CN110321954A - The driving style classification and recognition methods of suitable domestic people and system - Google Patents
The driving style classification and recognition methods of suitable domestic people and system Download PDFInfo
- Publication number
- CN110321954A CN110321954A CN201910595664.XA CN201910595664A CN110321954A CN 110321954 A CN110321954 A CN 110321954A CN 201910595664 A CN201910595664 A CN 201910595664A CN 110321954 A CN110321954 A CN 110321954A
- Authority
- CN
- China
- Prior art keywords
- driving style
- module
- database
- driving
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 230000009467 reduction Effects 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000001133 acceleration Effects 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 21
- 238000003909 pattern recognition Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 14
- 230000035939 shock Effects 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000002474 experimental method Methods 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 230000001537 neural effect Effects 0.000 claims 1
- 238000004088 simulation Methods 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000000446 fuel Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
It include driving style road environment analog module, data acquisition module, database processing module and dimensionality reduction module, database sample classification module, driving style identification module the present invention provides a kind of classification of the driving style of suitable domestic people and identifying system and method, identifying system.The present invention proposes 29 driving style characteristic parameters, realizes from many aspects and carries out comprehensive analysis and judgement to driving style；It is proposed the thinking of the driving style database of the domestic driver of foundation；It is proposed classifies to driving style using fuzzy C-mean algorithm classifier, solves the problems, such as to realize how to the Accurate classification of driving style sample to driving style database Rational Classification；It proposes that use pattern identifies neural network driving style identification model, improves driving style accuracy of identification, while reducing driving style identification difficulty.
Description
Technical field
The invention belongs to driving behavior analysis fields, classify more particularly, to a kind of driving style of suitable domestic people
With recognition methods and system.
Background technique
Driving style is exactly the driving behavior of driver, is embodied in the driver behavior row in driving procedure to vehicle
For, and thus caused vehicle response.Driving style influences the fuel economy of automobile, the often oil consumption of the driving style of radical type
It is higher, to improve fuel economy, need according to different driving styles using different energy control strategies；Join in intelligent network
Field, according to driver's driving style, intelligence system is supplied to the auxiliary driving mode that driver meets its travelling characteristic, increases
The human nature service of automobile.
Driving style is judged according to the characteristic parameter in driver's driving procedure, the average vehicle of radical driving style
The numerical value of the characteristic parameters such as speed, the max speed, maximum throttle aperture is generally higher.Country's driving style differentiates past in research at present
Past is the driving style for judging driver according to certain several characteristic parameter and driving, and selects the methods of BP neural network as knowledge
The recognition methods of other driver's driving style, this method there are the problem of have: first, less driving style evaluation index is not
It comprehensively can completely show the characteristics of driver drives, be also easy to produce the situation of driving style judgement inaccuracy；Second, do not mention
It appropriate driving style classification method and is applied, can not rationally classify to driving style out；Third, BP neural network
Although the methods of can be used for driving style identification, its in area of pattern recognition there are accuracy of identification it is not high enough and it is easy go out
The problem of existing local optimum.
Summary of the invention
In view of this, the present invention is directed to propose a kind of driving style classification of suitable domestic people and recognition methods and being
System, to solve the problems, such as the prior art to classify, unreasonable, recognition accuracy is low, while it is difficult to be greatly reduced driving style identification
Degree.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
A kind of the driving style classification and identifying system of suitable domestic people, including driving style road environment simulate mould
Block, data acquisition module, database processing module and dimensionality reduction module, database sample classification module, driving style identification module；
The driving style road environment analog module connection database processing module and dimensionality reduction module, are used for simulated experiment
Road environment；
The data acquisition module connection database processing module and dimensionality reduction module, for acquiring vehicle condition signal, with
Driving style road environment analog module establishes domestic people driving style database jointly；
The database processing module and dimensionality reduction module are also connected with database sample classification module, for handling driving style
Test data, including calculating the value of driving style characteristic parameter and carrying out dimensionality reduction to driving style evaluation index；
The database sample classification module is also connected with driving style identification module, for being divided database sample
Class；
The driving style identification module is used to establish driving style identification model by pattern recognition neural network, finally
Generate driving style recognizer.
Further, the driving style road environment analog module sets experiment condition as urban district, suburb, three kinds of high speed
Model experiment operating condition, driving environment are as follows: fine, road is good, wind speed is normal, the normal driving ring without peak on and off duty
Border.
Further, the equipment that the data acquisition module uses includes 3-axis acceleration sensor, millimetre-wave radar, side
To disk turning angle admeasuring apparatus, fuel consumption meter, the vehicle condition signal of acquisition includes speed, accelerator pedal position, brake pedal position, system
Dynamic pressure, acceleration, driving spacing, steering wheel angle, acceleration.
Further, the driving style characteristic parameter includes lane-change number, following distance, brake pressure maximum value, system
Dynamic pressure change rate maximum value, running time, the max speed, average speed, speed standard deviation, peak acceleration, average acceleration
Degree, average retardation rate, acceleration shock degree average value, deceleration shock degree average value, shock extent standard deviation, accelerates maximum deceleration
Shock extent maximum value, deceleration shock degree maximum value, maximum accelerator travel, accelerator open degree average value, accelerator open degree standard deviation,
Accelerator open degree change rate maximum value, accelerator pedal change rate average value, accelerator releasing pedal rate of change average value, accelerator pedal are opened
Change rate standard deviation is spent, accelerates traction activity of force maximum value, traction activity of force maximum value of slowing down, accelerate tractive force power averaging
Value, deceleration tractive force power average value, tractive force power standard are poor.
Further, the value for calculating driving style characteristic parameter, which is specifically included, is reduced to k for evaluation index using PCA algorithm
Principal component, and characteristic parameter is standardized.
Further, dimensionality reduction is carried out to driving style evaluation index, specifically includes and calculates covariance square using PCA algorithm
Battle array, feature vector, characteristic value, principal component scores, principal component contributor rate and coefficient matrix PC；Finally according to principal component contributor rate
Principle greater than 85% selects the number of principal component, it is assumed that the sum of contribution rate of preceding k principal component is greater than 85%, then selects preceding k
A principal component is as new characteristic parameter.
Further, the driving style identification module classifies to database using FCM algorithm, with the k of generation
Principal component is as new characteristic parameter, using the value of k principal component of database as the input of FCM classifier by database sample
It is divided into 3 kinds of driving styles, driving style classification number is not limited to 3 classes.
Further, the driving style identification module establishes driving style identification mould using pattern recognition neural network
Type, selecting 70% sample in database, as learning sample, remaining 30% sample is used as detection sample；With k principal component
Input of the value as pattern recognition neural network, using the classification results of database as the output of pattern recognition neural network；
The model hidden layer is set as 10 layers, hidden layer transmission function chooses sigmoid function, output layer transmission function is chosen
Softmax function, training function setup are trainscg function.
Another object of the present invention is to propose the driving style classification and recognition methods of a kind of suitable domestic people, specifically
Scheme is achieved in that
S1: driving style experimental situation is set by driving environment module, establishes domestic people driving style database；
S2: data collecting module collected vehicle condition signal is utilized；
S3: domestic driver group driving style data are generated using database processing module and dimensionality reduction module and calculate feature
Parameter completes the dimension-reduction treatment of driving style characteristic parameter using PCA algorithm；
S4: the classification of driving style sample is realized by FCM algorithm using database sample classification module；
S5: establishing driving style identification model by pattern recognition neural network using driving style identification module, generates
One driving style automatic identification procedure.
Compared with the existing technology, a kind of suitable domestic people of the present invention driving style classification and recognition methods and
System has the advantage that
According to 29 characteristic parameters, " description " driving style, realization style identification are not limited solely to a few the present invention comprehensively
A feature, but comprehensively, synthetically judge driver's driving habit；Feature vectors dimensional down, drop are completed using Principal Component Analysis
The correlation between sample parameter is also reduced while low calculating；The accurate and reasonable classification to database sample is realized, together
When according to the result establish identification model, reduce the difficulty of driving style identification, improve accuracy of identification, any driving population
The style of sample can judge according to the identification model；Fully consider the human factor and environmental factor for influencing driving style,
Establish the driving style database of domestic driver group
Detailed description of the invention
The attached drawing for constituting a part of the invention is used to provide further understanding of the present invention, schematic reality of the invention
It applies example and its explanation is used to explain the present invention, do not constitute improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the driving style classifying and identifying system structure chart in the embodiment of the present invention；
Fig. 2 is the driving style classification in the embodiment of the present invention, identifying system principle process schematic diagram；
Fig. 3 is principal component analysis block diagram；
Fig. 4 is FCM clustering method block diagram；
Fig. 5 is that pattern recognition neural network driving style identifies structure chart；
Fig. 6 is driving style recognizer interface.
Specific embodiment
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
As shown in Fig.1 and Fig.2, present embodiments provide a kind of driving style classifying identification method for domestic people and
System, including driving style road environment analog module are provided with three kinds of urban district, suburb, high speed typical experiment conditions, choose
Fine, road is good, off-hour, wind speed are smaller, moderate temperature driving environment；Data acquisition module is by number
Equipment acquisition motoring condition signal is adopted, the signal of acquisition is from CAN bus, 3-axis acceleration sensor, millimeter wave thunder
Reach, steering wheel angle measuring instrument, select all ages and classes, gender, occupation driver, establish domestic people driving style data
Library；Database processing module calculates the value of characteristic parameter by means of matlab software, and initial characteristics standard parameter uses
The dimensionality reduction of PCA algorithm completion driving style evaluation index；Database sample classification module completes database sample by FCM algorithm
This Accurate classification；Identification module establishes driving style identification model by pattern recognition neural network, ultimately generates driving wind
Lattice recognizer improves driving style accuracy of identification.
In the present embodiment, driving environment analog module is provided；Three kinds of Module Specification urban district, suburb, high speed typical cases
Experiment condition, it is specified that driving style experimental situation are as follows: avoid height on and off duty sooner or later during fine, working day working
Peak, vehicle belong to that same type, road conditions are good, wind speed is smaller, moderate temperature.
In the present embodiment, driving data acquisition module is provided；The equipment used includes 3-axis acceleration sensor, millimeter
Wave radar (measurement spacing), steering wheel angle measuring instrument, the signal of acquisition characterization motoring condition: acceleration, spacing, direction
Disk corner, speed, gear, accelerator open degree, brake pedal aperture number, engine speed, torque select n all ages and classes, property
Not, professional driver establishes domestic driver's driving style database.
In the present embodiment, driving style characteristic parameter processing module is provided；Using gradient, max in matlab,
The several Key Functions of mean, min, std calculate the value of driving style characteristic parameter, generate the numerical matrix of a n*29.
Partial Feature parameter calculation procedure language is as follows:
/ 2 accelerationx1=input1*gradient (acceleration)；
% acceleration slope i.e. shock extent input1 are sample frequency
X5=max (acceleration)；% peak acceleration
X6=mean (acceleration)；% average acceleration
X7=min (acceleration)；% minimum acceleration
X11=std (acceleration)；% acceleration standard deviation
Dimensionality reduction module is additionally provided in the present embodiment；By PCA algorithm realize driving style characteristic parameter dimensionality reduction, it is main at
Divide dimensionality reduction step such as Fig. 3.Specific embodiment is as follows:
Step 1: needing to be standardized initial characteristics parameter to eliminate the influence of dimension, standardized input is 29
Characteristic parameter, that is, the matrix (y of a new n*29 is obtained to matrix (y) standardization of a n*292), it is specific to calculate
Are as follows: new matrix y2The average value of the element column is subtracted again divided by the standard deviation of the column for each element in y.
Step 2: calculating covariance matrix, the characteristic value of covariance matrix, covariance matrix by PCA algorithm in matlab
Feature vector, the value of principal component (principal component scores), the contribution rate of principal component, coefficient matrix PC.Assuming that X1、X2、…、X29For
29 characteristic parameters, covariance calculate such as formula 4, calculate its characteristic value: λ1, λ2…λ29, calculate its feature vector: e1,e2…
e29, k-th of principal component calculating such as formula 5, principal component contributor rate calculate such as formula 6.
Covariance:
∑=Cov (X, X)=E [(X=E (X)) (X-E (X))T] (4)
K-th of principal component:
Yk=ek1X1+ek2X2…+ek29X29 (5)
Principal component contributor rate:
Step 3: selecting principal component number；Principal component number, the tribute of current k principal component are selected according to principal component contributor rate
When offering rate and being more than 85%, that is, think that this k principal component can sufficiently characterize 29 driving style characteristic parameters.N sample of database
The value of this k principal component is needed as FCM classifier, the input of pattern recognition neural network identification model.
Driving style database sample classification module is provided in the present embodiment；Using FCM classifier by n sample of database
Originally it is divided into plurality of classes, driving style is divided into radical type, plain edition, calm 3 class of type, FCM clustering method step under normal circumstances
Such as Fig. 4.
Step 1: the input classified using the value of k principal component as FCM randomly selects 3 vector conducts from database
Initial cluster center, if n sample is x1, x2...xn, randomly select initial cluster center are as follows: m1, m2, m3。
Step 2: initializing Subject Matrix U with random number of the value between 0,1, it is made to meet the constraint condition in formula 7.
In formula: uijThe subordinating degree function of jth class is corresponded to for i-th of sample
Step 3: new cluster centre is calculated according to formula 8.
In formula: b is smoothing factor
Step 4: calculating new subordinating degree function matrix, calculation formula such as 9, return step 8.
Step 5: calculating new cost matrix, calculating if its value meets threshold value terminates, and driving style is divided into 3 classes, root
The driving style of this 3 class sample is judged according to initial characteristics parameter.
Driving style identification module is provided in the present embodiment；Driving style identification is established according to pattern recognition neural network
Model may determine that the driving style of any driver, Fig. 5 are pattern recognition neural network identification model structure according to this model
Figure, the method for establishing model are as follows:
Step 1: using in database 70% sample is as learning sample, and the value of k principal component is as pattern-recognition nerve
The sample of the input of network, output of the sample classification result of FCM as pattern recognition neural network, calm type is denoted as [1 0
0], medium-sized sample is denoted as [0 1 0], the sample of radical type is denoted as [0 0 1].
Step 2: establishment model identifies that neural network driving style identification model, input layer number are k, output layer number
It is 1, empirically formula 10, hidden layer number are set as 10, hidden layer transmission function and choose sigmoid function, output layer transmitting
Function chooses softmax function, training function setup is trainscg function.
In formula: M is hidden layer number, and n is input layer number, and m is output layer number, some of a between [0 1 0]
Value.
Step 3: training neural network, Neural Network Self-learning randomly select weight w and bias b, then according to certain
Kind rule gradually improves input layer to hidden layer and hidden layer to weight between output layer and bias, until target output and in fact
Border output error meets threshold requirement.
Step 4: verifying the validity of the model, and the standard of the model is verified by remaining 30% sample in database
True property, accuracy of identification reach 95% or more and think that the model is effective.
In the present embodiment, driving style recognizer module is provided；The program has identification driver's driving style
Ability, the program computability characterize the characteristic parameter of driver's driving characteristics, while characteristic parameter being standardized and calculates k
The value of k principal component is input in driving style identification model by the value of principal component, identifies the driving style of the driver.
Such as the interface that Fig. 6 is the program, input button is clicked, (data are stored in driver's driving style data that selection needs to judge
In excel table), which will automatically calculate the value of characteristic parameter and identifies that the driving style of the driver, recognition result are defeated
Out in window as the result is shown, sample window shows the essential information of the driver, and graphical window shows driving in the form of images
The driving characteristics of member.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (9)
1. a kind of driving style of suitable domestic people is classified and identifying system, it is characterised in that: including driving style road ring
Border analog module, data acquisition module, database processing module and dimensionality reduction module, database sample classification module, driving style
Identification module；
The driving style road environment analog module connection database processing module and dimensionality reduction module, are used for simulated experiment road
Environment；
The data acquisition module connection database processing module and dimensionality reduction module, for acquiring vehicle condition signal, with driving
Style road environmental simulation module establishes domestic people driving style database jointly；
The database processing module and dimensionality reduction module are also connected with database sample classification module, for handling driving style test
Data, including calculating the value of driving style characteristic parameter and carrying out dimensionality reduction to driving style evaluation index；
The database sample classification module is also connected with driving style identification module, for classifying to database sample；
The driving style identification module is used to establish driving style identification model by pattern recognition neural network, ultimately generates
Driving style recognizer.
2. a kind of driving style of suitable domestic people according to claim 1 is classified and identifying system, it is characterised in that:
The driving style road environment analog module sets experiment condition as three kinds of urban district, suburb, high speed model experiment operating conditions, drives
Environment are as follows: fine, road is good, wind speed is normal, the normal driving environment without peak on and off duty.
3. a kind of driving style of suitable domestic people according to claim 1 is classified and identifying system, it is characterised in that:
The equipment that the data acquisition module uses includes 3-axis acceleration sensor, millimetre-wave radar, steering wheel angle measuring instrument, oil
Instrument is consumed, the vehicle condition signal of acquisition includes speed, accelerator pedal position, brake pedal position, brake pressure, acceleration, row
Vehicle spacing, steering wheel angle, acceleration.
4. a kind of driving style of suitable domestic people according to claim 1 is classified and identifying system, it is characterised in that:
The driving style characteristic parameter includes lane-change number, following distance, brake pressure maximum value, brake pressure variations rate maximum
Value, the max speed, average speed, speed standard deviation, peak acceleration, average acceleration, maximum deceleration, is put down at running time
Equal deceleration, deceleration shock degree average value, shock extent standard deviation, acceleration shock degree maximum value, is slowed down at acceleration shock degree average value
Shock extent maximum value, maximum accelerator travel, accelerator open degree average value, accelerator open degree standard deviation, accelerator open degree change rate are most
Big value, accelerator pedal change rate average value, accelerator releasing pedal rate of change average value, accelerator pedal aperture change rate standard deviation,
Accelerating traction activity of force maximum value, deceleration to draw, activity of force maximum value, acceleration tractive force power average value, slow down traction activity of force
Average value, tractive force power standard are poor.
5. a kind of driving style of suitable domestic people according to claim 1 is classified and identifying system, it is characterised in that:
The value for calculating driving style characteristic parameter, which is specifically included, is reduced to k principal component for evaluation index using PCA algorithm, and joins to feature
Number is standardized.
6. a kind of driving style of suitable domestic people according to claim 5 is classified and identifying system, it is characterised in that:
To driving style evaluation index carry out dimensionality reduction specifically include using PCA algorithm calculate covariance matrix, feature vector, characteristic value,
Principal component scores, principal component contributor rate and coefficient matrix PC；Finally the principle according to principal component contributor rate greater than 85% is selected
The number of principal component, it is assumed that the sum of contribution rate of preceding k principal component is greater than 85%, then k principal component is as new spy before selecting
Levy parameter.
7. a kind of driving style of suitable domestic people according to claim 5 is classified and identifying system, it is characterised in that:
The driving style identification module classifies to database using FCM algorithm, using k principal component of generation as new feature
Database sample is divided into 3 kinds of driving styles using the value of k principal component of database as the input of FCM classifier by parameter,
Driving style classification number is not limited to 3 classes.
8. a kind of driving style of suitable domestic people according to claim 5 is classified and identifying system, it is characterised in that:
The driving style identification module establishes driving style identification model using pattern recognition neural network, selects 70% in database
Sample is as learning sample, and remaining 30% sample is as detection sample；It is neural using the value of k principal component as pattern-recognition
The input of network, using the classification results of database as the output of pattern recognition neural network；The model hidden layer is set as 10
Layer, hidden layer transmission function choose sigmoid function, output layer transmission function chooses softmax function, training function setup is
Trainscg function.
9. utilizing the driving style classification and recognition methods of a kind of suitable domestic people of the claims, it is characterised in that:
Specifically comprise the following steps:
S1: driving style experimental situation is set by driving environment module, establishes domestic people driving style database；
S2: data collecting module collected vehicle condition signal is utilized；
S3: utilizing database processing module and dimensionality reduction module, generates domestic driver group driving style database and calculates feature
Parameter completes the dimension-reduction treatment of driving style characteristic parameter using PCA algorithm；
S4: the classification of driving style sample is realized by FCM algorithm using database sample classification module；
S5: driving style identification model is established by pattern recognition neural network using driving style identification module, generates one
Driving style automatic identification procedure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910595664.XA CN110321954A (en) | 2019-07-03 | 2019-07-03 | The driving style classification and recognition methods of suitable domestic people and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910595664.XA CN110321954A (en) | 2019-07-03 | 2019-07-03 | The driving style classification and recognition methods of suitable domestic people and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110321954A true CN110321954A (en) | 2019-10-11 |
Family
ID=68122439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910595664.XA Pending CN110321954A (en) | 2019-07-03 | 2019-07-03 | The driving style classification and recognition methods of suitable domestic people and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110321954A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111003619A (en) * | 2019-11-06 | 2020-04-14 | 猫岐智能科技（上海）有限公司 | Data acquisition method |
| CN111284497A (en) * | 2020-01-20 | 2020-06-16 | 北京津发科技股份有限公司 | Driving state recognition device |
| CN111591294A (en) * | 2020-05-29 | 2020-08-28 | 长安大学 | Early warning method for vehicle lane change in different traffic environments |
| CN112046489A (en) * | 2020-08-31 | 2020-12-08 | 吉林大学 | Driving style identification algorithm based on factor analysis and machine learning |
| CN112052895A (en) * | 2020-09-03 | 2020-12-08 | 同济大学 | Pure electric vehicle driving style clustering method |
| CN112149796A (en) * | 2020-08-13 | 2020-12-29 | 江苏大学 | Driving style identification method for optimizing BP neural network based on improved genetic algorithm |
| CN112319488A (en) * | 2020-10-20 | 2021-02-05 | 易显智能科技有限责任公司 | Method and system for identifying driving style of motor vehicle driver |
| CN112613181A (en) * | 2020-12-28 | 2021-04-06 | 浙江天行健智能科技有限公司 | Driving state modeling method based on simulated driver and ANN algorithm |
| CN112622920A (en) * | 2020-12-28 | 2021-04-09 | 华北科技学院 | Auxiliary driving system |
| CN112651443A (en) * | 2020-12-28 | 2021-04-13 | 华北科技学院 | Driving style identification model evaluation method, device, medium and equipment based on machine learning |
| CN113022576A (en) * | 2021-04-02 | 2021-06-25 | 东南大学 | Driving style analysis method, system and device for different driving task stages |
| CN113044046A (en) * | 2021-04-09 | 2021-06-29 | 联合汽车电子有限公司 | Driver style recognition method, system, electronic device and readable storage medium |
| CN113257023A (en) * | 2021-04-13 | 2021-08-13 | 哈尔滨工业大学 | L3-level automatic driving risk assessment and takeover early warning method and system |
| CN113297685A (en) * | 2021-07-27 | 2021-08-24 | 中汽研（天津）汽车工程研究院有限公司 | Vehicle operation condition mode identification method |
| CN113401130A (en) * | 2021-06-25 | 2021-09-17 | 华人运通(江苏)动力电池系统有限公司 | Driving style recognition method and device based on environmental information and storage medium |
| CN113591780A (en) * | 2021-08-11 | 2021-11-02 | 山东大学 | Method and system for identifying driving risk of driver |
| CN114162132A (en) * | 2021-12-07 | 2022-03-11 | 吉林大学 | Driving mode identification method based on subjective and objective evaluation |
| WO2022057745A1 (en) * | 2020-09-15 | 2022-03-24 | 华为技术有限公司 | Assisted-driving control method and apparatus |
| WO2022237212A1 (en) * | 2021-05-10 | 2022-11-17 | 江苏大学 | Complex network-based complex environment model for autonomous vehicle, and complex network-based cognitive system for autonomous vehicle and cognition method of complex network-based cognitive system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101633358A (en) * | 2008-07-24 | 2010-01-27 | 通用汽车环球科技运作公司 | Adaptive vehicle control system with integrated driving style recognition |
| US20100023223A1 (en) * | 2008-07-24 | 2010-01-28 | Gm Global Technology Operations, Inc. | Adaptive vehicle control system with driving style recognition |
| CN105034986A (en) * | 2015-06-10 | 2015-11-11 | 辽宁工业大学 | On-line identification method and on-line identification device for steering characteristics of drivers |
| CN107153916A (en) * | 2017-04-30 | 2017-09-12 | 安徽中科美络信息技术有限公司 | A kind of driving behavior evaluation method clustered based on FCM with BP neural network |
| CN108280415A (en) * | 2018-01-17 | 2018-07-13 | 武汉理工大学 | Driving behavior recognition methods based on intelligent mobile terminal |
| CN108629372A (en) * | 2018-05-07 | 2018-10-09 | 福州大学 | Obtain experimental system and the driving style recognition methods of driving style characteristic parameter |
-
2019
- 2019-07-03 CN CN201910595664.XA patent/CN110321954A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101633358A (en) * | 2008-07-24 | 2010-01-27 | 通用汽车环球科技运作公司 | Adaptive vehicle control system with integrated driving style recognition |
| US20100023223A1 (en) * | 2008-07-24 | 2010-01-28 | Gm Global Technology Operations, Inc. | Adaptive vehicle control system with driving style recognition |
| CN105034986A (en) * | 2015-06-10 | 2015-11-11 | 辽宁工业大学 | On-line identification method and on-line identification device for steering characteristics of drivers |
| CN107153916A (en) * | 2017-04-30 | 2017-09-12 | 安徽中科美络信息技术有限公司 | A kind of driving behavior evaluation method clustered based on FCM with BP neural network |
| CN108280415A (en) * | 2018-01-17 | 2018-07-13 | 武汉理工大学 | Driving behavior recognition methods based on intelligent mobile terminal |
| CN108629372A (en) * | 2018-05-07 | 2018-10-09 | 福州大学 | Obtain experimental system and the driving style recognition methods of driving style characteristic parameter |
Non-Patent Citations (2)
| Title |
|---|
| 周致成: ""驾驶员转向特性分类与辨识方法研究"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 郝景贤: ""混合动力汽车驾驶风格识别的研究"", 《汽车工程》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111003619A (en) * | 2019-11-06 | 2020-04-14 | 猫岐智能科技（上海）有限公司 | Data acquisition method |
| CN111284497A (en) * | 2020-01-20 | 2020-06-16 | 北京津发科技股份有限公司 | Driving state recognition device |
| CN111284497B (en) * | 2020-01-20 | 2022-04-12 | 北京津发科技股份有限公司 | Driving state recognition device |
| CN111591294B (en) * | 2020-05-29 | 2021-06-25 | 长安大学 | Early warning method for vehicle lane change in different traffic environments |
| CN111591294A (en) * | 2020-05-29 | 2020-08-28 | 长安大学 | Early warning method for vehicle lane change in different traffic environments |
| CN112149796A (en) * | 2020-08-13 | 2020-12-29 | 江苏大学 | Driving style identification method for optimizing BP neural network based on improved genetic algorithm |
| CN112046489A (en) * | 2020-08-31 | 2020-12-08 | 吉林大学 | Driving style identification algorithm based on factor analysis and machine learning |
| CN112046489B (en) * | 2020-08-31 | 2021-03-16 | 吉林大学 | Driving style identification algorithm based on factor analysis and machine learning |
| CN112052895A (en) * | 2020-09-03 | 2020-12-08 | 同济大学 | Pure electric vehicle driving style clustering method |
| WO2022057745A1 (en) * | 2020-09-15 | 2022-03-24 | 华为技术有限公司 | Assisted-driving control method and apparatus |
| CN112319488A (en) * | 2020-10-20 | 2021-02-05 | 易显智能科技有限责任公司 | Method and system for identifying driving style of motor vehicle driver |
| CN112651443A (en) * | 2020-12-28 | 2021-04-13 | 华北科技学院 | Driving style identification model evaluation method, device, medium and equipment based on machine learning |
| CN112622920A (en) * | 2020-12-28 | 2021-04-09 | 华北科技学院 | Auxiliary driving system |
| CN112613181B (en) * | 2020-12-28 | 2023-05-23 | 浙江天行健智能科技有限公司 | Driving state modeling method based on simulated driver and ANN algorithm |
| CN112613181A (en) * | 2020-12-28 | 2021-04-06 | 浙江天行健智能科技有限公司 | Driving state modeling method based on simulated driver and ANN algorithm |
| CN113022576A (en) * | 2021-04-02 | 2021-06-25 | 东南大学 | Driving style analysis method, system and device for different driving task stages |
| CN113022576B (en) * | 2021-04-02 | 2022-02-22 | 东南大学 | Driving style analysis method, system and device for different driving task stages |
| CN113044046A (en) * | 2021-04-09 | 2021-06-29 | 联合汽车电子有限公司 | Driver style recognition method, system, electronic device and readable storage medium |
| CN113257023A (en) * | 2021-04-13 | 2021-08-13 | 哈尔滨工业大学 | L3-level automatic driving risk assessment and takeover early warning method and system |
| WO2022237212A1 (en) * | 2021-05-10 | 2022-11-17 | 江苏大学 | Complex network-based complex environment model for autonomous vehicle, and complex network-based cognitive system for autonomous vehicle and cognition method of complex network-based cognitive system |
| CN113401130A (en) * | 2021-06-25 | 2021-09-17 | 华人运通(江苏)动力电池系统有限公司 | Driving style recognition method and device based on environmental information and storage medium |
| CN113297685A (en) * | 2021-07-27 | 2021-08-24 | 中汽研（天津）汽车工程研究院有限公司 | Vehicle operation condition mode identification method |
| CN113591780A (en) * | 2021-08-11 | 2021-11-02 | 山东大学 | Method and system for identifying driving risk of driver |
| CN114162132A (en) * | 2021-12-07 | 2022-03-11 | 吉林大学 | Driving mode identification method based on subjective and objective evaluation |
| CN114162132B (en) * | 2021-12-07 | 2023-11-21 | 吉林大学 | Driving mode identification method based on subjective and objective evaluation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110321954A (en) | The driving style classification and recognition methods of suitable domestic people and system | |
| Zhu et al. | Typical-driving-style-oriented personalized adaptive cruise control design based on human driving data | |
| Lv et al. | Hybrid-learning-based classification and quantitative inference of driver braking intensity of an electrified vehicle | |
| CN107169567B (en) | Method and device for generating decision network model for automatic vehicle driving | |
| Huang et al. | An intelligent multifeature statistical approach for the discrimination of driving conditions of a hybrid electric vehicle | |
| CN110949398B (en) | Method for detecting abnormal driving behavior of first-vehicle drivers in vehicle formation driving | |
| Suzdaleva et al. | An online estimation of driving style using data-dependent pointer model | |
| Chu et al. | Curve speed model for driver assistance based on driving style classification | |
| CN105426638A (en) | Driver behavior characteristic identification device | |
| Li et al. | Driver-identified supervisory control system of hybrid electric vehicles based on spectrum-guided fuzzy feature extraction | |
| Zhu et al. | Hazardous scenario enhanced generation for automated vehicle testing based on optimization searching method | |
| CN110182217A (en) | A kind of traveling task complexity quantitative estimation method towards complicated scene of overtaking other vehicles | |
| CN111907523B (en) | Vehicle following optimizing control method based on fuzzy reasoning | |
| Mase et al. | Capturing uncertainty in heavy goods vehicles driving behaviour | |
| CN115186594A (en) | Energy-saving speed optimization method under influence of man-vehicle-road coupling | |
| Shi et al. | Applying a WNN-HMM based driver model in human driver simulation: Method and test | |
| CN113642114B (en) | Personified random following driving behavior modeling method capable of making mistakes | |
| Cong et al. | An automatic vehicle avoidance control model for dangerous lane-changing behavior | |
| CN114148349B (en) | Vehicle personalized following control method based on generation of countermeasure imitation study | |
| Chen et al. | Platoon separation strategy optimization method based on deep cognition of a driver’s behavior at signalized intersections | |
| Zhou et al. | Objective evaluation of drivability in passenger cars with dual-clutch transmission: a case study of static gearshift condition | |
| Liang et al. | Dynamic neural network-based integrated learning algorithm for driver behavior | |
| Liu et al. | A method to improve accuracy of velocity prediction using Markov model | |
| Liu et al. | Driving intention identification based on long short-term memory neural network | |
| Sun et al. | Recognition method of drinking-driving behaviors based on PCA and RBF neural network |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230222 Address after: 300300 68 pioneer East Road, Dongli District, Tianjin Applicant after: CATARC AUTOMOTIVE TEST CENTER (TIANJIN) Co.,Ltd. Applicant after: CHINA AUTOMOTIVE TECHNOLOGY AND RESEARCH CENTER Co.,Ltd. Address before: 300457 TEDA MSD-B1-1907, 62 Second Avenue, Binhai New Area Development Zone, Tianjin Applicant before: CATARC (TIANJIN) AUTOMOTIVE ENGINEERING RESEARCH INSTITUTE Co.,Ltd. Applicant before: CHINA AUTOMOTIVE TECHNOLOGY AND RESEARCH CENTER Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191011 |