CN113297685B - Vehicle operation condition mode identification method - Google Patents

Vehicle operation condition mode identification method Download PDF

Info

Publication number
CN113297685B
CN113297685B CN202110847877.4A CN202110847877A CN113297685B CN 113297685 B CN113297685 B CN 113297685B CN 202110847877 A CN202110847877 A CN 202110847877A CN 113297685 B CN113297685 B CN 113297685B
Authority
CN
China
Prior art keywords
vehicle
condition
driving
data
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.)
Active
Application number
CN202110847877.4A
Other languages
Chinese (zh)
Other versions
CN113297685A (en
Inventor
王振峰
杨建森
李洪亮
许晟杰
董强强
李欣
武振江
韩忠良
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.)
China Automotive Technology and Research Center Co Ltd
CATARC Tianjin Automotive Engineering Research Institute Co Ltd
Original Assignee
China Automotive Technology and Research Center Co Ltd
CATARC Tianjin Automotive Engineering Research Institute 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 China Automotive Technology and Research Center Co Ltd, CATARC Tianjin Automotive Engineering Research Institute Co Ltd filed Critical China Automotive Technology and Research Center Co Ltd
Priority to CN202110847877.4A priority Critical patent/CN113297685B/en
Publication of CN113297685A publication Critical patent/CN113297685A/en
Application granted granted Critical
Publication of CN113297685B publication Critical patent/CN113297685B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • 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
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • 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
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/17—Mechanical parametric or variational 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/08—Probabilistic or stochastic CAD

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Vehicle Body Suspensions (AREA)

Abstract

The invention provides a vehicle running condition mode identification method, which comprises the following steps: s1, acquiring vehicle running state information; s2, carrying out grid cell division on the vehicle running state information acquired in the step S1 based on the road working condition and the driving working condition, and selecting initial cell data; s3, establishing vehicle driving condition parameterized models, including a road condition parameterized model and a driving style parameterized model; s4, compounding the information of the running condition after the grid cells are divided in the step S2, and constructing a Markov chain transfer matrix; s5, sampling and iterating the working condition transfer matrixes obtained in the step S4 by an MCMC method, and calculating and outputting stable running working condition proportion distribution; s6, combining with a real vehicle test, verifying the identification effect of the MCMC method on the vehicle system operation mode; the method and the device improve the identification precision of the vehicle system operation condition mode with parameter time variation and nonlinear characteristics based on real vehicle test data, and effectively realize the consistency identification of the road surface and the driver style.

Description

Vehicle operation condition mode identification method
Technical Field
The invention belongs to the technical field of automobile manufacturing, and particularly relates to a method for identifying a vehicle running condition mode.
Background
The electric, intelligent, networking and sharing of the vehicle is a necessary trend of the development of the automobile industry, and the improvement of the chassis performance of the automatic driving vehicle is still a hot spot and a difficult problem of the research of the international academic and industrial circles at present. The automatic driving vehicle can automatically judge the running condition of the vehicle according to the motion state of the vehicle, the surrounding environment and the like, and further can actively regulate and control the chassis performance of the vehicle in real time so that the chassis performance of the vehicle has the best overall vehicle dynamic performance. Meanwhile, the information input of the driver and the road surface is used as a core input source outside the vehicle, the accurate consistency identification of the information is realized, the operation working condition of the vehicle is reasonably and efficiently obtained, the influence difference of the working condition characteristics on the aspects of chassis cooperative control, energy management, fatigue durability of the whole vehicle and the like of the automatic driving vehicle is researched, and the method has a remarkable significance on the development of the performance of the automatic driving whole vehicle.
Due to the complexity of the vehicle running environment and the uncertainty of the psychological fluctuation of the driver, the environment-friendly cycle model based on the data is widely researched; however, in the process of identifying the vehicle running mode, the related data are analyzed by adopting single or multiple pieces of mutually independent running condition information, the consistency identification of the driver and the road grade information cannot be realized, and the corresponding real vehicle test data are relatively less; therefore, a method for identifying the operating condition mode of the vehicle is needed.
Disclosure of Invention
In view of the above, the present invention aims to provide a vehicle operation condition pattern recognition method, so as to solve the problem of consistency recognition between a driver and road grade information, further improve the vehicle system operation condition pattern recognition accuracy with parameter time variation and nonlinear characteristics, and effectively realize consistency recognition between a road surface and a driver style based on real vehicle test data.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a vehicle running condition mode identification method comprises the following steps:
s1, acquiring vehicle running state information;
s2, carrying out grid cell division on the vehicle running state information acquired in the step S1 based on the road working condition and the driving working condition, and selecting initial cell data;
s3, establishing vehicle driving condition parameterized models, including a road condition parameterized model and a driving style parameterized model;
s4, compounding the information of the running condition after the grid cells are divided in the step S2, and constructing a Markov chain transfer matrix;
s5, sampling and iterating the working condition transfer matrixes obtained in the step S4 by an MCMC method, and calculating and outputting stable running working condition proportion distribution;
and S6, combining with a real vehicle test, and verifying the identification effect of the MCMC method on the vehicle system operation mode.
Further, the vehicle running state information acquired in step S1 includes a suspension stroke, a longitudinal acceleration, a lateral acceleration, a vertical acceleration, a lateral acceleration, an accelerator opening, and a vehicle speed.
Further, the initial cell data acquired in step S2 is 50 m.
Further, the step S3 of establishing the vehicle driving condition parameterized model includes steps a and B executed synchronously:
the step A specifically comprises the following steps:
a1, acquiring relevant state parameters of road conditions, including vehicle speed, longitudinal acceleration, transverse acceleration, vertical acceleration and suspension dynamic travel;
a2, establishing a road condition parameterized model;
a3, judging the road surface grade working condition;
the step B specifically comprises the following steps:
b1, acquiring relevant state parameters of the driving condition, including vehicle speed, longitudinal acceleration, lateral acceleration and accelerator opening
B2, establishing a driving style parameterized model;
and B3, judging the driving style type.
Further, the step a2 of establishing the road condition parameterized model includes the following steps:
a201, characterization of road conditions, wherein a specific formula is as follows:
Figure 575588DEST_PATH_IMAGE001
；
wherein IRI index is the accumulated amount of the dynamic stroke of the standard 1/4 vehicle model suspension in unit driving mileage, z is the dynamic stroke of the suspension in mm, and L is the driving mileage of the vehicle in m;
a202, determining the relation between the vehicle speed and the suspension dynamic stroke cumulant, wherein the concrete formula is as follows:
Figure 633674DEST_PATH_IMAGE002
；
and is
Figure 944570DEST_PATH_IMAGE003
(ii) a In the formula, IRI0The cumulative amount of the suspension dynamic stroke measured for running the vehicle at 80km/h, v is the vehicle speed.
Further, the step B2 of establishing the driving style behavior parameterization model includes the following steps:
b201, representing the driving style of the driving condition-related state parameters obtained in the step B1 by using the mean value, the maximum value and the standard deviation of the state parameters as evaluation indexes;
and B202, carrying out PCA dimension reduction processing on the evaluation indexes in the step B201 by utilizing a PCA method so as to improve the recognition efficiency of the driving style classification, and specifically comprising the following steps:
b2021, normalizing the original data, wherein the specific formula is as follows:
Figure 605358DEST_PATH_IMAGE004
；
in the formula (I), the compound is shown in the specification,i=1, 2, 3… n; j=1, 2,3… 12；x ij as the original data, it is the original data,x j the mean value of j variable of the original data;σ j the standard deviation of the jth variable of the original data;
b2022, constructing a covariance matrix, wherein a specific formula is as follows:
Figure 560676DEST_PATH_IMAGE005
；
p ij in order to standardize the data after the processing,p i 、p j to normalize the mean of the ith or jth variable of the processed data,nis the amount of samples of the raw data,s ij the covariance of the normalized data;
b2023, obtaining eigenvalue lambda of covariance matrix i And corresponding feature vectorsa i ；
B2024, calculating principal component contribution rateτ j And cumulative contribution rateη j ；
B2025, calculating principal component valuel j ：l j =a j T *P。
Further, in step B3, a K-Mean algorithm is used, and 3 indexes are selected as a clustering basis to analyze the driving style based on the PCA dimension reduction result, and the specific algorithm flow is as follows:
b301, randomly selecting 3 samples from the data as a clustering center;
b302, calculating samplesl i And cluster centerμ j Is a distance ofd ij And dividing the sample into categories corresponding to the cluster centers with the minimum distance from the sample:
Figure 648718DEST_PATH_IMAGE006
；
in the formula (I), the compound is shown in the specification,μ j representing a cluster center;
b303, recalculating the clustering centers of the various sample points:
Figure 181330DEST_PATH_IMAGE007
；
in the formula (I), the compound is shown in the specification,C j is a cluster;
b304, judging whether the clustering center changes, if so, repeating the step B302 and the step B303, otherwise, outputting a clustering result.
Further, the formula for constructing the markov chain transition matrix in step S4 is as follows:
Figure 786755DEST_PATH_IMAGE008
；
in the formula (I), the compound is shown in the specification,N ij for vehicle driving state in discrete dataiChange to statejThe number of times of the operation of the motor,N i for the vehicle in driving condition in discrete dataiThe number of times.
Compared with the prior art, the vehicle operation condition mode identification method has the following beneficial effects:
(1) the vehicle running condition mode identification method is based on real vehicle test data, and can well realize accurate online identification of the vehicle running mode of the road surface reacting with the style of a driver under the complex running condition;
(2) the vehicle running condition mode identification method can effectively solve the difficulty of identifying the consistency of the driver and the road grade information, and further improves the vehicle system running condition mode identification precision with parameter time variation and nonlinear characteristics.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a method for identifying a vehicle operating condition mode according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating the relationship between vehicle speed and road type and the cumulative amount of suspension travel according to the embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the cumulative ratio of principal component contributions according to an embodiment of the invention;
FIG. 4 is a structural diagram of a K-Mean cluster analysis according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating a comparison of international flatness indexes of different grid cells according to an embodiment of the present invention;
FIG. 6 is a graph showing the variation of vehicle speed with time according to the embodiment of the present invention;
FIG. 7 is a diagram illustrating the variation of the suspension stroke with time according to an embodiment of the present invention;
FIG. 8 is a diagram illustrating longitudinal acceleration versus time variation fluctuation according to an embodiment of the present invention;
FIG. 9 is a diagram illustrating lateral acceleration versus time variation fluctuation according to an embodiment of the present invention;
FIG. 10 is a diagram illustrating variation fluctuation of throttle opening versus time according to an embodiment of the present invention;
FIG. 11 is a diagram illustrating a fluctuation of vertical acceleration with time according to an embodiment of the present invention;
fig. 12 is a diagram of an MCMC sampling iteration process according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
Referring to fig. 1, a method for identifying a vehicle operating mode includes the following steps:
s1, acquiring vehicle running state information;
s2, carrying out grid cell division on the vehicle running state information acquired in the step S1 based on the road working condition and the driving working condition, and selecting initial cell data;
s3, establishing vehicle driving condition parameterized models, including a road condition parameterized model and a driving style parameterized model;
s4, compounding the information of the running condition after the grid cells are divided in the step S2, and constructing a Markov chain transfer matrix;
s5, sampling and iterating the working condition transfer matrixes obtained in the step S4 by an MCMC method, and calculating and outputting stable running working condition proportion distribution;
and S6, combining with a real vehicle test, and verifying the identification effect of the MCMC method on the vehicle system operation mode.
The vehicle running state information acquired in step S1 includes suspension stroke, longitudinal acceleration, lateral acceleration, vertical acceleration, lateral acceleration, accelerator opening, and vehicle speed.
The initial cell data acquired in step S2 is 50 m; according to the convergence criterion of the grid cells, when the driving range reaches 50m, the influence of the initial value on the calculation result may be approximately zero.
The step S3 of establishing the vehicle driving condition parameterized model includes steps a and B executed synchronously:
the step A specifically comprises the following steps:
a1, acquiring relevant state parameters of road conditions, including vehicle speed, longitudinal acceleration, transverse acceleration, vertical acceleration and suspension dynamic travel;
a2, establishing a road condition parameterized model;
a3, judging the road surface grade working condition;
the step B specifically comprises the following steps:
b1, acquiring relevant state parameters of the driving condition, including vehicle speed, longitudinal acceleration, lateral acceleration and accelerator opening
B2, establishing a driving style parameterized model;
and B3, judging the driving style type.
The step A2 of establishing the road condition parameterized model comprises the following steps:
a201, characterization of road conditions, wherein a specific formula is as follows:
Figure 393317DEST_PATH_IMAGE001
；
wherein IRI index is the accumulated amount of the dynamic stroke of the standard 1/4 vehicle model suspension in unit driving mileage, z is the dynamic stroke of the suspension in mm, and L is the driving mileage of the vehicle in m; in engineering applications, the IRI index can be converted to discrete form based on measured suspension travel:
Figure 324364DEST_PATH_IMAGE009
；
in the formula (I), the compound is shown in the specification,z(x i ) Is that the vehicle is located atx i The dynamic stroke (m) of the suspension in position,Nis the data volume collected within a unit driving mileage;
there is a clear conversion relationship between IRI and the widely used standard road surface defined by the national organization for standardization (ISO), the power spectral density value of the reference point in the ISO definitionC spAnd IRI values can be converted by the following formula:
Figure 609852DEST_PATH_IMAGE010
；
wherein the content of the first and second substances,a=2.21；
a202, determining the relation between the vehicle speed and the suspension dynamic stroke cumulant, wherein the concrete formula is as follows:
Figure 750458DEST_PATH_IMAGE011
；
and is
Figure 805002DEST_PATH_IMAGE012
(ii) a In the formula, IRI0The cumulative amount of the suspension dynamic travel measured when the vehicle runs at 80km/h, and v is the vehicle speed; the relation between the vehicle speed and the accumulated amount of the suspension dynamic stroke is further researched by researching the change of the suspension dynamic stroke number under different vehicle speeds and road excitation working conditions by utilizing A standard road surface grade (ISO-A-H) division rule, and the relation is specifically shown in figure 2.
As can be seen from fig. 2, a strong nonlinear relationship exists between the suspension dynamic stroke accumulated amount and the vehicle speed and road grade, and for the same road grade, the dynamic stroke accumulated amount is large when the corresponding dynamic stroke accumulated amount under the low-speed driving condition is higher.
The step B2 of establishing the driving style working condition parameterized model comprises the following steps:
and B201, representing the driving style of the driving condition related state parameters (four groups of data including vehicle speed, longitudinal acceleration, lateral acceleration and accelerator opening degree) acquired in the step B1 by using the mean value, the maximum value and the standard deviation of the four groups of data as evaluation indexes, wherein the driving style is specifically shown in Table 1:
Figure 500426DEST_PATH_IMAGE013
TABLE 1
B202, performing PCA dimension reduction processing on the evaluation indexes (12 evaluation indexes formed by the four groups of data) in the step B201 by using a PCA method to improve the recognition efficiency of the driving style classification, specifically including the following steps:
b2021, normalizing the original data, wherein the specific formula is as follows:
Figure 882997DEST_PATH_IMAGE014
；
in the formula (I), the compound is shown in the specification,i=1, 2, 3… n; j=1, 2,3… 12；x ij as the original data, it is the original data,x j the mean value of j variable of the original data;σ j the standard deviation of the jth variable of the original data;
b2022, constructing a covariance matrix, wherein a specific formula is as follows:
Figure 423699DEST_PATH_IMAGE015
；
p ij in order to standardize the data after the processing,p i 、p j to normalize the mean of the ith or jth variable of the processed data,nis the amount of samples of the raw data,s ij to normalize the covariance of the processed data,
b2023, obtaining eigenvalue lambda of covariance matrix i And corresponding feature vectorsa i ；
B2024, calculating principal component contribution rateτ j And cumulative contribution rateη j ；
B2025, calculating principal component valuel j ：l j =a j T *P；In order to ensure that the principal component variable can better and effectively cover the original variable information, the cumulative contribution rate should be more than 85%; according to the calculation result of the cumulative contribution rate shown in fig. 3, 3 principal component variables are selected as evaluation indexes of subsequent driving style cluster analysis.
In the step B3, a K-Mean algorithm is utilized, 3 indexes are selected as clustering bases to analyze the driving style based on the PCA dimension reduction result, and the specific algorithm flow is as follows:
b301, randomly selecting 3 samples from the data as a clustering center;
b302, calculating samplesl i And cluster centerμ j Is a distance ofd ij And dividing the sample into categories corresponding to the cluster centers with the minimum distance from the sample:
Figure 332750DEST_PATH_IMAGE016
；
in the formula (I), the compound is shown in the specification,μ j representing a cluster center;
b303, recalculating the clustering centers of the various sample points:
Figure 933495DEST_PATH_IMAGE017
；
in the formula (I), the compound is shown in the specification,C j is a cluster;
and B304, judging whether the clustering center changes or not, repeating the step B302 and the step B303 when the clustering center changes, otherwise outputting the clustering result, and effectively obtaining the clustering result of each driving style through K-Mean clustering iterative computation, wherein as shown in figure 4, in the subsequent driving style identification based on the K-Mean clustering algorithm, the driving style of the sample point can be accurately identified in real time according to the distance from the collected sample point to each clustering center.
The Markov chain is a random process that describes that both the state value and the time parameter are discrete, i.e., intAt the moment the vehicle is in a statex iIn the case of (a) in (b),tthe state at the moment +1 is only ANDtThe time state is related tot-1，t-2, …, independent of the time of day, if the vehicle is driven by the driving modetTime of day state xiBecome totState at time +1x jHas a probability ofP ij Then callP ij A one-step state transition probability for the Markov chain;
Figure 803362DEST_PATH_IMAGE018
；
for discrete data, the state transition probability in step S4 is represented by the following equation:
Figure 413335DEST_PATH_IMAGE019
；
in the formula (I), the compound is shown in the specification,N ij for vehicle driving state in discrete dataiChange to statejThe number of times of the operation of the motor,N i for the vehicle in driving condition in discrete dataiThe number of times.
When the scheme is implemented, the SUV vehicle is used for carrying out relevant road tests, 10 drivers with different ages and sexes are selected for carrying out tests respectively, wherein the ratio of young, middle-aged and old drivers is 3:5:2, the ratio of male to female is 7:3, and the drivers carry out the tests in a free driving mode.
Meanwhile, in order to facilitate efficient identification of the subsequent vehicle operation condition modes, ISO-A-H grade road surfaces can be divided into flat road surfaces, ordinary road surfaces and hollow road surfaces according to the conversion relation between the power spectral density value of the road surface and the IRI index and by combining actual road surface information of A test field.
The parameters of the test field pavement related data acquisition equipment are shown in table 2:
Figure 317837DEST_PATH_IMAGE020
TABLE 2
One of the 10 drivers is randomly selected, and data related to the speed, the suspension moving distance, the longitudinal and transverse acceleration of the mass center, the opening degree of the accelerator and the vertical acceleration of the shaft head of the test vehicle can be effectively acquired after data acquisition equipment and filtering processing are utilized, and the data are shown in fig. 6-11.
Meanwhile, based on the test data of fig. 6 to 11, in combination with the above identification method, the above test data can also be used to perform effective analysis on MCMC method iterative convergence, thereby realizing consistency identification of vehicle operation condition modes, as shown in fig. 12, that is, the condition that the ratio distribution of each working condition is changed along with MCMC sampling iteration, wherein the first row to the third row represent that the road working conditions of vehicle driving are three types, namely, a flat road surface, a general road surface and a pothole road surface; the first column to the third column show that the driving style of the driver is a mild type, a normal type and an aggressive type, so 9 driving conditions are formed, taking the working conditions shown in the first row and the first column as an example, the working conditions show the distribution of the proportion of the working conditions when the driver drives on a flat road, as can be seen from fig. 12, in the initial stage of the MCMC sampling iteration, the fluctuation range of the proportion distribution of the working conditions is large and is rapidly increased from 0.0111 to 0.0231, after a period of fluctuation, when the quantity of the collected samples reaches 12000, the proportion of the working conditions is increased to 0.0305, and then small fluctuation is carried out in the vicinity of the sample, and the proportion distribution of the working conditions tends to be stable.
In addition, because MCMC sampling iteration has certain randomness, the convergence rate of each working condition is different, but each working condition finally obtains stable working condition proportion distribution, the identification of the vehicle running mode under complex working conditions is better realized, and the error of the corresponding MCMC iteration vehicle running working condition proportion and the actual working condition proportion distribution is not more than 20%.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (5)

1. A vehicle running condition mode identification method is characterized by comprising the following steps:
s1, acquiring vehicle running state information; the vehicle running state information comprises suspension dynamic travel, longitudinal acceleration, transverse acceleration, vertical acceleration, lateral acceleration, accelerator opening and vehicle speed
S2, carrying out grid cell division on the vehicle running state information acquired in the step S1 based on the road working condition and the driving working condition, and selecting initial cell data;
s3, establishing vehicle driving condition parameterized models, including a road condition parameterized model and a driving style parameterized model;
the step S3 of establishing the vehicle driving condition parameterized model includes steps a and B executed synchronously:
the step A specifically comprises the following steps:
a1, acquiring relevant state parameters of road conditions, including vehicle speed, longitudinal acceleration, transverse acceleration, vertical acceleration and suspension dynamic travel;
a2, establishing a road condition parameterized model;
the step A2 of establishing the road condition parameterized model comprises the following steps:
a201, characterization of road conditions, wherein a specific formula is as follows:
Figure FDA0003283890770000011
wherein IRI index is the accumulated amount of the dynamic stroke of the standard 1/4 vehicle model suspension in unit driving mileage, z is the dynamic stroke of the suspension in mm, and L is the driving mileage of the vehicle in m;
a202, determining the relation between the vehicle speed and the suspension dynamic stroke cumulant, wherein the concrete formula is as follows:
IRI＝1.5958αIRI0+5.3498α-3.3525；
and is
Figure FDA0003283890770000012
In the formula, IRI0The cumulative amount of the suspension dynamic travel measured when the vehicle runs at 80km/h, and v is the vehicle speed;
a3, judging the road surface grade working condition;
the step B specifically comprises the following steps:
b1, acquiring relevant state parameters of the driving condition, including vehicle speed, longitudinal acceleration, lateral acceleration and accelerator opening
B2, establishing a driving style parameterized model;
b3, judging the driving style type;
s4, compounding the information of the running condition after the grid cells are divided in the step S2, and constructing a Markov chain transfer matrix;
s5, sampling and iterating the working condition transfer matrixes obtained in the step S4 by an MCMC method, and calculating and outputting stable running working condition proportion distribution;
and S6, combining with a real vehicle test, and verifying the identification effect of the MCMC method on the vehicle system operation mode.
2. The vehicle operating condition mode identification method according to claim 1, characterized in that: the initial cell data acquired in step S2 is 50 m.
3. The vehicle operating condition mode identification method according to claim 2, characterized in that: the step B2 of establishing the driving style working condition parameterized model comprises the following steps:
b201, representing the driving style of the driving condition-related state parameters obtained in the step B1 by using the mean value, the maximum value and the standard deviation of the state parameters as evaluation indexes;
and B202, carrying out PCA dimension reduction processing on the evaluation indexes in the step B201 by utilizing a PCA method so as to improve the recognition efficiency of the driving style classification, and specifically comprising the following steps:
b2021, normalizing the original data, wherein the specific formula is as follows:
Figure FDA0003283890770000031
wherein i is 1,2,3 … n; j ═ 1,2,3 … 12; x is the number ofijAs raw data, xjThe mean value of j variable of the original data; sigmajThe standard deviation of the jth variable of the original data;
b2022, constructing a covariance matrix, wherein a specific formula is as follows:
Figure FDA0003283890770000032
pijfor normalizing the processed data, pi、pjIs the average value of the ith or j variables of the normalized data, n is the sample size of the original data, sijThe covariance of the normalized data;
b2023, obtaining eigenvalue lambda of covariance matrixiAnd corresponding feature vector ai；
B2024, calculating principal component contribution rate taujAnd cumulative contribution ηj；
B2025, calculating the principal component value lj：lj＝aj T*P。
4. The vehicle operating condition mode identification method according to claim 3, characterized in that: in the step B3, a K-Mean algorithm is utilized, 3 indexes are selected as clustering bases to analyze the driving style based on the PCA dimension reduction result, and the specific algorithm flow is as follows:
b301, randomly selecting 3 samples from the data as a clustering center;
b302, calculating a sample liAnd cluster center mujDistance d ofijAnd dividing the sample into categories corresponding to the cluster centers with the minimum distance from the sample:
dij＝||li-μj||2i＝1,2,…n,j＝1,2,…12；
in the formula, mujRepresenting a cluster center;
b303, recalculating the clustering centers of the various sample points:
Figure FDA0003283890770000033
in the formula, CjIs a cluster;
b304, judging whether the clustering center changes, if so, repeating the step B302 and the step B303, otherwise, outputting a clustering result.
5. The vehicle operating condition mode identification method according to claim 1, characterized in that: the formula for constructing the Markov chain transfer matrix in the step S4 is as follows:
Figure FDA0003283890770000041
in the formula, NijThe number of times the vehicle changes from driving state i to state j in the discrete data, NiThe number of times the vehicle is in the running state i in the discrete data.
CN202110847877.4A 2021-07-27 2021-07-27 Vehicle operation condition mode identification method Active CN113297685B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110847877.4A CN113297685B (en) 2021-07-27 2021-07-27 Vehicle operation condition mode identification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110847877.4A CN113297685B (en) 2021-07-27 2021-07-27 Vehicle operation condition mode identification method

Publications (2)

Publication Number Publication Date
CN113297685A CN113297685A (en) 2021-08-24
CN113297685B true CN113297685B (en) 2021-11-02

Family

ID=77331096

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110847877.4A Active CN113297685B (en) 2021-07-27 2021-07-27 Vehicle operation condition mode identification method

Country Status (1)

Country Link
CN (1) CN113297685B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114493191B (en) * 2022-01-07 2024-04-30 东南大学 Driving behavior modeling analysis method based on network about vehicle data
CN114965898A (en) * 2022-06-01 2022-08-30 北京市生态环境监测中心 Remote online monitoring method for heavy vehicle nitrogen oxide and carbon dioxide emission
CN115859123B (en) * 2023-03-01 2023-05-02 太原理工大学 Vehicle driving condition online identification method based on random prediction and machine learning

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107016205A (en) * 2017-04-14 2017-08-04 宋凯 A kind of multi-model construction method of groundwater Numerical Simulation
CN109446573A (en) * 2018-09-26 2019-03-08 力帆实业(集团)股份有限公司 A method of building multidimensional road surface simulation model
CN110126841A (en) * 2019-05-09 2019-08-16 吉林大学 EV Energy Consumption model prediction method based on road information and driving style
CN111731312A (en) * 2020-06-15 2020-10-02 苏州绿科智能机器人研究院有限公司 Experimental system for extracting driving style characteristic parameters and driving style identification method
DE102021000790A1 (en) * 2021-02-16 2021-04-15 Daimler Ag Process for merging sensor data
DE102019217730A1 (en) * 2019-11-18 2021-05-20 Volkswagen Aktiengesellschaft Method for operating an operating system in a vehicle and operating system for a vehicle

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101075615B1 (en) * 2006-07-06 2011-10-21 포항공과대학교 산학협력단 Apparatus and method for generating a auxiliary information of moving vehicles for driver
CA2891051C (en) * 2014-01-06 2016-05-10 Geodigital International Inc. Determining portions of a roadway model requiring updating
CN104462716B (en) * 2014-12-23 2017-10-27 北京理工大学 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
CN105548066A (en) * 2015-12-11 2016-05-04 贵州中烟工业有限责任公司 Method and system for distinguishing colloid types
CN107539317A (en) * 2016-06-28 2018-01-05 长城汽车股份有限公司 Control method, system and the vehicle of vehicle
CN107894223B (en) * 2017-11-14 2019-11-08 吉林大学 A kind of Road surface quality discrimination method based on inverse pseudo excitation method
CN108198425A (en) * 2018-02-10 2018-06-22 长安大学 A kind of construction method of Electric Vehicles Driving Cycle
CN108804814B (en) * 2018-06-08 2020-05-15 吉林大学 Method for extracting road surface spectrum parameters
CN109086508B (en) * 2018-07-24 2022-05-17 江苏大学 Threshold value dynamic matching method for automobile emergency call system
CN109436085B (en) * 2018-11-13 2020-08-11 常熟理工学院 Driving style-based drive-by-wire steering system transmission ratio control method
CN109711691A (en) * 2018-12-17 2019-05-03 长安大学 A kind of driving style evaluation method based on entropy weight model of fuzzy synthetic evaluation
CN110096748B (en) * 2019-04-01 2022-11-18 东南大学 Human-vehicle-road model modeling method based on vehicle kinematics model
CN110175557A (en) * 2019-05-24 2019-08-27 北京交通大学 Driver's driving behavior method for identifying and classifying and system based on driving characteristics group
CN110427825B (en) * 2019-07-01 2023-05-12 上海宝钢工业技术服务有限公司 Video flame identification method based on fusion of key frame and fast support vector machine
CN110321954A (en) * 2019-07-03 2019-10-11 中汽研（天津）汽车工程研究院有限公司 The driving style classification and recognition methods of suitable domestic people and system
CN110329255B (en) * 2019-07-19 2020-11-13 中汽研（天津）汽车工程研究院有限公司 Lane departure auxiliary control method based on man-machine cooperation strategy
CN110851916B (en) * 2019-10-30 2023-03-21 东南大学 Vehicle kinematics man-vehicle-road closed loop system suitable for road with any curvature
CN113076697B (en) * 2021-04-20 2022-11-29 潍柴动力股份有限公司 Typical driving condition construction method, related device and computer storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107016205A (en) * 2017-04-14 2017-08-04 宋凯 A kind of multi-model construction method of groundwater Numerical Simulation
CN109446573A (en) * 2018-09-26 2019-03-08 力帆实业(集团)股份有限公司 A method of building multidimensional road surface simulation model
CN110126841A (en) * 2019-05-09 2019-08-16 吉林大学 EV Energy Consumption model prediction method based on road information and driving style
DE102019217730A1 (en) * 2019-11-18 2021-05-20 Volkswagen Aktiengesellschaft Method for operating an operating system in a vehicle and operating system for a vehicle
CN111731312A (en) * 2020-06-15 2020-10-02 苏州绿科智能机器人研究院有限公司 Experimental system for extracting driving style characteristic parameters and driving style identification method
DE102021000790A1 (en) * 2021-02-16 2021-04-15 Daimler Ag Process for merging sensor data

Also Published As

Publication number Publication date
CN113297685A (en) 2021-08-24

Similar Documents

Publication Publication Date Title
CN113297685B (en) Vehicle operation condition mode identification method
Zhao et al. Development of a representative urban driving cycle construction methodology for electric vehicles: A case study in Xi’an
CN111301426B (en) Method for predicting energy consumption in future driving process based on GRU network model
CN113034210B (en) Vehicle running cost evaluation method based on data driving scene
CN112904219B (en) Big data-based power battery health state prediction method
CN112327168A (en) XGboost-based electric vehicle battery consumption prediction method
CN111191824B (en) Power battery capacity attenuation prediction method and system
US7640148B2 (en) Method of modeling vehicle parameter cycles
CN111348029B (en) Method for determining optimal value of calibration parameter of hybrid electric vehicle by considering working condition
CN114114039A (en) Method and device for evaluating consistency of single battery cells of battery system
CN114781245B (en) Transient automobile fuel consumption estimation method and system based on fuel consumption strong correlation parameter correction
CN113188807A (en) Abs result automatic judging algorithm
JP2023145303A (en) Evaluation method for influence of switching of work condition on fuel consumption of vehicle
CN113715629B (en) Residual driving range prediction method based on improved symbolic regression and XGBoost algorithm
CN112298155B (en) Method for predicting energy consumption of hybrid power truck based on variable time domain model
CN113987927A (en) Commercial vehicle-mounted quality detection method
CN113657432A (en) Commercial vehicle driving behavior risk level identification method based on Internet of vehicles data
CN112035536A (en) Electric automobile energy consumption prediction method considering dynamic road network traffic flow
CN116538286A (en) Commercial vehicle gear shifting system and method considering NVH characteristics
CN115792474A (en) New energy automobile electric drive assembly power acceleration test evaluation method
Darmawan et al. Comparison between ANN and multiple linear regression models for prediction of warranty cost
CN100402708C (en) Real-time control method in metal electrodeposition process based on neuron networks
CN114997748A (en) New energy automobile operation safety risk prediction method and system based on model fusion
CN114814707A (en) Intelligent ammeter stress error analysis method, equipment, terminal and readable medium
CN113985853A (en) Industrial process visual monitoring method based on data dependence kernel discriminant analysis

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