CN113239599A - Intelligent tire wear life estimation method and device based on BP neural network - Google Patents
Intelligent tire wear life estimation method and device based on BP neural network Download PDFInfo
- Publication number
- CN113239599A CN113239599A CN202110658879.9A CN202110658879A CN113239599A CN 113239599 A CN113239599 A CN 113239599A CN 202110658879 A CN202110658879 A CN 202110658879A CN 113239599 A CN113239599 A CN 113239599A
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- training
- tire
- hidden layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 47
- 238000003062 neural network model Methods 0.000 claims abstract description 110
- 238000012549 training Methods 0.000 claims abstract description 96
- 238000012360 testing method Methods 0.000 claims abstract description 42
- 238000012795 verification Methods 0.000 claims abstract description 30
- 230000006870 function Effects 0.000 claims description 41
- 238000004590 computer program Methods 0.000 claims description 17
- 230000005284 excitation Effects 0.000 claims description 15
- 210000002569 neuron Anatomy 0.000 claims description 15
- 230000004913 activation Effects 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000010606 normalization Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 125000004122 cyclic group Chemical group 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000000630 rising effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Abstract
The invention provides an intelligent tire wear life estimation method and device based on a BP neural network, wherein the intelligent tire wear life estimation method comprises the following steps: acquiring a data set containing tire pressure, vehicle speed, load and 2-6-order radial lifting modal frequency of a tire, and randomly splitting the data set into a training set, a verification set and a test set; creating a BP neural network model, wherein the input of the network model is data in a data set, and the output is tire wear loss; training the BP neural network model based on a training set and a preset mean square error, determining the structure and network parameters of the BP neural network model, and verifying by using a verification set; and inputting the data in the test set into the trained BP neural network model, and estimating the wear life of the tire to which the data belongs. The method is based on the BP neural network technology, provides a low-cost and high-efficiency prediction method for automobile tire wear life prediction, and solves the problem of tire life prediction.
Description
Technical Field
The invention relates to the technical field of neural networks, in particular to an intelligent tire wear life estimation method and device based on a BP neural network.
Background
With the continuous development of the automobile industry, automobiles have gradually become a main walking tool for people to go out, and the safe running of the automobiles also gradually becomes the focus of attention of people. At present, more than half of traffic accidents on expressways in China are caused by tire wear problems, most of the accidents are tire burst, and the tire burst is mainly caused by serious tire surface wear and abnormal tire air pressure under the conditions of high-speed driving, emergency braking and the like. The tire, which is one of the main parts of an automobile, affects the performance and safety of the vehicle during running, and the importance of tire detection for the vehicle is obviously important, so that the running safety of the vehicle can be greatly improved.
At present, the main detection method of the automobile tire wear degree is manual detection, the tread pattern wear degree is defined and measured mainly by detecting the tire pattern depth and the pattern wear of tire shoulders, although the wear degree of the automobile tire can be judged by experience, the accuracy is not high, and is particularly difficult for novices. In addition, in daily life, a driver often ignores checking the degree of wear of tires, thereby causing an accident. Therefore, a method capable of accurately predicting the degree of wear of the automobile tires and reminding a driver at regular time is a demand.
Disclosure of Invention
Aiming at the problems, the invention provides an intelligent tire wear life prediction method and device based on a BP neural network, provides a low-cost and high-efficiency prediction method for automobile tire wear life prediction based on a BP neural network technology, and solves the problem of tire life prediction.
The technical scheme provided by the invention is as follows:
in one aspect, the invention provides an intelligent tire wear life estimation method based on a BP neural network, which comprises the following steps:
acquiring a data set containing tire pressure, vehicle speed, load and 2-6-order radial lifting modal frequency of a tire, and randomly splitting the data set into a training set, a verification set and a test set;
creating a BP neural network model, wherein the input of the network model is the data in the data set, and the output of the network model is the tire wear amount;
training the BP neural network model based on the training set, the verification set and a preset mean square error, and determining the structure and network parameters of the BP neural network model;
and inputting the data in the test set into a trained BP neural network model, and estimating the wear life of the tire to which the data belongs.
Further preferably, the BP neural network model includes a hidden layer, and the activation function is tan sig;
the creating of the BP neural network model comprises the following steps:
determining the range of the hidden layer node number according to the relation among the hidden layer node number, the input layer node number and the output layer node number:
wherein p is the number of hidden layer nodes, n is the number of input layer nodes, q is the number of output layer nodes, and a is a constant between 1 and 10;
and establishing a corresponding BP neural network model according to the range of the hidden layer node number.
Further preferably, the training the BP neural network model based on the training set and a preset mean square error, and determining the structure and the network parameters of the BP neural network model includes:
sequentially carrying out iterative training on BP neural network models containing different numbers of hidden layer nodes, and recording the mean square error after each iteration, wherein the training method is a rainlm training method;
and comparing the mean square error of each iteration, selecting the node number corresponding to the minimum value of the mean square error as the node number of the hidden layer, and determining the structure and the network parameters of the BP neural network model according to the node number.
Further preferably, in the determined structure and network parameters of the BP neural network model, the number of nodes of the hidden layer is 11, and an excitation function of each node of the hidden layer is as follows:
wherein, OjJ is the excitation of the jth hidden node, 1,2, …, 11; tan sig is the transfer function of the hidden layer; w is ajlWeights for the jth hidden node of the hidden layer to the ith neuron of the output layer; x is the number ofiIs the ith input parameter, i ═ 1,2, …, 8; thetajA jth hidden node threshold for the hidden layer;
the tire wear M predicted by the BP neural network model is as follows:
wherein the purelin function is an excitation function of the output layer; w is aijThe weight from the ith hidden node to the jth neuron of the output layer is calculated; thetamThe mth neuron threshold of the output layer.
On the other hand, the invention also provides an intelligent tire wear life estimation device based on the BP neural network, which comprises the following components:
the data acquisition module is used for acquiring a data set containing tire pressure, vehicle speed, load and 2-6-order elevation modal frequency in the radial direction of the tire, and randomly splitting the data set into a training set, a verification set and a test set;
the neural network creating module is used for creating a BP neural network model, the input of the network model is the data in the data set, and the output of the network model is the tire wear loss;
the neural network training module is used for training the BP neural network model based on the training set, the verification set and a preset mean square error, and determining the structure and the network parameters of the BP neural network model;
and the tire wear life estimation module is used for inputting the data in the test set into the trained BP neural network model and estimating the wear life of the tire to which the data belongs.
Further preferably, the BP neural network model includes a hidden layer, and the activation function is tan sig;
the neural network creating module comprises:
a hidden layer node number range determining unit, configured to determine a range of a hidden layer node number according to a relationship among the hidden layer node number, the input layer node number, and the output layer node number:
wherein p is the number of hidden layer nodes, n is the number of input layer nodes, q is the number of output layer nodes, and a is a constant between 1 and 10;
and the neural network creating unit is used for creating a corresponding BP neural network model according to the range of the hidden layer node number.
Further preferably, the neural network training module includes:
the training unit is used for carrying out iterative training on BP neural network models containing different numbers of hidden layer nodes in sequence and recording the mean square error after each iteration, and the training method is a rainlm training method;
and the network determining unit is used for comparing the mean square errors of each iteration, selecting the node number corresponding to the minimum mean square error as the node number of the hidden layer, and determining the structure and the network parameters of the BP neural network model according to the node number.
Further preferably, the number of hidden layer nodes of the BP neural network model determined by the neural network training module is 11, and the excitation function of each node of the hidden layer is as follows:
wherein, OjJ is the excitation of the jth hidden node, 1,2, …, 11; tan sig is the transfer function of the hidden layer; w is ajlWeights for the jth hidden node of the hidden layer to the ith neuron of the output layer; x is the number ofiIs the ith input parameter, i ═ 1,2, …, 8; thetajA jth hidden node threshold for the hidden layer;
the tire wear life estimation module predicts the tire wear amount M as follows:
wherein the purelin function is an excitation function of the output layer; w is aijThe weight from the ith hidden node to the jth neuron of the output layer is calculated; thetamThe mth neuron threshold of the output layer.
In another aspect, the present invention further provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the intelligent tire wear life estimation method based on the BP neural network when executing the computer program.
In another aspect, a computer readable storage medium stores a computer program which, when executed by a processor, implements the steps of the intelligent BP neural network-based tire wear life estimation method described above.
The intelligent tire wear life estimation method and device based on the BP neural network, provided by the invention, are based on the BP neural network model, and are combined with the generalization and convergence of the BP neural network model to process the regression and prediction problems of a nonlinear system such as tire parameters. Establishing a finite element model of a target tire through finite element software to extract data required by neural network training, thereby greatly reducing time cost and capital cost; after training of the BP neural network model is carried out through training sample data and the structure and the parameters of the BP neural network model are determined, the wear life of the tire is predicted by using the determined BP neural network model, the operation is simple, the prediction accuracy is high, the problem that the wear life of the tire is difficult to accurately predict is solved, and the application is convenient. In addition, in practical application, the predicted tire wear life can be displayed on an automobile instrument panel similarly to the tire air pressure, and a driver is reminded of the tire wear condition constantly, so that the driving safety of the automobile is improved.
Drawings
The foregoing features, technical features, advantages and embodiments are further described in the following detailed description of the preferred embodiments, which is to be read in connection with the accompanying drawings.
FIG. 1 is a schematic flow chart of an embodiment of an intelligent tire wear life estimation method based on a BP neural network according to the present invention;
FIG. 2 is a diagram showing the relationship between the modal frequency and the modal order of tires under different air pressures according to the present invention;
FIG. 3 is a graph of the relationship between the radial modal frequency and the modal order of the tire at different speeds in accordance with the present invention;
FIG. 4 is a graph of radial modal frequency versus modal order for tires under different loads in accordance with the present invention;
FIG. 5 is a graph showing the relationship between the radial modal frequency and the modal order of a tire under different amounts of wear in the present invention;
FIG. 6 is a portion of data in a data set acquired in accordance with an example of the present invention;
FIG. 7 is a graph of MSE as a function of number of hidden layer nodes in the example data set obtained in FIG. 6;
FIG. 8 is a diagram of a BP neural network model structure with a hidden layer node number of 11 in the data set example obtained in FIG. 6;
FIG. 9 is a graph of the relationship between MSE and iteration steps in the BP neural network model of FIG. 8;
FIG. 10 is a graph of BP neural network model versus test set prediction results as in FIG. 8;
FIG. 11 is a graph of the percentage of error for a prediction test set of the BP neural network model as in FIG. 8;
FIG. 12 is a schematic structural diagram of an embodiment of an intelligent tire wear life estimation device based on a BP neural network according to the present invention;
fig. 13 is a schematic structural diagram of a terminal device in the present invention.
Reference numerals:
100-a tire wear life estimation device, 110-a data acquisition module, 120-a neural network creation module, 130-a neural network training module, and 140-a tire wear life estimation module.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.
In a first embodiment of the present invention, as shown in fig. 1, an intelligent tire wear life estimation method based on a BP neural network includes:
s10, acquiring a data set containing tire pressure, vehicle speed, load and 2-6-order radial lifting modal frequency of the tire, and randomly splitting the data set into a training set, a verification set and a test set;
s20, creating a BP neural network model, wherein the input of the network model is data in a data set, and the output is tire wear loss;
s30, training the BP neural network model based on the training set, the verification set and the preset mean square error, and determining the structure and the network parameters of the BP neural network model;
and S40, inputting the data in the test set into the trained BP neural network model, and estimating the wear life of the tire to which the data belongs.
In the embodiment, the tire wear life is estimated based on the modal analysis related theory, and the basic modal formula is as follows (1):
wherein f is the modal frequency, k is the stiffness of the tire, and m is the mass of the tire.
When the tire air pressure, the vehicle speed, the load and the tire wear amount are changed, the corresponding tires respectively change the rigidity and the mass, so that the modal frequency of the tires is influenced, namely, a certain relation exists among the tire air pressure, the vehicle speed, the load, the tire wear amount and the tire modal frequency, and the basic relation between the neural network output and the output parameter is met. In the selection process, as shown in fig. 2 to 5 (fig. 2 is a relation graph of tire modal frequency and modal order under different air pressures; fig. 3 is a relation graph of tire radial modal frequency and modal order under different speeds; fig. 4 is a relation graph of tire radial modal frequency and modal order under different loads; fig. 5 is a relation graph of tire radial modal frequency and modal order under different wear amounts), the tire radial modal frequency generally tends to increase along with the increase of the inflation pressure and the tire wear amount (the pressure in fig. 2 gradually increases from 0.18MPa to 0.24MPa, and the tire wear amount in fig. 5 gradually increases from no wear to wear of 6mm), and increases along with the increase of the load and the vehicle speed (the speed in fig. 3 gradually increases from 0 to 60km/h, and the load in fig. 4 gradually increases from 2000N to 5000N). However, as can be further seen from fig. 3, the radial first-order modal frequency is not sensitive to the vehicle speed, so in order to improve the prediction accuracy of the BP neural network model, data of 2-6-order rising modal frequency is selected as the input of the BP neural network model, and the output is the tire wear amount.
After the input and the output of the BP neural network model are selected, the BP neural network model is created, and the collected data set is randomly split into a training set, a verification set and a test set, wherein the training set trains the BP neural network model, the verification set is used for preventing the network from being over-fitted in the network training process, and the test set is used for testing the performance of the trained network. The data volumes of the training set, the verification set, and the test set may be set according to actual situations, for example, in an example, the training set, the verification set, and the test set account for 0.7, 0.2, and 0.1 of the total data set, respectively.
For the created BP neural network model, considering that the amount of collected data and the number of input parameters are not large, in order to avoid complexity, the number of hidden layers is set to 1, and tan sig is selected as an activation function. In order to determine the number of hidden layer nodes in the hidden layer, in the establishment of the BP neural network model, the range of the number of hidden layer nodes is determined according to the relation among the number of hidden layer nodes, the number of input layer nodes and the number of output layer nodes in the formula (2), and then a corresponding BP neural network model is established according to the range of the number of hidden layer nodes.
Wherein p is the number of hidden layer nodes, n is the number of input layer nodes (determined by the actual number of input), q is the number of output layer nodes (determined by the actual requirement), and a is a constant between 1 and 10. In this embodiment, the number of the hidden layer nodes is preliminarily determined to be within the range of [4,13] by combining equation (2) with the number of the input parameters and the output parameters (n is 8, q is 1), so as to sequentially build the BP neural network model in which the number of the hidden layer nodes is increased from 4 to 13.
In the training process, a set cyclic algorithm brings a training set and a verification set into a BP neural network model for training, preset times (such as 50 times, 100 times or more) are circularly and iteratively calculated for the BP neural network model containing different hidden layer node numbers, a storage is set to automatically store the minimum mean square error MSE (the training method is a train lm training method, and the calculation formula of the MSE is as shown in formula (3)) of each hidden layer node number circularly and iteratively calculated training set, and meanwhile, the BP neural network model corresponding to the current minimum mean square error MSE is automatically stored through a save function. After all BP neural network models are iterated, the mean square errors of each iteration are compared, the number of nodes corresponding to the minimum value of the mean square errors is selected as the number of nodes of the optimal hidden layer, the structure and the network parameters of the BP neural network models are determined according to the number of the nodes, and then the BP neural network models are used for estimating the tire wear life of the data in the test set.
Wherein, yiReal value, y ', of tire wear amount corresponding to ith input data of training set'iAnd predicting expected values of corresponding input data for the BP neural network module, wherein N is the number of samples in the training set.
In the process of predicting a test set by using a trained BP neural network model, the prediction accuracy is measured by the absolute error epsilon of a tire wear prediction value and an actual value, and the formula is (4):
ε＝x-a (4)
wherein x is the predicted value of tire wear and a is the tire wear.
Because the numerical difference of the acquired data is too large, in order to improve the precision of the estimation algorithm, in other embodiments, the data in the training set, the verification set and the test set need to be normalized and disordered sequentially by using a randderm function to improve the robustness of the estimation algorithm, the value range of the normalized data is between (0,1), the normalized data conforms to the normal distribution of the standard, and 0 is avoided in the subsequent calculation; and performing reverse normalization treatment after prediction is finished. Specifically, the normalization and the denormalization are expressed by the formulas (5) to (7):
Ypredict＝(Ypredict,Nor+1)Ymax-Ypredict,NorYmin (7)
wherein X and Y represent input and output values of the training data, respectively, XnorAnd YnorRespectively representing input and output values, X, of the normalized training dataminAnd XmaxRespectively representing the minimum and maximum values of the input values in the training data, YminAnd YmaxRespectively representing the minimum and maximum values of the output value, Ypredict,NorRepresenting the normalized BP neural network model prediction, YpredictAnd predicting the result of the BP neural network model after the denormalization.
In another embodiment of the present invention, an intelligent tire wear life estimation device 100 based on a BP neural network, as shown in fig. 12, includes: the data acquisition module 110 is used for acquiring a data set containing tire pressure, vehicle speed, load and 2-6 order raising modal frequency in the radial direction of the tire, and randomly splitting the data set into a training set, a verification set and a test set; a neural network creating module 120, configured to create a BP neural network model, where an input of the network model is data in a data set, and an output of the network model is a tire wear amount; the neural network training module 130 is used for training the BP neural network model based on a training set, a verification set and a preset mean square error, and determining the structure and network parameters of the BP neural network model; and the tire wear life estimation module 140 is used for inputting the data concentrated in the test into the trained BP neural network model and estimating the wear life of the tire to which the data belongs.
In this embodiment, the wear life of the tire is estimated based on a modal analysis correlation theory, and when the tire pressure, the vehicle speed, the load and the tire wear amount change, the corresponding tires respectively change in stiffness and mass, so that the modal frequencies of the tires are affected, that is, a certain relationship exists among the tire pressure, the vehicle speed, the load, the tire wear amount and the tire modal frequencies, and the basic relationship between the neural network output and the output parameters is satisfied. In the selection process, as shown in fig. 2 to 5 (fig. 2 is a relation graph of tire modal frequency and modal order under different air pressures; fig. 3 is a relation graph of tire radial modal frequency and modal order under different speeds; fig. 4 is a relation graph of tire radial modal frequency and modal order under different loads; fig. 5 is a relation graph of tire radial modal frequency and modal order under different wear amounts), the tire radial modal frequency generally tends to increase along with the increase of the inflation pressure and the tire wear amount (the pressure in fig. 2 gradually increases from 0.18MPa to 0.24MPa, and the tire wear amount in fig. 5 gradually increases from no wear to wear of 6mm), and increases along with the increase of the load and the vehicle speed (the speed in fig. 3 gradually increases from 0 to 60km/h, and the load in fig. 4 gradually increases from 2000N to 5000N). However, as can be further seen from fig. 3, the radial first-order modal frequency is not sensitive to the vehicle speed, so in order to improve the prediction accuracy of the BP neural network model, data of 2-6-order rising modal frequency is selected as the input of the BP neural network model, and the output is the tire wear amount.
After the input and the output of the BP neural network model are selected, the BP neural network model is created, and the collected data set is randomly split into a training set, a verification set and a test set, wherein the training set trains the BP neural network model, the verification set is used for preventing the network from being over-fitted in the network training process, and the test set is used for testing the performance of the trained network. The data volumes of the training set, the verification set, and the test set may be set according to actual situations, for example, in an example, the training set, the verification set, and the test set account for 0.7, 0.2, and 0.1 of the total data set, respectively.
For the created BP neural network model, considering that the amount of collected data and the number of input parameters are not large, in order to avoid complexity, the number of hidden layers is set to 1, and tan sig is selected as an activation function. In order to determine the number of hidden layer nodes in the hidden layer, in the establishment of the BP neural network model, a hidden layer node number range determining unit first determines the range of the hidden layer node number according to the relation among the hidden layer node number, the input layer node number and the output layer node number shown in the formula (2), and then a neural network establishing unit establishes a corresponding BP neural network model according to the range of the hidden layer node number. The number range of the hidden layer nodes can be preliminarily determined to be in the interval [4,13] by the number combination formula (2) of the input parameters and the output parameters in the embodiment, so that the BP neural network model with the number of the hidden layer nodes gradually increased from 4 to 13 is sequentially established.
In the training process, a circulation algorithm arranged in a training unit brings a training set and a verification set into a BP neural network model for training, preset times (such as 50 times, 100 times or more) are circularly and iteratively calculated for the BP neural network model containing different hidden layer node numbers, a storage is arranged to automatically store each hidden layer node number for circularly and iteratively calculating the minimum mean square error MSE (the training method is a train lm training method, and the calculation formula of the MSE is as shown in formula (3)), and meanwhile, the BP neural network model corresponding to the current minimum mean square error MSE is automatically stored through a save function. After all BP neural network models are iterated, the network determining unit compares the mean square error of each iteration, selects the node number corresponding to the minimum value of the mean square error as the optimal hidden layer node number, determines the structure and the network parameters of the BP neural network model according to the node number, and then uses the BP neural network model to estimate the tire wear life of the data in the test set. In the process of predicting the test set by using the trained BP neural network model, the prediction accuracy is measured by the absolute error epsilon of the tire wear prediction value and the actual value, as shown in the formula (4).
Because the numerical difference of the acquired data is too large, in order to improve the precision of the estimation algorithm, in other embodiments, the data in the training set, the verification set and the test set need to be normalized and disordered sequentially by using a randderm function to improve the robustness of the estimation algorithm, the value range of the normalized data is between (0,1), the normalized data conforms to the normal distribution of the standard, and 0 is avoided in the subsequent calculation; and performing reverse normalization treatment after prediction is finished. Specifically, the normalization and the denormalization are expressed by the formulas (5) to (7).
In one example, 324 sets of simulation data between different tire pressures, loads, vehicle speeds and abrasion losses and radial 2-6 order radial rising modal frequencies are extracted as a data set in a tire finite element simulation environment based on a finite element modal analysis method in combination with a control variable method, so that the time cost and the capital cost of the test are reduced. The extracted partial data is shown in fig. 6, and each set of data includes 8 input parameters of wear loss, tire pressure, load, vehicle speed, radial 2-order tire modal frequency, radial 3-order tire modal frequency, radial 4-order tire modal frequency, and radial 5-order tire modal frequency.
As shown in fig. 13, after 324 groups of data samples are loaded, the data set is divided into a training set, a validation set and a test set by a divideparam function, accounting for 0.7, 0.2 and 0.1 of the total data amount, wherein the training set is used for training the BP neural network model, the validation set is used for preventing the network from falling into overfitting during the network training process, and the test set is used for testing the performance of the trained network. And then respectively carrying out normalization processing on the data in the training set, the verification set and the test set.
After a BP neural network model is created, the training precision of each parameter of the model is set to be 0.0004, the learning rate is 0.1, the maximum iteration step number is 10000 steps, the activation function of a hidden layer is tan sig, and the expression is
The activation function of the output layer is purelin, the expression is purelin (n) ═ n, the training method adopts the gradient decreasing training function of tranlmm self-adapting lrBP, and uses [ net, tr]And the function is trained, so that detailed result parameters of network training can be obtained conveniently at the later stage.
In the training of a BP neural network model with hidden nodes in a range of [4,13], a set cyclic algorithm brings a training set and a verification set into a network for training, wherein the number of nodes of a hidden layer is sequentially increased from 4 to 13, 100 times of calculation is repeated at each node number, a storage is set to automatically store the number of nodes of each hidden layer for calculating the minimum mean square error MSE of the training set for 100 times, the BP neural network model corresponding to the current minimum MSE is automatically stored through a save function, and the minimum MSE corresponding to the nodes 4-13 is stored in the storage after the cyclic algorithm is executed. As shown in fig. 7, it can be seen that the optimum hidden layer node number of the BP neural network model in this example is 11, and the corresponding BP neural network model structure is as shown in fig. 8, and includes 8 input parameters, i.e., a wear loss, a tire pressure, a load, a vehicle speed, a radial 2-step tire modal frequency, a radial 3-step tire modal frequency, a radial 4-step tire modal frequency, and a radial 5-step tire modal frequency, 1 output parameter of the tire wear loss, and 1 hidden layer including 11 hidden layer node numbers. Fig. 9 shows the relationship between MSE and iteration step number (corresponding to Epoch in the diagram) when the number of hidden layer nodes is 11, that is, the training of the BP neural network model is stopped at step 45, and the root mean square error MSE at this time is 7.0026e-4, which is lower than the set target value 4e5 (the maximum verification step number of the verification set reaches the maximum set step number in the training process, so the training of the network is terminated in advance to prevent the over-fitting phenomenon from occurring).
In the prediction of the test set by using the trained BP neural network model, the prediction result is shown in fig. 10, and it can be seen that the error values are all small in different test samples (samples in the test set), and the average tire wear error of the neural network is 0.0874 mm. FIG. 11 shows the error percentages of the BP neural network model prediction test set, the prediction error percentages are within + -10%, the average error percentage is 2.78%, and the prediction precision is high.
At this time, the excitation function of each node of the hidden layer is as follows:
wherein, OjJ is the excitation of the jth hidden node, 1,2, …, 11; tan sig is the transfer function of the hidden layer; w is ajlWeights for the jth hidden node of the hidden layer to the ith neuron of the output layer; x is the number ofiIs the ith input parameter, i ═ 1,2, …, 8; thetajA jth hidden node threshold for the hidden layer;
the tire wear M predicted by the BP neural network model is as follows:
wherein the purelin function is an excitation function of the output layer; w is aijThe weight from the ith hidden node to the jth neuron of the output layer is calculated; thetamThe mth neuron threshold of the output layer.
And (3) after the BP neural network model carries out tire wear quantity M prediction on the data samples in the test set, carrying out inverse normalization processing on the predicted data, and evaluating the prediction precision according to the formula (4) so as to determine the final tire wear life prediction neural network.
At this time, assume that the tread thickness of the new tire is Dnewmm, the residual wear service life eta of the tire at the momentuseCan be expressed as formula (10), thereby realizing the prediction of the service life of the tire:
in practical application, the predicted tire wear life can be displayed on an automobile instrument panel like the tire air pressure, and can also be displayed in other modes, so that the wear condition and the service life of the tire of a driver are reminded constantly, the problem that the driver often ignores the tire state is solved, and the driving safety of the automobile is improved.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of program modules is illustrated, and in practical applications, the above-described distribution of functions may be performed by different program modules, that is, the internal structure of the apparatus may be divided into different program units or modules to perform all or part of the above-described functions. Each program module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one processing unit, and the integrated unit may be implemented in a form of hardware, or may be implemented in a form of software program unit. In addition, the specific names of the program modules are only used for distinguishing the program modules from one another, and are not used for limiting the protection scope of the application.
Fig. 13 is a schematic structural diagram of a terminal device provided in an embodiment of the present invention, and as shown, the terminal device 200 includes: a processor 220, a memory 210, and a computer program 211 stored in the memory 210 and executable on the processor 220, such as: and (3) an intelligent tire wear life estimation correlation program based on the BP neural network. The processor 220 executes the computer program 211 to implement the steps of the above-mentioned embodiments of the intelligent tire wear life estimation method based on the BP neural network, or the processor 220 executes the computer program 211 to implement the functions of the modules of the above-mentioned embodiments of the intelligent tire wear life estimation device based on the BP neural network.
The terminal device 200 may be a notebook, a palm computer, a tablet computer, a mobile phone, or the like. Terminal device 200 may include, but is not limited to, processor 220, memory 210. Those skilled in the art will appreciate that fig. 13 is merely an example of the terminal device 200, does not constitute a limitation of the terminal device 200, and may include more or less components than those shown, or combine some components, or different components, such as: terminal device 200 may also include input-output devices, display devices, network access devices, buses, and the like.
The Processor 220 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor 220 may be a microprocessor or the processor may be any conventional processor or the like.
The memory 210 may be an internal storage unit of the terminal device 200, such as: a hard disk or a memory of the terminal device 200. The memory 210 may also be an external storage device of the terminal device 200, such as: a plug-in hard disk, an intelligent TF memory Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the terminal device 200. Further, the memory 210 may also include both an internal storage unit of the terminal device 200 and an external storage device. The memory 210 is used to store the computer program 211 and other programs and data required by the terminal device 200. The memory 210 may also be used to temporarily store data that has been output or is to be output.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or recited in detail in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described apparatus/terminal device embodiments are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and may be implemented in other ways, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by sending instructions to relevant hardware by the computer program 211, where the computer program 211 may be stored in a computer-readable storage medium, and when the computer program 211 is executed by the processor 220, the steps of the method embodiments may be implemented. Wherein the computer program 211 comprises: computer program code which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable storage medium may include: any entity or device capable of carrying the code of computer program 211, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the content of the computer readable storage medium can be increased or decreased according to the requirements of the legislation and patent practice in the jurisdiction, for example: in certain jurisdictions, in accordance with legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunications signals.
It should be noted that the above embodiments can be freely combined as necessary. The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for persons skilled in the art, numerous modifications and adaptations can be made without departing from the principle of the present invention, and such modifications and adaptations should be considered as within the scope of the present invention.
Claims (10)
1. An intelligent tire wear life estimation method based on a BP neural network is characterized by comprising the following steps:
acquiring a data set containing tire pressure, vehicle speed, load and 2-6-order radial lifting modal frequency of a tire, and randomly splitting the data set into a training set, a verification set and a test set;
creating a BP neural network model, wherein the input of the network model is the data in the data set, and the output of the network model is the tire wear amount;
training the BP neural network model based on the training set, the verification set and a preset mean square error, and determining the structure and network parameters of the BP neural network model;
and inputting the data in the test set into a trained BP neural network model, and estimating the wear life of the tire to which the data belongs.
2. The intelligent tire wear life estimation method of claim 1, wherein the BP neural network model comprises a hidden layer, and the activation function is tan sig;
the creating of the BP neural network model comprises the following steps:
determining the range of the hidden layer node number according to the relation among the hidden layer node number, the input layer node number and the output layer node number:
wherein p is the number of hidden layer nodes, n is the number of input layer nodes, q is the number of output layer nodes, and a is a constant between 1 and 10;
and establishing a corresponding BP neural network model according to the range of the hidden layer node number.
3. The intelligent tire wear life estimation method of claim 2,
training the BP neural network model based on the training set and a preset mean square error, and determining the structure and the network parameters of the BP neural network model, wherein the training comprises the following steps:
sequentially carrying out iterative training on BP neural network models containing different numbers of hidden layer nodes, and recording the mean square error after each iteration, wherein the training method is a rainlm training method;
and comparing the mean square error of each iteration, selecting the node number corresponding to the minimum value of the mean square error as the node number of the hidden layer, and determining the structure and the network parameters of the BP neural network model according to the node number.
4. An intelligent tire wear life estimation method as claimed in claim 3, wherein in the determined structure and network parameters of the BP neural network model, the number of nodes of the hidden layer is 11, and the excitation function of each node of the hidden layer is as follows:
wherein, OjJ is the excitation of the jth hidden node, 1,2, …, 11; tan sig is the transfer function of the hidden layer; w is ajlWeights for the jth hidden node of the hidden layer to the ith neuron of the output layer; x is the number ofiIs the ith input parameter, i ═ 1,2, …, 8; thetajA jth hidden node threshold for the hidden layer;
the tire wear M predicted by the BP neural network model is as follows:
wherein the purelin function is an excitation function of the output layer; w is aijThe weight from the ith hidden node to the jth neuron of the output layer is calculated; thetamThe mth neuron threshold of the output layer.
5. An intelligent tire wear life estimation device based on a BP neural network is characterized by comprising:
the data acquisition module is used for acquiring a data set containing tire pressure, vehicle speed, load and 2-6-order elevation modal frequency in the radial direction of the tire, and randomly splitting the data set into a training set, a verification set and a test set;
the neural network creating module is used for creating a BP neural network model, the input of the network model is the data in the data set, and the output of the network model is the tire wear loss;
the neural network training module is used for training the BP neural network model based on the training set, the verification set and a preset mean square error, and determining the structure and the network parameters of the BP neural network model;
and the tire wear life estimation module is used for inputting the data in the test set into the trained BP neural network model and estimating the wear life of the tire to which the data belongs.
6. An intelligent tire wear life estimation device as claimed in claim 5, wherein said BP neural network model comprises a hidden layer, and the activation function is tan sig;
the neural network creating module comprises:
a hidden layer node number range determining unit, configured to determine a range of a hidden layer node number according to a relationship among the hidden layer node number, the input layer node number, and the output layer node number:
wherein p is the number of hidden layer nodes, n is the number of input layer nodes, q is the number of output layer nodes, and a is a constant between 1 and 10;
and the neural network creating unit is used for creating a corresponding BP neural network model according to the range of the hidden layer node number.
7. The intelligent tire wear life estimation device of claim 6, wherein the neural network training module comprises:
the training unit is used for carrying out iterative training on BP neural network models containing different numbers of hidden layer nodes in sequence and recording the mean square error after each iteration, and the training method is a rainlm training method;
and the network determining unit is used for comparing the mean square errors of each iteration, selecting the node number corresponding to the minimum mean square error as the node number of the hidden layer, and determining the structure and the network parameters of the BP neural network model according to the node number.
8. The intelligent tire wear life estimation device of claim 6, wherein the number of hidden layer nodes of the BP neural network model determined by the neural network training module is 11, and the excitation function of each node of the hidden layer is as follows:
wherein, OjJ is the excitation of the jth hidden node, 1,2, …, 11; tan sig is the transfer function of the hidden layer; w is ajlWeights for the jth hidden node of the hidden layer to the ith neuron of the output layer; x is the number ofiIs the ith input parameter, i ═ 1,2, …, 8; thetajA jth hidden node threshold for the hidden layer;
the tire wear life estimation module predicts the tire wear amount M as follows:
wherein the purelin function is an excitation function of the output layer; w is aijThe weight from the ith hidden node to the jth neuron of the output layer is calculated; thetamThe mth neuron threshold of the output layer.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the intelligent BP neural network-based tire wear life estimation method according to any one of claims 1 to 4 when executing the computer program.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the intelligent BP neural network-based tire wear life estimation method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110658879.9A CN113239599A (en) | 2021-06-15 | 2021-06-15 | Intelligent tire wear life estimation method and device based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110658879.9A CN113239599A (en) | 2021-06-15 | 2021-06-15 | Intelligent tire wear life estimation method and device based on BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113239599A true CN113239599A (en) | 2021-08-10 |
Family
ID=77139856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110658879.9A Pending CN113239599A (en) | 2021-06-15 | 2021-06-15 | Intelligent tire wear life estimation method and device based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113239599A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114004143A (en) * | 2021-10-18 | 2022-02-01 | 星河智联汽车科技有限公司 | Method and device for predicting tire life, terminal device and storage medium |
| CN114330131A (en) * | 2021-12-30 | 2022-04-12 | 武汉大学 | Method for rapidly determining depth of abrasive particle water jet preventive grinding steel rail |
| CN114379482A (en) * | 2022-01-21 | 2022-04-22 | 浙江吉利控股集团有限公司 | Tire maintenance prediction method and apparatus, and computer-readable storage medium |
| CN116522510A (en) * | 2023-06-28 | 2023-08-01 | 中信戴卡股份有限公司 | Inversion method and system for tire material parameters for wheel performance simulation |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520412A (en) * | 2009-03-23 | 2009-09-02 | 中国计量学院 | Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network |
| CN102426662A (en) * | 2011-11-08 | 2012-04-25 | 四川大学 | Embedded software system structural level energy consumption modeling method |
| CN102737153A (en) * | 2011-04-07 | 2012-10-17 | 中国人民解放军第三〇二医院 | Neural network hepatofibrosis diagnosis method and system |
| CN103886372A (en) * | 2014-04-12 | 2014-06-25 | 青岛科技大学 | Tire body temperature soft measurement method based on wavelet neural network |
| US20150061852A1 (en) * | 2012-11-20 | 2015-03-05 | Liming FU | Tire pressure monitoring systems and methods |
| CN105095962A (en) * | 2015-07-27 | 2015-11-25 | 中国汽车工程研究院股份有限公司 | Method for predicting dynamic mechanical property of material based on BP artificial neural network |
| US20170298115A1 (en) * | 2016-04-15 | 2017-10-19 | Alder Biopharmaceuticals, Inc. | Humanized anti-pacap antibodies and uses thereof |
| CN107379899A (en) * | 2017-07-07 | 2017-11-24 | 淮阴工学院 | A kind of tire condition intelligent monitor system based on wireless sensor network |
| CN107379898A (en) * | 2017-07-07 | 2017-11-24 | 淮阴工学院 | A kind of Intelligent Sensing System for Car Tire Safety |
| CN109115525A (en) * | 2018-08-16 | 2019-01-01 | 杭州容大智造科技有限公司 | A kind of equipment and automobile using current detecting tyre life |
| CN109446593A (en) * | 2018-10-10 | 2019-03-08 | 南京航空航天大学 | The one-dimensional design method of multi stage axial flow compressor based on artificial neural network |
| CN111079891A (en) * | 2019-01-18 | 2020-04-28 | 兰州理工大学 | Centrifugal pump performance prediction method based on double hidden layer BP neural network |
| CN111324989A (en) * | 2020-03-19 | 2020-06-23 | 重庆大学 | GA-BP neural network-based gear contact fatigue life prediction method |
| CN111353245A (en) * | 2020-02-26 | 2020-06-30 | 南京航空航天大学 | Mechanical elastic wheel wear degree measuring method |
| CN111762096A (en) * | 2020-06-27 | 2020-10-13 | 王亚鹏 | New energy automobile safety early warning method and system based on artificial intelligence |
| CN111907265A (en) * | 2020-08-17 | 2020-11-10 | 科大讯飞股份有限公司 | Tire wear condition judgment method, device, equipment and storage medium |
| CN112685834A (en) * | 2020-12-31 | 2021-04-20 | 合肥工业大学智能制造技术研究院 | Collision energy absorption prediction method, medium and terminal for vehicle body front end structural component |
| CN112734305A (en) * | 2021-02-24 | 2021-04-30 | 西南交通大学 | Roadbed compaction quality evaluation method, device and equipment and readable storage medium |
-
2021
- 2021-06-15 CN CN202110658879.9A patent/CN113239599A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520412A (en) * | 2009-03-23 | 2009-09-02 | 中国计量学院 | Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network |
| CN102737153A (en) * | 2011-04-07 | 2012-10-17 | 中国人民解放军第三〇二医院 | Neural network hepatofibrosis diagnosis method and system |
| CN102426662A (en) * | 2011-11-08 | 2012-04-25 | 四川大学 | Embedded software system structural level energy consumption modeling method |
| US20150061852A1 (en) * | 2012-11-20 | 2015-03-05 | Liming FU | Tire pressure monitoring systems and methods |
| CN103886372A (en) * | 2014-04-12 | 2014-06-25 | 青岛科技大学 | Tire body temperature soft measurement method based on wavelet neural network |
| CN105095962A (en) * | 2015-07-27 | 2015-11-25 | 中国汽车工程研究院股份有限公司 | Method for predicting dynamic mechanical property of material based on BP artificial neural network |
| US20170298115A1 (en) * | 2016-04-15 | 2017-10-19 | Alder Biopharmaceuticals, Inc. | Humanized anti-pacap antibodies and uses thereof |
| CN107379898A (en) * | 2017-07-07 | 2017-11-24 | 淮阴工学院 | A kind of Intelligent Sensing System for Car Tire Safety |
| CN107379899A (en) * | 2017-07-07 | 2017-11-24 | 淮阴工学院 | A kind of tire condition intelligent monitor system based on wireless sensor network |
| CN109115525A (en) * | 2018-08-16 | 2019-01-01 | 杭州容大智造科技有限公司 | A kind of equipment and automobile using current detecting tyre life |
| CN109446593A (en) * | 2018-10-10 | 2019-03-08 | 南京航空航天大学 | The one-dimensional design method of multi stage axial flow compressor based on artificial neural network |
| CN111079891A (en) * | 2019-01-18 | 2020-04-28 | 兰州理工大学 | Centrifugal pump performance prediction method based on double hidden layer BP neural network |
| CN111353245A (en) * | 2020-02-26 | 2020-06-30 | 南京航空航天大学 | Mechanical elastic wheel wear degree measuring method |
| CN111324989A (en) * | 2020-03-19 | 2020-06-23 | 重庆大学 | GA-BP neural network-based gear contact fatigue life prediction method |
| CN111762096A (en) * | 2020-06-27 | 2020-10-13 | 王亚鹏 | New energy automobile safety early warning method and system based on artificial intelligence |
| CN111907265A (en) * | 2020-08-17 | 2020-11-10 | 科大讯飞股份有限公司 | Tire wear condition judgment method, device, equipment and storage medium |
| CN112685834A (en) * | 2020-12-31 | 2021-04-20 | 合肥工业大学智能制造技术研究院 | Collision energy absorption prediction method, medium and terminal for vehicle body front end structural component |
| CN112734305A (en) * | 2021-02-24 | 2021-04-30 | 西南交通大学 | Roadbed compaction quality evaluation method, device and equipment and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| BO LI等: "An estimation algorithm for tire wear using intelligent tire concept", 《PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS, PART D: JOURNAL OF AUTOMOBILE ENGINEERING》, vol. 235, no. 10, 26 February 2021 (2021-02-26), pages 2712 - 2725 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114004143A (en) * | 2021-10-18 | 2022-02-01 | 星河智联汽车科技有限公司 | Method and device for predicting tire life, terminal device and storage medium |
| CN114330131A (en) * | 2021-12-30 | 2022-04-12 | 武汉大学 | Method for rapidly determining depth of abrasive particle water jet preventive grinding steel rail |
| CN114330131B (en) * | 2021-12-30 | 2023-07-07 | 武汉大学 | Method for rapidly determining abrasive particle water jet preventive grinding steel rail depth |
| CN114379482A (en) * | 2022-01-21 | 2022-04-22 | 浙江吉利控股集团有限公司 | Tire maintenance prediction method and apparatus, and computer-readable storage medium |
| CN116522510A (en) * | 2023-06-28 | 2023-08-01 | 中信戴卡股份有限公司 | Inversion method and system for tire material parameters for wheel performance simulation |
| CN116522510B (en) * | 2023-06-28 | 2023-09-01 | 中信戴卡股份有限公司 | Inversion method and system for tire material parameters for wheel performance simulation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113239599A (en) | Intelligent tire wear life estimation method and device based on BP neural network | |
| CN107680375B (en) | Vehicle load calculation method and device and storage medium | |
| CN111192631B (en) | Methods and systems for constructing models for predicting protein-RNA interaction binding sites | |
| CN110411729B (en) | Brake pad service life prediction method and device | |
| CN109572706B (en) | Driving safety evaluation method and device | |
| CN116090111B (en) | Automobile leaf spring fatigue life prediction method based on deep learning model | |
| CN109543710B (en) | Model training method and related equipment | |
| CN113761649A (en) | Intelligent automobile tire eccentric wear prediction method based on one-dimensional convolutional neural network | |
| CN103489034A (en) | Method and device for predicting and diagnosing online ocean current monitoring data | |
| CN115817500A (en) | Driving style determination method and device, vehicle and storage medium | |
| CN112819217A (en) | Method, system and storage medium for predicting main influence factors of mobile source pollution emission | |
| CN112183947A (en) | Rail transit vehicle comprehensive evaluation method and device, electronic equipment and storage medium | |
| CN111275453A (en) | Industry identification method and system of Internet of things equipment | |
| CN112816885A (en) | Battery abnormity detection method and device, electronic equipment and storage medium | |
| CN114297894A (en) | Online estimation method and device for tire slip angle, terminal and readable storage medium | |
| CN113360412B (en) | Test scene selection method and device, electronic equipment and storage medium | |
| CN114595627A (en) | Model quantization method, device, equipment and storage medium | |
| CN113561714A (en) | Tire load monitoring method, device, equipment and storage medium | |
| CN109918900B (en) | Sensor attack detection method, device, equipment and computer readable storage medium | |
| CN114550147B (en) | Automobile data acquisition, analysis and processing method and system based on Internet of things | |
| CN111538752A (en) | Vehicle use identification method and system based on Internet of vehicles and storage medium | |
| CN116522510B (en) | Inversion method and system for tire material parameters for wheel performance simulation | |
| CN113449382B (en) | Simulation method and system for whole vehicle emission result | |
| CN113188807B (en) | Automatic abs result judging algorithm | |
| CN114329342B (en) | Expressway traffic capacity calculation method based on extremum-Gaussian mixture distribution model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |