain acceleration, vibration, temperature, and load light data of various target components in its own chassis based on speed sensors, vibration sensors, temperature sensors, and pressure sensors installed on its own chassis.

[0066] In actual implementation, the target component may be a mechanical component installed in the chassis of the target vehicle, such as an upper wishbone, a lower wishbone, or any other theoretically feasible mechanical component.

[0067] In some embodiments, the target vehicle may obtain chassis operation data of its own chassis based on the driving status of the vehicle.

[0068] In some embodiments, the chassis operation data of the target vehicle can be obtained by the server. In some embodiments, after the target vehicle obtains the chassis operation data of its own chassis, the target vehicle can upload the chassis operation data to the server.

[0069] In actual implementation, the server can be a cloud server or any theoretically feasible server, and this application does not impose any specific restrictions on this.

[0070] In some embodiments, the target vehicle may cache the acquired chassis operation data in its own cache space.

[0071] In actual implementation, the cache space of the target vehicle can be located in the memory space of the target vehicle, or in any built-in storage space or external storage space of the target vehicle. This application does not impose any specific restrictions on this.

[0072] Step 120: Input the chassis operation data into the trained chassis health status prediction model to obtain the predicted remaining service life of the target component output by the chassis health status prediction model.

[0073] In some embodiments, before the chassis operation data is input into the trained chassis health status prediction model, the chassis operation data may be filtered, denoised, and feature extracted to ensure data quality.

[0074] In some embodiments, the chassis health status prediction model may be trained by a server and downloaded to the target vehicle.

[0075] In some embodiments, the chassis health status prediction model may be used to obtain a predicted remaining useful life of a target component based on at least one of acceleration, vibration, temperature, and load of the target component.

[0076] In some embodiments, the chassis health status prediction model may predict the damage condition of a target component based on chassis operation data, and obtain a predicted remaining service life of the target component based on the damage condition of the target component.

[0077] In some embodiments, as Figure 2 As shown in Figure 2, the chassis health status prediction model is trained as follows:

[0078] Step 210: Acquire first chassis operation data based on the vehicle fatigue endurance test, and acquire second chassis operation data based on multi-body dynamics simulation analysis.

[0079] In practice, the vehicle fatigue endurance test can be conducted in a laboratory or on an actual road environment, simulating the vehicle's operating state under various road conditions (e.g., steep slopes, potholes, bumps, turns, etc.) to collect first chassis operating data. The first chassis operating data can include data on the forces, vibrations, and deformations of various chassis components.

[0080] In some embodiments, the multi-body dynamics simulation analysis may be a process of simulating the dynamic response of a vehicle under complex road conditions using multi-body dynamics simulation technology to obtain the second chassis operation data. The second chassis operation data may include force distribution data of the vehicle chassis.

[0081] Step 220: Construct a target training database based on the first chassis operation data and the second chassis operation data.

[0082] In actual implementation, the target training database may be a database required for training and generating a chassis health status prediction model.

[0083] In some embodiments, damage analysis may be performed based on the second chassis operation data, and the obtained damage analysis results may be integrated with the first chassis operation data to construct a target training database.

[0084] Step 230: Based on the target training database, the target prediction model is trained to obtain a chassis health status prediction model.

[0085] In actual implementation, the target prediction model may be a nonlinear autoregressive outer integral (NLARX) model or any theoretically feasible model, and this application does not impose any specific restrictions on this.

[0086] In some embodiments, a target prediction model can be trained based on a target training database in combination with a machine learning algorithm to obtain a chassis health status prediction model. The chassis health status prediction model can be used to predict damage and evaluate the remaining service life of target components in the chassis of a target vehicle.

[0087] In some embodiments, after the chassis operation data is input into a trained chassis health status prediction model and the predicted remaining service life is obtained as output by the chassis health status prediction model, the actual remaining service life and the predicted remaining service life of the target component can be obtained, and the chassis health status prediction model can be optimized and updated based on the actual remaining service life and the predicted remaining service life of the target component.

[0088] In some embodiments, after the chassis operation data is input into a trained chassis health status prediction model and the predicted remaining service life output by the chassis health status prediction model is obtained, the chassis of the target vehicle can be rendered and displayed based on the predicted remaining service life corresponding to each target component.

[0089] According to the vehicle chassis remaining service life prediction method of the embodiment of the present application, the predicted remaining service life of the target component output by the chassis health status prediction model is obtained based on the chassis operation data of the target vehicle through a trained chassis health status prediction model, and the chassis health status prediction model is obtained by obtaining first chassis operation data based on a whole vehicle fatigue endurance test and second chassis operation data based on a multi-body dynamics simulation analysis; a target training database is constructed based on the first chassis operation data and the second chassis operation data; and a target prediction model is trained and obtained based on the target training database, and the predicted remaining service life of the target component is obtained through the chassis health status prediction model to improve the real-time and intelligent detection of the health status of the target vehicle's own chassis.

[0090] In some embodiments, when the target vehicle is in a first load scenario, the chassis operation data of the target vehicle can be obtained based on a first sampling method; or, when the target vehicle is in a second load scenario, the chassis operation data of the target vehicle can be obtained based on a second sampling method.

[0091] In actual implementation, the first load scenario may be a high-load scenario such as a vehicle traveling at high speed, emergency braking, or frequent steering, etc. The second load scenario may be a low-load scenario such as a vehicle traveling at low speed, idling, or parking, etc.

[0092] In actual implementation, the first sampling method may be a sampling method for acquiring data collected by all sensors in the chassis of the target vehicle. The second sampling method may be a sampling method for acquiring data collected by some of all sensors in the chassis of the target vehicle, or a sampling method for acquiring some of the data collected by all sensors in the chassis of the target vehicle.

[0093] In some embodiments, chassis operation data of the target vehicle may be acquired based on a first sampling method at a first sampling frequency when the target vehicle is in a first load scenario. For example, the first sampling frequency may be greater than 1 kHz.

[0094] In some embodiments, when the target vehicle is in a second load scenario, chassis operation data of the target vehicle may be acquired at a second sampling frequency and based on a second sampling method. For example, the second sampling frequency may be less than 1 kHz.

[0095] According to the vehicle chassis remaining service life prediction method of the embodiment of the present application, the predicted remaining service life of the target component output by the chassis health status prediction model is obtained based on the chassis operation data of the target vehicle through the trained chassis health status prediction model, and when the target vehicle is in a first load scenario, the chassis operation data of the target vehicle is obtained based on a first sampling method; when the target vehicle is in a second load scenario, the chassis operation data of the target vehicle is obtained based on a second sampling method, thereby reducing the energy consumption generated in the process of obtaining the chassis operation data of the target vehicle while ensuring that the vehicle power protection mechanism is not triggered.

[0096] In some embodiments, the cache space occupancy ratio can be obtained; when the cache space occupancy ratio is greater than or equal to the preset occupancy ratio, based on the first-in-first-out mechanism, the target historical chassis operation data in the cache space is cleared and the chassis operation data is cached to the cache space.

[0097] In actual implementation, the preset occupancy ratio may be a set value. For example, the preset occupancy ratio may be adjusted based on actual storage usage of the target vehicle.

[0098] In some embodiments, when the cache space occupancy ratio is greater than or equal to a preset occupancy ratio, a first-in, first-out (FIFO) mechanism may be triggered to clear the target historical chassis operation data in the cache space. For example, when the cache space occupancy ratio is greater than or equal to 80%, the target historical chassis operation data in the cache space may be cleared based on the FIFO mechanism.

[0099] In actual execution, the target historical chassis operation data may be the historical chassis operation data stored in the cache space and stored in the cache space earliest.

[0100] In some embodiments, when the cache space occupancy ratio is less than a preset occupancy ratio, the chassis operation data may be cached normally in the cache space.

[0101] According to the vehicle chassis remaining service life prediction method of an embodiment of the present application, a trained chassis health status prediction model is used to obtain the predicted remaining service life of the target component output by the chassis health status prediction model based on the chassis operation data of the target vehicle. In the case where the cache space occupancy ratio is greater than or equal to the preset occupancy ratio, based on the first-in-first-out mechanism, the target historical chassis operation data in the cache space is cleared, and the chassis operation data is cached to the cache space to reduce the cache pressure of the target vehicle.

[0102] In some embodiments, target damage data may be acquired based on finite element transient analysis for the second chassis operation data; and a target training database may be constructed based on the first chassis operation data and the target damage data.

[0103] In actual implementation, the finite element transient analysis is used to perform transient dynamic analysis of the chassis structure of the target vehicle using the finite element method. Based on the second chassis operation data, target damage data is calculated. The target damage data may include damage conditions of target components of the target vehicle chassis under different stress conditions.

[0104] According to the vehicle chassis remaining service life prediction method of the embodiment of the present application, the predicted remaining service life of the target component output by the chassis health status prediction model is obtained based on the chassis operation data of the target vehicle through a trained chassis health status prediction model, and the chassis health status prediction model is obtained by obtaining first chassis operation data based on a whole vehicle fatigue endurance test, and second chassis operation data based on multi-body dynamics simulation analysis; for the second chassis operation data, target damage data is obtained based on finite element transient analysis; a target training database is constructed based on the first chassis operation data and the target damage data; and the target prediction model is trained and obtained based on the target training database, and the predicted remaining service life of the target component is obtained through the chassis health status prediction model to improve the real-time and intelligent detection of the health status of the target vehicle's own chassis.

[0105] In some embodiments, after the chassis operation data is input into a trained chassis health status prediction model and the predicted remaining service life is obtained as output by the chassis health status prediction model, the driving change data, maintenance data and the actual remaining service life and predicted remaining service life of the target vehicle can be obtained; based on the driving change data, maintenance data and the actual remaining service life and predicted remaining service life of the target component, the chassis health status prediction model is optimized and updated.

[0106] In actual implementation, driving change data can include bus data such as the target vehicle's longitudinal acceleration and steering angle during driving. Maintenance data can include fault information and repair information recorded during after-sales maintenance. The actual remaining service life can be the remaining service life of the target component obtained by various sensors installed on the target vehicle chassis.

[0107] In some embodiments, the driving change data may be acquired through an electronic stability control system (ESC) of the target vehicle.

[0108] In some embodiments, priority may be given to determining whether a target component of the target vehicle's chassis is damaged and whether the target vehicle has encountered an extreme driving scenario. If the target component of the target vehicle's chassis is not damaged and the target vehicle has not encountered an extreme driving scenario, the chassis health status prediction model is determined to be inaccurate, triggering an optimization update of the chassis health status prediction model.

[0109] In some embodiments, the server can obtain target operating data of at least one target vehicle, where the target operating data includes driving change data, maintenance data, and the actual remaining service life and predicted remaining service life of target components of each target vehicle, and perform federated learning based on the target operating data of at least one target vehicle to optimize and update the chassis health status prediction model.

[0110] In some embodiments, the server may include an aggregator. Each of the at least one target vehicle may encrypt and send target operating data to the aggregator. The aggregator decrypts the encrypted target operating data sent by each target vehicle using a decryption technology, and then performs federated learning based on the target operating data of the at least one target vehicle to optimize and update the chassis health status prediction model.

[0111] In some embodiments, after the server completes the optimization and update of the chassis health status prediction model, the optimized chassis health status prediction model can be downloaded and updated to the target vehicle through wireless communication technology (OTA), ensuring that the target vehicle always uses the latest and most accurate chassis health status prediction model.

[0112] According to the vehicle chassis remaining service life prediction method of the embodiment of the present application, through the trained chassis health status prediction model, based on the chassis operation data of the target vehicle, the predicted remaining service life of the target component output by the chassis health status prediction model is obtained, and the driving change data, maintenance data and the actual remaining service life and predicted remaining service life of the target component of the target vehicle can be obtained; based on the driving change data, maintenance data and the actual remaining service life and predicted remaining service life of the target component, the chassis health status prediction model is optimized and updated, so as to optimize and update the chassis health status prediction model using the actual remaining service life and predicted remaining service life, thereby improving the prediction accuracy and adaptability of the chassis health status prediction model.

[0113] In some embodiments, whether the target component is damaged is determined based on maintenance data and predicted remaining service life; if the target component is damaged, whether the target vehicle encounters an extreme driving scenario is determined based on driving change data; if the target vehicle does not encounter an extreme driving scenario, the chassis health status prediction model is optimized and updated based on the predicted remaining service life and the actual remaining service life.

[0114] In some embodiments, if a sensor mounted on the target vehicle's chassis is damaged, the chassis operating data input into the chassis health prediction model will be erroneous, resulting in inaccurate predictions. However, this inaccuracy is not caused by the chassis health prediction model itself. To eliminate the possibility that a damaged sensor mounted on the target vehicle's chassis could interfere with the accuracy of the chassis health prediction model's predictions, damage to the target component can be determined based on maintenance data and the predicted remaining useful life.

[0115] In some embodiments, if both the maintenance data and the predicted remaining useful life indicate that the target component is damaged, the target component is determined to be damaged. Conversely, if both the maintenance data and the predicted remaining useful life indicate that the target component is not damaged, the sensor mounted on the chassis of the target vehicle is determined to be damaged, while the target component is not damaged.

[0116] In some embodiments, if the target vehicle encounters an extreme driving scenario, the chassis operating data input to the chassis health prediction model may be inaccurate, resulting in inaccurate predictions from the chassis health prediction model. However, this inaccuracy is not caused by the chassis health prediction model itself. To eliminate the possibility that extreme driving scenarios (such as curb impact, pothole impact, or icy or snowy roads) may interfere with the accuracy of the chassis health prediction model's predictions, the driving variation data may be used to determine whether the target vehicle has encountered an extreme driving scenario.

[0117] In some embodiments, it may be determined that the target vehicle encounters an extreme driving scenario when the driving change data shows a sudden change in the longitudinal acceleration or the steering angle of the target vehicle.

[0118] In some embodiments, when the target component is not damaged and the target vehicle does not encounter extreme driving scenarios, it is determined that the reason why the chassis health status prediction model's prediction results are inaccurate comes from the chassis health status prediction model itself, and the chassis health status prediction model is optimized and updated based on the predicted remaining service life and the actual remaining service life.

[0119] According to the vehicle chassis remaining service life prediction method of the embodiment of the present application, through the trained chassis health status prediction model, based on the chassis operation data of the target vehicle, the predicted remaining service life of the target component output by the chassis health status prediction model is obtained, and the driving change data, maintenance data and the actual remaining service life and predicted remaining service life of the target component of the target vehicle can be obtained; based on the driving change data, maintenance data and the actual remaining service life and predicted remaining service life of the target component, the chassis health status prediction model is optimized and updated, so as to optimize and update the chassis health status prediction model using the actual remaining service life and predicted remaining service life, thereby improving the prediction accuracy and adaptability of the chassis health status prediction model.

[0120] In some embodiments, when the difference between the predicted remaining service life and the actual remaining service life is greater than the target difference, the structural parameters of the chassis health status prediction model are adjusted to optimize and update the chassis health status prediction model; the structural parameters include the number of time delays of input and output, the number of perception layers, and the number of nodes in each perception layer.

[0121] In some embodiments, the chassis health status prediction model may be obtained by training the NLARX model.

[0122] In some embodiments, as Figure 3 As shown in Figure 1, the NLARX model consists of an input layer, an output layer, and an intermediate layer. Before the input signal and the feedback output signal enter the intermediate layer for processing, they must first pass through a time delay line (TDL) model to determine the number of time delay steps for the signal. During training, the output of the NLARX model at each time step is the result of nonlinear processing of the current input signal, the input signal for several past time steps, and the output signal through the intermediate layer. The entire data processing process can be expressed as a nonlinear function.

[0123] y(t)=F(y1(t-1),...y1(t-na1),y2(t-1),...y2(t-na2),...,y n0 (t-1),...

[0124] y n0 (t-na n0 ),μ1(t),...,μ1(t-nb1+1),μ2(t),...,μ2(t-nb2+1),...,

[0125] u ni (t),...u ni (t-nb ni +1);

[0126] Among them, μi (t) represents the value of the i-th input signal at the t-th time step, y k (t) represents the value of the kth output signal at the tth time step, no represents the number of output variables, ni represents the number of input variables, na1, na2, ..., na no represents the number of time delays for each output variable, nb1, nb2, ..., nb ni represents the number of time delays for each input variable, and F represents the transfer function between the input signal and the output result determined by the multilayer perceptron in the middle layer.

[0127] In practical engineering applications, the input and output variables of the NLARX model often have different value ranges, and this difference can have a significant impact on the model's prediction accuracy. Therefore, before using a neural network for nonlinear fitting, it is usually necessary to standardize the input and output variables to eliminate dimensional differences and improve the model's convergence speed and prediction accuracy. In addition, to avoid overfitting of the model, the sample data is usually divided into a training set and a validation set. The training set is used to optimize the model's structural parameters, while the validation set is used to evaluate the model's generalization ability. The model's predictive performance will vary depending on the structural parameters, so the core goal of the training process is to find a reasonable set of structural parameters that optimizes the model's performance on the validation set.

[0128] Key structural parameters for the NLARX model include the number of input and output time delays, the number of perception layers, and the number of nodes in each perception layer. By properly setting these parameters, the predictive performance of the NLARX model can be effectively improved, ensuring its reliability in practical applications.

[0129] In some embodiments, when the difference between the predicted remaining service life and the actual remaining service life is greater than the target difference, the structural parameters of the chassis health status prediction model can be increased, such as increasing the number of time delays of input and output, increasing the number of perception layers, or increasing the number of nodes in each perception layer.

[0130] According to the vehicle chassis remaining service life prediction method of the embodiment of the present application, through the trained chassis health status prediction model, based on the chassis operation data of the target vehicle, the predicted remaining service life of the target component output by the chassis health status prediction model is obtained, and the driving change data, maintenance data and the actual remaining service life and predicted remaining service life of the target component of the target vehicle can be obtained; based on the driving change data, maintenance data and the actual remaining service life and predicted remaining service life of the target component, the chassis health status prediction model is optimized and updated, so as to optimize and update the chassis health status prediction model using the actual remaining service life and predicted remaining service life, thereby improving the prediction accuracy and adaptability of the chassis health status prediction model.

[0131] In some embodiments, after the chassis operation data is input into a trained chassis health status prediction model and the predicted remaining service life output by the chassis health status prediction model is obtained, the target component and the health status information corresponding to the target component can be rendered and displayed based on the predicted remaining service life corresponding to each target component.

[0132] In some embodiments, the server can transmit the predicted remaining service life corresponding to each target component to the target vehicle's onboard HMI (human-computer interface) in real time through the WebSocket protocol, so that the target vehicle renders and displays the target component and the health status information corresponding to the target component.

[0133] In some embodiments, each target component in the target vehicle chassis and the health status information corresponding to the component may be rendered and displayed.

[0134] In actual implementation, each target component in the target vehicle chassis and the corresponding health status information of the component are rendered and displayed through multi-screen splicing display.

[0135] In actual implementation, the health status information may include a warning signal for the target component and safety measures proposed according to the damage degree of the target component.

[0136] According to the vehicle chassis remaining service life prediction method of the embodiment of the present application, after obtaining the predicted remaining service life of the target components output by the chassis health status prediction model based on the chassis operation data of the target vehicle through the trained chassis health status prediction model, the target components and the health status information corresponding to the target components are rendered and displayed based on the predicted remaining service life corresponding to each target component, so as to intuitively display the health status of each target component of the target vehicle chassis, provide users with a full range of health status display, and facilitate users to quickly locate hidden dangers.

[0137] In some embodiments, when the predicted remaining service life of the target component is greater than or equal to a first health threshold, the target vehicle renders the target component based on the first identifier and displays the health information status of the target component based on a first drawing mode;

[0138] or

[0139] When the predicted remaining useful life of the target component is less than a first health threshold and greater than or equal to a second health threshold, the target vehicle renders the target component based on the first identifier and displays the health information status of the target component based on the second drawing mode; the second health threshold is less than the first health threshold;

[0140] or

[0141] When the predicted remaining service life of the target component is less than the second health threshold and greater than or equal to the third health threshold, the target vehicle renders the target component based on the second identifier and displays the health information status of the target component based on the second drawing mode; the third health threshold is less than the second health threshold;

[0142] or

[0143] When the predicted remaining service life of the target component is less than a third health threshold, the target vehicle renders the target component based on the third identifier and displays the health information status of the target component based on the second drawing mode.

[0144] In actual implementation, the first identifier, the second identifier, and the third identifier may be identifiers of three different colors or shapes. The first drawing mode and the second drawing mode may be different graphic drawing technologies.

[0145] In actual implementation, if the predicted remaining useful life of a target component is greater than or equal to a first health threshold, the target vehicle renders the target component based on a first indicator, indicating that the target component is in good health and can be used normally, and displays the target component's health information status based on a first drawing mode. For example, if the predicted remaining useful life of a target component is greater than or equal to 95%, the target component is rendered with a green indicator in the chassis structure diagram of the target vehicle, and a waveform diagram based on the target component's remaining useful life is drawn using Canvas lightweight graphics rendering technology.

[0146] In actual implementation, if the predicted remaining useful life of a target component is less than a first health threshold and greater than or equal to a second health threshold, the target vehicle renders the target component based on the first indicator, indicating that the target component is in good health and can be used normally, and displays the target component's health information status based on the second rendering mode. For example, if the predicted remaining useful life of a target component is less than 95% and greater than or equal to 60%, the target component is rendered with a green indicator in the chassis structure diagram of the target vehicle, and a heat map based on the predicted remaining useful life of the target component is drawn using OpenGL high-performance graphics shading technology.

[0147] In actual implementation, if the predicted remaining useful life of a target component is less than a second health threshold and greater than or equal to a third health threshold, the target vehicle renders the target component based on a second indicator, indicating that the target component's health has deteriorated and recommending that the user inspect the component. The target component's health information is then displayed based on a second rendering mode. For example, if the predicted remaining useful life of a target component is less than 60% and greater than or equal to 30%, the target component is rendered with a yellow indicator in the chassis structure diagram of the target vehicle, and a heat map based on the predicted remaining useful life of the target component is drawn using OpenGL high-performance graphics shading technology.

[0148] In actual implementation, if the predicted remaining useful life of a target component is less than a third health threshold, the target vehicle renders the target component based on a third indicator, indicating that the target component is in poor health, poses a safety hazard, and requires immediate repair. The target component's health information is then displayed based on a second rendering mode. For example, if the predicted remaining useful life of a target component is less than 60% and greater than or equal to 30%, the target component is rendered in red in the chassis structure diagram of the target vehicle, and a heat map based on the predicted remaining useful life of the target component is drawn using OpenGL high-performance graphics shading technology.

[0149] According to the vehicle chassis remaining service life prediction method of the embodiment of the present application, after obtaining the predicted remaining service life of the target components output by the chassis health status prediction model based on the chassis operation data of the target vehicle through the trained chassis health status prediction model, the target components and the health status information corresponding to the target components are rendered and displayed based on the predicted remaining service life corresponding to each target component, so as to intuitively display the health status of each target component of the target vehicle chassis, provide users with a full range of health status display, and facilitate users to quickly locate hidden dangers.

[0150] In order to better understand the method for predicting the remaining useful life of a vehicle chassis provided in the embodiment of the present application, further explanation is given below. It should be understood that the discussion below is only exemplary.

[0151] This application provides a method for predicting the remaining service life of a vehicle chassis. The specific steps can be as follows: Figure 4 As shown:

[0152] Step 410: Acquire first chassis operation data based on the vehicle fatigue endurance test, and acquire second chassis operation data based on multi-body dynamics simulation analysis.

[0153] In practice, the vehicle fatigue endurance test can be conducted in a laboratory or on an actual road environment, simulating the vehicle's operating state under various road conditions (e.g., steep slopes, potholes, bumps, turns, etc.) to collect first chassis operating data. The first chassis operating data can include data on the forces, vibrations, and deformations of various chassis components.

[0154] In some embodiments, the multi-body dynamics simulation analysis may be a process of simulating the dynamic response of a vehicle under complex road conditions using multi-body dynamics simulation technology to obtain the second chassis operation data. The second chassis operation data may include force distribution data of the vehicle chassis.

[0155] Step 420: Construct a target training database based on the first chassis operation data and the second chassis operation data.

[0156] In actual implementation, the target training database may be a database required for training and generating a chassis health status prediction model.

[0157] In some embodiments, damage analysis may be performed based on the second chassis operation data, and the obtained damage analysis results may be integrated with the first chassis operation data to construct a target training database.

[0158] In some embodiments, target damage data may be acquired based on finite element transient analysis for the second chassis operation data; and a target training database may be constructed based on the first chassis operation data and the target damage data.

[0159] In actual implementation, the finite element transient analysis is used to perform transient dynamic analysis of the chassis structure of the target vehicle using the finite element method. Based on the second chassis operation data, target damage data is calculated. The target damage data may include damage conditions of target components of the target vehicle chassis under different stress conditions.

[0160] Step 430: Based on the target training database, the target prediction model is trained to obtain a chassis health status prediction model.

[0161] In actual implementation, the target prediction model may be a nonlinear autoregressive outer integral (NLARX) model or any theoretically feasible model, and this application does not impose any specific restrictions on this.

[0162] In some embodiments, as Figure 5 As shown, the target prediction model can be trained based on the target training database in combination with the machine learning algorithm to obtain a chassis health status prediction model. The chassis health status prediction model can be used to predict damage and evaluate the remaining service life of target components in the chassis of the target vehicle.

[0163] Step 440: Acquire chassis operation data of the target vehicle and cache the chassis operation data; the chassis operation data includes at least one of acceleration, vibration, temperature and load of target components in the chassis of the target vehicle itself, and the number of target components is at least one.

[0164] In some embodiments, the target vehicle can obtain chassis operating data of its own chassis. In some embodiments, the target vehicle can obtain chassis operating data based on various sensors installed on its own chassis. For example, the target vehicle can obtain acceleration, vibration, temperature, and load light data of various target components in its own chassis based on speed sensors, vibration sensors, temperature sensors, and pressure sensors installed on its own chassis.

[0165] In actual implementation, the target component may be a mechanical component installed in the chassis of the target vehicle, such as an upper wishbone, a lower wishbone, or any other theoretically feasible mechanical component.

[0166] In some embodiments, the target vehicle may obtain chassis operation data of its own chassis based on the driving status of the vehicle.

[0167] In some embodiments, the chassis operation data of the target vehicle can be obtained by the server. In some embodiments, after the target vehicle obtains the chassis operation data of its own chassis, the target vehicle can upload the chassis operation data to the server.

[0168] In actual implementation, the server can be a cloud server or any theoretically feasible server, and this application does not impose any specific restrictions on this.

[0169] In some embodiments, the target vehicle may cache the acquired chassis operation data in its own cache space.

[0170] In actual implementation, the cache space of the target vehicle can be located in the memory space of the target vehicle, or in any built-in storage space or external storage space of the target vehicle. This application does not impose any specific restrictions on this.

[0171] In some embodiments, as Figure 6 As shown, the chassis operation data of the target vehicle can be obtained based on the first sampling method when the target vehicle is in a first load scenario; or, the chassis operation data of the target vehicle can be obtained based on the second sampling method when the target vehicle is in a second load scenario.

[0172] In actual implementation, the first load scenario may be a high-load scenario such as a vehicle traveling at high speed, emergency braking, or frequent steering, etc. The second load scenario may be a low-load scenario such as a vehicle traveling at low speed, idling, or parking, etc.

[0173] In actual implementation, the first sampling method may be a sampling method for acquiring data collected by all sensors in the chassis of the target vehicle. The second sampling method may be a sampling method for acquiring data collected by some of all sensors in the chassis of the target vehicle, or a sampling method for acquiring some of the data collected by all sensors in the chassis of the target vehicle.

[0174] In some embodiments, chassis operation data of the target vehicle may be acquired based on a first sampling method at a first sampling frequency when the target vehicle is in a first load scenario. For example, the first sampling frequency may be greater than 1 kHz.

[0175] In some embodiments, when the target vehicle is in a second load scenario, chassis operation data of the target vehicle may be acquired at a second sampling frequency and based on a second sampling method. For example, the second sampling frequency may be less than 1 kHz.

[0176] In some embodiments, the cache space occupancy ratio can be obtained; when the cache space occupancy ratio is greater than or equal to the preset occupancy ratio, based on the first-in-first-out mechanism, the target historical chassis operation data in the cache space is cleared and the chassis operation data is cached to the cache space.

[0177] In actual implementation, the preset occupancy ratio may be a set value. For example, the preset occupancy ratio may be adjusted based on actual storage usage of the target vehicle.

[0178] In some embodiments, when the cache space occupancy ratio is greater than or equal to a preset occupancy ratio, a first-in, first-out (FIFO) mechanism may be triggered to clear the target historical chassis operation data in the cache space. For example, when the cache space occupancy ratio is greater than or equal to 80%, the target historical chassis operation data in the cache space may be cleared based on the FIFO mechanism.

[0179] In actual execution, the target historical chassis operation data may be the historical chassis operation data stored in the cache space and stored in the cache space earliest.

[0180] In some embodiments, when the cache space occupancy ratio is less than a preset occupancy ratio, the chassis operation data may be cached normally in the cache space.

[0181] Step 450: Input the chassis operation data into the trained chassis health status prediction model to obtain the predicted remaining service life of the target component output by the chassis health status prediction model.

[0182] In some embodiments, before the chassis operation data is input into the trained chassis health status prediction model, the chassis operation data may be filtered, denoised, and feature extracted to ensure data quality.

[0183] In some embodiments, the chassis health status prediction model may be trained by a server and downloaded to the target vehicle.

[0184] In some embodiments, the chassis health status prediction model may be used to obtain a predicted remaining useful life of a target component based on at least one of acceleration, vibration, temperature, and load of the target component.

[0185] In some embodiments, the chassis health status prediction model may predict the damage condition of a target component based on chassis operation data, and obtain a predicted remaining service life of the target component based on the damage condition of the target component.

[0186] Step 460: Obtain the target vehicle's driving change data, maintenance data, and the actual remaining service life and predicted remaining service life of the target component; and optimize and update the chassis health status prediction model based on the driving change data, maintenance data, and the actual remaining service life and predicted remaining service life of the target component.

[0187] In actual implementation, driving change data can include bus data such as the target vehicle's longitudinal acceleration and steering angle during driving. Maintenance data can include fault information and repair information recorded during after-sales maintenance. The actual remaining service life can be the remaining service life of the target component obtained by various sensors installed on the target vehicle chassis.

[0188] In some embodiments, the driving change data may be acquired through an electronic stability control system (ESC) of the target vehicle.

[0189] In some embodiments, priority may be given to determining whether a target component of the target vehicle's chassis is damaged and whether the target vehicle has encountered an extreme driving scenario. If the target component of the target vehicle's chassis is not damaged and the target vehicle has not encountered an extreme driving scenario, the chassis health status prediction model is determined to be inaccurate, triggering an optimization update of the chassis health status prediction model.

[0190] In some embodiments, the server can obtain target operating data of at least one target vehicle, where the target operating data includes driving change data, maintenance data, and the actual remaining service life and predicted remaining service life of target components of each target vehicle, and perform federated learning based on the target operating data of at least one target vehicle to optimize and update the chassis health status prediction model.

[0191] In some embodiments, the server may include an aggregator. Figure 7 As shown, each of at least one target vehicle can encrypt the target operating data and send it to the aggregator. After the aggregator decrypts the target operating data encrypted and sent by each target vehicle through decryption technology, federated learning is performed based on the target operating data of at least one target vehicle to optimize and update the chassis health status prediction model.

[0192] In some embodiments, after the server completes the optimization and update of the chassis health status prediction model, the optimized chassis health status prediction model can be downloaded and updated to the target vehicle through wireless communication technology (OTA), ensuring that the target vehicle always uses the latest and most accurate chassis health status prediction model.

[0193] In some embodiments, whether the target component is damaged is determined based on maintenance data and predicted remaining service life; if the target component is damaged, whether the target vehicle encounters an extreme driving scenario is determined based on driving change data; if the target vehicle does not encounter an extreme driving scenario, the chassis health status prediction model is optimized and updated based on the predicted remaining service life and the actual remaining service life.

[0194] In some embodiments, if a sensor mounted on the target vehicle's chassis is damaged, the chassis operating data input into the chassis health prediction model will be erroneous, resulting in inaccurate predictions. However, this inaccuracy is not caused by the chassis health prediction model itself. To eliminate the possibility that a damaged sensor mounted on the target vehicle's chassis could interfere with the accuracy of the chassis health prediction model's predictions, damage to the target component can be determined based on maintenance data and the predicted remaining useful life.

[0195] In some embodiments, if both the maintenance data and the predicted remaining useful life indicate that the target component is damaged, the target component is determined to be damaged. Conversely, if both the maintenance data and the predicted remaining useful life indicate that the target component is not damaged, the sensor mounted on the chassis of the target vehicle is determined to be damaged, while the target component is not damaged.

[0196] In some embodiments, if the target vehicle encounters an extreme driving scenario, the chassis operating data input to the chassis health prediction model may be inaccurate, resulting in inaccurate predictions from the chassis health prediction model. However, this inaccuracy is not caused by the chassis health prediction model itself. To eliminate the possibility that extreme driving scenarios (such as curb impact, pothole impact, or icy or snowy roads) may interfere with the accuracy of the chassis health prediction model's predictions, the driving variation data may be used to determine whether the target vehicle has encountered an extreme driving scenario.

[0197] In some embodiments, it may be determined that the target vehicle encounters an extreme driving scenario when the driving change data shows a sudden change in the longitudinal acceleration or the steering angle of the target vehicle.

[0198] In some embodiments, when the target component is not damaged and the target vehicle does not encounter extreme driving scenarios, it is determined that the reason why the chassis health status prediction model's prediction results are inaccurate comes from the chassis health status prediction model itself, and the chassis health status prediction model is optimized and updated based on the predicted remaining service life and the actual remaining service life.

[0199] In some embodiments, when the difference between the predicted remaining service life and the actual remaining service life is greater than the target difference, the structural parameters of the chassis health status prediction model are adjusted to optimize and update the chassis health status prediction model; the structural parameters include the number of time delays of input and output, the number of perception layers, and the number of nodes in each perception layer.

[0200] Step 470 : Based on the predicted remaining service life of each target component, render and display the target component and the health status information corresponding to the target component.

[0201] In some embodiments, step 470 may be performed before step 460 , after step 460 , or simultaneously with step 460 .

[0202] In some embodiments, the server can transmit the predicted remaining service life corresponding to each target component to the target vehicle's onboard HMI (human-computer interface) in real time through the WebSocket protocol, so that the target vehicle renders and displays the target component and the health status information corresponding to the target component.

[0203] In some embodiments, each target component in the target vehicle chassis and the health status information corresponding to the component may be rendered and displayed.

[0204] In actual implementation, each target component in the target vehicle chassis and the corresponding health status information of the component are rendered and displayed through multi-screen splicing display.

[0205] In actual implementation, the health status information may include a warning signal for the target component and safety measures proposed according to the damage degree of the target component.

[0206] In some embodiments, when the predicted remaining service life of the target component is greater than or equal to a first health threshold, the target vehicle renders the target component based on the first identifier and displays the health information status of the target component based on a first drawing mode;

[0207] or

[0208] When the predicted remaining useful life of the target component is less than a first health threshold and greater than or equal to a second health threshold, the target vehicle renders the target component based on the first identifier and displays the health information status of the target component based on the second drawing mode; the second health threshold is less than the first health threshold;

[0209] or

[0210] When the predicted remaining service life of the target component is less than the second health threshold and greater than or equal to the third health threshold, the target vehicle renders the target component based on the second identifier and displays the health information status of the target component based on the second drawing mode; the third health threshold is less than the second health threshold;

[0211] or

[0212] When the predicted remaining service life of the target component is less than a third health threshold, the target vehicle renders the target component based on the third identifier and displays the health information status of the target component based on the second drawing mode.

[0213] In actual implementation, the first identifier, the second identifier, and the third identifier may be identifiers of three different colors or shapes. The first drawing mode and the second drawing mode may be different graphic drawing technologies.

[0214] In actual implementation, when the predicted remaining service life of the target component is greater than or equal to the first health threshold, the target vehicle renders the target component based on the first identifier, indicating that the target component is in good health and can be used normally, and displays the health information status of the target component based on the first rendering mode. Figure 8 As shown, for example, when the predicted remaining service life of the target component is greater than or equal to 95%, the target component is rendered in green in the chassis structure diagram of the target vehicle, and a waveform diagram is drawn based on the remaining service life of the target component through the Canvas lightweight graphics drawing technology.

[0215] In actual implementation, if the predicted remaining useful life of a target component is less than a first health threshold and greater than or equal to a second health threshold, the target vehicle renders the target component based on the first indicator, indicating that the target component is in good health and can be used normally, and displays the target component's health information status based on the second rendering mode. For example, if the predicted remaining useful life of a target component is less than 95% and greater than or equal to 60%, the target component is rendered with a green indicator in the chassis structure diagram of the target vehicle, and a heat map based on the predicted remaining useful life of the target component is drawn using OpenGL high-performance graphics shading technology.

[0216] In actual implementation, if the predicted remaining useful life of a target component is less than a second health threshold and greater than or equal to a third health threshold, the target vehicle renders the target component based on a second indicator, indicating that the target component's health has deteriorated and recommending that the user inspect the component. The target component's health information is then displayed based on a second rendering mode. For example, if the predicted remaining useful life of a target component is less than 60% and greater than or equal to 30%, the target component is rendered with a yellow indicator in the chassis structure diagram of the target vehicle, and a heat map based on the predicted remaining useful life of the target component is drawn using OpenGL high-performance graphics shading technology.

[0217] In actual implementation, if the predicted remaining useful life of a target component is less than a third health threshold, the target vehicle renders the target component based on a third indicator, indicating that the target component is in poor health, poses a safety hazard, and requires immediate repair. The target component's health information is then displayed based on a second rendering mode. For example, if the predicted remaining useful life of a target component is less than 60% and greater than or equal to 30%, the target component is rendered in red in the chassis structure diagram of the target vehicle, and a heat map based on the predicted remaining useful life of the target component is drawn using OpenGL high-performance graphics shading technology.

[0218] The present application also provides a vehicle for executing the vehicle chassis remaining useful life prediction method provided in any of the above embodiments.

[0219] The vehicle in the embodiment of the present application may include an electronic device, and may also include components in the electronic device, such as an integrated circuit or chip. The electronic device may be a terminal, or may be a device other than a terminal. For example, the electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a mobile Internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc. It may also be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), an ATM or a self-service machine, etc., and the embodiment of the present application does not specifically limit it.

[0220] The vehicle in the embodiment of the present application may be a device having an operating system. The operating system may be a Microsoft (Windows) operating system, an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0221] The vehicle provided in the embodiment of the present application can achieve Figures 1 to 8 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0222] In some embodiments, as Figure 9 As shown, an embodiment of the present application also provides an electronic device 900, including a processor 901, a memory 902, and a computer program stored in the memory 902 and executable on the processor 901. When the program is executed by the processor 901, each process of the above-mentioned vehicle chassis remaining service life prediction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0223] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0224] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the various processes of the above-mentioned vehicle chassis remaining service life prediction method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0225] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0226] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned method for predicting the remaining useful life of a vehicle chassis when executed by a processor.

[0227] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0228] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned vehicle chassis remaining service life prediction method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0229] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0230] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0231] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0232] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0233] Throughout this specification, reference to terms such as "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 application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0234] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for predicting the remaining useful life of a vehicle chassis, characterized in that: include: Acquiring chassis operation data of a target vehicle and caching the chassis operation data; The chassis operation data includes at least one of acceleration, vibration, temperature and load of a target component in the chassis of the target vehicle itself, and the number of the target component is at least one; The chassis operation data is input into a trained chassis health status prediction model to obtain the predicted remaining service life of the target component output by the chassis health status prediction model; wherein the chassis health status prediction model is trained in the following manner: Obtaining first chassis operation data based on a vehicle fatigue endurance test, and obtaining second chassis operation data based on a multi-body dynamics simulation analysis; Building a target training database based on the first chassis operation data and the second chassis operation data; Based on the target training database, the target prediction model is trained to obtain the chassis health status prediction model.

2. The method for predicting the remaining useful life of a vehicle chassis according to claim 1, characterized in that: The acquiring chassis operation data of the target vehicle and caching the chassis operation data includes: When the target vehicle is in a first load scenario, obtaining chassis operation data of the target vehicle based on a first sampling method; or When the target vehicle is in a second load scenario, the chassis operation data of the target vehicle is acquired based on a second sampling method.

3. The method for predicting the remaining useful life of a vehicle chassis according to claim 1, wherein: The acquiring chassis operation data of the target vehicle and caching the chassis operation data includes: Get the cache space occupancy ratio; When the cache space occupancy ratio is greater than or equal to a preset occupancy ratio, the target historical chassis operation data in the cache space is cleared based on a first-in-first-out mechanism, and the chassis operation data is cached in the cache space.

4. The method for predicting the remaining useful life of a vehicle chassis according to claim 1, wherein: The constructing a target training database based on the first chassis operation data and the second chassis operation data includes: Obtaining target damage data based on finite element transient analysis for the second chassis operation data; A target training database is constructed based on the first chassis operation data and the target damage data.

5. The method for predicting the remaining useful life of a vehicle chassis according to claim 1, characterized in that: After inputting the chassis operation data into a trained chassis health status prediction model to obtain the predicted remaining service life of the target component output by the chassis health status prediction model, the method includes: Acquiring driving change data, maintenance data of the target vehicle, and the actual remaining service life and the predicted remaining service life of the target component; The chassis health status prediction model is optimized and updated based on the driving change data, the maintenance data, and the actual remaining service life and the predicted remaining service life of the target component.

6. The method for predicting the remaining useful life of a vehicle chassis according to claim 5, characterized in that: The optimizing and updating of the chassis health status prediction model based on the driving change data, the maintenance data, and the actual remaining service life and the predicted remaining service life of the target component includes: determining whether the target component is damaged based on the maintenance data and the predicted remaining service life; In the event that the target component is damaged, determining whether the target vehicle encounters an extreme driving scenario based on the driving change data; In a case where the target vehicle does not encounter an extreme driving scenario, the chassis health status prediction model is optimized and updated based on the predicted remaining service life and the actual remaining service life.

7. The method for predicting the remaining useful life of a vehicle chassis according to claim 6, characterized in that: The optimizing and updating the chassis health status prediction model based on the predicted remaining service life and the actual remaining service life includes: When the difference between the predicted remaining service life and the actual remaining service life is greater than the target difference, the structural parameters of the chassis health status prediction model are adjusted to optimize and update the chassis health status prediction model; the structural parameters include the number of input and output time delays, the number of perception layers, and the number of nodes in each perception layer.

8. The method for predicting the remaining useful life of a vehicle chassis according to any one of claims 1 to 7, characterized in that: After inputting the chassis operation data into a trained chassis health status prediction model to obtain the predicted remaining service life of the target component output by the chassis health status prediction model, the method includes: Based on the predicted remaining service life corresponding to each target component, the target component and the health status information corresponding to the target component are rendered and displayed.

9. The method for predicting the remaining useful life of a vehicle chassis according to claim 8, characterized in that: The rendering and displaying of the target component and the health status information corresponding to the target component based on the predicted remaining service life corresponding to each target component includes: When the predicted remaining service life of the target component is greater than or equal to a first health threshold, the target vehicle renders the target component based on a first identifier and displays the health information status of the target component based on a first drawing mode; or When the predicted remaining useful life of the target component is less than the first health threshold and greater than or equal to a second health threshold, the target vehicle renders the target component based on a first identifier and displays the health information status of the target component based on a second drawing mode; the second health threshold is less than the first health threshold; or When the predicted remaining useful life of the target component is less than the second health threshold and greater than or equal to a third health threshold, the target vehicle renders the target component based on a second identifier and displays the health information status of the target component based on a second drawing mode; the third health threshold is less than the second health threshold; or When the predicted remaining service life of the target component is less than the third health threshold, the target vehicle renders the target component based on a third indicator and displays the health information status of the target component based on a second drawing mode.

10. A vehicle, characterized in that: The vehicle is used to execute the steps of the vehicle chassis remaining service life prediction method according to any one of claims 1 to 9.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the vehicle chassis remaining service life prediction method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting the remaining useful life of a vehicle chassis according to any one of claims 1 to 9 are implemented.

13. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for predicting the remaining useful life of a vehicle chassis according to any one of claims 1 to 9 are implemented.

Images