CN112801143B - Steering road feel simulation method based on K-Means and Gaussian process regression - Google Patents
Steering road feel simulation method based on K-Means and Gaussian process regression Download PDFInfo
- Publication number
- CN112801143B CN112801143B CN202110033492.4A CN202110033492A CN112801143B CN 112801143 B CN112801143 B CN 112801143B CN 202110033492 A CN202110033492 A CN 202110033492A CN 112801143 B CN112801143 B CN 112801143B
- Authority
- CN
- China
- Prior art keywords
- steering
- gaussian process
- test
- vehicle
- process regression
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
The invention discloses a steering road feel simulation method based on K-Means and Gaussian process regression, which comprises the following steps: carrying out a multi-working-condition real vehicle test; preprocessing test data; carrying out normalized test data clustering by using a K-Means clustering algorithm; dividing a training data set and a test data set; training a steering road feel model based on K-Means and Gaussian process regression, wherein the input variables are vehicle vertical load, steering wheel corner speed, longitudinal vehicle speed, vehicle lateral acceleration and vehicle yaw rate, and the output variables are steering wheel moment; testing a steering road feel model based on K-Means and Gaussian process regression; and performing road feel simulation according to the obtained steering road feel model. Compared with the prior art, the method has the advantages of convenience in data acquisition, easiness in implementation of a modeling process, high modeling time, high accuracy of the obtained model and good instantaneity.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to a steering road feel simulation method based on K-Means and Gaussian process regression.
Background
The steering road sense, also called steering force sense and steering wheel feedback torque, refers to the reverse resistance torque sensed by the driver through the steering wheel feedback torque. Because steering road feel can transmit important vehicle running state and running environment information, the simulation of the steering road feel is important for the drive-by-wire steering device, and at present, the main flow road feel modeling method is to analyze road feel generation reasons from a dynamic angle, establish a functional model and approach a real steering system. The method is often used for designing settings of a plurality of parameters, has higher requirements on knowledge background, and has lower modeling efficiency and accuracy.
The Chinese patent with publication number of CN110606121A and name of a drive-by-wire steering road feel simulation control method relates to a steering wheel feedback force control system, a steering load model is constructed through dynamics to calculate steering resistance moment, a typical mechanism modeling method is adopted, parameters needing to be regulated are numerous, and accuracy is difficult to guarantee.
Disclosure of Invention
The invention aims to provide a steering road feel simulation method based on K-Means and Gaussian process regression, which is used for modeling by using real vehicle test data, a K-Means clustering algorithm and a Gaussian process regression algorithm to obtain a steering road feel model based on K-Means and Gaussian process regression, so that more realistic steering road feel is simulated, and the problems of complex model structure, low precision and the like in traditional mechanism modeling are solved.
In order to achieve the above purpose, the invention provides a steering road feel simulation method based on K-Means and Gaussian process regression, which comprises the following steps:
step one, carrying out a multi-working-condition real vehicle test: the driver drives the real vehicle to run on the road comprising various road surface types, and the running conditions of the test vehicle comprise straight running, reversing, turning and in-situ steering; the data collected in the test comprise vehicle vertical load, steering wheel angle speed, longitudinal vehicle speed, vehicle lateral acceleration, vehicle yaw rate and steering wheel moment;
step two, test data pretreatment: preprocessing test data comprises deleting abnormal points and normalizing;
step three, normalized data clustering: clustering the normalized test data by using a K-Means clustering algorithm to obtain a plurality of cluster center coordinates and the same number of data classes corresponding to the plurality of cluster center coordinates;
step four, dividing training and testing data sets: dividing the clustered normalized test data set into a training data set and a test data set;
training a steering road feel model: training to obtain a plurality of steering road feel models which are the same in number as data classes and are based on K-Means and Gaussian process regression by using a training data set and Gaussian process regression algorithm; when the model is trained, the input variables of the model comprise vehicle vertical load, steering wheel angle speed, longitudinal vehicle speed, vehicle transverse acceleration and vehicle yaw rate; the output variable is steering wheel torque;
step six, testing a steering road feel model: using a test data set to test the obtained steering road feel model based on K-Means and Gaussian process regression;
step seven, judging whether the model is acceptable or not: judging whether the model is acceptable according to the test result, if so, modeling is successful, otherwise, carrying out a multi-working-condition real vehicle test again;
and step eight, performing steering road feel simulation according to the obtained multiple steering road feel models based on K-Means and Gaussian process regression.
Further, in step one, the road surface types involved in the real vehicle test include expressways, urban roads, rural roads, and suburban roads.
Further, in the second step, the deleted outliers include data points that are out of the normal range of values and data points whose distribution is severely deviated.
The data points beyond the normal value range are defined as: if the data corresponding to one or more variables in a data point is beyond the normal value range, the data point is called a point beyond the normal range. For example, if the vehicle is traveling forward only in a certain test among the data points, but the vehicle speed in the obtained data has a negative value, all the data points with negative vehicle speeds in the test can be deleted.
The data points for which the distribution deviates significantly are defined as: the data are distributed at points outside the range of standard deviation of a plurality of times of the whole related variable data. The multiple is preferably, but not limited to, 1.5 times, i.e., the standard deviation of each variable data collected in a test is calculated, and if one or several variable values of a data point is greater than 1.5 times the standard deviation of the related variable or less than minus 1.5 times the related variable, the data point is called the point where the distribution is severely deviated.
Further, the test data is normalized according to the following formula to obtain normalized test data:
wherein i is the data number, j is the variable number, x i,j Represents the j-th variable, X in the unnormalized i-th set of data j And (3) representing a set formed by variable data values corresponding to all j, wherein min represents the minimum value of the related variable in the test data after the abnormal point is deleted, and max represents the maximum value of the related variable in the test data after the abnormal point is deleted.
Preferably, in step three, when the K-Means clustering algorithm is used for clustering, variables involved in the clustering include, but are not limited to, vehicle vertical load, steering wheel angle speed, longitudinal vehicle speed, vehicle lateral acceleration, vehicle yaw rate. Steering wheel moments may not participate in the clustering. When K-Means is adopted to cluster the normalized test data, the clustering quantity K is required to be set. And after the clustering is finished, k clustering center point coordinates can be obtained. These coordinates are normalized data for the variables that participate in the cluster.
In a specific embodiment, the number of clusters of the K-Means clustering algorithm is set to 4. And k=4 cluster center point coordinates can be obtained after the clustering is finished. These coordinates are normalized correlation variable values.
Preferably, in the step four, when the training data set and the test data set are divided, a certain number of data points with a certain proportion are randomly selected from the normalized test data set as the training data set, and the others are all used as the test data set. In a preferred embodiment, this proportion is 70%. That is, the ratio of the number of data points in the training data set to the number of data points in the test data set is 7:3.
Preferably, in the fifth step, modeling is performed by using a training data set and a gaussian process regression algorithm, and the training is performed to obtain the steering road feel models based on K-Means and gaussian process regression, where the number of steering road feel models is the same as the number of data classes, and in this embodiment, k=4 steering road feel models are obtained. When the model is trained, the input variables of the Gaussian process regression model comprise vehicle vertical load, steering wheel angle speed, longitudinal vehicle speed, vehicle lateral acceleration and vehicle yaw rate; the output variable is steering wheel torque. The model obtained by training the training data points of the same type is related to the type of the data points, namely, the steering road feel model corresponding to the training data points of a certain type can only be used for predicting the steering wheel moment of the data points of the certain type. Training the multiple types of training data points will result in a corresponding multiple steering feel model.
When training a steering road feel model based on K-Means and Gaussian process regression, the specific steps are as follows:
for the gaussian process regression algorithm, the training dataset is represented as:
D＝(X,y)
wherein:
X＝{x i }，y＝{y i }，x i represents the ith input data, y i Representing an i-th output value;
y＝f(x n )+ξ n
mean value u, kernel function k (x i ,x j ) The method comprises the steps of carrying out a first treatment on the surface of the The noise matrix isThen
y～N[0,K(X,X)+σ 2 I]
Wherein K (X, X) is the corresponding kernel function, I is the corresponding identity matrix, given a new data input X * The corresponding output is y * The method comprises the steps of carrying out a first treatment on the surface of the According to the Bayesian principle, the output value y * The joint distribution with training data is:
calculating corresponding posterior distribution y; the predicted output y can be expressed as:
y*|X,y,x * ～N(μ,∑)
wherein, the liquid crystal display device comprises a liquid crystal display device,
the mean of the predicted distribution in the equation is actually an estimate of the test output.
Using the square-index covariance function (squared exponential covariance function, SE) to solve for the super-parameters of the kernel function, including sigma, by maximum likelihood estimation n 、σ f And l. The SE kernel function may be expressed as:
further, when testing a steering feel model based on K-Means and Gaussian process regression, a mean square error, or MSE, may be used, but is not limited to, as a criterion for model quality. When the test data set is used for testing the steering road feel model based on K-Means and Gaussian process regression, the method comprises the following steps:
sequentially inputting the numerical values of input variables corresponding to the test data points in the test data set into a steering road feel model to obtain a predicted steering wheel moment value; calculating to obtain MSE values between the steering wheel moment values obtained by predicting the test data points of the whole test data set and the real steering wheel moment values; and judging whether the steering road feel model is acceptable according to the MSE value. Specifically, if the MSE value is smaller than a preset threshold value gamma, the steering road feel model based on data driving obtained through training is considered to be acceptable, and modeling is successful. Otherwise, the model is not acceptable, and a supplementary road mining test is needed.
The threshold γ is empirically determined by an expert and in a preferred embodiment, the threshold γ is set to 0.15.
After the modeling is completed, the method further comprises a model application step, and steering road feel simulation is carried out according to the obtained multiple steering road feel models based on K-Means and Gaussian process regression. The specific process is as follows: collecting real-time running data of a vehicle as new data, wherein the real-time running data comprise vehicle vertical load, steering wheel corner speed, longitudinal vehicle speed, vehicle transverse acceleration and vehicle yaw rate, and calculating Euclidean distances between the real-time running data and k cluster center coordinates according to the running data, wherein the data class of the cluster center with the smallest Euclidean distance is the data class of the new data. And then, inputting the driving data into a steering road feel model corresponding to the data class and based on K-Means and Gaussian process regression, calculating to obtain a predicted steering wheel moment value, and controlling the steering wheel according to the steering wheel moment value to simulate more realistic steering road feel.
By adopting the technical scheme, the invention achieves the following technical effects: based on real vehicle test data, a K-Means clustering algorithm is adopted to cluster the test data and model the test data based on a Gaussian process regression algorithm, so that the data acquisition is convenient, the modeling speed is high, and the obtained steering road feel model is good in robustness and high in accuracy; the steering road feel simulation is carried out according to the obtained steering road feel model, so that a driver can obtain more realistic steering road feel, the real-time performance is good, and the defects of the prior art are overcome.
Drawings
FIG. 1 is a flow chart of modeling steps in a steering feel simulation method based on K-Means and Gaussian process regression in accordance with the present invention.
Fig. 2 is a steering wheel torque curve (local) for suburban conditions acquired in an embodiment according to the invention.
Fig. 3 is model test data (local) in an embodiment according to the invention.
Detailed Description
In order that the present invention may be better understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings, in which it is to be understood that the invention is illustrated in the appended drawings. All other embodiments obtained under the premise of equivalent changes and modifications made by those skilled in the art based on the embodiments of the present invention shall fall within the scope of the present invention.
Referring to fig. 1 to 3, the present embodiment provides a steering feel simulation method based on K-Means and gaussian process regression, which includes modeling steps S1 to S7, and model application steps. Steps S1-S7 of the modeling process are described in detail below in conjunction with fig. 1.
S1, performing a multi-working-condition real vehicle test:
selecting a driver to perform a real vehicle test, wherein the driving vehicle runs in a test road, and the road surface type of the test road comprises, but is not limited to, expressways, urban roads, rural roads, suburban roads and the like; the vehicle driving conditions involved include, but are not limited to, straight, reverse, cornering, in-situ steering, and the like. The selected driver has 2 years of driving age, and the driving duration per week in the last year is not less than 2 hours. Test data collected in the real vehicle test comprises vehicle vertical load, steering wheel angle speed, longitudinal vehicle speed, vehicle transverse acceleration, vehicle yaw rate, steering wheel moment and the like. The data acquisition frequency in this example was 100Hz and about 16820000 sets of test data were acquired in total. Wherein, steering wheel corner, steering wheel angular velocity, steering wheel moment use the corner torque sensor to measure, model KISTLER MSW DTI sensors. The longitudinal speed, the lateral acceleration and the yaw rate of the vehicle are measured by an inertial navigation system, and the model is OxTs RT3002.
As shown in fig. 2, the steering wheel torque curve (local) for suburban operation collected in the test of this example is represented by the actual steering wheel torque-data numbering curve.
S2, preprocessing test data:
the data preprocessing comprises the steps of deleting abnormal points and normalizing test data. The deleted outliers include data points outside the normal range of values and data points with severely deviated distribution. The abnormal point can be deleted manually or filtered by a low-pass filter. And carrying out normalization processing on the acquired test data according to the following formula to obtain normalized test data. The normalization formula may take, but is not limited to, the following:
wherein i is the data number and j is the variable codeNumber, x i,j Represents the j-th variable, X in the unnormalized i-th set of data j And (3) representing a set formed by variable data values corresponding to all j, wherein min represents the minimum value of the related variable in the test data after the abnormal point is deleted, and max represents the maximum value of the related variable in the test data after the abnormal point is deleted.
After pretreatment, a normalized test dataset was obtained.
S3, normalized data clustering
And clustering the normalized test data by using a K-Means clustering algorithm, wherein 4 data classes with the same number as the clustering number are obtained after clustering in the embodiment. When clustering is performed using the K-Means clustering algorithm, variables involved in the clustering include, but are not limited to, vehicle vertical load, steering wheel angle speed, longitudinal vehicle speed, vehicle lateral acceleration, vehicle yaw rate. Steering wheel moments may not participate in the clustering.
The clustering step of the K-Means algorithm is as follows:
(1) The number of clusters k required is determined.
(2) Randomly selecting k data points in a data set to be clustered as central points of k class groups;
(3) Calculating Euclidean distances from all data points of non-center points to k center points determined in the last step, wherein a community corresponding to the center point with the nearest data point distance is the community to which the data point belongs;
(4) Sequentially selecting a point in each community, calculating the sum of Euclidean distances between the point and all other points in the current community, and taking the point with the smallest obtained Euclidean distance sum as a new center point of the community;
(5) Repeating the steps (2) and (3) until the center point of each cluster is not changed.
In this embodiment, the number of clusters is determined to be 4 in the K-Means algorithm. And 4 clustering center point coordinates are the data of related variables participating in clustering.
And when the new data is predicted, calculating to obtain the Euclidean distance between the new data and the coordinates of the clustering centers, wherein the data class corresponding to the clustering center with the smallest Euclidean distance is the data class to which the new data belongs.
S4, dividing a training data set test data set:
when dividing the training data set and the test data set, 70% of the data points from the normalized test data set are randomly selected as the training data set, and the others are all used as the test data set. The ratio of the number of data points in the training data set to the number of data points in the test data set is 7:3. The training data set after clustering is called as a training data set after clustering; the clustered test data set is referred to as clustered test data aggregate.
S5, training a steering road feel model:
modeling is carried out by using a clustered training data set and a Gaussian process regression algorithm, a plurality of steering road feel models with the same data class number and based on K-Means and Gaussian process regression are obtained through training, and 4 steering road feel models are obtained in the embodiment. When the model is trained, the input variables of the Gaussian process regression model comprise vehicle vertical load, steering wheel angle speed, longitudinal vehicle speed, vehicle lateral acceleration and vehicle yaw rate; the output variable is steering wheel torque. The model obtained by training the training data points of the same type is related to the type of the data points, namely, the steering road feel model corresponding to the training data points of a certain type can only be used for predicting the steering wheel moment of the data points of the certain type. In this embodiment, 4 data classes obtained by clustering are adopted, and after training, corresponding 4 steering road feel models are obtained.
When training a steering road feel model based on K-Means and Gaussian process regression, the specific steps are as follows:
the training dataset is represented as:
D＝(X,y)
wherein:
X＝{x i }，y＝{y i }，x i represents the ith input data, y i Representing an i-th output value;
y＝f(x n )+ξ n
mean value u, kernel function k (x i ,x j ) The method comprises the steps of carrying out a first treatment on the surface of the The noise matrix isThen
y～N[0,K(X,X)+σ 2 I]
Wherein K (X, X) is the corresponding kernel function, I is the corresponding identity matrix, given a new data input X * The corresponding output is y * The method comprises the steps of carrying out a first treatment on the surface of the According to the Bayesian principle, the output value y * The joint distribution with training data is:
calculating corresponding posterior distribution y; the predicted output y can be expressed as:
y*|X,y,x * ～N(μ,∑)
wherein, the liquid crystal display device comprises a liquid crystal display device,
the mean of the predicted distribution in the equation is actually an estimate of the test output.
Selecting square index covariance function SE for solving super-parameters of kernel function by maximum likelihood estimation, including sigma n 、σ f And l. The SE kernel function may be expressed as:
the present example was trained using the hewlett-packard Z1G6 workstation, and the total training time for the 4-turn road feel model was 2 minutes and 32 seconds.
S6, testing a steering road feel model:
when testing the steering road feel model based on K-Means and Gaussian process regression, the step of using the clustered test data set to test the obtained steering road feel model based on K-Means and Gaussian process regression is as follows: sequentially inputting the numerical values of input variables corresponding to the test data points in the test data set into a steering road feel model to obtain a predicted steering wheel moment value; calculating to obtain MSE values between the steering wheel moment values obtained by predicting the test data points of the whole test data set and the real steering wheel moment values; if the MSE value is smaller than the preset threshold value gamma, the steering road feel model based on data driving obtained through training is considered to be acceptable, and modeling is successful. In this embodiment, as shown in fig. 3, which shows a model test curve (local), it can be seen from the graph that the simulated steering wheel moment-time curve (sim) substantially coincides with the actual steering wheel moment-time curve (real) within a period of 0-200s, and the MSE value is 0.091.
S7, judging whether the model is acceptable according to the test result
Judging whether the model is acceptable according to the test result, namely the model precision, if the model is acceptable, modeling is successful, otherwise, carrying out the multi-working-condition real vehicle test again. The MSE value=0.091 obtained by the test in the step S6 is far smaller than the preset threshold value gamma=0.15, the precision of the obtained steering road feel model based on K-Means and Gaussian process regression meets the requirement, the model is acceptable, and the road acquisition test or the supplementary road acquisition test is not needed to be carried out again.
Model application step:
after modeling is completed, the steering road feel simulation method according to the invention further comprises a model application step: and performing road feel simulation according to the obtained steering road feel model based on K-Means and Gaussian process regression. The obtained 4 steering road feel models based on K-Means and Gaussian process regression are input into a driving simulator, when a simulated driving test is carried out on the driving simulator, running state parameters such as vehicle vertical load, steering wheel rotation angle speed, longitudinal speed, vehicle transverse acceleration, vehicle yaw rate and the like of a simulated vehicle are acquired in real time, euclidean distances between the steering road feel models and coordinates of 4 clustering centers are calculated according to a K-Means clustering algorithm, and the data class of the clustering center with the smallest Euclidean distance is the data class of new data. And then, the corresponding variable of the running state parameter is used as an input variable to be input into a steering road feel model corresponding to the data class, a steering wheel moment value is calculated through the steering road feel model based on K-Means and Gaussian process regression, and the steering wheel is controlled in real time according to the steering wheel moment value, so that more realistic road feel can be simulated. Experiments prove that the steering road feel model built by the invention has stable performance, high precision and high operation speed, and overcomes the defects of the prior art to a certain extent.
The foregoing is merely a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention; it will be apparent to those skilled in the relevant art and it is intended to implement the invention in light of the foregoing disclosure without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. The steering road feel simulation method based on K-Means and Gaussian process regression is characterized by comprising the following steps of:
step one, carrying out a multi-working-condition real vehicle test: the driver drives the real vehicle to run on the road comprising various road surface types, and the running conditions of the test vehicle comprise straight running, reversing, turning and in-situ steering; the data collected in the test comprise vehicle vertical load, steering wheel angle speed, longitudinal vehicle speed, vehicle lateral acceleration, vehicle yaw rate and steering wheel moment;
step two, test data pretreatment: preprocessing test data comprises deleting abnormal points and normalizing;
step three, normalized data clustering: clustering the normalized test data by using a K-Means clustering algorithm to obtain a plurality of cluster center coordinates and the same number of data classes corresponding to the plurality of cluster center coordinates;
step four, dividing training and testing data sets: dividing the clustered normalized test data set into a training data set and a test data set;
training a steering road feel model: training to obtain a plurality of steering road feel models which are the same in number as data classes and are based on K-Means and Gaussian process regression by using a training data set and Gaussian process regression algorithm; when the model is trained, the input variables of the model comprise vehicle vertical load, steering wheel angle speed, longitudinal vehicle speed, vehicle transverse acceleration and vehicle yaw rate; the output variable is steering wheel torque;
step six, testing a steering road feel model: using a test data set to test the obtained steering road feel model based on K-Means and Gaussian process regression;
step seven, judging whether the model is acceptable or not: judging whether the model is acceptable according to the test result, if so, modeling is successful, otherwise, carrying out a multi-working-condition real vehicle test again;
and step eight, performing steering road feel simulation according to the obtained multiple steering road feel models based on K-Means and Gaussian process regression.
2. The method of simulating steering feel based on K-Means and gaussian process regression according to claim 1, characterized in that the road surface types involved in the real vehicle test include expressways, urban roads, rural roads and suburban roads.
3. The method of claim 1, wherein in the second step, the deleted outliers include data points out of the normal range and data points with a severely deviated distribution.
4. The steering feel simulation method based on K-Means and Gaussian process regression according to claim 1, wherein in the second step, the test data is normalized according to the following formula to obtain normalized test data:
wherein i is the data number, j is the variable number, x i,j Represents the jth variable in the unnormalized ith set of data，X j And (3) representing a set formed by variable data values corresponding to all j, wherein min represents the minimum value of the related variable in the test data after the abnormal point is deleted, and max represents the maximum value of the related variable in the test data after the abnormal point is deleted.
5. The steering feel simulation method based on K-Means and Gaussian process regression according to claim 1, wherein in the third step, when clustering is performed by using a K-Means clustering algorithm, variables involved in clustering include vehicle vertical load, steering wheel angle speed, longitudinal vehicle speed, vehicle lateral acceleration and vehicle yaw rate.
6. The steering feel simulation method based on K-Means and Gaussian process regression according to claim 1, wherein in the fourth step, when a training data set and a test data set are divided, a certain number of data points in proportion are randomly selected from a normalized test data set as the training data set, and other data points are all used as the test data set.
7. The method according to any one of claims 1 to 6, wherein in the fifth step, when training the steering feel model based on the K-Means and gaussian process regression, the square index covariance function SE is selected to be used, and the super-parameters of the kernel function are solved by maximum likelihood estimation.
8. The steering feel simulation method based on K-Means and Gaussian process regression according to claim 1, wherein the specific steps of testing the steering feel model based on K-Means and Gaussian process regression and judging whether the model is acceptable according to the test result are as follows:
inputting the numerical value of the input variable corresponding to the test data point in the test data set into a steering road feel model to obtain a predicted steering wheel moment value; calculating to obtain MSE values between the steering wheel moment values obtained by predicting the test data points of the whole test data set and the real steering wheel moment values; and judging whether the steering road feel model based on K-Means and Gaussian process regression obtained through training is acceptable or not according to the MSE value.
9. The steering feel simulation method based on K-Means and Gaussian process regression according to claim 8, wherein if the MSE value is smaller than a preset threshold gamma, the obtained steering feel model based on K-Means and Gaussian process regression is considered acceptable, and modeling is successful.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110033492.4A CN112801143B (en) | 2021-01-11 | 2021-01-11 | Steering road feel simulation method based on K-Means and Gaussian process regression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110033492.4A CN112801143B (en) | 2021-01-11 | 2021-01-11 | Steering road feel simulation method based on K-Means and Gaussian process regression |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112801143A CN112801143A (en) | 2021-05-14 |
| CN112801143B true CN112801143B (en) | 2023-08-15 |
Family
ID=75809968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110033492.4A Active CN112801143B (en) | 2021-01-11 | 2021-01-11 | Steering road feel simulation method based on K-Means and Gaussian process regression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801143B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949173A (en) * | 2021-02-26 | 2021-06-11 | 南京经纬达汽车科技有限公司 | Road feel simulation method based on K-Medoids and Gaussian process regression |
| CN113135192B (en) * | 2021-05-20 | 2022-12-20 | 北京理工大学 | Estimation method for slip ratio of tracked vehicle capable of obtaining estimation uncertainty |
| CN113135191B (en) * | 2021-05-20 | 2022-11-18 | 北京理工大学 | Tracked vehicle slip rate estimation method based on road surface classification and machine learning |
| CN113933012B (en) * | 2021-10-14 | 2024-01-30 | 西安现代控制技术研究所 | Propeller rotating speed measuring method based on K-means clustering |
| CN114841292B (en) * | 2022-07-04 | 2022-11-01 | 岚图汽车科技有限公司 | Method and device for obtaining endurance test load of automobile steering system rack |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800801A (en) * | 2019-01-10 | 2019-05-24 | 浙江工业大学 | K-Means clustering lane method of flow based on Gauss regression algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110246409A1 (en) * | 2010-04-05 | 2011-10-06 | Indian Statistical Institute | Data set dimensionality reduction processes and machines |
-
2021
- 2021-01-11 CN CN202110033492.4A patent/CN112801143B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800801A (en) * | 2019-01-10 | 2019-05-24 | 浙江工业大学 | K-Means clustering lane method of flow based on Gauss regression algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 基于高斯过程模型的异常检测算法;于冰洁;夏战国;王久龙;;计算机工程与设计(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112801143A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112801143B (en) | Steering road feel simulation method based on K-Means and Gaussian process regression | |
| CN112356830B (en) | Intelligent parking method based on model reinforcement learning | |
| CN105741637B (en) | Four-wheel hub motor electric car automated steering control method | |
| CN105136469A (en) | Unmanned vehicle speed control method based on PSO and RBF neutral network | |
| CN105034986B (en) | A kind of driver's steering characteristic on-line identification method and device | |
| CN104462716B (en) | A kind of the brain-computer interface parameter and kinetic parameter design method of the brain control vehicle based on people's bus or train route model | |
| CN112632705B (en) | Road feel simulation method based on GMM and Gaussian process regression | |
| CN112632706B (en) | Road feel simulation method based on GMM and CART regression tree | |
| CN112749508B (en) | Road feel simulation method based on GMM and BP neural network | |
| CN112550450B (en) | Road feel simulation method based on K-Means and CART regression tree | |
| CN112580149A (en) | Vehicle following model generation method based on generation of countermeasure network and driving duration | |
| CN113642114B (en) | Personified random following driving behavior modeling method capable of making mistakes | |
| CN116560223A (en) | Intelligent vehicle dynamics model, ILQR control algorithm and track tracking controller based on physical information neural network | |
| CN111967308A (en) | Online road surface unevenness identification method and system | |
| CN114547963A (en) | Tire modeling method and medium based on data driving | |
| CN112528568B (en) | Road feel simulation method based on K-Means and BP neural network | |
| CN112937587A (en) | Road feel simulation method based on K-Medoids and classification regression tree | |
| CN112381376A (en) | Method and device for evaluating driving ability process | |
| CN111923916A (en) | Human-simulated steering modeling method and steering control system based on visual perception behaviors and ANFIS | |
| CN112651134A (en) | Steering road feel simulation method based on Gaussian process regression | |
| CN116538286A (en) | Commercial vehicle gear shifting system and method considering NVH characteristics | |
| CN112685956A (en) | Road feel simulation method based on CART regression tree | |
| Chen et al. | DCFS-based deep learning supervisory control for modeling lane keeping of expert drivers | |
| CN112597597A (en) | Road feel simulation method based on K-Medoids and BP neural network | |
| CN112836722B (en) | Road feel simulation method based on data driving |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |