CN112966352B - System and method for rapidly calculating vehicle deformation collision energy in traffic accident - Google Patents
System and method for rapidly calculating vehicle deformation collision energy in traffic accident Download PDFInfo
- Publication number
- CN112966352B CN112966352B CN202110258827.2A CN202110258827A CN112966352B CN 112966352 B CN112966352 B CN 112966352B CN 202110258827 A CN202110258827 A CN 202110258827A CN 112966352 B CN112966352 B CN 112966352B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- deformation
- collision
- accident
- module
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 30
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 238000007619 statistical method Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 abstract description 5
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241001244708 Moroccan pepper virus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000032823 cell division Effects 0.000 description 1
- 230000005489 elastic deformation Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of traffic accident information, and particularly relates to a system and a method for quickly calculating vehicle deformation collision energy in a traffic accident. The specific technical scheme is as follows: selecting a known accident vehicle, calculating energy lost due to deformation in the collision process according to the vehicle speed before collision and the vehicle speed after collision, dividing the known accident vehicle into a plurality of continuous cell units, measuring the number of the deformed cell units and the corresponding deformation amount, taking the lost energy as a training sample, and calculating the rigidity coefficient of the deformed cell units by using a convolutional neural network algorithm; selecting a plurality of accident vehicles, and training for a plurality of times until the rigidity coefficients of all the cell units are calculated; and when collision actually occurs, calculating the energy loss caused by deformation according to the number of the deformed cell units and the corresponding rigidity coefficients. The method has high calculation precision, does not need a complex modeling process, and has quick calculation time; and the calculated energy absorbed by the collision deformation part of the vehicle is closer to the real data.
Description
Technical Field
The invention belongs to the technical field of traffic accident information, and particularly relates to a system and a method for quickly calculating vehicle deformation collision energy in a traffic accident.
Background
Most traffic accidents are car collision accidents, and the collision accidents have the following characteristics: the vehicles exchange energy mutually, the collision part is easy to damage (plastic deformation), and the collision vehicles repel each other (elastic deformation), so that the momentum conservation and energy conservation laws are met. For the division of traffic accident responsibility, calculating the vehicle speed before and after the vehicle collision is a very critical factor, and the vehicle speed before the collision can be calculated according to the energy absorbed by the vehicle deformation and the vehicle speed after the collision; the speed of the vehicle after collision can be calculated according to the ground brake marks and the motion track of the vehicle after collision.
At present, two methods for calculating the energy absorbed by deformation during vehicle collision exist.
The method is characterized in that a two-dimensional simplified calculation model is given, a fixed stiffness is given, the deformation size of a deformation part when a vehicle collides in an accident is measured, and the absorbed energy is calculated according to the deformation size and the fixed stiffness of the vehicle.
The other method is to use PC-CRASH software simulation, the software models parts of each part of the vehicle, and provides an independent rigidity coefficient for each part assembly, the simulation calculation is carried out according to the multi-rigid-body dynamics mode during collision, and the energy absorbed by the collision deformation part of the vehicle is worked out.
Disclosure of Invention
The invention aims to provide a system and a method for quickly calculating vehicle deformation collision energy in a traffic accident.
In order to realize the purpose of the invention, the technical scheme adopted by the invention is as follows: a method for quickly calculating vehicle deformation collision energy in a traffic accident comprises the steps of selecting a known accident vehicle, calculating energy lost due to deformation in a collision process according to the vehicle speed before collision and the vehicle speed after collision, dividing the known accident vehicle into a plurality of continuous cell units, measuring the number of the deformed cell units and the corresponding deformation amount of the deformed cell units, taking the lost energy as a training sample, and calculating the rigidity coefficient of the deformed cell units by utilizing a CNN convolutional neural network algorithm; selecting a plurality of accident vehicles of the same type, and training for a plurality of times until the rigidity coefficients of all the cell units are calculated; and when collision actually occurs, calculating the energy loss caused by deformation according to the number of the deformed cell units and the corresponding rigidity coefficients.
Preferably: comprises the following steps of (a) carrying out,
a1, selecting the known accident vehicle according to the speed v before the accident vehicle collides 1 Post-collision velocity v 2 Calculating the energy loss E of the deformation occurring during the collision 0 ；
A2, establishing a three-dimensional model of the accident vehicle, dividing the accident vehicle into n continuous cell units in a three-dimensional space, and recording the rigidity coefficient of each cell unit as C 1 、C 2 、C 3 ……C n-1 、C n ；
A3, measuring the number a of deformed cell units in the deformed area of the accident vehicle and the corresponding deformation amount b of each deformed cell unit, and marking the cell units in a three-dimensional model;
a4, loss of energy E 0 As a training sample, the stiffness coefficient C n As an output result, calculating the rigidity coefficient C of each deformed cell unit by using a CNN convolutional neural network algorithm n ；
A5, selecting a plurality of accident vehicles of the same type, repeating the steps A1-A4 for a plurality of times of training, and obtaining the rigidity coefficient C of each cell unit of the accident vehicles n ；
A6, number a of cells that deform in actual collision, and the number a of cells that deform in accordance with vehicleCorresponding stiffness coefficient C n Calculating the loss energy E 0 。
Preferably: in the step a3, the deformation amount b is a ratio of cell unit deformation, and b ═ V is calculated 0 -V)/V 0 *100％，V 0 Is the volume of the cell unit before deformation and V is the volume of the cell unit after deformation.
Preferably: in the step a3, the deformation amount b is a ratio of cell unit deformation, and 4 grades are set, which are 25%, 50%, 75%, and 100%, respectively.
Preferably: in the step A1-A6, the cell units are of a regular hexahedron type.
Preferably, the following components: in the step a5, the energy loss E caused by the deformation of the same type of vehicle is classified according to the type of the vehicle, the actual vehicle weight of the vehicle, the wheel base of the vehicle, the driving mode of the vehicle, and the power source of the vehicle 0 The calculation is performed as a training sample of the same set.
Correspondingly: the system comprises a user side and a database, wherein the user side comprises a photographing module, a three-dimensional modeling module, an image comparison module and an energy loss calculation module, the photographing module is used for photographing an accident vehicle and uploading a picture to the three-dimensional modeling module, the three-dimensional modeling module establishes a vehicle three-dimensional model according to the picture of the vehicle, the image comparison module compares the accident vehicle three-dimensional model with a vehicle three-dimensional model of a vehicle with the model, and determines a region deformed due to collision and a deformation amount of the region, and the energy loss calculation module can calculate energy loss caused by collision deformation according to the region deformed due to collision and the deformation amount of the region, and a rigidity coefficient stored in the database; and data are interacted between the database and the user side.
Preferably, the following components: and three-dimensional models of vehicles of different models and the rigidity coefficient of each cell unit are stored in the database.
Preferably, the following components: the management end comprises a rigidity coefficient calculation module, a statistical analysis module and a classification query module, wherein the rigidity coefficient calculation module can calculate the rigidity coefficient of the cell unit according to energy loss caused by collision deformation, store the calculated rigidity coefficient into a database according to the type of the vehicle, and continuously update the rigidity coefficient of the vehicle cell unit corresponding to the database; the statistical analysis module can analyze safe driving speeds, vehicle easily-damaged parts, vehicle collision-resistant parts and the like of different vehicles according to user requirements; the classification query module can query the rigidity coefficients of different vehicles and different parts according to the needs of a user; and data is interacted among the management end, the user end and the database.
Compared with the prior art, the invention has the following beneficial effects:
1. the method divides the automobile model into an infinite number of continuous cell units, defines a rigidity coefficient for each cell unit, and calculates the energy absorbed by the collision deformation part of the automobile based on the rigidity coefficient and the deformation of the deformed cell unit.
2. In the early stage, the real accident vehicle is used as an accident vehicle model, the number and the deformation amount of the cell units in the deformation area are measured, the rigidity coefficient of the deformed cell units is calculated based on the data, the certain authenticity of the rigidity coefficient of the cell units is given, and the calculated energy absorbed by the collision deformation part of the vehicle is closer to the real data.
Drawings
FIG. 1 is a flow chart of a method for rapidly calculating vehicle deformation collision energy in a traffic accident according to the present invention;
FIG. 2 is a block diagram of a system for rapidly calculating vehicle deformation collision energy in a traffic accident according to the present invention;
FIG. 3 is a schematic diagram of cell division of a three-dimensional model of an automobile according to the present invention.
The mark in the figure is:
the system comprises a user terminal 1, a photographing module 11, a three-dimensional modeling module 12, an image comparison module 13 and an energy loss calculation module 14; the system comprises a management end 2, a rigidity coefficient calculation module 21, a statistical analysis module 22 and a classification query module 23; a database 3.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Unless otherwise specified, the technical means used in the examples are conventional means well known to those skilled in the art.
As shown in fig. 1, the method for rapidly calculating vehicle deformation collision energy in a traffic accident according to the present invention selects a known accident vehicle, calculates energy lost due to vehicle deformation during a collision process according to a vehicle speed before collision and a vehicle speed after collision, divides the accident vehicle into a plurality of continuous cell units, each cell unit corresponds to an independent stiffness coefficient, measures the number of deformed cell units and the corresponding deformation, uses the lost energy as a training sample, uses the stiffness coefficient of the deformed cell units as an output result, and calculates the stiffness coefficient of each deformed cell unit by using a CNN convolutional neural network algorithm; training for multiple times until the rigidity coefficients of all the cell units are calculated; when collision actually occurs, the energy lost due to the deformation is calculated according to the number of the cell units deformed in the collision process and the corresponding rigidity coefficients.
As a specific embodiment of the invention, the method for rapidly calculating the vehicle deformation collision energy in the traffic accident comprises the following steps,
a1, selecting the known accident vehicle according to the speed v before the accident vehicle collides 1 Post-collision velocity v 2 Calculating the loss energy E of deformation during collision 0 Loss of energy E 0 The calculation formula is E 0 ＝1/2mv 1 2 -1/2mv 2 2 In order to simplify the calculation, the energy lost by collision deformation only considers the kinetic energy change and does not consider the heat energy generated by collision friction; note that the pre-collision velocity v 1 Post-collision velocity v 2 May be obtained from on-site video surveillance or a vehicle crash event recording system (CDR);
a2, establishing the three-dimension of the accident vehicleThe accident vehicle is divided into n continuous cell units in a three-dimensional space, and the rigidity coefficient of each cell unit is respectively marked as C 1 、C 2 、C 3 ……C n-1 、C n (ii) a The vehicle three-dimensional modeling can adopt any one of T-springs software, 3DFZephyr software, Solidworks software and the like, the T-springs software and the 3DFZephyr software are optimized, the 3DF Zephyr software can directly convert a real object picture into a three-dimensional model, a plurality of vehicle appearance pictures with different angles are prepared, and the pictures are taken around the vehicle for one circle at three heights, so that the vehicle high-precision three-dimensional modeling can be carried out;
a3, measuring the deformation area of the accident vehicle on site, measuring the number a of deformed cell units in the deformation area and the corresponding deformation b, and marking in a three-dimensional model; or photographing the collided vehicle by using 3DFZephyr software to establish a three-dimensional model of the collided vehicle, comparing the three-dimensional model of the vehicle before collision, and recording and measuring the number a of deformed cell units in a deformation region and the deformation b of each deformed cell unit;
a4, will lose energy E 0 As a training sample, the stiffness coefficient C of the cell unit to be deformed n As a result of the output, a rigidity coefficient C of each cell unit that is deformed is calculated n (ii) a It should be noted that, the stiffness coefficient C of each cell unit is calculated by using the CNN convolutional neural network algorithm n . The CNN convolutional neural network algorithm uses an algorithm module carried in Python Tensiow software or an existing algorithm module in other software.
A5, selecting a plurality of accident vehicles of the same type and with different deformation areas, repeating the steps A1-A4, and obtaining the rigidity coefficient C of each cell unit of the accident vehicle after a plurality of times of training n ；
A6, calculating the loss energy E according to the number a of the cell units deformed by the vehicle and the corresponding rigidity coefficient C when the vehicle actually collides 0 。
In step a3, the distortion amount b is a ratio of cell unit distortion, and b is calculated by the method of (V ═ V) 0 -V)/V 0 *100％，V 0 When the deformation amount of the vehicle collision part is more regular, the three-dimensional model can quickly calculate the cell deformation proportion through comparison, for example, the longitudinal beam of the engine compartment collapses after collision, and the collapse length can accurately reflect through pictures.
Further, in the step a3, the deformation amount b is a ratio of cell deformation, and 4 levels, 25%, 50%, 75% and 100% are provided, and when the deformation of the vehicle collision region is irregular, such as a part of the fender panel is collapsed and twisted after the vehicle is collided with by an oblique collision, the deformation ratio of the cell can be adjusted by manually selecting the deformation ratio.
The two modes can be used respectively or in combination, for example, for the regular deformation part of the vehicle collision rear, the deformation proportion of the cell units is automatically calculated, and the irregular deformation part of the vehicle collision part is manually set, so that the deformation proportion of each cell unit can be quickly and accurately set.
Further, in the step a1-a 6, the cell unit may be any one of a cuboid, a cube, a hexahedron and other polyhedrons, preferably a hexahedron, and the cell unit is divided for the three-dimensional model of the vehicle, a mesh division method in finite element software may be adopted, as shown in fig. 3, after the three-dimensional model is built in CATIA or SolidWorks software, the model is directly introduced into ansys or hypermesh software for automatic division, and for a vehicle under the same group of training samples, a plurality of three-dimensional models may be directly simplified into one model.
Further, in order to avoid the lack of training samples, in the step a5, the vehicles are classified according to the type of the vehicle, the actual vehicle weight, the vehicle wheel base, the vehicle driving style and the vehicle power source, and the lost energy E of the same type of vehicle is deformed 0 Calculating as training samples of the same group; the vehicle types can be divided into cars, SUVs, MPVs, pick-up trucks, medium-sized trucks, heavy-duty trucks, and the different vehicle types are further subdivided by the respective parameters of the vehicle, for example, into purely electric, hybrid, fuelThe fuel vehicle is divided into a front drive, a rear drive and a four-wheel drive; it should be noted here that, for vehicles of different brands, when each parameter is relatively close, the vehicle can be used as the same training sample group, and a plurality of collision experiments prove that when each parameter of the vehicle is relatively close, the rigidity coefficients of the vehicle body are relatively consistent, so that a large number of training samples can be rapidly accumulated, and the training accuracy is ensured.
As shown in fig. 2, the system for rapidly calculating vehicle deformation collision energy in a traffic accident according to the present invention includes a user end 1 and a database 3, where the user end 1 includes a photographing module 11, a three-dimensional modeling module 12, an image comparison module 13 and an energy loss calculation module 14, the photographing module 11 is electrically or wirelessly connected to the three-dimensional modeling module 12, the three-dimensional modeling module 12 is electrically or wirelessly connected to the image comparison module 13, and the image comparison module 13 is electrically or wirelessly connected to the energy loss calculation module 14, where functions of each module are described as follows:
the photographing module 11 is used for photographing an accident vehicle and uploading a photo to the three-dimensional modeling module 12, it should be noted that the photographing module 11 may be a gropor camera, a handheld three-dimensional photographing scanner, or a camera with other modes, and when the handheld three-dimensional photographing scanner is used, the three-dimensional modeling module is integrated.
The three-dimensional modeling module 12 builds a three-dimensional model of the vehicle according to the shot vehicle picture, and may adopt other existing modeling software capable of realizing the function, such as T-profiles software, 3DF Zephyr software, Solidworks software, and the like.
The image comparison module 13 compares the three-dimensional model of the accident vehicle with the three-dimensional model of a vehicle with a good model of the accident vehicle, and determines a deformed region and a deformation amount thereof due to collision, it should be noted that after the three-dimensional model is established, the three-dimensional model is led into the image comparison module 13 for comparison, the image comparison module 13 may be a common image comparison and identification module used in python software or a common image comparison and identification module used in MATLAB software, and the two pieces of software can compare different photos and then directly output the change ratio of different parts in the photos, that is, inherit the common image comparison and identification module 14, and certainly, may also be other forms of software for realizing an image comparison function.
The energy loss calculation module 14 can calculate the energy loss caused by collision deformation according to the deformed region, the deformation amount of the deformed region, and the stiffness coefficient stored in the database, and it should be noted that a server, a single chip microcomputer, a PLC controller, a processor, or other devices capable of implementing the function may be used as a program carrier of the collision energy fast calculation method, and the specific models of the devices may be selected according to the requirements of the required calculation capacity, calculation time, and the like.
It should be noted that, the user end 1 is convenient for the user to carry and use, the photographing module 11 can use a camera on the mobile phone of the user, an algorithm for realizing three-dimensional modeling, image comparison and energy loss calculation functions is written on a mobile phone APP, the program software is given with the authority to obtain the mobile phone photo, and the carrier for running the program software can be a chip or a processor in the mobile phone, so that the user can directly use the program software only by downloading the software of the user end 1, and the use is convenient.
Data are interacted between the database 3 and the user side 1, three-dimensional models of vehicles of different types and rigidity coefficients of all cell units are stored in the database 3, and the database 3 can be a self-built server or an existing cloud database.
In a more preferred embodiment, the system for rapidly calculating the vehicle deformation collision energy in the traffic accident further includes a management terminal 2, the management terminal 2 includes a stiffness coefficient calculation module 21, a statistical analysis module 22 and a classification query module 23, the stiffness coefficient calculation module 21 is electrically or wirelessly connected with the statistical analysis module 22, the statistical analysis module 22 is electrically or wirelessly connected with the classification query module 23, and functions of each module are described as follows:
the rigidity coefficient calculation module 21 can calculate the rigidity coefficient of the cell unit according to the energy loss caused by collision deformation, store the calculated rigidity coefficient into the database 3 according to the type of the vehicle, and continuously update the rigidity coefficient of the vehicle cell unit corresponding to the database 3; it should be noted that a server, a single chip, a PLC controller, a processor, or other devices capable of implementing the function may be used as a program carrier of the stiffness coefficient calculation method, and specific models of these devices may be selected according to requirements such as required calculation capacity and calculation time.
The statistical analysis module 22 can analyze safe driving speeds, vehicle vulnerable parts, vehicle collision-resistant parts and the like of different vehicles according to user requirements; the classification query module 23 can query the stiffness coefficients of different vehicles and different parts according to the user requirements; and data interaction is carried out between the management terminal 2 and the user terminal 1 and between the management terminal 2 and the database 3.
It should be noted that the management terminal 2 is mainly used by an operator manager, and for convenience of use, the algorithm for implementing the functions of rigidity coefficient calculation, statistical analysis and classified query can be implemented by a mobile phone APP, a web page, an independently configured server or other manners.
The above-described embodiments are only intended to describe the preferred embodiments of the present invention, and not to limit the scope of the present invention, and various modifications, variations, modifications, and substitutions which may be made by those skilled in the art to the technical solution of the present invention without departing from the spirit of the present invention are intended to fall within the scope of the present invention defined by the claims.
Claims (8)
1. The method for quickly calculating the vehicle deformation collision energy in the traffic accident is characterized by comprising the following steps: the method comprises the following steps:
a1, selecting the known accident vehicle according to the speed v before the accident vehicle collides 1 Post-collision velocity v 2 Calculating the energy loss E0 of deformation during collision;
a2, establishing a three-dimensional model of the accident vehicle, dividing the accident vehicle into n continuous cell units in a three-dimensional space, and recording the rigidity coefficient of each cell unit as C1, C2, C3 … … Cn-1 and Cn respectively;
a3, measuring the number a of deformed cell units in the deformed area of the accident vehicle and the corresponding deformation b of each deformed cell unit, and marking the cell units in a three-dimensional model;
a4, taking the energy loss E0 as a training sample, taking the rigidity coefficient Cn as an output result, and calculating the rigidity coefficient Cn of each deformed cell unit by using a CNN convolutional neural network algorithm;
a5, selecting a plurality of accident vehicles of the same type, repeating the steps A1-A4, training for a plurality of times, and solving the rigidity coefficient Cn of each cell unit of the accident vehicles;
a6, calculating the loss energy E0 according to the number a of the cells in which the vehicle is deformed and the corresponding stiffness coefficient Cn when the vehicle actually collides.
2. The method for rapidly calculating the vehicle deformation collision energy in the traffic accident according to claim 1, wherein: in the step a3, the deformation amount b is the ratio of the deformed cell units, and is calculated by b = (V0-V)/V0 = 100%, V0 is the volume of the cell units before deformation, and V is the volume of the cell units after deformation.
3. The method for rapidly calculating collision energy with vehicle deformation in a traffic accident according to claim 1, characterized in that: in the step a3, the deformation amount b is a ratio of cell unit deformation, and 4 grades are set, which are 25%, 50%, 75%, and 100%, respectively.
4. The method for rapidly calculating collision energy with vehicle deformation in a traffic accident according to claim 1, characterized in that: in the step A1-A6, the cell units are of a regular hexahedron type.
5. The method for rapidly calculating collision energy with vehicle deformation in a traffic accident according to claim 1, characterized in that: in the step a5, the types of vehicles, the actual vehicle weights of the vehicles, the wheel base of the vehicles, the driving forms of the vehicles and the power sources of the vehicles are classified, and the energy loss E0 of the same type of vehicle, which is deformed, is calculated as a training sample of the same group.
6. The computing system corresponding to the method for rapidly computing the vehicle deformation collision energy in the traffic accident according to claim 1, is characterized in that: the computing system comprises a user side (1) and a database (3), wherein the user side (1) comprises a photographing module (11), a three-dimensional modeling module (12), an image comparison module (13) and an energy loss computing module (14), the photographing module (11) is used for photographing an accident vehicle and uploading the photograph to the three-dimensional modeling module (12), the three-dimensional modeling module (12) establishes a vehicle three-dimensional model according to the vehicle photograph, the image comparison module (13) compares the accident vehicle three-dimensional model with a perfect vehicle three-dimensional model with the same accident vehicle model to determine a region deformed due to collision and a deformation amount of the region, and the energy loss computing module (14) can compute energy loss caused by collision deformation according to the deformed region and the deformation amount of the region, and a rigidity coefficient stored in the database (3); and data are interacted between the database (3) and the user side (1).
7. The computing system corresponding to the method for rapidly computing the vehicle deformation collision energy in the traffic accident according to claim 6, wherein: three-dimensional models of vehicles of different types and rigidity coefficients of all cell units are stored in the database (3).
8. The calculation system corresponding to the method for rapidly calculating the vehicle deformation collision energy in the traffic accident according to any one of claims 6 and 7, is characterized in that: the vehicle cell unit stiffness analysis system is characterized by further comprising a management end (2), wherein the management end (2) comprises a stiffness coefficient calculation module (21), a statistical analysis module (22) and a classification query module (23), the stiffness coefficient calculation module (21) can calculate the stiffness coefficient of a cell unit according to energy loss caused by collision deformation, the calculated stiffness coefficient is stored in the database (3) according to the type of a vehicle, and the stiffness coefficient of the corresponding vehicle cell unit in the database (3) is continuously updated; the statistical analysis module (22) can analyze safe driving speeds, vehicle easily damaged parts and vehicle collision-resistant parts of different vehicles according to user requirements; the classification query module (23) can query the rigidity coefficients of different vehicles and different parts according to the user requirements; and data are interacted among the management end (2), the user end (1) and the database (3).
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210718498.XA CN115017649A (en) | 2021-03-10 | 2021-03-10 | Method for calculating vehicle deformation collision energy in traffic accident based on cell unit method |
| CN202110258827.2A CN112966352B (en) | 2021-03-10 | 2021-03-10 | System and method for rapidly calculating vehicle deformation collision energy in traffic accident |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110258827.2A CN112966352B (en) | 2021-03-10 | 2021-03-10 | System and method for rapidly calculating vehicle deformation collision energy in traffic accident |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210718498.XA Division CN115017649A (en) | 2021-03-10 | 2021-03-10 | Method for calculating vehicle deformation collision energy in traffic accident based on cell unit method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112966352A CN112966352A (en) | 2021-06-15 |
| CN112966352B true CN112966352B (en) | 2022-08-19 |
Family
ID=76277031
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110258827.2A Expired - Fee Related CN112966352B (en) | 2021-03-10 | 2021-03-10 | System and method for rapidly calculating vehicle deformation collision energy in traffic accident |
| CN202210718498.XA Withdrawn CN115017649A (en) | 2021-03-10 | 2021-03-10 | Method for calculating vehicle deformation collision energy in traffic accident based on cell unit method |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210718498.XA Withdrawn CN115017649A (en) | 2021-03-10 | 2021-03-10 | Method for calculating vehicle deformation collision energy in traffic accident based on cell unit method |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN112966352B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114715146A (en) * | 2022-05-09 | 2022-07-08 | 吉林大学 | Method for predicting severity of potential collision accident |
| CN116189114B (en) * | 2023-04-21 | 2023-07-14 | 西华大学 | Method and device for identifying collision trace of vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101173856A (en) * | 2007-08-30 | 2008-05-07 | 上海交通大学 | Vehicle collision accident reappearance method based on phototopography and exterior profile deformation of car body |
| DE102007012137A1 (en) * | 2007-03-12 | 2008-09-18 | Benteler Automobiltechnik Gmbh | Crashbox and automobile bumper assembly |
| CN101865930A (en) * | 2010-04-16 | 2010-10-20 | 中国人民解放军第三军医大学野战外科研究所 | Method for detecting collision speed of vehicle though spectrum |
| CN105808857A (en) * | 2016-03-10 | 2016-07-27 | 清华大学 | Prediction method of automobile active safety system effectiveness on the basis of collision deformation depth |
| CN109492346A (en) * | 2019-01-21 | 2019-03-19 | 中南大学 | A kind of construction method of track train collision simulation simplified model |
-
2021
- 2021-03-10 CN CN202110258827.2A patent/CN112966352B/en not_active Expired - Fee Related
- 2021-03-10 CN CN202210718498.XA patent/CN115017649A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102007012137A1 (en) * | 2007-03-12 | 2008-09-18 | Benteler Automobiltechnik Gmbh | Crashbox and automobile bumper assembly |
| CN101173856A (en) * | 2007-08-30 | 2008-05-07 | 上海交通大学 | Vehicle collision accident reappearance method based on phototopography and exterior profile deformation of car body |
| CN101865930A (en) * | 2010-04-16 | 2010-10-20 | 中国人民解放军第三军医大学野战外科研究所 | Method for detecting collision speed of vehicle though spectrum |
| CN105808857A (en) * | 2016-03-10 | 2016-07-27 | 清华大学 | Prediction method of automobile active safety system effectiveness on the basis of collision deformation depth |
| CN109492346A (en) * | 2019-01-21 | 2019-03-19 | 中南大学 | A kind of construction method of track train collision simulation simplified model |
Non-Patent Citations (3)
| Title |
|---|
| "事故车辆塑性变形三维重建与有限元塑性能计算研究";谭鑫培;《中国优秀硕士学位论文全文数据库 工程科技II辑》;20200131(第1期);C034-1364 * |
| 有限元方法在汽车碰撞事故再现中的应用展望;张晓云等;《农业机械学报》;20041201;第35卷(第06期);第206-210页 * |
| 谭鑫培."事故车辆塑性变形三维重建与有限元塑性能计算研究".《中国优秀硕士学位论文全文数据库 工程科技II辑》.2020,(第1期),C034-1364. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112966352A (en) | 2021-06-15 |
| CN115017649A (en) | 2022-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112966352B (en) | System and method for rapidly calculating vehicle deformation collision energy in traffic accident | |
| CN110091751B (en) | Electric automobile endurance mileage prediction method, device and medium based on deep learning | |
| US20210334420A1 (en) | Driving simulation method and apparatus, electronic device, and computer storage medium | |
| CN101173856B (en) | Vehicle collision accident reappearance method based on phototopography and exterior profile deformation of car body | |
| CN110001653A (en) | A kind of driving behavior appraisal procedure, server and computer-readable medium | |
| CN104354699A (en) | Method and device for detecting driving behavior information based on OBD (on-board diagnostic) terminal | |
| EP4099118A1 (en) | Vehicle control method and apparatus | |
| CN109931856A (en) | Acquisition method/system of road evenness, evaluation system, medium and server-side | |
| US10946852B2 (en) | Systems and methods for determining engine start time during predicted acceleration events | |
| US20230047094A1 (en) | Image processing method, network training method, and related device | |
| US20150073933A1 (en) | Vehicle powertrain selector | |
| EP4209975A1 (en) | Carbon footprint estimation method and system for vehicle | |
| CN109131336A (en) | Obtain the method and system of coefficient of road adhesion | |
| König et al. | Package planning of autonomous vehicle concepts | |
| Salunkhe et al. | Energy optimization for CAN bus and media controls in electric vehicles using deep learning algorithms | |
| US10336210B2 (en) | Selection of range for an electric device having a rechargeable energy storage unit | |
| CN106202972A (en) | A kind of method determining electric automobile power battery energy under state of cyclic operation | |
| EP4293630A1 (en) | Method for generating lane line, vehicle, storage medium and chip | |
| Sagaama et al. | Proposal of more accurate energy model of electric vehicle for sumo | |
| CN116859881A (en) | Test method and device | |
| CN114872802B (en) | Vehicle windage control method, device and storage medium | |
| CN207730458U (en) | A kind of carriage device for crash tests | |
| CN114162133B (en) | Risk assessment method, risk assessment device and computer-readable storage medium for driving scene | |
| CN115257692A (en) | Visual traffic information-based PHEV energy management method and system | |
| Ebaid et al. | Feasibility studies of micro wind turbines installed on electric vehicles as range extenders using real-time analytical simulation with multi driving cycles scenarios |
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 |
Effective date of registration: 20220729 Address after: Room 10401-410, tower C, Liren Science Park, No. 52, Gaoxin 6th Road, high tech Zone, Xi'an, Shaanxi 710000 Applicant after: Shaanxi Lande Intelligent Transportation Technology Co.,Ltd. Address before: Xihua University, 999 Jinzhou Road, Jinniu District, Chengdu, Sichuan 610039 Applicant before: XIHUA University |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220819 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |