Method, device and equipment for predicting ultimate strength grade of vehicle and storage medium
By generating a vehicle's ultimate intensity level prediction model, using neural network training and prediction technology, the deterministic problem of vehicle's function loss under extreme operating conditions is solved, and accurate prediction of vehicle's ultimate intensity level is achieved.
Patent Information
- Application Number
- CN202510462993.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-14
- Publication Date
- 2025-08-05
AI Technical Summary
The prior art cannot determine whether a vehicle loses its function under various road limit operating conditions.
By obtaining the generated data set to be trained, including multiple sets of data to be trained and the marked vehicle limit intensity level, the preset neural network is trained to generate a vehicle limit intensity level prediction model, and predict the prediction data based on the model to obtain the target vehicle limit intensity level.
It is possible to predict whether the vehicle loses its function under various road limit operating conditions based on the known parameters of the vehicle itself, which solves the problem that the vehicle loses its function under the limit operating conditions.
Smart Images
Figure CN120429706A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of vehicle performance prediction, and particularly to a prediction method, device, equipment and storage medium for the ultimate strength of operating vehicles. Background Art
[0002] With the continuous development of the automotive industry, when manufacturing automobiles, some vehicle factories will observe the performance of the whole vehicle and each component under various extreme usage conditions on the road in society through test vehicles, so as to ensure the stability of the performance of the produced automobiles. In the related art, to test whether a structural member loses its function, it passes through speed bumps, square roadblocks, trapezoidal pits, and square pits with or without braking at different vehicle speeds, for a total of three rounds. However, the prior art cannot determine whether the vehicle loses its function under various extreme usage conditions on the road. Summary of the Invention
[0003] This application provides a prediction method, device, equipment and computer-readable storage medium for the ultimate strength level of a vehicle, which can solve the technical problem in the prior art that it is impossible to determine whether the vehicle loses its function under various extreme usage conditions on the road.
[0004] In a first aspect, an embodiment of this application provides a prediction method for the ultimate strength level of a vehicle. The prediction method for the ultimate strength level of the vehicle includes:
[0005] Obtain the generated training dataset to be trained, where the training dataset to be trained includes multiple groups of training data to be trained, and each group of training data to be trained includes vehicle parameters to be trained and labeled ultimate strength levels of the vehicle;
[0006] Train a preset neural network according to the training dataset to be trained to generate a prediction model for the ultimate strength level of the vehicle;
[0007] Based on the prediction model for the ultimate strength level of the vehicle, predict the data to be predicted obtained, and obtain the target ultimate strength level of the vehicle output by the prediction model for the ultimate strength level of the vehicle, where the data to be predicted includes vehicle parameters to be predicted.
[0008] In combination with the first aspect, in an implementation manner, before obtaining the generated training dataset to be trained, it further includes:
[0009] Obtain the target test data of the vehicle to be tested under each preset condition, where the target test data includes the target front wheel rim diameter, the target wheel alignment value, the target bolt torque value, and the target wheel camber angle value;
[0010] Calculate the difference between each group of the target test data and the preset test data respectively according to each group of the target test data and the preset test data;
[0011] According to the difference values of each group and the preset limit strength level table, obtain the vehicle limit strength level of the vehicle to be tested under different preset working conditions, and record the vehicle parameters of the vehicle to be tested in different preset working conditions;
[0012] Generate a training dataset based on the vehicle limit strength level and vehicle parameters of the test vehicle under different preset working conditions.
[0013] Combined with the first aspect, in one implementation, each of the preset working conditions includes: a pothole impact condition, a pothole braking condition, a road step impact condition, a road step extrusion condition, and a limit braking condition.
[0014] Combined with the first aspect, in one implementation, the obtaining of multiple groups of target test data of the vehicle to be tested under multiple preset working conditions includes:
[0015] Obtain multiple groups of test data of the vehicle to be tested under multiple preset working conditions;
[0016] Determine the target test data from the multiple groups of test data of each of the preset working conditions according to the preset rules, so as to obtain the target test data of each of the preset working conditions.
[0017] Combined with the first aspect, in one implementation, the training of the preset neural network according to the training dataset to generate a vehicle limit strength level prediction model includes:
[0018] Input the training dataset into the preset neural network and train the preset neural network;
[0019] Determine whether the trained preset neural network is in a converged state;
[0020] If it is determined that the trained preset neural network is in a converged state, generate a vehicle limit strength level prediction model.
[0021] Combined with the first aspect, in one implementation, the determining whether the trained preset neural network is in a converged state includes:
[0022] Obtain the loss value of the trained preset neural network;
[0023] If the loss value is less than or equal to the preset standard loss value, determine that the preset neural network is in a converged state;
[0024] If the loss value is greater than the preset standard loss value, determine that the preset neural network is not in a converged state, and train the preset neural network again until the preset neural network is in a converged state.
[0025] In combination with the first aspect, in one embodiment, determining whether the pre-trained pre-set neural network is in a converged state includes:
[0026] Obtain the number of training times of the pre-set neural network;
[0027] If the number of training times is less than the pre-set standard number of training times, determine that the pre-set neural network is not in a converged state, and train the pre-set neural network again until the pre-set neural network is in a converged state;
[0028] If the number of training times is greater than or equal to the pre-set standard number of times, determine that the pre-set neural network is in a converged state.
[0029] In a second aspect, an embodiment of the present application provides a prediction device for the vehicle ultimate strength level, characterized in that the prediction device for the vehicle ultimate strength level includes:
[0030] An acquisition module, configured to acquire a generated training dataset to be trained, where the training dataset to be trained includes multiple groups of training data to be trained, and each group of training data to be trained includes training vehicle parameters to be trained and labeled vehicle ultimate strength levels;
[0031] A training module, configured to train a pre-set neural network according to the training dataset to be trained to generate a vehicle ultimate strength level prediction model;
[0032] A prediction module, configured to predict the acquired data to be predicted based on the vehicle ultimate strength level prediction model to obtain the target vehicle ultimate strength level output by the vehicle ultimate strength level prediction model, where the data to be predicted includes vehicle parameters to be predicted.
[0033] In a third aspect, an embodiment of the present application provides a prediction device for the vehicle ultimate strength level, characterized in that the prediction device for the vehicle ultimate strength level includes a processor, a memory, and a vehicle ultimate strength level prediction program stored on the memory and executable by the processor, where when the vehicle ultimate strength level prediction program is executed by the processor, the steps of the vehicle ultimate strength level prediction method according to any one of claims 1 to 7 are implemented.
[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, characterized in that a vehicle ultimate strength level prediction program is stored on the computer-readable storage medium, where when the vehicle ultimate strength level prediction program is executed by a processor, the steps of the vehicle ultimate strength level prediction method according to any one of claims 1 to 7 are implemented.
[0035] The beneficial effects brought by the technical solution provided in the embodiment of the present application at least include: by obtaining the generated training dataset to be trained, where the training dataset to be trained includes multiple groups of training data to be trained, and each group of training data to be trained includes vehicle parameters to be trained and labeled vehicle limit strength levels; training a preset neural network according to the training dataset to be trained to generate a vehicle limit strength level prediction model; predicting the obtained data to be predicted based on the vehicle limit strength level prediction model to obtain the target vehicle limit strength level output by the vehicle limit strength level prediction model, where the data to be predicted includes vehicle parameters to be predicted, which solves the technical problem in the related art that it is impossible to determine whether a vehicle loses its function under various road limit usage conditions. The present application can predict the vehicle limit strength level according to the known parameters of the vehicle itself, so as to determine whether the vehicle loses its function under various road limit usage conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 It is a schematic flowchart of an embodiment of the method for predicting the vehicle limit strength level of the present application;
[0037] Figure 2 For the present application Figure 1 It is a schematic flowchart of the refinement of step S10 in the present application;
[0038] Figure 3 It is a schematic diagram of the functional modules of an embodiment of the device for predicting the vehicle limit strength level of the present application;
[0039] Figure 4 It is a schematic diagram of the hardware structure of the device for predicting the vehicle limit strength level involved in the solution of the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0040] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
[0041] In the description of the specification, claims, and the above-mentioned drawings of this application, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices. Descriptions such as "first", "second", and "third" are used to distinguish different objects, etc., and do not represent a sequential order, nor do they limit that "first", "second", and "third" are of different types.
[0042] In the description of the embodiments of this application, terms such as "exemplary", "for example", or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary", "for example", or "for instance" in the embodiments of this application should not be construed as more preferred or more advantageous than other embodiments or design solutions. Rather, the use of words such as "exemplary", "for example", or "for instance" is intended to present relevant concepts in a specific manner.
[0043] In the description of the embodiments of this application, unless otherwise specified, " / " means "or". For example, A / B can mean A or B; "and / or" in the text is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more than two.
[0044] In some processes described in the embodiments of this application, multiple operations or steps appear in a specific order. However, it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of this application or may be executed in parallel. The serial numbers of the operations are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.
[0045] First, some technical terms in this application are explained to facilitate understanding of this application by those skilled in the art.
[0046] To make the purpose, technical solution, and advantages of this application clearer, the following will further describe the embodiments of this application in detail with reference to the drawings.
[0047] In a first aspect, an embodiment of this application provides a method for predicting the vehicle ultimate strength level.
[0048] In one embodiment, referring to Figure 1, Figure 1 This is a schematic flowchart of the first embodiment of the prediction method for the vehicle ultimate strength level of this application. As Figure 1 shown, the prediction method for the vehicle ultimate strength level includes:
[0049] Step S10: Obtain the generated training dataset to be trained, where the training dataset to be trained includes multiple groups of training data to be trained, and each group of training data to be trained includes vehicle parameters to be trained and labeled vehicle ultimate strength levels;
[0050] Exemplarily, first directly measure the own parameters of multiple vehicles to obtain the vehicle parameters to be trained. The parameters to be trained include wheelbase, track width, vehicle center of mass height, front and rear axle loads, spring elastic coefficient, shock absorber dynamic parameters, bushing stiffness curve, and suspension hard point information. Label the vehicle ultimate strength level, and then it becomes the labeled vehicle ultimate strength level.
[0051] Step S20: Train a pre-set neural network according to the training dataset to be trained to generate a vehicle ultimate strength level prediction model;
[0052] Exemplarily, input the obtained multiple groups of training data to be trained into the pre-set neural network for training until the pre-set neural network is in a converged state. When the number of training times or the loss value of the pre-set neural network reaches the pre-set standard value, it means that the pre-set neural network is in a converged state. After that, generate a vehicle ultimate strength level prediction model. Among them, a neural network is a machine learning model that mimics the human brain's nervous system and realizes artificial intelligence by simulating the working mode of biological neurons. It consists of multiple node layers, including an input layer, a hidden layer, and an output layer. Each node is connected to other nodes through weights and thresholds. When the output of the node exceeds the threshold, the node is activated and the data is passed to the next layer.
[0053] The types of neural networks include:
[0054] Perceptron: The oldest neural network, created by Frank Rosenblatt in 1958.
[0055] Feedforward neural network (Multi-Layer Perceptron, MLP): Consisting of an input layer, one or more hidden layers, and an output layer, it is often used in computer vision and natural language processing.
[0056] Convolutional neural network (CNN): Used for image recognition and pattern recognition.
[0057] Recurrent neural network (RNN): Used for predicting time series data, such as stock market prediction.
[0058] The training process of a neural network includes forward propagation and backward propagation. Forward propagation calculates the activation value of each node from the input layer to the output layer, while backward propagation adjusts the weights of each layer backward according to the error of the output layer. Commonly used optimization algorithms include gradient descent and backpropagation algorithms.
[0059] Neural networks have a wide range of applications in many fields, such as speech recognition, image recognition, natural language processing, etc. They can classify and cluster data at high speed and are more efficient compared to manual recognition by human experts.
[0060] The strength of neural networks lies in their ability to learn and simulate complex patterns, making them an important tool in the fields of artificial intelligence and machine learning.
[0061] Specifically, training the pre-set neural network according to the to-be-trained data set to generate a vehicle ultimate strength level prediction model includes: inputting the to-be-trained data set into the pre-set neural network to train the pre-set neural network; determining whether the trained pre-set neural network is in a convergent state; if it is determined that the trained pre-set neural network is in a convergent state, then generating a vehicle ultimate strength level prediction model.
[0062] Exemplarily, input the to-be-trained data set into the pre-set neural network for training until the pre-set neural network is in a convergent state, and then generate a vehicle ultimate strength level prediction model according to the neural network in the convergent state; input the obtained self-parameters of the vehicle into the vehicle ultimate strength level prediction model to predict the vehicle ultimate strength level. The vehicle ultimate strength level includes excellent, good, average, and poor. When the vehicle ultimate strength level is excellent, good, or average, it is determined that the vehicle will not lose its function under various road extreme use conditions.
[0063] Specifically, determining whether the trained pre-set neural network is in a convergent state includes: obtaining the loss value of the trained pre-set neural network; if the loss value is less than or equal to the pre-set standard loss value, then determining that the pre-set neural network is in a convergent state; if the loss value is greater than the pre-set standard loss value, then determining that the pre-set neural network is not in a convergent state, and training the pre-set neural network again until the pre-set neural network is in a convergent state.
[0064] Exemplary, when the loss value is 0.1, and at this time the loss value is less than the preset standard loss value of 0.5, it is determined that the preset neural network is in a convergent state; when the loss value is 0.6, and at this time the loss value is greater than the preset standard loss value of 0.5, it is determined that the preset neural network is not in a convergent state, and the preset neural network is trained again until the preset neural network is in a convergent state; when the loss value is 0.5, and at this time the loss value is equal to the standard loss value of 0.5, it is determined that the preset neural network is in a convergent state.
[0065] Specifically, determining whether the preset neural network after training is in a convergent state includes: obtaining the number of training times of the preset neural network; if the number of training times is less than the preset standard number of training times, it is determined that the preset neural network is not in a convergent state, and the preset neural network is trained again until the preset neural network is in a convergent state; if the number of training times is greater than or equal to the preset standard number of times, it is determined that the preset neural network is in a convergent state.
[0066] Exemplary, when the number of training times is greater than or equal to the preset standard number of training times of 10000, it is determined that the preset neural network is in a convergent state, and when the number of training times is less than the preset standard number of training times of 10000, it is determined that the preset neural network is not in a convergent state.
[0067] Step S30: Predict the obtained data to be predicted based on the vehicle ultimate strength level prediction model, and obtain the target vehicle ultimate strength level output by the vehicle ultimate strength level prediction model, where the data to be predicted includes the parameters of the vehicle to be predicted.
[0068] Exemplary, obtaining the data to be predicted includes the wheelbase, the wheel track, the height of the vehicle's center of mass, the front and rear axle loads, the spring stiffness coefficient, the shock absorber dynamic parameters, the bushing stiffness curve, and the suspension hard point information. Input the data to be predicted into the vehicle ultimate strength level prediction model, and then the model outputs the target vehicle ultimate strength level. For example, input the data to be predicted into the vehicle ultimate strength level prediction model. If the predicted ultimate strength level of the model is good, it is determined that the vehicle will not lose its function under various road extreme use conditions; if the predicted ultimate strength level of the model is poor, it is determined that the vehicle will lose its function under various road extreme use conditions.
[0069] In this embodiment, by obtaining the generated training dataset to be trained, where the training dataset to be trained includes multiple groups of training data, and each group of training data includes vehicle parameters to be trained and the marked vehicle limit strength level; training a preset neural network according to the training dataset to be trained to generate a vehicle limit strength level prediction model; predicting the obtained data to be predicted based on the vehicle limit strength level prediction model to obtain the target vehicle limit strength level output by the vehicle limit strength level prediction model, where the data to be predicted includes vehicle parameters to be predicted, it solves the problem in the related art that it is impossible to determine whether the vehicle loses its function under various road limit usage conditions. This embodiment can predict the vehicle limit strength level according to the known parameters of the vehicle itself, so as to determine whether the vehicle loses its function under various road limit usage conditions.
[0070] Further, in an embodiment, referring to Figure 2 , Figure 2 is the detailed flow schematic diagram of step S10 in this application. As Figure 1 shown, before obtaining the generated training dataset to be trained, it further includes: Figure 2 shown, before obtaining the generated training dataset to be trained, it further includes:
[0071] Step S11: Obtain target test data under each preset condition, where the target test data includes target front wheel rim diameter, target wheel alignment value, target bolt torque value, and target wheel camber angle value;
[0072] Exemplarily, first, prepare before the experiment. Before each experiment, it is necessary to prepare experimental-related equipment such as a test vehicle, a crash test dummy, a trunk counterweight, a CAN bus data recorder, a GPS recorder, a lift, and a camera, and check whether the functions of components including tires, brake pads, engines, gearboxes, suspensions, and wheels are normal. Then measure the front wheel rim diameter, wheel alignment value, bolt torque value, and wheel camber angle value before the experiment as the preset test data.
[0073] Specifically, the preset conditions include: pothole impact condition, pothole braking condition, curb impact condition, curb extrusion condition, and extreme braking condition.
[0074] Exemplarily, when it is determined that the experimental condition is the pothole impact experimental condition, the vehicle is continuously controlled multiple times to pass through one or more preset potholes at one or more different preset vehicle speeds. When it is determined that the experimental condition is the pothole braking experimental condition, the vehicle is continuously controlled multiple times to brake on one or more preset potholes at one or more different preset vehicle speeds, and the wheels are locked. When it is determined that the experimental condition is the curb impact experimental condition, the vehicle is continuously controlled multiple times to pass through one or more preset curbs at one or more different preset vehicle speeds. When it is determined that the experimental condition is the curb departure experimental condition, the vehicle is continuously controlled multiple times to stop beside multiple different preset curbs, and then the steering wheel is rotated to make the vehicle slide laterally away from the preset curb. When it is determined that the experimental condition is the extreme braking experimental condition, the vehicle is continuously controlled multiple times to drive from a normal road surface to a Belgian road surface at one or more different preset vehicle speeds, and then emergency braking is performed.
[0075] Each preset experimental condition is repeated multiple times, and the front wheel rim diameter value, wheel alignment value, bolt torque value, and wheel camber angle value after each experiment are measured and recorded as test data. Then, according to the preset rules, a set of test data is selected from multiple groups of test data as the target test data. For example, the average value of each data in multiple groups of test data is calculated as the target test data.
[0076] Specifically, obtaining multiple groups of target test data of the vehicle to be tested under multiple preset conditions includes: obtaining multiple groups of test data of the vehicle to be tested under multiple preset conditions; determining the target test data from the multiple groups of test data of each preset condition according to the preset rules to obtain the target test data of each preset condition.
[0077] Exemplarily, each preset experimental condition is repeated multiple times, and the front wheel rim diameter value, wheel alignment value, bolt torque value, and wheel camber angle value after each experiment are measured and recorded as test data. Then, the test data recorded in the last experiment is used as the target test data, or the average value of multiple experiment data is used as the target test data, or the maximum value of multiple experiments is used as the target test data, or the minimum value of multiple experiments is used as the target test data.
[0078] Step S12: Calculate the difference between each group of the target test data and the preset test data according to each group of the target test data and the preset test data;
[0079] Exemplarily, for instance, subtract the rim diameter before the experiment from the rim diameter after the experiment to obtain the difference between the rim diameter before the experiment and the rim diameters after multiple experiments; subtract the front wheel set value before the experiment from the front wheel set value after the experiment to obtain the difference between the front wheel set value before the experiment and the front wheel set values after multiple experiments; subtract the bolt torque value before the experiment from the bolt torque value after the experiment to obtain the difference between the rim diameter before the experiment and the rim diameters after multiple experiments;
[0080] Step S13: According to the differences in each group and the preset limit strength grade table, obtain the vehicle limit strength grade of the vehicle to be tested under different preset conditions, and record the vehicle parameters of the vehicle to be tested in different preset conditions;
[0081] The preset limit strength grade table is as follows:
[0082]
[0083] When obtaining the vehicle limit strength grade of the vehicle to be tested under different preset conditions according to the differences in each group and the preset limit strength grade table, take the worst vehicle limit strength grade of the corresponding grade as the standard. For example, the difference in the front wheel set value is 15', the difference in the camber angle is 11', the difference in the bolt torque value is 10%, and the difference in the rim diameter value is 1 mm. Among them, the vehicle limit strength grade corresponding to the front wheel set value is the worst, which is good. Then the vehicle limit strength grade of the vehicle to be tested is good.
[0084] Step S14: Generate a training dataset based on the vehicle limit strength grade and vehicle parameters of the test vehicle under different preset conditions.
[0085] Exemplarily, label the vehicle limit strength grade of the vehicle under different preset conditions. The labeled vehicle limit strength grade can be one type in the training dataset. The vehicle parameters include wheelbase, track width, vehicle center of mass height, front and rear axle loads, spring elastic coefficient, shock absorber dynamic parameters, bushing stiffness curve, and suspension hard point information.
[0086] In this embodiment, by obtaining target test data under various preset working conditions, where the target test data includes a target front rim diameter, a target wheel alignment value, a target bolt torque value, and a target wheel camber angle value; calculating the difference between each group of the target test data and the preset test data respectively according to each group of the target test data and the preset test data; obtaining the vehicle limit strength level of the vehicle to be tested under different preset working conditions according to each group of the differences and a preset limit strength level table, and recording the vehicle parameters of the vehicle to be tested in different preset working conditions; generating a training dataset to be trained based on the vehicle limit strength level and vehicle parameters of the test vehicle under different preset working conditions, the problem in the related art that a training dataset to be trained for predicting the vehicle limit strength level cannot be obtained is solved. This embodiment provides a method for obtaining a training dataset to be trained for predicting the vehicle limit strength level, so that a training dataset to be trained for predicting the vehicle limit strength level can be obtained.
[0087] In a second aspect, an embodiment of the present application further provides a prediction device for vehicle limit strength level.
[0088] In one embodiment, referring to Figure 4 , Figure 4 is a schematic diagram of functional modules of an embodiment of the prediction device for vehicle limit strength level of the present application. As Figure 4 shown, the prediction device for vehicle limit strength level includes:
[0089] An acquisition module 01, configured to acquire the generated training dataset to be trained, where the training dataset to be trained includes multiple groups of training data to be trained, and each group of training data to be trained includes vehicle parameters to be trained and labeled vehicle limit strength levels;
[0090] A training module 02, configured to train a preset neural network according to the training dataset to be trained to generate a vehicle limit strength level prediction model;
[0091] A prediction module 03, configured to predict the acquired data to be predicted based on the vehicle limit strength level prediction model to obtain the target vehicle limit strength level output by the vehicle limit strength level prediction model, where the data to be predicted includes vehicle parameters to be predicted.
[0092] Further, in one embodiment, the training module 02 is further configured to:
[0093] Input the training dataset to be trained into the preset neural network to train the preset neural network;
[0094] Determine whether the trained preset neural network is in a converged state;
[0095] If it is determined that the pre-set neural network after training is in a convergent state, a vehicle ultimate strength level prediction model is generated.
[0096] Among them, the function implementation of each module in the above vehicle ultimate strength level prediction device corresponds to each step in the above vehicle ultimate strength level prediction method embodiment, and its function and implementation process will not be elaborated here one by one.
[0097] In a third aspect, an embodiment of the present application provides a vehicle ultimate strength level prediction device. The vehicle ultimate strength level prediction device may be a device with data processing functions such as a personal computer (PC), a notebook computer, a server, etc.
[0098] Refer to Figure 3 , Figure 3 which is a schematic hardware structure diagram of the vehicle ultimate strength level prediction device involved in the embodiment solution of the present application. In the embodiment of the present application, the vehicle ultimate strength level prediction device may include a processor, a memory, a communication interface, and a communication bus.
[0099] Among them, the communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.
[0100] The communication interface includes interfaces such as input / output (I / O) interfaces, physical interfaces, and logical interfaces for interconnecting components inside the vehicle ultimate strength level prediction device, as well as interfaces for interconnecting the vehicle ultimate strength level prediction device with other devices (such as other computing devices or user devices). The physical interface may be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device may be a display screen (Display), a keyboard (Keyboard), etc.
[0101] The memory may be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical memory, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.
[0102] The processor may be a general-purpose processor, which can call the prediction program of the vehicle limit strength level stored in the memory and execute the vehicle limit strength level prediction method provided by the embodiments of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the prediction program of the vehicle limit strength level is called may refer to the various embodiments of the vehicle limit strength level prediction method of the present application, which will not be elaborated here.
[0103] Those skilled in the art can understand that Figure 3 the hardware structure shown in does not constitute a limitation to the present application, and may include more or fewer components than shown in the figure, or combine some components, or arrange different components.
[0104] Fourthly, the embodiments of the present application also provide a readable storage medium.
[0105] The prediction program of the vehicle limit strength level is stored on the readable storage medium of the present application. When the prediction program of the vehicle limit strength level is executed by a processor, the steps of the vehicle limit strength level prediction method as described above are implemented.
[0106] The method implemented when the prediction program of the vehicle limit strength level is executed may refer to the various embodiments of the vehicle limit strength level prediction method of the present application, which will not be elaborated here.
[0107] It should be noted that the serial numbers of the above embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.
[0108] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device to execute the methods described in the various embodiments of the present application.
[0109] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present application, or directly or indirectly applied to other related technical fields, shall be included in the patent protection scope of the present application in the same way.
Claims
1. A method for predicting the ultimate strength grade of a vehicle, characterized in that: The method for predicting the vehicle ultimate strength grade includes: Obtaining a generated data set to be trained, wherein the data set to be trained includes multiple groups of data to be trained, and each group of data to be trained includes parameters of a vehicle to be trained and a marked vehicle ultimate strength grade; Training a preset neural network according to the data set to be trained to generate a vehicle ultimate strength grade prediction model; The acquired data to be predicted is predicted based on the vehicle ultimate strength grade prediction model to obtain a target vehicle ultimate strength grade output by the vehicle ultimate strength grade prediction model, wherein the data to be predicted includes vehicle parameters to be predicted.
2. The method for predicting the vehicle ultimate strength grade according to claim 1, wherein: Before obtaining the generated dataset to be trained, the method further includes: Acquiring target test data under various preset working conditions, wherein the target test data includes a target front wheel rim diameter, a target wheel toe value, a target bolt torque value, and a target wheel camber angle value; Calculating the difference between each group of target test data and the preset test data according to each group of target test data and the preset test data; Obtaining the vehicle ultimate strength grade of the vehicle to be tested under different preset working conditions according to the difference values of each group and the preset ultimate strength grade table, and recording the vehicle parameters of the vehicle to be tested under the different preset working conditions; A data set to be trained is generated based on the vehicle ultimate strength grade and vehicle parameters of the test vehicle under different preset working conditions.
3. The method for predicting the vehicle ultimate strength grade according to claim 2, wherein: The preset working conditions include: pothole impact working condition, pothole braking working condition, step impact working condition, step squeeze-off working condition and extreme braking working condition.
4. The method for predicting the vehicle ultimate strength grade according to claim 2, wherein: The step of obtaining multiple sets of target test data of the vehicle to be tested under multiple preset working conditions includes: Obtain multiple sets of test data of the vehicle to be tested under multiple preset working conditions; Target test data is determined from multiple groups of test data of each preset working condition according to preset rules to obtain target test data of each preset working condition.
5. The method for predicting the vehicle ultimate strength grade according to claim 1, wherein: The step of training a preset neural network according to the data set to be trained to generate a vehicle ultimate strength grade prediction model includes: Inputting the to-be-trained data set into a preset neural network to train the preset neural network; Determining whether the preset neural network after training is in a convergence state; If it is determined that the preset neural network after training is in a convergence state, a vehicle ultimate strength grade prediction model is generated.
6. The method for predicting the vehicle ultimate strength grade according to claim 5, characterized in that: Determining whether the preset neural network after training is in a convergence state includes: Obtaining a loss value of the preset neural network after training; If the loss value is less than or equal to a preset standard loss value, determining that the preset neural network is in a convergence state; If the loss value is greater than a preset standard loss value, it is determined that the preset neural network is not in a convergence state, and the preset neural network is trained again until the preset neural network is in a convergence state.
7. The method for predicting the vehicle ultimate strength grade according to claim 5, wherein: Determining whether the preset neural network after training is in a convergence state includes: Obtaining the number of training times of the preset neural network; If the number of training times is less than a preset standard number of training times, determining that the preset neural network is not in a convergence state, and training the preset neural network again until the preset neural network is in a convergence state; If the number of training times is greater than or equal to a preset standard number of times, it is determined that the preset neural network is in a convergence state.
8. A vehicle ultimate strength grade prediction device, characterized in that: The vehicle ultimate strength grade prediction device comprises: An acquisition module is used to acquire the generated data set to be trained, wherein the data set to be trained includes multiple groups of data to be trained, and each group of data to be trained includes parameters of the vehicle to be trained and annotated vehicle ultimate strength level; A training module, configured to train a preset neural network based on the data set to be trained to generate a vehicle ultimate strength grade prediction model; A prediction module is used to predict the acquired data to be predicted based on the vehicle ultimate strength level prediction model, and obtain the target vehicle ultimate strength level output by the vehicle ultimate strength level prediction model, wherein the data to be predicted includes the vehicle parameters to be predicted.
9. A vehicle ultimate strength grade prediction device, characterized in that: The vehicle ultimate strength grade prediction device includes a processor, a memory, and a vehicle ultimate strength grade prediction program stored in the memory and executable by the processor. When the vehicle ultimate strength grade prediction program is executed by the processor, the steps of the vehicle ultimate strength grade prediction method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a vehicle ultimate strength grade prediction program, wherein when the vehicle ultimate strength grade prediction program is executed by a processor, the steps of the vehicle ultimate strength grade prediction method according to any one of claims 1 to 7 are implemented.