CN113670524B - Detection method and detection system for automobile collision fuel leakage - Google Patents
Detection method and detection system for automobile collision fuel leakage Download PDFInfo
- Publication number
- CN113670524B CN113670524B CN202110790382.2A CN202110790382A CN113670524B CN 113670524 B CN113670524 B CN 113670524B CN 202110790382 A CN202110790382 A CN 202110790382A CN 113670524 B CN113670524 B CN 113670524B
- Authority
- CN
- China
- Prior art keywords
- fuel
- leakage
- image
- collision
- fuel system
- 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
- 239000000446 fuel Substances 0.000 title claims abstract description 199
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000002474 experimental method Methods 0.000 claims abstract description 5
- 239000002828 fuel tank Substances 0.000 claims description 38
- 239000000945 filler Substances 0.000 claims description 31
- 230000001133 acceleration Effects 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 24
- 239000003921 oil Substances 0.000 claims description 16
- 238000013136 deep learning model Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 13
- 239000007788 liquid Substances 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 9
- 239000000295 fuel oil Substances 0.000 claims description 7
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 description 11
- 238000013461 design Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000033772 system development Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention relates to a detection method and a detection system for fuel leakage in an automobile collision, which are characterized in that a fuel system collision image database is established, the situation that fuel leakage possibly occurs after the fuel system collides is classified, corresponding leakage pictures are marked and stored, an actual collision experiment fuel system collision image acquired by a camera acquisition system is compared with an original fuel system image and an actual collision experiment fuel system deformation non-leakage and deformation and leakage image in the database, whether the collision fuel system leaks or not is determined, then the accuracy of manual rechecking judgment is adopted, and finally the collision fuel system image is marked and stored, so that the fuel system collision image database is further improved, and the accuracy of subsequent collision judgment is improved.
Description
Technical Field
The invention relates to the technical field of automobile collision detection, in particular to a detection method for automobile collision fuel leakage.
Background
The conventional fuel light bus is characterized in that the fuel filler is generally positioned below the B column of the bus body due to the structural design characteristics of the conventional fuel light bus. When a traffic accident occurs, the oil filler and peripheral parts thereof are easy to be impacted or the inertial impact causes the leakage of fuel, thereby seriously affecting the personal safety. This requires the automobile factories to take this risk into account in the fuel system development process.
However, the test method of the whole car collision is used for detecting and judging whether the risks are not in accordance with the actual design requirements, on the one hand, the time is not allowed, the physical detection is carried out after the test sample car comes out, and if the fuel leakage still exists, the scheme is not changed; on the other hand, the test sample car and the test cost are huge, and are not matched with the development direction of the industry 4.0. On the basis of guaranteeing design targets, reasonably reducing development cost becomes a main research direction of current automobile safety parts.
The existing fuel leakage detection method mainly collects collision images through a camera, and has the advantages of low efficiency, long discrimination period and easy generation of missed discrimination through manual discrimination, thereby causing potential safety hazards for subsequent whole vehicle production.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the detection method for the automobile collision fuel leakage, which has the advantages of reducing the test cost, improving the test fuel leakage detection efficiency and improving the detection accuracy.
The technical scheme adopted by the invention is as follows:
a detection method for fuel leakage of an automobile collision comprises the following steps:
s101, rigidly connecting a white car body and a pulley through a fixed tool; the lower surface of the white car body is 400mm higher than the upper surface of the pulley;
s102, filling liquid into a fuel tank, wherein the filling amount of the liquid in the fuel tank is 90% of the volume of the fuel tank;
s103, normally installing the fuel tank, normally installing components near the fuel tank, normally connecting a filler neck, normally locking a filler cap,
s104, the camera collects an original fuel system image;
s105, simulating the situation of fuel leakage after the collision of the fuel system, and collecting the fuel system image of the corresponding leakage situation;
s106, the fuel system adopts static background modeling, pixel difference is carried out on the acquired image frame before the collision of the fuel system and the image frame after the collision of the simulated fuel system, and corresponding images are marked; marking the corresponding image frame as a corresponding leak point; storing the data in a database;
s107, the camera collects images of the fuel system during actual collision;
s108, making differences between all acquired image frames of the fuel system in actual collision and the image frames in the database, determining whether fuel is leaked or not according to the difference making results, and further determining the positions of fuel leakage points;
and S109, outputting a detection result to finish the detection of the fuel system leakage.
Preferably, checking all the image frames determined to be leaked by the fuel system, judging that the comparison is correct, marking the corresponding image frames, and storing the corresponding image frames into a fuel leakage picture database; and (3) comparing errors, marking corresponding image frames, and storing the corresponding image frames into a fuel system non-leakage picture database.
Preferably, the situation that fuel leakage occurs after the collision of the fuel system is simulated, and the position of the image collected by the camera is the same as that of the original fuel system image.
Preferably, the simulated fuel system collision image includes: slight collision, slight deformation, no leakage; moderate collision, moderate deformation and no leakage; high collision, high deformation and no leakage; high impact, high deformation, and leakage.
Preferably, simulating a fuel system collision, the fuel system leakage image includes: the fuel tank, the fuel filler pipe and the fuel filler cap leak images at the same time; fuel tank and filler tube leak images; oil filler tube and oil filler cap leakage images; fuel tank and filler cap leak images.
A detection method for fuel leakage of an automobile collision comprises the following steps:
s101, acquiring an image to be detected of a fuel system;
s102, performing image segmentation processing on the image to be detected to obtain images of areas to be detected of the fuel tank, the fuel filling pipe and the fuel filling cover;
s103, extracting image contour features for each region image to be detected, and then if corresponding fuel system components are identified according to the extracted image contour features, sequentially executing steps S301 to S302:
s301, determining an applicable deep learning model which is subjected to fuel system component image recognition training according to a fuel system component recognition result, and then guiding an area image to be detected into the deep learning model for prediction operation to obtain a corresponding fuel system component image recognition type and fuel system component image recognition accuracy, wherein the fuel system component image recognition type comprises a leakage type and a non-leakage type;
s302, if the obtained fuel system component image identification type is a leakage type and the leakage image identification accuracy is not less than a set threshold, the fuel system component image identification type and the fuel system component image identification accuracy are obtained on the fuel system component image to be detected and the position mark corresponding to the region image to be detected;
s104, storing an image of the fuel system component mark;
s105, outputting a result of whether the fuel system leaks or not.
Preferably, prior to the step S301, the leakage image recognition training is performed on the deep learning model applied to a certain fuel system component according to the following steps S201 to S203:
s201, acquiring sample images of fuel system components and marked leakage image recognition types bound with each sample image, wherein the number of corresponding sample images is not less than 100 for each leakage image recognition type;
s202, taking each sample image and the corresponding marked leakage image recognition type as a training sample, and importing the sample images and the corresponding marked leakage image recognition type into a deep learning model for image recognition training, wherein the sample images are taken as sample input data, and the marked image recognition types corresponding to the sample images are taken as sample verification data;
and S203, in the image recognition training process, continuously optimizing the deep learning model according to the matching result of the image recognition type obtained by training and the sample verification data until the training is completed or until the matching rate of the image recognition type obtained by training and the sample verification data reaches a set threshold value.
The detection system for the collision fuel leakage of the automobile comprises a white automobile body, an acceleration pulley used for carrying the white automobile body, wherein the white automobile body is fixed on the acceleration pulley through a fixing tool, a fuel system consisting of a fuel tank, a fuel filling pipe and a fuel filling cover is arranged at the bottom of the white automobile body, an acceleration pulley servo system is arranged in front of the acceleration pulley, a first camera used for collecting the fuel leakage at a fuel filling opening is arranged at the outer side of the acceleration pulley, and a second camera is arranged below the fuel tank on the surface of the acceleration pulley; the front of the fuel tank on the surface of the accelerating pulley is provided with a third camera, and the other side of the outer side of the accelerating pulley corresponding to the first camera is provided with a fourth camera.
Preferably, the fixing tool is a front fixing frame arranged in front of the white car body and a rear fixing bracket arranged at the rear.
Preferably, the third camera is arranged on the front fixing frame.
Compared with the prior art, the invention has the beneficial effects that:
according to the detection method for the collision fuel leakage of the automobile, the white automobile body and the fuel system are fixed on the acceleration pulley, the actual automobile body acceleration signal is input, the acceleration pulley is transmitted, the movement and deformation conditions of the oil filling cover, the oil filling pipe and the oil tank in the collision process are simulated, whether the fuel system is in liquid leakage or not is detected, the time is saved, the test period is shortened, and the judging efficiency is improved; the test cost is reduced, and the test safety is improved.
The invention relates to a detection method for fuel leakage in automobile collision, which classifies the possible occurrence of fuel leakage after the collision of a fuel system by establishing a fuel system collision image database, marks and stores corresponding leakage pictures, compares the actual collision experiment fuel system collision image acquired by a camera acquisition system with the original fuel system image and the deformation non-leakage and deformation and leakage images in the database, determines whether the collision fuel system is leaked or not, then marks and stores the collision fuel system image through the accuracy of manual rechecking judgment, thereby further improving the fuel system collision image database and improving the accuracy of subsequent collision judgment.
Drawings
FIG. 1 is a schematic structural view of a detection method for fuel leakage in an automobile collision;
FIG. 2 is a schematic diagram of a fuel tank mounting structure for a method of detecting fuel leakage in an automobile collision;
FIG. 3 is a schematic illustration of the placement of a fuel filler and camera for a method of detecting vehicle collision fuel leakage;
FIG. 4 is a flow chart of a method for detecting a vehicle collision fuel leak.
The main component symbols in the drawings illustrate:
in the figure: 1. the automobile body in white, 2, fuel oil system, 3, fixed frock, 4, acceleration pulley, 5, acceleration pulley servo system, 6, fuel tank, 7, filler neck, 8, filler cap.
Detailed Description
The invention is described in detail below with reference to the attached drawings and examples:
according to the invention, through an AI algorithm, similar points of two pictures are searched, and if the comparison analysis of the characteristic points reaches more than 90%, the two pictures are the same or similar by default. And realizing the picture comparison based on an open source algorithm to perform the picture full-image and partial comparison.
1-4, a method for detecting fuel leakage in the event of a collision of an automobile comprises the following steps:
s101, rigidly connecting a white car body and a pulley through a fixed tool; the lower surface of the white car body is 400mm higher than the upper surface of the pulley;
s102, filling liquid into a fuel tank, wherein the filling amount of the liquid in the fuel tank is 90% of the volume of the fuel tank;
s103, normally installing the fuel tank, normally installing components near the fuel tank, normally connecting a filler neck, normally locking a filler cap,
s104, the camera collects an original fuel system image;
s105, simulating the situation of fuel leakage after the collision of the fuel system, and collecting the fuel system image of the corresponding leakage situation;
s106, the fuel system adopts static background modeling, pixel difference is carried out on the acquired image frame before the collision of the fuel system and the image frame after the collision of the fuel system simulated in the database, and corresponding images are marked; marking the corresponding image frames as leakage points of corresponding components of the fuel system; storing the data in a database;
s107, the camera collects images of the fuel system during actual collision;
s108, making differences between all acquired image frames of the fuel system in actual collision and the image frames in the database, determining whether fuel is leaked or not according to the difference making results, and further determining the positions of fuel leakage points;
and S109, outputting a detection result to finish the detection of the fuel system leakage.
Rechecking all the image frames determined to be leaked by the fuel system, judging that the comparison is correct, marking the corresponding image frames, and storing the corresponding image frames into a fuel leakage picture database; and (3) comparing errors, marking corresponding image frames, and storing the corresponding image frames into a fuel system non-leakage picture database.
The situation that fuel oil leakage occurs after the collision of the fuel oil system is simulated, and the position of the image collected by the camera is the same as that of the original fuel oil system image.
The simulated fuel system collision image includes: slight collision, slight deformation, no leakage; moderate collision, moderate deformation and no leakage; high collision, high deformation and no leakage; and the high collision and the high deformation generate leakage, and the collision leakage images of the simulated fuel system are four types.
Simulating a fuel system collision, the fuel system leakage image comprising: the fuel tank, the fuel filler pipe and the fuel filler cap leak images at the same time; fuel tank and filler tube leak images; oil filler tube and oil filler cap leakage images; fuel tank and filler cap leak images.
A detection method for fuel leakage of an automobile collision comprises the following steps:
s101, acquiring an image to be detected of a fuel system;
s102, performing image segmentation processing on the image to be detected to obtain images of areas to be detected of the fuel tank, the fuel filling pipe and the fuel filling cover;
s103, extracting image contour features for each region image to be detected, and then if corresponding fuel system components are identified according to the extracted image contour features, sequentially executing steps S301 to S302:
s301, determining an applicable deep learning model which is subjected to fuel system component image recognition training according to a fuel system component recognition result, and then guiding an area image to be detected into the deep learning model for prediction operation to obtain a corresponding fuel system component image recognition type and fuel system component image recognition accuracy, wherein the fuel system component image recognition type comprises a leakage type and a non-leakage type;
s302, if the obtained fuel system component image identification type is a leakage type and the leakage image identification accuracy is not less than a set threshold, the fuel system component image identification type and the fuel system component image identification accuracy are obtained on the fuel system component image to be detected and the position mark corresponding to the region image to be detected;
s104, storing an image of the fuel system component mark;
s105, outputting a result of whether the fuel system leaks or not.
Preferably, prior to the step S301, the leakage image recognition training is performed on the deep learning model applied to a certain fuel system component according to the following steps S201 to S203:
s201, acquiring sample images of fuel system components and marked leakage image recognition types bound with each sample image, wherein the number of corresponding sample images is not less than 100 for each leakage image recognition type;
s202, taking each sample image and the corresponding marked leakage image recognition type as a training sample, and importing the sample images and the corresponding marked leakage image recognition type into a deep learning model for image recognition training, wherein the sample images are taken as sample input data, and the marked image recognition types corresponding to the sample images are taken as sample verification data;
and S203, in the image recognition training process, continuously optimizing the deep learning model according to the matching result of the image recognition type obtained by training and the sample verification data until the training is completed or until the matching rate of the image recognition type obtained by training and the sample verification data reaches a set threshold value.
The detection system for the collision fuel leakage of the automobile comprises a white automobile body 1 and an acceleration pulley 4 for carrying the white automobile body 1, wherein the white automobile body 1 is fixed on the acceleration pulley 4 through a fixing tool 3, a fuel system 2 consisting of a fuel tank 6, a fuel filling pipe 7 and a fuel filling cover 8 is arranged at the bottom of the white automobile body, an acceleration pulley servo system 5 is arranged in front of the acceleration pulley 4, a first camera 21 for collecting the fuel leakage at a fuel filling opening is arranged at the outer side of the acceleration pulley, and a second camera 22 is arranged below a fuel tank on the surface of the acceleration pulley 4; the front of the fuel tank on the surface of the accelerating pulley 4 is provided with a third camera 23, and the other side of the outer side of the accelerating pulley 4 corresponding to the first camera is provided with a fourth camera 24.
The fixing tool is a front fixing frame arranged in front of the white car body 1 and a rear fixing bracket arranged behind the white car body 1.
The third camera is arranged on the front fixing frame.
According to the detection method for the collision fuel leakage of the automobile, the white automobile body and the fuel system are fixed on the acceleration pulley, the actual automobile body acceleration signal is input, the acceleration pulley is transmitted, the movement and deformation conditions of the oil filling cover, the oil filling pipe and the oil tank in the collision process are simulated, whether the fuel system is in liquid leakage or not is detected, the time is saved, the test period is shortened, and the judging efficiency is improved; the test cost is reduced, and the test safety is improved.
The invention relates to a detection method for fuel leakage in automobile collision, which classifies the possible occurrence of fuel leakage after the collision of a fuel system by establishing a fuel system collision image database, marks and stores corresponding leakage pictures, compares the actual collision experiment fuel system collision image acquired by a camera acquisition system with the original fuel system image and the deformation non-leakage and deformation and leakage images in the database, determines whether the collision fuel system is leaked or not, then marks and stores the collision fuel system image through the accuracy of manual rechecking judgment, thereby further improving the fuel system collision image database and improving the accuracy of subsequent collision judgment.
According to the invention, the white car body and the fuel system are fixed on the acceleration pulley, an actual car body acceleration signal is input, the acceleration pulley is transmitted, the movement and deformation conditions of the oil filling cover, the oil filling pipe and the oil tank in the collision process are simulated, and whether the fuel system is in liquid leakage or not is detected.
The above description is only of the preferred embodiment of the present invention, and is not intended to limit the structure of the present invention in any way. Any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present invention fall within the technical scope of the present invention.
Claims (10)
1. A detection method for fuel leakage during automobile collision is characterized by comprising the following steps: the method comprises the following steps:
s101, rigidly connecting a white car body and a pulley through a fixed tool;
s102, filling liquid into a fuel tank, wherein the filling amount of the liquid in the fuel tank is 90% of the volume of the fuel tank;
s103, normally installing a fuel tank, normally installing components near the fuel tank, normally connecting a filler neck, and normally locking a filler cap;
s104, the camera collects an original fuel system image;
s105, simulating the situation of fuel leakage after the collision of the fuel system, and collecting the fuel system image of the corresponding leakage situation;
s106, the fuel system adopts static background modeling, pixel difference is carried out on the acquired image frame before the collision of the fuel system and the image frame after the collision of the simulated fuel system, and corresponding images are marked; marking the corresponding image frame as a corresponding leak point; storing the data in a database;
s107, the camera collects images of the fuel system during actual collision;
s108, comparing the image after collision of the actual collision experiment fuel system acquired by the camera acquisition system with the original image of the fuel system in the database, the image after collision deformation which is not leaked and the image after deformation and leakage, determining whether fuel is leaked or not according to the comparison result, and further determining the position of a fuel leakage point;
and S109, outputting a detection result to finish the detection of the fuel system leakage.
2. The detection method for fuel leakage in the event of a collision of a vehicle according to claim 1, wherein: rechecking all the image frames determined to be leaked by the fuel system, judging that the comparison is correct, marking the corresponding image frames, and storing the corresponding image frames into a fuel leakage picture database; and (3) comparing errors, marking corresponding image frames, and storing the corresponding image frames into a fuel system non-leakage picture database.
3. The detection method for fuel leakage in the event of a collision of a vehicle according to claim 1, wherein: the situation that fuel oil leakage occurs after the collision of the fuel oil system is simulated, and the position of the image collected by the camera is the same as that of the original fuel oil system image.
4. The detection method for fuel leakage in the event of a collision of a vehicle according to claim 1, wherein: the simulated fuel system collision image includes: slight collision, slight deformation, no leakage; moderate collision, moderate deformation, no leakage; high collision, high deformation and no leakage; high impact, high deformation, and leakage.
5. The detection method for fuel leakage in the event of a collision of a vehicle according to claim 1, wherein: simulating a fuel system collision, the fuel system leakage image comprising: the fuel tank, the fuel filler pipe and the fuel filler cap leak images at the same time; fuel tank and filler tube leak images; oil filler tube and oil filler cap leakage images; fuel tank and filler cap leak images.
6. A detection method for fuel leakage of an automobile collision comprises the following steps:
s101, acquiring an image to be detected of a fuel system;
s102, performing image segmentation processing on the image to be detected to obtain images of areas to be detected of the fuel tank, the fuel filling pipe and the fuel filling cover;
s103, for each region image to be detected, firstly extracting image contour features, and then identifying corresponding fuel system components according to the extracted image contour features, and sequentially executing steps S301-S302:
s301, determining an applicable deep learning model which is subjected to fuel system component image recognition training according to a fuel system component recognition result, and then guiding an area image to be detected into the deep learning model for prediction operation to obtain a corresponding fuel system component image recognition type and fuel system component image recognition accuracy, wherein the fuel system component image recognition type comprises a leakage type and a non-leakage type;
s302, if the obtained fuel system component image identification type is a leakage type and the leakage image identification accuracy is not less than a set threshold, the fuel system component image identification type and the fuel system component image identification accuracy are obtained on the fuel system component image to be detected and the position mark corresponding to the region image to be detected;
s104, storing an image of the fuel system component mark;
s105, outputting a result of whether the fuel system leaks or not.
7. The method for detecting fuel leakage in the event of a collision of a vehicle according to claim 6, wherein prior to said step S301, a leakage image recognition training is performed on a deep learning model applied to a certain fuel system component according to the following steps S201 to S203:
s201, acquiring sample images of fuel system components and marked leakage image recognition types bound with each sample image, wherein the number of corresponding sample images is not less than 100 for each leakage image recognition type;
s202, taking each sample image and the corresponding marked leakage image recognition type as a training sample, and importing the sample images and the corresponding marked leakage image recognition type into a deep learning model for image recognition training, wherein the sample images are taken as sample input data, and the marked image recognition types corresponding to the sample images are taken as sample verification data;
and S203, in the image recognition training process, continuously optimizing the deep learning model according to the matching result of the image recognition type obtained by training and the sample verification data until the training is completed or until the matching rate of the image recognition type obtained by training and the sample verification data reaches a set threshold value.
8. The utility model provides a detecting system for car collision fuel leakage, includes white automobile body for carry on the acceleration block of white automobile body, white automobile body is fixed on accelerating block through fixed frock, the bottom of white automobile body is equipped with the fuel system who comprises fuel tank, filler pipe and filler cap, is equipped with accelerating block servo system in accelerating block's the place ahead, its characterized in that: the first camera used for collecting fuel leakage at the fuel filling port is arranged on the outer side of the accelerating pulley, and the second camera is arranged below the fuel tank on the surface of the accelerating pulley; the front of the fuel tank on the surface of the accelerating pulley is provided with a third camera, and the other side of the outer side of the accelerating pulley corresponding to the first camera is provided with a fourth camera.
9. The detection system for vehicle collision fuel leakage according to claim 8, wherein: the fixing tool is a front fixing frame arranged in front of the white car body and a rear fixing bracket arranged at the rear.
10. The detection system for vehicle collision fuel leakage according to claim 8, wherein: the third camera is arranged on the front fixing frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110790382.2A CN113670524B (en) | 2021-07-13 | 2021-07-13 | Detection method and detection system for automobile collision fuel leakage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110790382.2A CN113670524B (en) | 2021-07-13 | 2021-07-13 | Detection method and detection system for automobile collision fuel leakage |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113670524A CN113670524A (en) | 2021-11-19 |
| CN113670524B true CN113670524B (en) | 2023-12-19 |
Family
ID=78539240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110790382.2A Active CN113670524B (en) | 2021-07-13 | 2021-07-13 | Detection method and detection system for automobile collision fuel leakage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113670524B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115457297B (en) * | 2022-08-23 | 2023-09-26 | 中国航空油料集团有限公司 | Oil leakage detection method and device for aviation oil depot and aviation oil safety operation and maintenance system |
| CN119239402B (en) * | 2024-10-31 | 2025-03-11 | 江苏兴邦能源科技有限公司 | Hydrogen fuel cell monitoring and management method and system for hydrogen energy two-wheel vehicle |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0470533A (en) * | 1990-07-11 | 1992-03-05 | Tokyo Electric Power Co Inc:The | Oil-leakage detecting method |
| JP2002162314A (en) * | 2000-11-27 | 2002-06-07 | Mitsubishi Heavy Ind Ltd | Apparatus and method for vehicle crash simulation |
| KR20070015321A (en) * | 2005-07-30 | 2007-02-02 | 씨멘스 오토모티브 주식회사 | How to detect fuel tank leaks in cars |
| JP2010190696A (en) * | 2009-02-18 | 2010-09-02 | Orient Burein Kk | Leakage detection device |
| CN111145239A (en) * | 2019-12-30 | 2020-05-12 | 南京航空航天大学 | An automatic detection method of aircraft fuel tank excess based on deep learning |
| CN111209876A (en) * | 2020-01-10 | 2020-05-29 | 汕头大学 | Method and system for detecting oil leakage defect |
| CN111402186A (en) * | 2018-12-14 | 2020-07-10 | 奥迪股份公司 | Liquid leakage detection method, system, computer device and storage medium |
| CN112508944A (en) * | 2020-12-27 | 2021-03-16 | 中信重工开诚智能装备有限公司 | Leakage detection method applied to underground water supply pipeline of coal mine |
| CN113095114A (en) * | 2019-12-23 | 2021-07-09 | 新疆金风科技股份有限公司 | Method, device and equipment for detecting oil leakage of hydraulic system |
| CN113504008A (en) * | 2021-07-13 | 2021-10-15 | 江铃汽车股份有限公司 | Detection method, detection test paper and reagent for automobile collision fuel leakage |
| CN113514193A (en) * | 2021-07-13 | 2021-10-19 | 江铃汽车股份有限公司 | Automobile collision fuel leakage detection method based on image recognition |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103217256A (en) * | 2013-03-20 | 2013-07-24 | 北京理工大学 | Local gray level-entropy difference leak detection locating method based on infrared image |
| DE102015005622B4 (en) * | 2015-04-30 | 2022-01-27 | Audi Ag | Method and device for detecting operating fluid leaks in an engine compartment and/or in the wheel housings of a motor vehicle |
| JP6498552B2 (en) * | 2015-07-15 | 2019-04-10 | 株式会社日立製作所 | Oil leak detection system |
| CN110494861B (en) * | 2017-03-31 | 2023-09-22 | 横河电机株式会社 | Image-based anomaly detection method and system |
| JP6989444B2 (en) * | 2018-01-18 | 2022-01-05 | 株式会社日立製作所 | Work terminal, oil leak detection device, and oil leak detection method |
| KR102067242B1 (en) * | 2018-05-23 | 2020-01-16 | 한국해양과학기술원 | Method for detecting oil spills on satellite sar images using artificial neural network |
| CN109325520B (en) * | 2018-08-24 | 2021-06-29 | 北京航空航天大学 | Method, device and system for checking oil leakage |
| CN110705601A (en) * | 2019-09-09 | 2020-01-17 | 安徽继远软件有限公司 | Transformer substation equipment oil leakage image identification method based on single-stage target detection |
| CN111126196A (en) * | 2019-12-10 | 2020-05-08 | 安徽银河物联通信技术有限公司 | Equipment oil leakage detection method |
-
2021
- 2021-07-13 CN CN202110790382.2A patent/CN113670524B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0470533A (en) * | 1990-07-11 | 1992-03-05 | Tokyo Electric Power Co Inc:The | Oil-leakage detecting method |
| JP2002162314A (en) * | 2000-11-27 | 2002-06-07 | Mitsubishi Heavy Ind Ltd | Apparatus and method for vehicle crash simulation |
| KR20070015321A (en) * | 2005-07-30 | 2007-02-02 | 씨멘스 오토모티브 주식회사 | How to detect fuel tank leaks in cars |
| JP2010190696A (en) * | 2009-02-18 | 2010-09-02 | Orient Burein Kk | Leakage detection device |
| CN111402186A (en) * | 2018-12-14 | 2020-07-10 | 奥迪股份公司 | Liquid leakage detection method, system, computer device and storage medium |
| CN113095114A (en) * | 2019-12-23 | 2021-07-09 | 新疆金风科技股份有限公司 | Method, device and equipment for detecting oil leakage of hydraulic system |
| CN111145239A (en) * | 2019-12-30 | 2020-05-12 | 南京航空航天大学 | An automatic detection method of aircraft fuel tank excess based on deep learning |
| CN111209876A (en) * | 2020-01-10 | 2020-05-29 | 汕头大学 | Method and system for detecting oil leakage defect |
| CN112508944A (en) * | 2020-12-27 | 2021-03-16 | 中信重工开诚智能装备有限公司 | Leakage detection method applied to underground water supply pipeline of coal mine |
| CN113504008A (en) * | 2021-07-13 | 2021-10-15 | 江铃汽车股份有限公司 | Detection method, detection test paper and reagent for automobile collision fuel leakage |
| CN113514193A (en) * | 2021-07-13 | 2021-10-19 | 江铃汽车股份有限公司 | Automobile collision fuel leakage detection method based on image recognition |
Non-Patent Citations (4)
| Title |
|---|
| 基于SAR图像的海面溢油检测研究;冯景;《中国博士学位论文全文数据库（工程科技Ⅰ辑）》;2016年(第03期);全文 * |
| 基于X射线图像和卷积神经网络的石油钢管焊缝缺陷检测与识别;刘涵;郭润元;;仪器仪表学报(第04期);全文 * |
| 基于卷积神经网络的主变压器外观缺陷检测方法;位一鸣;童力;罗麟;杨珊;;浙江电力(第04期);全文 * |
| 基于合成孔径雷达海洋溢油图像的油膜提取和边缘检测;胡冠华;《中国优秀硕士学位论文全文数据库（信息科技辑）》;2015年(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113670524A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113670524B (en) | Detection method and detection system for automobile collision fuel leakage | |
| Wang | Research and application of traffic sign detection and recognition based on deep learning | |
| CN113514193B (en) | Automobile collision fuel leakage detection method based on image recognition | |
| CN109934452A (en) | Road Comfort Evaluation method based on multi-source data | |
| CN113504008B (en) | Detection method, detection test paper and reagent for automobile collision fuel leakage | |
| CN103465857A (en) | Mobile-phone-based active safety early-warning method for automobile | |
| CN113033604A (en) | Vehicle detection method, system and storage medium based on SF-YOLOv4 network model | |
| WO2013179588A1 (en) | Human detection apparatus | |
| CN112330646A (en) | A two-dimensional image-based anomaly detection method for the underbody of a motor vehicle | |
| CN103927548A (en) | A New Braking Behavior Detection Method for Vehicle Collision Avoidance | |
| CN107167172A (en) | A kind of on-line monitoring method of bus type automobile digital instrument pointer functionality | |
| CN112085018A (en) | License plate recognition system based on neural network | |
| CN112801110B (en) | Target detection method and device for image distortion correction of linear array camera of rail train | |
| CN113743218B (en) | License plate recognition method, license plate recognition device and computer readable storage medium | |
| CN117635599A (en) | Defect detection model training and defect detection method, device, equipment and medium | |
| CN103258218A (en) | Matte detection frame generation method and device and defect detection method and device | |
| CN112801466A (en) | Method and system for early warning illegal operation of oil discharge operation of gas station | |
| CN107622667B (en) | Method and system for detecting altered license plate number | |
| CN111814582A (en) | Method and device for processing driver behavior monitoring image | |
| CN112766306B (en) | Deceleration strip area identification method based on SVM algorithm | |
| CN112124074B (en) | Method for realizing automatic control of vehicle speed based on surrounding conditions of vehicle | |
| CN110334608B (en) | Real-time traffic speed limit sign identification method of vehicle-mounted image | |
| CN115457215A (en) | Camera sensor modeling method applied to automatic driving | |
| CN111833291B (en) | Semantic segmentation training set manual annotation evaluation method and device | |
| CN112580736A (en) | Drunk driving vehicle identification method based on SVM algorithm |
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 |