CN112550450A - Road feel simulation method based on K-Means and CART regression tree - Google Patents

Road feel simulation method based on K-Means and CART regression tree Download PDF

Info

Publication number
CN112550450A
CN112550450A CN202011570750.4A CN202011570750A CN112550450A CN 112550450 A CN112550450 A CN 112550450A CN 202011570750 A CN202011570750 A CN 202011570750A CN 112550450 A CN112550450 A CN 112550450A
Authority
CN
China
Prior art keywords
test data
vehicle
data set
cart regression
road
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.)
Granted
Application number
CN202011570750.4A
Other languages
Chinese (zh)
Other versions
CN112550450B (en
Inventor
赵蕊
蔡锦康
邓伟文
丁娟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Tianxingjian Intelligent Technology Co ltd
Original Assignee
Zhejiang Tianxingjian Intelligent Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Tianxingjian Intelligent Technology Co ltd filed Critical Zhejiang Tianxingjian Intelligent Technology Co ltd
Priority to CN202011570750.4A priority Critical patent/CN112550450B/en
Publication of CN112550450A publication Critical patent/CN112550450A/en
Application granted granted Critical
Publication of CN112550450B publication Critical patent/CN112550450B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
    • B62D—MOTOR VEHICLES; TRAILERS
    • B62D6/00—Arrangements for automatically controlling steering depending on driving conditions sensed and responded to, e.g. control circuits
    • B62D6/008—Control of feed-back to the steering input member, e.g. simulating road feel in steer-by-wire applications
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/15—Vehicle, aircraft or watercraft design
    • 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

Abstract

The invention discloses a road feel simulation method based on K-Means and CART regression trees, which comprises the following steps: carrying out an actual vehicle road mining test and collecting test data; preprocessing test data; clustering the test data by using a K-Means clustering algorithm; dividing a training data set and a test data set; training a road feeling simulation model based on K-Means and the CART regression tree by using a CART regression tree algorithm; testing a road feel simulation model based on K-Means and CART regression trees; and performing road feel simulation according to the obtained road feel simulation model based on the K-Means and CART regression tree. The real vehicle is used for collecting test data, the K-Means clustering algorithm and the CART regression tree algorithm are adopted for modeling the road feel simulation model, the modeling time is short, the model calculation speed is high, the accuracy of the obtained road feel simulation model is high, the real-time performance is good, and the defects of the prior art are overcome.

Description

Road feel simulation method based on K-Means and CART regression tree
Technical Field
The invention relates to the technical field of automobiles, in particular to a road feel simulation method based on K-Means and CART regression trees.
Background
The steering road feel, also called steering force feel and steering wheel feedback torque, refers to the reverse resistance torque felt by the driver through the steering wheel feedback torque. The steering force sense can enable a driver to obtain key vehicle running state and running environment information to a certain extent, so that the driver can make a decision in a mode most suitable for the current running working condition, and running safety is guaranteed. At present, the main road feel modeling method is a mechanism modeling method, and the method has a plurality of parameters needing to be adjusted and is difficult to achieve high precision.
The Chinese patent with the publication number of CN110606121A and the name of 'a line control steering road feel simulation control method' relates to a control system of steering wheel feedback force, a steering resistance moment is calculated by building a steering load model through dynamics, and the method belongs to mechanism modeling, has a plurality of parameters needing to be adjusted, and is difficult to ensure the precision.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a road feel simulation method based on K-Means and CART regression trees, which is used for obtaining a road feel simulation model based on the K-Means and CART regression trees by using real vehicle test data, a K-Means algorithm and a CART regression tree algorithm and solving the problems of complex model structure, low precision and the like in the traditional mechanism modeling.
In order to achieve the aim, the invention provides a road feel simulation method based on K-Means and CART regression trees, which comprises the following steps:
step one, carrying out an actual vehicle road mining test and acquiring data: selecting a driver to carry out an actual vehicle test, wherein the vehicle runs in a test road, and the collected test data comprises the longitudinal speed of the vehicle, the transverse acceleration of the vehicle, the yaw velocity of the vehicle, the vertical load of the vehicle, the turning angle of a steering wheel, the angular speed of the steering wheel and the torque of the steering wheel;
step two, test data preprocessing: carrying out normalization processing on the test data after removing abnormal points to obtain a normalized test data set;
step three, carrying out normalized test data clustering by using K-Means: clustering the normalized test data by using a K-Means clustering algorithm to obtain a plurality of clustering centers and a plurality of corresponding data classes after clustering;
step four, dividing a training data set and a testing data set: dividing the clustered normalized test data into a clustered training data set and a clustered test data set;
step five, training a road feeling model based on K-Means and CART regression trees: when a road feel simulation model based on K-Means and CART regression trees is trained by using a clustered training data set and a CART regression tree algorithm, input variables of the CART regression tree model are vehicle longitudinal speed, vehicle transverse acceleration, vehicle yaw angular velocity, vehicle vertical load, steering wheel turning angle and steering wheel angular velocity, output variables are steering wheel moment, and road feel simulation models based on K-Means and CART regression trees and with the same quantity as data classes are obtained through training;
step six, testing a road feel model based on K-Means and CART regression trees; testing a road feel simulation model based on K-Means and CART regression trees by using the clustered test data set;
step seven, judging whether the model is acceptable; if the model is acceptable, the modeling is successful, otherwise, the actual vehicle road mining test is carried out again;
and step eight, carrying out road feel simulation according to the obtained road feel simulation model based on the K-Means and CART regression tree.
Further, in the real vehicle test of the step one:
the test road types comprise urban roads, expressways, suburban roads and rural roads;
the vehicle running conditions comprise uphill, downhill, straight running, backing, turning and pivot steering conditions.
Further, in step two, the removed abnormal points include data points beyond the normal value range, data points with severely deviated distribution, and data points with a variation range beyond the normal range.
The data points beyond the normal value range are defined as: and (3) acquiring a certain data point in a certain real vehicle test, wherein the numerical value of one or more variables exceeds the actual normal value range of the corresponding variable of the real vehicle test. For example, in a certain test, the highest vehicle longitudinal speed is only 90km/h, and in the data collected in the test, the data points with the vehicle longitudinal speed value greater than 90km/h are all out-of-range points. For another example, if the steering wheel angle range is [ -100 °,100 ° ] in a certain test, the points of the steering wheel angle values exceeding [ -100 °,100 ° ] in the data collected in the test are all out of the normal range.
The heavily distributed data points are defined as: and calculating the standard deviation of each variable of the test data acquired in a certain real vehicle test, and if the numerical value of one or more variables of a certain data point is more than 3.5 times of the standard deviation of the corresponding variable or less than minus 3.5 times of the standard deviation of the corresponding variable, determining that the distribution of the data point is seriously deviated.
The data points with the variation amplitude exceeding the normal range are defined as follows: the maximum instantaneous change amplitude of each variable under the normal condition is preset, and if the absolute value of the difference value of one or more variable values of a certain data point relative to the corresponding variable value of the previous data point in the actual test data set is larger than the maximum instantaneous change amplitude of the related variable, the maximum instantaneous change amplitude of each variable exceeds the normal range. If the expert confirms that the maximum instantaneous change amplitude of the steering wheel torque is 0.5N when a high-speed driving test is performed by using a small passenger car, the data points in which the absolute value of the difference between the steering wheel torque value and the previous data point is greater than 0.5N are all points with the change amplitude exceeding the normal range.
Further, in the second step, the test data is normalized according to the following formula to obtain normalized test data:
Figure BDA0002862549980000031
wherein i is a data number, j is a variable number, and xi,jDenotes the j variable, X, in the non-normalized i group of datajAnd representing a set consisting of variable data values corresponding to all j, min representing the minimum value of the related variable in the test data after the abnormal point is removed, and max representing the maximum value of the related variable in the test data after the abnormal point is removed.
Preferably, in the third step, when the K-Means clustering algorithm is used for clustering the normalized test data, the number of clusters is set to 4, 4 cluster centers are obtained after clustering, and the normalized test data is divided into 4 data classes according to the coordinates of the 4 cluster centers. The specific steps of clustering the test data by adopting the K-means clustering algorithm comprise:
1) setting the number K of clusters needing to be divided to be 4;
2) clustering the normalized test data by using a K-means clustering algorithm to obtain K which is 4 category central points;
3) and calculating Euclidean distances between a certain newly input data point and the central points of the 4 categories, wherein the type of the central point corresponding to the minimum Euclidean distance value is the type of the newly input data point.
Preferably, in the fourth step, when the training data set and the test data set are divided, a certain number of data points 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;
the clustered training data set is called a clustered training data set; the clustered test data set is referred to as a post-clustering test data aggregation.
Preferably, in the step five, when the road feeling simulation model based on the K-Means and CART regression tree is trained, the specific steps are as follows:
the CART regression tree model is represented as:
Figure BDA0002862549980000032
wherein, f (x) is a CART regression tree function, m is a positive integer greater than 1, I is a unit matrix, and x is an input variable; the data space is divided into R1～RmCells, each cell having a fixed output value cm；
Calculating the error of the model output value and the actual value:
Figure BDA0002862549980000041
wherein x isiFor input of the i-th data of variable x, yiIs the actual output value; i is a positive integer greater than 1;
suppose that the jth input variable x is selectedjThe input variable is any one of a longitudinal speed of a vehicle, a lateral acceleration of the vehicle, a yaw velocity of the vehicle, a vertical load of the vehicle, a steering wheel angle and an angular velocity of the steering wheel, and j is a variable number; taking the value s of the segmentation variable as a segmentation point to obtain two regions R1，R2：
R1(j,s)＝{x|x(f)≤s}；R2(j,s)＝{x|x(f)＞s}
When j and s are fixed, find the representative value c of the two regions1，c2The squared difference over the respective intervals is minimized, i.e.:
Figure BDA0002862549980000042
in the formula c1，c2Is the average over the interval, i.e.:
Figure BDA0002862549980000043
the working steps of training the CART regression tree model using the clustered training data set are as follows:
1) inputting: a training data set D;
2) and (3) outputting: regression tree f (x);
3) recursively dividing each region into two sub-regions in an input space where the training data set is located, and determining an output value of each sub-region; constructing a binary decision tree, comprising the steps of:
selecting an optimal segmentation variable j and a segmentation point s, and solving:
Figure BDA0002862549980000044
secondly, traversing the variable j, scanning a segmentation point s for the fixed segmentation variable j, and selecting a pair (j, s) which enables the above formula to reach the minimum value;
-dividing the area by the selected pair (j, s) and determining the corresponding output value:
R1(j,s)＝{x|x(f)≤s}；R2(j,s)＝{x|x(f)＞s}
Figure BDA0002862549980000045
in the formula, NmIs the total number of data points in space;
fourthly, continuously calling the steps (1) and (2) for the two subregions until the circulation times reach the upper limit value, namely the tree depth reaches the upper limit value;
divide the input space into M regions R1,R2,...,RMAnd generating a decision tree.
Preferably, in a specific embodiment, the upper limit value of the number of cycles of the step (iv) is 10.
When the road feel simulation model of the CART regression tree is trained, the model obtained by training the same type of training data points is related to the type of the data points, namely the road feel simulation model corresponding to a certain type of training data points can only be used for predicting the steering wheel moment of the type of data points. After the training data points of multiple types are trained, multiple corresponding road feel simulation models are obtained.
Further, when testing road feel simulation models based on K-Means and CART regression trees, the Mean Square Error (MSE) value can be used, but is not limited to being used, as the evaluation criterion of the model quality. When the road feel simulation model based on the K-Means and CART regression tree is tested by using a test data set, the steps are as follows:
1) taking out a test data point in the test data set, and inputting the value of an input variable corresponding to the test data point into a road feel simulation model corresponding to the class to which the test data point belongs to obtain a predicted steering wheel torque value;
2) repeating the step 1) until all the test data points are predicted by using the road feel simulation model;
3) calculating a Mean Square Error (MSE) value between a predicted steering wheel moment value and a real steering wheel moment value through a model at a test data point of the whole test data set obtained through calculation;
4) judging whether to carry out the test again: and if the MSE value is smaller than a preset threshold value alpha, the road feel simulation model based on the data drive obtained by training is considered to meet the precision requirement, the model is acceptable, and the modeling is successful. Otherwise, the model is not acceptable, and a supplementary road mining test is required. The threshold value alpha is determined empirically by an expert.
Due to the adoption of the technical scheme, the invention achieves the following technical effects: the method is based on data acquired by a real vehicle test, adopts a CART regression tree algorithm to carry out modeling after clustering by a K-Means clustering algorithm, obtains a road feel simulation model for predicting the steering wheel torque, and has high model calculation speed and high precision; road feel simulation is carried out according to the obtained road feel simulation model, and the problems that the model of the traditional mechanism modeling is low in precision, real-time performance in the application process is difficult to guarantee and the like are solved.
Drawings
FIG. 1 is a flow chart of modeling steps in a road feel simulation method based on K-Means and CART regression trees according to the present invention.
FIG. 2 is a partial steering wheel angle data (partial) collected for pivot steering conditions in an embodiment in accordance with the invention.
FIG. 3 is model test data (partial) in an embodiment in accordance with the invention.
Detailed Description
In order to make the technical solution of the embodiments of the present invention better understood, the technical solution of the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by equivalent changes and modifications by one skilled in the art based on the embodiments of the present invention, shall fall within the scope of the present invention.
Example one
Referring to fig. 1 to 3, the present embodiment provides a road feel simulation method based on K-Means and CART regression trees, including real vehicle testing and modeling steps S1-S7, and model application step S8. Steps S1-S6 of the modeling process are described in detail below in conjunction with FIG. 1.
S1, carrying out an actual vehicle road mining test and collecting test data:
selecting a driver to carry out a real vehicle test, wherein the vehicle runs in a test road, and the test road types include but are not limited to urban roads, expressways, suburban roads and rural roads; the vehicle running conditions comprise uphill, downhill, straight running, backing, turning and pivot steering conditions.
The selected driver had a driving age of 3 years and was driven no less than 5 hours per week during the last year. The data acquisition frequency was 100 Hz. The total test mileage is 128 kilometers, and the total test time is about 3 hours.
The collected test data includes vehicle longitudinal velocity, vehicle lateral acceleration, vehicle yaw rate, vehicle vertical load, steering wheel angle, steering wheel angular velocity, and steering wheel moment. As shown in FIG. 2, the partial steering wheel angle data (local) of the pivot steering condition collected in the test of the present embodiment is represented by the actual steering wheel angle-data number curve, wherein the steering wheel angle ranges from [ -500 °,500 ° ]]Data number from 0 to 5X 104。
S2, test data preprocessing:
processing the test data includes removing outliers and normalizing the data. The removed abnormal points include data points outside the normal value range, data points with severely deviated distribution and data points with the variation amplitude exceeding the normal range.
In this embodiment, the collected test data is normalized according to the following formula, so as to obtain normalized test data. The normalization formula may take the following formula, but is not limited to it:
Figure BDA0002862549980000061
wherein i is a data number, j is a variable number, and xi,jDenotes the j variable, X, in the non-normalized i group of datajAnd representing a set consisting of variable data values corresponding to all j, min representing the minimum value of the related variable in the test data after the abnormal point is removed, and max representing the maximum value of the related variable in the test data after the abnormal point is removed.
S3, carrying out normalized test data clustering by using K-Means
Variables participating in clustering include, but are not limited to, vehicle longitudinal velocity, vehicle lateral acceleration, vehicle yaw rate, vehicle vertical load, steering wheel angle, steering wheel angular velocity, and the like. When the K-Means clustering algorithm is used for clustering the normalized test data, the number of clusters is set to be K equal to 4, and after clustering, 4 cluster center coordinates are obtained, wherein the coordinates are the normalized related variable values. The normalized test data was divided into 4 data classes according to the 4 cluster center coordinates.
S4, dividing training data set test data set
When the training data set and the test data set are divided, data points in a certain proportion are randomly selected from the normalized test data set to serve as the training data set, and the other data points 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 was 9: 1.
The clustered training data set is called a clustered training data set; the clustered test data set is referred to as a post-clustering test data aggregation.
S5, training a road feel model based on K-Means and CART regression trees:
and modeling by using the clustered training data set and the CART regression tree algorithm, and training to obtain the road feel simulation model which has the same number with the data set and is based on the K-Means and the CART regression tree. The input variables of the CART regression tree model comprise vehicle longitudinal speed, vehicle lateral acceleration, vehicle yaw rate, steering wheel angle, steering wheel angular speed and vehicle vertical load; the output variable is the steering wheel torque. The number of road feel simulation models obtained by training based on K-Means and CART regression trees is K equal to 4, and the models correspond to 4 clustering centers respectively. Set to 10 at the maximum tree depth. When the model is trained, the model obtained by training the same type of modeling data points is related to the related type, namely, the data points of a certain type of model can only be used for predicting the data points of the type. The number of models trained using the training data points is the same as the number of data point types.
The CART regression tree model is represented as:
Figure BDA0002862549980000071
wherein, f (x) is a CART regression tree function, m is a positive integer greater than 1, I is a unit matrix, and x is an input variable; the data space is divided into R1～RmCells, each cell having a fixed output value cm；
Calculating the error of the model output value and the actual value:
Figure BDA0002862549980000072
wherein x isiFor input of the i-th data of variable x, yiIs the actual output value; i is a positive integer greater than 1;
suppose that the jth input variable x is selectedjFor the segmentation variables, the input variables are vehicle longitudinal speed, vehicle lateral acceleration, vehicle yaw rate, vehicleAny one of the vertical load, the steering wheel angle and the steering wheel angular speed is a segmentation variable, and j is a variable number; taking the value s of the segmentation variable as a segmentation point to obtain two regions R1，R2：
R1(j,s)＝{x|x(f)≤s}；R2(j,s)＝{x|x(f)＞s}
When j and s are fixed, find the representative value c of the two regions1，c2The squared difference over the respective intervals is minimized, i.e.:
Figure BDA0002862549980000081
in the formula c1，c2Is the average over the interval, i.e.:
Figure BDA0002862549980000082
the working steps of training the CART regression tree model using the clustered training data set are as follows:
1) inputting: a training data set D;
2) and (3) outputting: regression tree f (x);
3) recursively dividing each region into two sub-regions in an input space where the training data set is located, and determining an output value of each sub-region; constructing a binary decision tree, comprising the steps of:
selecting an optimal segmentation variable j and a segmentation point s, and solving:
Figure BDA0002862549980000083
secondly, traversing the variable j, scanning a segmentation point s for the fixed segmentation variable j, and selecting a pair (j, s) which enables the above formula to reach the minimum value;
in the formula, NmIs the total number of data points in space;
-dividing the area by the selected pair (j, s) and determining the corresponding output value:
R1(j,s)＝{x|x(f)≤s}；R2(j,s)＝{x|x(f)＞s}
Figure BDA0002862549980000084
fourthly, the steps (1) and (2) are continuously called for the two subregions until the cycle times reach the upper limit value of 10 times, namely the maximum tree depth is reached;
divide the input space into M regions R1,R2,...,RMAnd generating a decision tree.
S6, testing a road feel model based on K-Means and CART regression trees:
when testing the road feel model based on the K-Means and CART regression trees, the steps of using the test data set to test the obtained road feel simulation model based on the K-Means and CART regression trees are as follows:
1) and sequentially inputting data points in the test data set into a road feel simulation model based on K-Means and CART regression trees to obtain a predicted normalized steering wheel moment value. The input data are normalized vehicle longitudinal speed, vehicle lateral acceleration, vehicle yaw rate, vehicle vertical load, steering wheel angle, and steering wheel angular velocity.
2) The MSE value used to measure the quality of the road feel simulation model based on K-Means and CART regression trees was calculated to be 0.11645. As shown in fig. 3, which represents a model test curve (local), it can be seen that the simulated steering wheel moment-time curve (sim) almost coincides with the real steering wheel moment-time curve (real) in a time period of 0-200s, and the MSE value is 0.11645.
S7, judging whether the model meets the precision requirement or not, and determining whether a supplementary road mining test is carried out or not;
and (3) testing to obtain an MSE value of 0.11645 which is far smaller than a threshold value alpha preset by an expert of 0.2, wherein the obtained model is acceptable and a supplementary road mining test is not required.
After the modeling is completed, the road feel simulation method further comprises the step of predicting the steering wheel moment by using the obtained 4 road feel simulation models, namely road feel simulation. Inputting the obtained 4 road feel simulation models into a driving simulator, acquiring running state parameters such as vehicle longitudinal speed, vehicle transverse acceleration, vehicle yaw velocity, steering wheel turning angle, steering wheel angular velocity, vehicle vertical load and the like of a simulated vehicle in real time when a simulated driving test is carried out on the driving simulator, inputting the running state parameters into the road feel simulation models as input variables, determining the data types of the running state parameters according to the correlation degree of the running state parameters and the clustering center coordinates, calculating the steering wheel moment value through the road feel simulation models corresponding to the data types, and controlling the steering wheel in real time according to the steering wheel moment value, so that more realistic road feel is simulated.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention; also, the above description should be understood as being readily apparent to those skilled in the relevant art and can be implemented, and therefore, other equivalent changes and modifications without departing from the concept disclosed herein are intended to be included within the scope of the present invention.

Claims (9)

1. A road feeling simulation method based on K-Means and CART regression trees is characterized by comprising the following steps:
step one, carrying out an actual vehicle road mining test and acquiring data: selecting a driver to carry out an actual vehicle test, wherein the vehicle runs in a test road, and the collected test data comprises the longitudinal speed of the vehicle, the transverse acceleration of the vehicle, the yaw velocity of the vehicle, the vertical load of the vehicle, the turning angle of a steering wheel, the angular speed of the steering wheel and the torque of the steering wheel;
step two, test data preprocessing: carrying out normalization processing on the test data after removing abnormal points to obtain a normalized test data set;
step three, carrying out normalized test data clustering by using K-Means: clustering the normalized test data by using a K-Means clustering algorithm to obtain a plurality of clustering centers and a plurality of corresponding data classes after clustering;
step four, dividing a training data set and a testing data set: dividing the clustered normalized test data into a clustered training data set and a clustered test data set;
step five, training a road feeling model based on K-Means and CART regression trees: when a road feel simulation model based on K-Means and CART regression trees is trained by using a clustered training data set and a CART regression tree algorithm, input variables of the CART regression tree model are vehicle longitudinal speed, vehicle transverse acceleration, vehicle yaw angular velocity, vehicle vertical load, steering wheel turning angle and steering wheel angular velocity, output variables are steering wheel moment, and road feel simulation models based on K-Means and CART regression trees and with the same quantity as data classes are obtained through training;
step six, testing a road feel model based on K-Means and CART regression trees; testing a road feel simulation model based on K-Means and CART regression trees by using the clustered test data set;
step seven, judging whether the model is acceptable; if the model is acceptable, the modeling is successful, otherwise, the actual vehicle road mining test is carried out again;
and step eight, carrying out road feel simulation according to the obtained road feel simulation model based on the K-Means and CART regression tree.
2. The road feel simulation method based on K-Means and CART regression trees according to claim 1, characterized in that in the real vehicle test of step one:
the test road types comprise urban roads, expressways, suburban roads and rural roads;
the vehicle running conditions comprise uphill, downhill, straight running, backing, turning and pivot steering conditions.
3. The road feel simulation method based on the K-Means and CART regression tree as claimed in claim 1, wherein in the second step, the removed abnormal points include data points beyond the normal value range, data points with severely deviated distribution and data points with the variation amplitude beyond the normal range.
4. The road feel simulation method based on K-Means and CART regression tree according to claim 1, characterized in that in step two, the test data is normalized according to the following formula:
Figure FDA0002862549970000021
wherein i is a data number, j is a variable number, and xi,jDenotes the j variable, X, in the non-normalized i group of datajAnd representing a set consisting of variable data values corresponding to all j, min representing the minimum value of the related variable in the test data after the abnormal point is removed, and max representing the maximum value of the related variable in the test data after the abnormal point is removed.
5. The road feel simulation method based on the K-Means and CART regression tree according to claim 1, characterized in that in the fourth step, when the training data set and the test data set are divided, a certain number of data points in 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;
the clustered training data set is called a clustered training data set; the clustered test data set is referred to as a post-clustering test data aggregation.
6. The road feel simulation method based on K-Means and CART regression tree according to any one of claims 1-5, characterized in that in the third step, when clustering is performed on the normalized test data by using K-Means clustering algorithm, the number of clusters is set to 4, 4 cluster centers are obtained after clustering, and the normalized test data is divided into 4 data classes according to the coordinates of the 4 cluster centers.
7. The road feeling simulation method based on the K-Means and CART regression tree as claimed in any one of claims 1-5, wherein in the fifth step, when training the road feeling simulation model based on the K-Means and CART regression tree, the concrete steps are:
the CART regression tree model is represented as:
Figure FDA0002862549970000022
wherein, f (x) is a CART regression tree function, m is a positive integer greater than 1, I is a unit matrix, and x is an input variable; the data space is divided into R1～RmCells, each cell having a fixed output value cm；
Calculating the error of the model output value and the actual value:
Figure FDA0002862549970000023
wherein x isiFor input of the i-th data of variable x, yiIs the actual output value; i is a positive integer greater than 1;
suppose that the jth input variable x is selectedjThe input variable is any one of a longitudinal speed of a vehicle, a lateral acceleration of the vehicle, a yaw velocity of the vehicle, a vertical load of the vehicle, a steering wheel angle and an angular velocity of the steering wheel, and j is a variable number; taking the value s of the segmentation variable as a segmentation point to obtain two regions R1，R2：
R1(j,s)＝{x|x(f)≤s}；R2(j,s)＝{x|x(f)＞s}
When j and s are fixed, find the representative value c of the two regions1，c2The squared difference over the respective intervals is minimized, i.e.:
Figure FDA0002862549970000031
in the formula c1，c2Is the average over the interval, i.e.:
Figure FDA0002862549970000032
the working steps of training the CART regression tree model using the clustered training data set are as follows:
1) inputting: a training data set D;
2) and (3) outputting: regression tree f (x);
3) recursively dividing each region into two sub-regions in an input space where the training data set is located, and determining an output value of each sub-region; constructing a binary decision tree, comprising the steps of:
selecting an optimal segmentation variable j and a segmentation point s, and solving:
Figure FDA0002862549970000033
secondly, traversing the variable j, scanning a segmentation point s for the fixed segmentation variable j, and selecting a pair (j, s) which enables the above formula to reach the minimum value;
-dividing the area by the selected pair (j, s) and determining the corresponding output value:
R1(j,s)＝{x|x(f)≤s}；R2(j,s)＝{x|x(f)＞s}
Figure FDA0002862549970000034
in the formula, NmIs the total number of data points in space;
fourthly, continuously calling the steps (1) and (2) for the two subregions until the cycle number reaches an upper limit value;
divide the input space into M regions R1,R2,...,RMAnd generating a decision tree.
8. The road feel simulation method based on K-Means and CART regression tree according to claim 1, characterized in that the specific steps of testing the data-driven road feel simulation model and judging whether the model is acceptable are as follows:
1) taking out a test data point in the test data set, and inputting the value of an input variable corresponding to the test data point into a road feel simulation model corresponding to the class to which the test data point belongs to obtain a predicted steering wheel torque value;
2) repeating the step 1), and sequentially predicting the steering wheel torque values corresponding to all the test data points;
3) calculating an MSE value between a steering wheel torque value obtained by predicting test data points of the whole test data set and a real steering wheel torque value;
4) and if the MSE value is smaller than a preset threshold value alpha, the road feel simulation model based on the data driving obtained by training is considered to be acceptable, and the modeling is successful.
9. The K-Means and CART regression tree based road feel simulation method of claim 8, wherein the threshold a is 0.2.
CN202011570750.4A 2020-12-26 2020-12-26 Road feel simulation method based on K-Means and CART regression tree Active CN112550450B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011570750.4A CN112550450B (en) 2020-12-26 2020-12-26 Road feel simulation method based on K-Means and CART regression tree

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011570750.4A CN112550450B (en) 2020-12-26 2020-12-26 Road feel simulation method based on K-Means and CART regression tree

Publications (2)

Publication Number Publication Date
CN112550450A true CN112550450A (en) 2021-03-26
CN112550450B CN112550450B (en) 2022-03-29

Family

ID=75033360

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011570750.4A Active CN112550450B (en) 2020-12-26 2020-12-26 Road feel simulation method based on K-Means and CART regression tree

Country Status (1)

Country Link
CN (1) CN112550450B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112937587A (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 classification regression tree
CN116465647A (en) * 2023-04-18 2023-07-21 日照朝力信息科技有限公司 Automobile performance testing method and system based on virtual reality technology

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH1114507A (en) * 1997-06-19 1999-01-22 Denso Corp Vehicle simulation device
CN103150774A (en) * 2013-03-07 2013-06-12 吉林省高速公路管理局 System and method for identifying vehicles of highway green channel
CN105352741A (en) * 2015-11-16 2016-02-24 重庆交通大学 Brake performance evaluation method based on virtual road load conditions and system thereof
US20190049980A1 (en) * 2017-08-08 2019-02-14 TuSimple Neural network based vehicle dynamics model
CN110606121A (en) * 2019-08-28 2019-12-24 中国第一汽车股份有限公司 Drive-by-wire steering road feel simulation control method
CN111242206A (en) * 2020-01-08 2020-06-05 吉林大学 High-resolution ocean water temperature calculation method based on hierarchical clustering and random forests

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH1114507A (en) * 1997-06-19 1999-01-22 Denso Corp Vehicle simulation device
CN103150774A (en) * 2013-03-07 2013-06-12 吉林省高速公路管理局 System and method for identifying vehicles of highway green channel
CN105352741A (en) * 2015-11-16 2016-02-24 重庆交通大学 Brake performance evaluation method based on virtual road load conditions and system thereof
US20190049980A1 (en) * 2017-08-08 2019-02-14 TuSimple Neural network based vehicle dynamics model
CN109388073A (en) * 2017-08-08 2019-02-26 北京图森未来科技有限公司 A kind of method and apparatus of dynamic vehicle simulation
CN110606121A (en) * 2019-08-28 2019-12-24 中国第一汽车股份有限公司 Drive-by-wire steering road feel simulation control method
CN111242206A (en) * 2020-01-08 2020-06-05 吉林大学 High-resolution ocean water temperature calculation method based on hierarchical clustering and random forests

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112937587A (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 classification regression tree
CN116465647A (en) * 2023-04-18 2023-07-21 日照朝力信息科技有限公司 Automobile performance testing method and system based on virtual reality technology
CN116465647B (en) * 2023-04-18 2024-03-26 日照朝力信息科技有限公司 Automobile performance testing method and system based on virtual reality technology

Also Published As

Publication number Publication date
CN112550450B (en) 2022-03-29

Similar Documents

Publication Publication Date Title
CN112801143B (en) Steering road feel simulation method based on K-Means and Gaussian process regression
CN112550450B (en) Road feel simulation method based on K-Means and CART regression tree
CN110569783B (en) Method and system for identifying lane changing intention of driver
CN112632706B (en) Road feel simulation method based on GMM and CART regression tree
CN107273805A (en) A kind of GM HMM prediction driving behavior methods of view-based access control model characteristic
CN109887279B (en) Traffic jam prediction method and system
CN112149796A (en) Driving style identification method for optimizing BP neural network based on improved genetic algorithm
CN112632705B (en) Road feel simulation method based on GMM and Gaussian process regression
CN112668172A (en) Following behavior modeling method considering heterogeneity of vehicle type and driving style and model thereof
CN112749508B (en) Road feel simulation method based on GMM and BP neural network
CN114169444B (en) Driving style classification method considering risk potential field distribution under vehicle following working condition
CN112685956A (en) Road feel simulation method based on CART regression tree
CN112937587A (en) Road feel simulation method based on K-Medoids and classification regression tree
CN112528568B (en) Road feel simulation method based on K-Means and BP neural network
CN112396118A (en) GM-HMM-based driver acceleration intention modeling method
CN112098869A (en) Self-adaptive electric vehicle SOC estimation method based on big data
CN116975671A (en) L3-level automatic driving vehicle driver trust evaluation method and system
CN116946183A (en) Commercial vehicle driving behavior prediction method considering driving capability and vehicle equipment
CN114148349B (en) Vehicle personalized following control method based on generation of countermeasure imitation study
CN112651134A (en) Steering road feel simulation method based on Gaussian process regression
CN112597597A (en) Road feel simulation method based on K-Medoids and BP neural network
CN112836722B (en) Road feel simulation method based on data driving
CN114707573A (en) Unsupervised driving style analysis method based on basic driving operation event
CN114140286A (en) Driving training guidance method and terminal
CN112308171A (en) Vehicle position prediction modeling method based on simulated driver

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