CN112766306B - Deceleration strip area identification method based on SVM algorithm - Google Patents
Deceleration strip area identification method based on SVM algorithm Download PDFInfo
- Publication number
- CN112766306B CN112766306B CN202011570770.1A CN202011570770A CN112766306B CN 112766306 B CN112766306 B CN 112766306B CN 202011570770 A CN202011570770 A CN 202011570770A CN 112766306 B CN112766306 B CN 112766306B
- Authority
- CN
- China
- Prior art keywords
- deceleration strip
- data set
- svm algorithm
- test data
- area identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tires In General (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to the technical field of vehicle auxiliary driving, and discloses a deceleration strip area identification method based on an SVM algorithm, which comprises the following steps: acquiring real-time running state parameters of a vehicle, wherein the running state parameters comprise vehicle speed, vehicle speed vertical acceleration and tire vertical displacement; inputting the vehicle speed, the calculated tire vertical maximum vibration amplitude and the tire vertical maximum vibration frequency into a preset deceleration strip area identification model based on an SVM algorithm, and identifying whether the vehicle runs in a deceleration strip area or not through the deceleration strip area identification model. The method collects data through a simulated driving test, establishes a deceleration strip area identification model based on an SVM algorithm, has the advantages of convenience in data collection, low cost, small calculated amount, high calculation speed and good robustness, and overcomes the defects of the prior art.
Description
Technical Field
The invention relates to the technical field of vehicle auxiliary driving, in particular to a deceleration strip area identification method based on an SVM algorithm.
Background
During the running of a vehicle, a deceleration strip is a type of road surface that often occurs. For automobiles equipped with adjustable suspensions such as air suspensions, timely identification of the deceleration strip can help the ECU to properly adjust the rigidity or damping of the suspension, so that the automobile stably passes through the deceleration strip area, thereby improving the comfort of passengers and reducing the adverse effect of the deceleration strip.
The Chinese patent with the application number of CN201910552000.5 and the name of a deceleration strip recognition method and system proposes a method for realizing deceleration strip recognition by using a convolutional neural network technology, wherein on one hand, the method requires a large amount of relevant picture memorability training of the deceleration strip, and on the other hand, in the practical application process, the image quality is sensitive to weather and illumination, and the robustness is difficult to ensure.
Chinese patent application No. CN202010489774.0 entitled "a deceleration strip detection method and apparatus based on vision and storage medium thereof" also proposes a deceleration strip recognition method based on machine vision technology, which mainly uses a deep learning algorithm for modeling. This method is computationally intensive and has similar problems to the aforementioned patent.
Therefore, there is a need for a deceleration strip area identification method with good robustness and fast computation.
Disclosure of Invention
The invention mainly aims to develop a deceleration strip area identification method based on SVM (support vector machine) algorithm, which has the advantages of good robustness, small calculated amount and high calculation speed, so as to overcome the defects of the prior art.
In order to achieve the above purpose, the invention provides a deceleration strip area identification method based on SVM algorithm, which mainly comprises the following steps:
acquiring real-time running state parameters of a vehicle, wherein the running state parameters comprise vehicle speed, vehicle speed vertical acceleration and tire vertical displacement;
inputting the vehicle speed, the calculated tire vertical maximum vibration amplitude and the tire vertical maximum vibration frequency into a preset deceleration strip area identification model based on an SVM algorithm, and identifying whether the vehicle runs in a deceleration strip area or not through the deceleration strip area identification model.
Preferably, the speed bump area identification model based on the SVM algorithm is obtained through the following modeling steps:
and (3) performing a simulated driving test: the driver uses the simulated driver to control the simulated vehicle to run through a virtual road comprising a deceleration strip area, and the collected test data comprise the vehicle speed, the vehicle speed vertical acceleration and the tire vertical displacement;
processing test data: intercepting test data according to a certain time window length and a certain time window interval, solving the average vehicle speed and the average vehicle vertical acceleration in each time window, and obtaining the tire vertical maximum vibration amplitude and the tire vertical maximum vibration frequency through Fourier transform calculation; marking all data when the vehicle runs in the deceleration strip area as deceleration strip data to obtain a deceleration strip data set; marking all data when the vehicle runs outside the deceleration strip area as non-deceleration strip data, and obtaining a non-deceleration strip data set;
training a deceleration strip area identification model based on an SVM algorithm: training to obtain a deceleration strip recognition model based on the deceleration strip data set, the non-deceleration strip data set and the SVM algorithm; in the training process, the vehicle speed, the tire vertical maximum vibration amplitude and the tire vertical maximum vibration amplitude vibration frequency are used as independent variables, and the data marks in the data points are used as dependent variables; when the obtained deceleration strip area identification model based on the SVM algorithm is used, whether the vehicle runs in the deceleration strip area or not is judged according to the calculated data mark.
Further preferably, in the simulated driving test, the virtual road environment includes an urban condition and a high-speed condition; the total driving mileage exceeds 100km, wherein the length of the deceleration strip area accounts for 1/3 of the total mileage; the acquisition frequency of the test data was 10Hz.
Further preferably, when the test data are processed, the test data are intercepted by taking a certain time period t=2s as a window length and taking l=0.5s as a time window interval, the average vehicle speed and the average vehicle body vertical acceleration in each time window are obtained, and the tire vertical maximum vibration amplitude and the tire vertical maximum vibration frequency are obtained through Fourier transform calculation.
Further preferably, the deceleration strip data set and the non-deceleration strip data set are randomly divided into two parts according to a certain proportion respectively to obtain a deceleration strip training data set, a deceleration strip test data set, a non-deceleration strip training data set and a non-deceleration strip test data set;
taking a combined set consisting of the deceleration strip training data set and the non-deceleration strip training data set as a training data set; taking a combined set consisting of the deceleration strip test data set and the non-deceleration strip test data set as a test data set; training by using a training data set to obtain a deceleration strip area identification model based on an SVM algorithm, and testing the deceleration strip area identification model based on the SVM algorithm obtained by training by using a testing data set.
The training process of the SVM algorithm follows the following rules and steps:
the training dataset is expressed as:
T＝{(x 1 ,y 1 ),(x 2 ,y 2 ),...，(x n ,y n )}
wherein x is i Belongs to an n-dimensional space, and y i Is 1 or-1, and i=1, 2 i For the ith feature vector, y i Is a category label. 1 represents a positive example; -1 represents a negative example. In the invention, the characteristic vector consists of a vehicle speed, a vehicle speed vertical acceleration and a tire vertical displacement, wherein a mark symbol 1 is positioned in a deceleration strip area, and a mark symbol-1 is positioned in a non-deceleration strip area.
1) Selecting proper kernel function and penalty parameter C >0, constructing and solving convex quadratic programming problem, as shown in the following formula:
2) The optimal solution is found (typically using gradient descent method):
3) Calculation b *
4) Classification decision function:
the invention uses Gaussian kernel function, punishment parameter C=15, solves alpha * When using the gradient descent method, the gaussian kernel function is represented by the following formula:
still further preferably, the deceleration strip data set is randomly divided into two parts according to a certain proportion k=8:2, so as to obtain a deceleration strip training data set and a deceleration strip test data set;
and randomly dividing the non-deceleration strip data set into two parts according to a certain proportion k=8:2 to obtain a non-deceleration strip training data set and a non-deceleration strip test data set.
Still more preferably, when testing the deceleration strip area identification model, the vehicle speed, the tire vertical maximum vibration amplitude and the tire vertical maximum vibration amplitude vibration frequency are used as input variables, and the output variables are data marks predicted by corresponding test data points; and if the data mark predicted by the test data point through model calculation is consistent with the real data mark, the prediction success of the deceleration strip area recognition model based on the SVM algorithm is indicated in the test data point, otherwise, the prediction failure is indicated.
If the proportion of the predicted successful test data points to the total data points in the test data set is greater than a certain threshold value alpha, the modeling is successful, otherwise, a supplementary simulation driving test is needed to be carried out and test data are collected.
In a specific embodiment, the threshold α is 85%. According to actual needs, the threshold value allows different values according to different precision requirements.
According to the invention, a simulated driver is used for carrying out a simulated driving test to obtain test data of a vehicle passing through a deceleration strip area and a non-deceleration strip area, a deceleration strip area identification model is obtained based on SVM algorithm training, and according to the model, whether the vehicle runs in the deceleration strip area can be accurately identified through inputting the speed of the vehicle, the vertical maximum vibration amplitude of a tire and the vertical maximum vibration amplitude vibration frequency of the tire, so that the vehicle is ensured to stably pass through the deceleration strip area, the comfort and the safety are improved, and some limitations and defects of the prior art are overcome. Compared with the prior art, the deceleration strip area identification method has the advantages that the calculation amount of the model adopted is small, the calculation speed is high, the method is not influenced by illumination and weather of the vehicle running environment, and the robustness is better.
Drawings
Fig. 1 is a schematic flow chart of steps of a modeling process in a deceleration strip area recognition method based on an SVM algorithm according to the present invention.
Detailed Description
In order that the present invention may be better understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings, in which it is to be understood that the invention is illustrated in the appended drawings. All other embodiments obtained under the premise of equivalent changes and modifications made by those skilled in the art based on the embodiments of the present invention shall fall within the scope of the present invention.
Referring to fig. 1, the present embodiment provides a deceleration strip area identification method based on an SVM algorithm, which includes the steps of:
step one: acquiring real-time running state parameters of a vehicle, wherein the running state parameters comprise vehicle speed, vehicle speed vertical acceleration and tire vertical displacement;
step two: inputting the vehicle speed, the calculated tire vertical maximum vibration amplitude and the tire vertical maximum vibration frequency into a preset deceleration strip area identification model based on an SVM algorithm, and identifying whether the vehicle runs in a deceleration strip area or not through the deceleration strip area identification model.
Referring to fig. 1, the deceleration strip area recognition model based on the SVM algorithm preset in the second step is obtained through the following modeling steps S1-S4:
s1, performing a driver-in-loop simulation driving test and collecting data:
the driver uses the simulated driver to control the simulated vehicle to run through the virtual road comprising the deceleration strip area, and in the simulated driving test, the virtual road environment comprises urban working conditions and high-speed working conditions. The total mileage driven exceeds 100km, wherein the length of the deceleration strip area accounts for 1/3 of the total mileage. The collected test data comprise vehicle speed, vehicle speed vertical acceleration and tire vertical displacement, and the collection frequency of the test data is 10Hz.
S2, processing test data:
performing Fourier transform on the tire vertical displacement at a certain time window length t=2s and a time window interval L=0.5 s to obtain a tire maximum vibration amplitude and a corresponding vibration frequency, namely a tire vertical maximum vibration amplitude and a tire vertical maximum vibration frequency; the average vertical acceleration of the vehicle body and the average vehicle body are obtained according to a certain time window length t=2s and a time window interval l=0.05 s.
Marking all data when the vehicle runs in the deceleration strip area as deceleration strip data to obtain a deceleration strip data set; and marking all data when the vehicle runs outside the deceleration strip area as non-deceleration strip data, and obtaining a non-deceleration strip data set. In the present embodiment, the data marks of the deceleration strip data are denoted by the numeral "1", and the data marks of the non-deceleration strip data are denoted by the numeral "0".
Randomly dividing a deceleration strip data set into two parts according to a certain proportion k=8:2 to obtain a deceleration strip training data set and a deceleration strip test data set; and randomly dividing the non-deceleration strip data set into two parts according to a certain proportion k=8:2 to obtain a non-deceleration strip training data set and a non-deceleration strip test data set.
Taking a combined set consisting of the deceleration strip training data set and the non-deceleration strip training data set as a training data set; and taking a combined set consisting of the deceleration strip test data set and the non-deceleration strip test data set as a test data set.
S3, training a deceleration strip area identification model based on SVM algorithm
When the recognition model is trained, training a training data set to obtain a deceleration strip area recognition model based on an SVM algorithm; in the training process, the vehicle speed, the tire vertical maximum vibration amplitude and the tire vertical maximum vibration amplitude vibration frequency are taken as independent variables, and the data marks in the data points are taken as dependent variables.
The training process of the SVM algorithm follows the following rules and steps:
the training dataset is expressed as:
T＝{(x 1 ,y 1 ),(x 2 ,y 2 ),...，(x n ,y n )}
wherein x is i Belongs to an n-dimensional space, and y i Is 1 or-1, and i=1, 2 i For the ith feature vector, y i Is a category label. 1 represents a positive example; -1 represents a negative example. In the invention, the characteristic vector consists of a vehicle speed, a vehicle speed vertical acceleration and a tire vertical displacement, wherein a mark symbol 1 is positioned in a deceleration strip area, and a mark symbol-1 is positioned in a non-deceleration strip area.
1) Selecting proper kernel function and penalty parameter C >0, constructing and solving convex quadratic programming problem, as shown in the following formula:
2) The optimal solution is found (typically using gradient descent method):
3) Calculation b *
4) Classification decision function:
the invention uses Gaussian kernel function, punishment parameter C=15, solves alpha * When gradient descent is used, the Gaussian kernel function is as followsThe formula is shown as follows:
s4, testing an identification model:
and testing the training-obtained deceleration strip area identification model based on the SVM algorithm by using a test data set. When the deceleration strip area identification model is tested, the vehicle speed, the tire vertical maximum vibration amplitude and the tire vertical maximum vibration amplitude vibration frequency are taken as input variables, and the output variables are data marks predicted by corresponding test data points; and if the data mark predicted by the test data point through model calculation is consistent with the real data mark, the prediction success of the deceleration strip area recognition model based on the SVM algorithm is indicated in the test data point, otherwise, the prediction failure is indicated.
If the proportion of the predicted successful test data points to the total data points in the test data set is greater than a certain threshold value alpha, the modeling is successful, otherwise, a supplementary simulation driving test is needed to be carried out and test data are collected. In this embodiment, the threshold α is 85%. The threshold allows different values depending on different accuracy requirements.
After modeling is completed, the invention carries out deceleration strip area identification according to the obtained deceleration area identification model based on the SVM algorithm. In the running process of the vehicle, running state parameters of the vehicle, including the speed, the vertical acceleration of the speed and the vertical displacement of the tire, are collected in real time, the average speed and the vertical acceleration of the vehicle body are calculated by taking 2s as the time window length, and the vertical maximum vibration amplitude vibration frequency of the tire are obtained through Fourier transform calculation; the vehicle speed, the tire vertical maximum vibration amplitude and the tire vertical maximum vibration amplitude vibration frequency are input into a deceleration strip area identification model based on an SVM algorithm to obtain a predicted data mark, and if the output value of the data mark is 1, the vehicle is judged to be in a deceleration strip area for running. At this time, the ECU of the vehicle can appropriately adjust the suspension stiffness or damping so that the vehicle smoothly passes through the deceleration strip region. If the output value of the data mark is 0, the vehicle is judged to be in the non-deceleration zone area for running.
Compared with the prior art, the method has the advantages of convenience in modeling data acquisition, low modeling cost, small model calculation amount and high calculation speed, only the running state parameters of the vehicle are required to be detected in the using step of the model, the method is not interfered by road light environment and weather, the identification of the deceleration strip is more accurate, the robustness of the model is better, and the limitation of the prior art is effectively overcome.
The foregoing is merely a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention; it will be apparent to those skilled in the relevant art and it is intended to implement the invention in light of the foregoing disclosure without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (6)
1. The deceleration strip area identification method based on the SVM algorithm is characterized by comprising the following steps of:
acquiring real-time running state parameters of a vehicle, wherein the running state parameters comprise vehicle speed, vehicle speed vertical acceleration and tire vertical displacement;
inputting the vehicle speed, the calculated tire vertical maximum vibration amplitude and the tire vertical maximum vibration frequency into a preset speed reduction zone area identification model based on an SVM algorithm, and identifying whether the vehicle runs in a speed reduction zone area or not through the speed reduction zone area identification model;
the deceleration strip area identification model based on the SVM algorithm is obtained through the following modeling steps:
and (3) performing a simulated driving test: the driver uses the simulated driver to control the simulated vehicle to run through a virtual road comprising a deceleration strip area, and the collected test data comprise the vehicle speed, the vehicle speed vertical acceleration and the tire vertical displacement;
processing test data: when test data are processed, taking a certain time length t=2s as a window length, taking L=0.5s as a time window interval, intercepting the test data, solving the average vehicle speed and the average vehicle vertical acceleration in each time window, and carrying out Fourier transformation on the tire vertical displacement to obtain the tire maximum vibration amplitude and the corresponding vibration frequency, namely the tire vertical maximum vibration amplitude and the tire vertical maximum vibration amplitude vibration frequency; marking all data when the vehicle runs in the deceleration strip area as deceleration strip data to obtain a deceleration strip data set; marking all data when the vehicle runs outside the deceleration strip area as non-deceleration strip data, and obtaining a non-deceleration strip data set;
training a deceleration strip area identification model based on an SVM algorithm: training to obtain a deceleration strip recognition model based on the deceleration strip data set, the non-deceleration strip data set and the SVM algorithm; in the training process, the vehicle speed, the tire vertical maximum vibration amplitude and the tire vertical maximum vibration amplitude vibration frequency are used as independent variables, and the data marks in the data points are used as dependent variables; when the obtained deceleration strip area identification model based on the SVM algorithm is used, judging whether the vehicle runs in the deceleration strip area or not according to the calculated data mark; the method comprises the following specific steps: dividing the deceleration strip data set and the non-deceleration strip data set into two parts at random according to a certain proportion to obtain a deceleration strip training data set, a deceleration strip test data set, a non-deceleration strip training data set and a non-deceleration strip test data set;
taking a combined set consisting of the deceleration strip training data set and the non-deceleration strip training data set as a training data set; taking a combined set consisting of the deceleration strip test data set and the non-deceleration strip test data set as a test data set; training by using a training data set to obtain a deceleration strip area identification model based on an SVM algorithm, and testing the deceleration strip area identification model based on the SVM algorithm obtained by training by using a testing data set.
2. The speed bump area identifying method based on the SVM algorithm according to claim 1, wherein: in the simulated driving test, the virtual road environment comprises urban working conditions and high-speed working conditions; the total driving mileage exceeds 100km, wherein the length of the deceleration strip area accounts for 1/3 of the total mileage; the acquisition frequency of the test data was 10Hz.
3. The speed bump area identifying method based on the SVM algorithm according to claim 1, wherein:
randomly dividing a deceleration strip data set into two parts according to a certain proportion k=8:2 to obtain a deceleration strip training data set and a deceleration strip test data set;
and randomly dividing the non-deceleration strip data set into two parts according to a certain proportion k=8:2 to obtain a non-deceleration strip training data set and a non-deceleration strip test data set.
4. A deceleration strip region identification method based on an SVM algorithm according to claim 1 or 3, characterized in that: when the deceleration strip area identification model is tested, the vehicle speed, the tire vertical maximum vibration amplitude and the tire vertical maximum vibration amplitude vibration frequency are taken as input variables, and the output variables are data marks predicted by corresponding test data points; and if the data mark predicted by the test data point through model calculation is consistent with the real data mark, the prediction success of the deceleration strip area recognition model based on the SVM algorithm is indicated in the test data point, otherwise, the prediction failure is indicated.
5. The method for identifying a deceleration strip based on SVM algorithm according to claim 4, wherein if the ratio of the predicted successful test data points to the total number of data points in the test data set is greater than a certain thresholdαAnd if the modeling is successful, otherwise, a supplementary simulation driving test is needed and test data are acquired.
6. The SVM algorithm based deceleration strip area identification method of claim 5, wherein said threshold valueα85%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011570770.1A CN112766306B (en) | 2020-12-26 | 2020-12-26 | Deceleration strip area identification method based on SVM algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011570770.1A CN112766306B (en) | 2020-12-26 | 2020-12-26 | Deceleration strip area identification method based on SVM algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112766306A CN112766306A (en) | 2021-05-07 |
| CN112766306B true CN112766306B (en) | 2023-06-27 |
Family
ID=75695839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011570770.1A Active CN112766306B (en) | 2020-12-26 | 2020-12-26 | Deceleration strip area identification method based on SVM algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112766306B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115615422B (en) * | 2022-12-20 | 2023-03-28 | 禾多科技（北京）有限公司 | Deceleration strip detection method and device, electronic equipment and computer readable medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08138189A (en) * | 1994-11-04 | 1996-05-31 | Honda Motor Co Ltd | Road surface state detecting device |
| JPH09243345A (en) * | 1996-03-12 | 1997-09-19 | Unisia Jecs Corp | Road surface condition detecting device |
| CN1608012A (en) * | 2001-12-21 | 2005-04-20 | 株式会社普利司通 | Method and apparatus for estimating road surface state and tire running state, abs and vehicle control using the same |
| CN102289674A (en) * | 2011-07-15 | 2011-12-21 | 王世峰 | Pavement type recognition method and device based on vertical acceleration and pavement image |
| CN103235891A (en) * | 2013-05-05 | 2013-08-07 | 吉林大学 | Road identification system and method based on vehicle vertical vibration system identification |
| CN103318180A (en) * | 2013-05-28 | 2013-09-25 | 万向钱潮股份有限公司 | Vehicular road surface irregularity automatic identification system and method |
| CN104120644A (en) * | 2013-04-26 | 2014-10-29 | 同济大学 | Gravitational acceleration sensor based road surface flatness detection method |
| CN104755345A (en) * | 2014-03-19 | 2015-07-01 | 株式会社小松制作所 | Pavement state determination method, pavement state output method, pavement state determination device and pavement state output device |
| CN108513676A (en) * | 2018-04-25 | 2018-09-07 | 深圳市锐明技术股份有限公司 | A kind of road conditions recognition methods, device and equipment |
| JP2019003369A (en) * | 2017-06-14 | 2019-01-10 | スズキ株式会社 | Road surface state analyzer |
| CN109263654A (en) * | 2018-11-19 | 2019-01-25 | 吉林大学 | A kind of automobile crosses deceleration strip adaptive speed regulation system and speed regulating method |
| CN109910886A (en) * | 2017-12-11 | 2019-06-21 | 郑州宇通客车股份有限公司 | A kind of road bump detection method, control method for vehicle and system |
| CN111504436A (en) * | 2020-04-17 | 2020-08-07 | 清华大学 | Vehicle load and road condition monitoring method and device based on vehicle vibration data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101275900A (en) * | 2008-05-08 | 2008-10-01 | 江汉大学 | Method for recognizing road surface types based on vehicle wheel vibration |
| CN105473983B (en) * | 2014-06-09 | 2020-05-12 | 尼拉动力公司 | Detection of short-term irregularities on a road surface |
| JP6783184B2 (en) * | 2017-05-12 | 2020-11-11 | 株式会社ブリヂストン | Road surface condition determination method and road surface condition determination device |
| CN111582288B (en) * | 2020-05-06 | 2024-05-03 | 武汉理工大学 | Non-contact vehicle overload recognition system based on vehicle body vibration model |
| CN111976731B (en) * | 2020-08-04 | 2023-06-13 | 大连民族大学 | Road surface unevenness recognition method based on vehicle frequency domain response |
-
2020
- 2020-12-26 CN CN202011570770.1A patent/CN112766306B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08138189A (en) * | 1994-11-04 | 1996-05-31 | Honda Motor Co Ltd | Road surface state detecting device |
| JPH09243345A (en) * | 1996-03-12 | 1997-09-19 | Unisia Jecs Corp | Road surface condition detecting device |
| CN1608012A (en) * | 2001-12-21 | 2005-04-20 | 株式会社普利司通 | Method and apparatus for estimating road surface state and tire running state, abs and vehicle control using the same |
| CN102289674A (en) * | 2011-07-15 | 2011-12-21 | 王世峰 | Pavement type recognition method and device based on vertical acceleration and pavement image |
| CN104120644A (en) * | 2013-04-26 | 2014-10-29 | 同济大学 | Gravitational acceleration sensor based road surface flatness detection method |
| CN103235891A (en) * | 2013-05-05 | 2013-08-07 | 吉林大学 | Road identification system and method based on vehicle vertical vibration system identification |
| CN103318180A (en) * | 2013-05-28 | 2013-09-25 | 万向钱潮股份有限公司 | Vehicular road surface irregularity automatic identification system and method |
| CN104755345A (en) * | 2014-03-19 | 2015-07-01 | 株式会社小松制作所 | Pavement state determination method, pavement state output method, pavement state determination device and pavement state output device |
| JP2019003369A (en) * | 2017-06-14 | 2019-01-10 | スズキ株式会社 | Road surface state analyzer |
| CN109910886A (en) * | 2017-12-11 | 2019-06-21 | 郑州宇通客车股份有限公司 | A kind of road bump detection method, control method for vehicle and system |
| CN108513676A (en) * | 2018-04-25 | 2018-09-07 | 深圳市锐明技术股份有限公司 | A kind of road conditions recognition methods, device and equipment |
| CN109263654A (en) * | 2018-11-19 | 2019-01-25 | 吉林大学 | A kind of automobile crosses deceleration strip adaptive speed regulation system and speed regulating method |
| CN111504436A (en) * | 2020-04-17 | 2020-08-07 | 清华大学 | Vehicle load and road condition monitoring method and device based on vehicle vibration data |
Non-Patent Citations (3)
| Title |
|---|
| 《Reconstruction of road defects and road roughness classification using Artificial Neural Networks simulation and vehicle dynamic responses：application to experimental data》;H.M.Ngwangwa et al.;《Journal of Terramechanics》;全文 * |
| 《基于ＧＡ－ＢＰ网络的矿山路面不平度辨识》;谷正气 等;《中国机械工程》;第25卷(第23期);全文 * |
| 《基于车辆响应识别路面不平度的神经网络方法研究》;谷盛丰;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112766306A (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105069415B (en) | Method for detecting lane lines and device | |
| CN104802737B (en) | Mobile phone based vehicle abnormality driving behavior detection method | |
| EP3498559B1 (en) | Method for recognizing the driving style of a driver of a land vehicle, and corresponding apparatus | |
| CN111504644B (en) | Bearing fault diagnosis method for adaptive anti-domain based on embedding distinguishability condition | |
| CN105892471A (en) | Automatic automobile driving method and device | |
| CN109050535B (en) | Rapid terrain condition identification method based on vehicle attitude | |
| CN106314438A (en) | Method and system for detecting abnormal track in driver driving track | |
| CN107341864A (en) | The evaluation system of driver's driving behavior is analyzed by vehicle bus recording equipment | |
| JP7377154B2 (en) | Road surface condition determination device | |
| CN114997218B (en) | Identification and detection method for polygonal abrasion of wheels of railway vehicles | |
| CN112766306B (en) | Deceleration strip area identification method based on SVM algorithm | |
| CN109229108A (en) | A kind of driving behavior safe evaluation method based on driving fingerprint | |
| CN112710273A (en) | Crowd-sourced road surface pothole detection method based on smart phone sensor and machine learning | |
| CN106845482A (en) | A kind of license plate locating method | |
| CN109214289A (en) | A kind of Activity recognition method of making a phone call from entirety to local two stages | |
| CN111062093A (en) | Automobile tire service life prediction method based on image processing and machine learning technology | |
| CN110263836A (en) | A kind of bad steering state identification method based on multiple features convolutional neural networks | |
| CN105427339A (en) | Characteristic screening and secondary positioning combined fast compression tracking method | |
| CN113314142B (en) | Engine fault detection method, system, storage medium and equipment | |
| CN104966064A (en) | Pedestrian ahead distance measurement method based on visual sense | |
| CN113269005A (en) | Safety belt detection method and device and electronic equipment | |
| CN109591846A (en) | A kind of wheel tread online test method | |
| CN110772267B (en) | Human body physiological fatigue data marking method and fatigue identification model | |
| CN112580736A (en) | Drunk driving vehicle identification method based on SVM algorithm | |
| CN112685956B (en) | Road feel simulation method based on CART regression tree |
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 |