CN111754508A - Contact net limiting nail-stopping allowance state detection system - Google Patents
Contact net limiting nail-stopping allowance state detection system Download PDFInfo
- Publication number
- CN111754508A CN111754508A CN202010633369.1A CN202010633369A CN111754508A CN 111754508 A CN111754508 A CN 111754508A CN 202010633369 A CN202010633369 A CN 202010633369A CN 111754508 A CN111754508 A CN 111754508A
- Authority
- CN
- China
- Prior art keywords
- nail
- stopping
- allowance
- module
- contact net
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 113
- 238000004458 analytical method Methods 0.000 claims abstract description 39
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 abstract description 18
- 230000007547 defect Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000003708 edge detection Methods 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a contact net limiting nail-stopping allowance state detection system which comprises an image acquisition module, an image positioning module, a nail-stopping allowance calculation module, a nail-stopping allowance analysis module and an analysis result output module, wherein the image positioning module comprises a high-pixel positioner detection network and a low-pixel nail-stopping detection network. According to the system for detecting the state of the limit nail stopping allowance of the contact net, the state of the nail stopping allowance in the image of the high-speed railway contact net is intelligently analyzed, the analysis speed is increased while the analysis accuracy of the state of the allowance is increased, and compared with the existing method for manually checking the state of the nail stopping allowance, the system for detecting the state of the nail stopping allowance of the contact net limiting positioner automatically and intelligently analyzes whether the state of the limit nail stopping allowance of the contact net limiting positioner is too much or too little by utilizing the high-definition image of the contact net, the labor cost is reduced, and errors possibly occurring in manual checking are avoided.
Description
Technical Field
The invention relates to the technical field of contact net limiting and nail stopping allowance state detection, in particular to a contact net limiting and nail stopping allowance state detection system.
Background
With the great development of the economy of China, China has become the country with the most mileage of the high-speed railways in the world, and the great increase of the high-speed mileage brings about the increase of the difficulty of maintenance and overhaul. The contact net is an important device in a power supply system of a high-speed railway, has the characteristics of complex structure, open-air arrangement and the like, and has the possibility of influencing the safety of the power supply system and a running train of the whole railway once problems occur. The overhead line system suspension state detection and monitoring system (4C) can timely eliminate fault hidden dangers and guarantee good operation of components by carrying out high-precision imaging on railway overhead line system components.
The spacing nail allowance of spacing locator is an important parameter in the contact net spare part, and when adopting spacing locator, locator and nail should have suitable allowance. However, due to long-term exposure to the sun and rain, mechanical stress, strong electromagnetic field, even vibration caused by train running and the like, the screw loosening of the stop nail is easy to occur, so that the allowance is changed, and even the normal operation of the train is influenced to cause accidents in severe cases.
The existing method for analyzing the state of the limiting nail-stopping allowance of the limiting positioner of the contact network mainly combines manual regular inspection with the technical personnel for checking the high-precision image of the 4C contact network. The former has high labor intensity, long working period and is not easy to find defects. In the latter case, although the workload of troubleshooting is reduced to a great extent, technicians still need to find the limiting positioner from a huge amount of high-precision image data of the contact net and analyze and judge the allowance state of the limiting stop nail, which is time-consuming and labor-consuming and is easy to cause missed detection due to visual fatigue. Therefore, designing a system for detecting and monitoring various faults automatically and intelligently for high-precision images of contact networks becomes a problem to be faced. The system for intelligently detecting the nail-stopping allowance state of the limiting positioner is designed to have very important practical significance for guaranteeing the safe operation of a contact net.
At present, whether the limitation locator nail-stopping allowance in the high-definition image of the contact network has excessive or insufficient detection of two defect states is not good, the detection still stays in the stage of manually checking the high-definition image, the intelligent analysis research on the limitation locator nail-stopping allowance state of the contact network at home and abroad is few, and the method for detecting the limitation locator nail-stopping allowance state by using the high-precision image is also almost none.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a system for detecting the state of the limit nail allowance of a contact network, which solves the problems that at present, no good method exists for detecting whether the limit locator nail allowance in a high-definition image of the contact network has two defect states of too much or not, the method still stays at the stage of manually checking the high-definition image, the intelligent analysis of the state of the limit nail allowance of the contact network is rarely researched at home and abroad, and the method for detecting the state of the limit locator nail allowance by using a high-precision image is almost nonexistent.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme: the utility model provides a spacing nail surplus state detection system that ends of contact net, includes image acquisition module, image orientation module, ends nail surplus calculation module, ends nail surplus analysis module and analysis result output module, image orientation module includes high pixel locator detection network and low pixel and ends nail detection network, the output of high pixel locator detection network is connected with the input of low pixel nail detection network.
Preferably, the nail stopping allowance calculation module comprises an edge picture, a new detection frame, a new nail stopping coordinate and a nail stopping allowance.
Preferably, the output end of the edge picture is connected with the input end of the new detection frame, and the output end of the edge picture is connected with the input end of the new nail stopping coordinate.
Preferably, the output end of the new detection frame is connected with the input end of the new nail stopping coordinate, and the output end of the new nail stopping coordinate is connected with the input end of the nail stopping allowance.
Preferably, the nail stopping allowance analysis module comprises a detection result and nail stopping allowance, a positioning detection module and judgment result output.
Preferably, the output end of the detection result and the nail stopping allowance is connected with the input end of the positioning detection module, and the output end of the positioning detection module is connected with the input end of the judgment result output.
Preferably, the output end of the image acquisition module is respectively connected with the input ends of the image positioning module, the nail stopping allowance calculation module and the nail stopping allowance analysis module.
Preferably, the output ends of the image positioning module, the nail stopping allowance calculating module and the nail stopping allowance analyzing module are all connected with the input end of the analysis result output module.
(III) advantageous effects
The invention provides a contact net limiting stop nail allowance state detection system. Compared with the prior art, the method has the following beneficial effects:
(1) the contact net limiting and nail stopping allowance state detection system comprises an image acquisition module, an image positioning module, a nail stopping allowance calculation module, a nail stopping allowance analysis module and an analysis result output module, wherein the output end of the image acquisition module is respectively connected with the input ends of the image positioning module, the nail stopping allowance calculation module and the nail stopping allowance analysis module, the output ends of the image positioning module, the nail stopping allowance calculation module and the nail stopping allowance analysis module are respectively connected with the input end of the analysis result output module, the intelligent analysis is carried out on the nail stopping allowance state in the high-speed railway contact net image, the analysis speed is improved while the analysis accuracy of the allowance state is increased, and compared with the existing method for manually checking the nail stopping allowance state, the contact net utilizes a high-definition image, automatically and intelligently analyzes whether the nail stopping allowance of a limiting positioner has an excessive or insufficient state, the labor cost is greatly reduced, and errors possibly caused by manual troubleshooting are avoided.
(2) The contact net limit nail-stopping allowance state detection system comprises a high-pixel locator detection network and a low-pixel nail-stopping detection network on an image positioning module, wherein the output end of the high-pixel locator detection network is connected with the input end of the low-pixel nail-stopping detection network, a nail-stopping allowance calculation module comprises an edge picture, a new detection frame, a new nail-stopping coordinate and a nail-stopping allowance, the output end of the edge picture is connected with the input end of the new detection frame, the output end of the edge picture is connected with the input end of the new nail-stopping coordinate, the output end of the new nail-stopping coordinate is connected with the input end of the nail-stopping allowance, the locator and the nail-stopping can be respectively identified by adopting two depth learning detection models aiming at the high pixel and the low pixel, the required detection frame can be accurately extracted, and the calculation mode is carried out by picture edge extraction and cooperation with the detection frame, and (3) calculating the pixel value of the nail stopping allowance in an abstract mode, and indirectly bypassing the step of estimating the true length of the nail stopping allowance.
(3) This spacing nail surplus state detection system that ends of contact net, through include testing result and nail surplus that ends at nail surplus analysis module, location detection module and judged result output, the output of testing result and nail surplus that ends is connected with location detection module's input, location detection module's output is connected with the input of judged result output, through ending the sufficient of nail surplus state or not, abstract conversion has become the mode of calculating nail surplus pixel value and nail length pixel proportion that ends, the state of nail surplus is ended in the analysis that can be fine, thereby the problem of the unable accurate quantization of locator size that leads to far and near because of the camera when the picture was shot has been walked around to concrete value.
Drawings
FIG. 1 is a system architecture provided by an embodiment of the present invention;
FIG. 2 is a flowchart of an image positioning method according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for calculating a nail stopping margin according to an embodiment of the present invention;
fig. 4 is a flowchart of a method for analyzing a nail stopping margin according to an embodiment of the present invention.
In the figure, 101, an image acquisition module; 102. an image positioning module; 201. a high pixel locator detection network; 202. a low pixel nail detection network; 103. a nail stopping allowance calculation module; 301. an edge picture; 302. a new detection frame; 303. new nail stopping coordinates; 304. stopping the nail allowance; 104. a nail stopping allowance analysis module; 401. detecting the result and the nail stopping allowance; 402. a positioning detection module; 403. outputting a judgment result; 105. and an analysis result output module.
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. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a technical solution: a contact net limiting nail stopping allowance state detection system comprises an image acquisition module 101, an image positioning module 102, a nail stopping allowance calculation module 103, a nail stopping allowance analysis module 104 and an analysis result output module 105.
The image acquisition module 101: the image acquisition module acquires a high-precision contact network image from the contact network suspension state detection monitoring system (4C);
the image localization module 102: the image positioning module is used for inputting the contact net picture output by the 101 module into a depth learning detection model aiming at high pixels, detecting a detection frame of the limiting positioner, cutting out the positioner picture, inputting the positioner picture into a depth learning detection model aiming at low pixels, and detecting the detection frames of the nail stopping and the nail stopping backing;
the nail stopping allowance calculation module 103: the nail stopping allowance calculation module is used for carrying out gray processing on the locator picture output by the 102 module, calculating the edge of the cut limiting locator image by using a double-threshold Canny edge detection operator, and combining the nail stopping and the nail stopping detection frame to obtain the nail stopping allowance;
the nail remaining amount analysis module 104: the nail stopping allowance analyzing module is used for carrying out combined calculation on the nail stopping allowance output by the 103 module and the nail stopping detection frame output by the 102 module, and analyzing whether the nail stopping allowance is within a preset threshold value according to the proportion of the nail stopping allowance to the nail stopping length to obtain an analysis result;
the analysis result output module 105: the analysis result output module is used for marking the analysis result of the nail stopping allowance on the contact net picture and outputting the final analysis result, intelligently analyzing the state of the nail stopping allowance in the high-speed railway contact net picture, increasing the analysis accuracy rate of the state of the allowance and simultaneously improving the analysis speed.
As shown in fig. 2, which is a flowchart of an image positioning method, the image positioning module 102 includes a high pixel positioner detection network 201 and a low pixel nail-stopping detection network 202, an output end of the high pixel positioner detection network 201 is connected to an input end of the low pixel nail-stopping detection network 202, and specific implementation modules are as follows:
high pixel locator detection network 201: the module 201 firstly sends the contact network picture into a YOLOV3 target detection network with 1024 × 1024 inputs to obtain a limit locator detection frame in the picture, and then cuts out the limit locator picture from the original picture;
low pixel nail detection network 202: the module 202 sends the clipped picture of the limit locator in the module 201 to a 512 x 512 YOLOV3 target detection network to obtain the detection boxes of the stop nail and the stop backing in the picture, and outputs the clipped picture of the limit locator, the detection boxes of the stop nail and the detection boxes of the stop backing at the same time.
As shown in fig. 3, the nail-stopping margin calculation module 103 includes an edge picture 301, a new detection frame 302, a new nail-stopping coordinate 303 and a nail-stopping margin 304, an output end of the edge picture 301 is connected to an input end of the new detection frame 302, an output end of the edge picture 301 is connected to an input end of the new nail-stopping coordinate 303, an output end of the new detection frame 302 is connected to an input end of the new nail-stopping coordinate 303, and an output end of the new nail-stopping coordinate 303 is connected to an input end of the nail-stopping margin 304, and the specific implementation modules are as follows:
edge picture 301: the module 301 firstly processes the obtained limit locator picture, and sequentially performs graying, binarization and Canny edge detection operator edge extraction to obtain an edge picture of the limit locator;
new detection block 302: the module 302 firstly combines the obtained nail stopping detection frame with the nail stopping detection frame, takes the minimum value of the x coordinate and the minimum value of the y coordinate at the upper left corner of the nail stopping and nail stopping detection frame to generate new coordinates (xmin2, ymin2), and takes the maximum value of the x coordinate and the maximum value of the y coordinate at the lower right corner to generate new coordinates (xmax3, ymax 3). Generating a new detection frame which simultaneously comprises the nail stopping and the nail stopping backing by using the two new coordinate points;
new nail stopping coordinates 303: the module 303 firstly intercepts the edge picture of the new detection frame on the processed edge picture of the limit positioner according to the coordinates of the new detection frame obtained by the module 302, and then calculates the new detection frame of the nail stop and the new detection frame of the nail stop in the new detection frame generated by the module 302 through the nail stop detection frame and the nail stop detection frame;
nail allowance 304: the module 304 firstly finds out a pixel point with a pixel value equal to 255 at the nearest position of the new nail stopping detection frame from the nail stopping position in the new edge picture generated by the module 303, sets the pixel point as a starting point s1, then continuously traverses the abscissa in the direction of the new nail stopping detection frame through the pixel point s1, finds out a pixel point s2 with a second pixel value equal to 255, and outputs the nail stopping margin, and abstractly calculates the pixel value of the nail stopping margin through the picture edge extraction and the calculation of the detection frame, thereby indirectly bypassing the step of estimating the true length of the nail stopping margin.
As shown in fig. 4, which is a flowchart of a method for analyzing a nail-stopping residual amount, the nail-stopping residual amount analyzing module 104 includes a detection result and nail-stopping residual amount 401, a positioning detection module 402 and a determination result output 403, an output end of the detection result and nail-stopping residual amount 401 is connected to an input end of the positioning detection module 402, an output end of the positioning detection module 402 is connected to an input end of the determination result output 403, and specific implementation modules are as follows:
detection result and nail stopping allowance 401: the module 401 obtains the detection result of the positioner, the detection result of the nail stopping and the nail stopping backing pan, and the pixel value of the nail stopping allowance;
the positioning detection module 402: the module 402 analyzes whether the nail stopping allowance is sufficient, and when the following three conditions are simultaneously met, the allowance is determined to be appropriate, (1) the input locator detection result exists; (2) the input nail stopping detection results and the input nail stopping detection results exist simultaneously and have uniqueness respectively; (3) the calculated ratio of the nail stopping margin pixel value to the nail stopping width pixel value is within a preset threshold range;
judgment result output 403: the module 403 outputs the analysis result obtained by the module 402, and abstractly converts the state of the nail-stopping allowance into a mode of calculating the proportion of the pixel value of the nail-stopping allowance to the pixel value of the nail-stopping length by whether the state of the nail-stopping allowance is sufficient or not, so that the state of the nail-stopping allowance can be well analyzed, and the problem that the size of a locator cannot be accurately quantized into a specific value due to the fact that the distance between a camera and a camera is short or short when a picture is taken is solved.
And those not described in detail in this specification are well within the skill of those in the art.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The utility model provides a spacing nail surplus state detecting system that ends of contact net, includes image acquisition module (101), image orientation module (102), ends nail surplus calculation module (103), ends nail surplus analysis module (104) and analysis result output module (105), its characterized in that: the image positioning module (102) comprises a high-pixel positioner detection network (201) and a low-pixel nail-stopping detection network (202), wherein the output end of the high-pixel positioner detection network (201) is connected with the input end of the low-pixel nail-stopping detection network (202).
2. The contact net limiting stop nail allowance state detection system according to claim 1, characterized in that: the nail stopping allowance calculation module (103) comprises an edge picture (301), a new detection frame (302), a new nail stopping coordinate (303) and a nail stopping allowance (304).
3. The contact net limiting stop nail allowance state detection system according to claim 2, characterized in that: the output end of the edge picture (301) is connected with the input end of the new detection frame (302), and the output end of the edge picture (301) is connected with the input end of the new nail stopping coordinate (303).
4. The contact net limiting stop nail allowance state detection system according to claim 3, characterized in that: the output end of the new detection frame (302) is connected with the input end of a new nail stopping coordinate (303), and the output end of the new nail stopping coordinate (303) is connected with the input end of a nail stopping allowance (304).
5. The contact net limiting stop nail allowance state detection system according to claim 1, characterized in that: the nail stopping allowance analysis module (104) comprises a detection result and nail stopping allowance (401), a positioning detection module (402) and a judgment result output (403).
6. The contact net limiting stop nail allowance state detection system according to claim 5, characterized in that: the output end of the detection result and the nail stopping allowance (401) is connected with the input end of a positioning detection module (402), and the output end of the positioning detection module (402) is connected with the input end of a judgment result output (403).
7. The contact net limiting stop nail allowance state detection system according to claim 1, characterized in that: the output end of the image acquisition module (101) is respectively connected with the input ends of the image positioning module (102), the nail stopping allowance calculation module (103) and the nail stopping allowance analysis module (104).
8. The contact net limiting stop nail allowance state detection system according to claim 1, characterized in that: the output ends of the image positioning module (102), the nail stopping allowance calculating module (103) and the nail stopping allowance analyzing module (104) are connected with the input end of the analysis result output module (105).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010633369.1A CN111754508A (en) | 2020-07-06 | 2020-07-06 | Contact net limiting nail-stopping allowance state detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010633369.1A CN111754508A (en) | 2020-07-06 | 2020-07-06 | Contact net limiting nail-stopping allowance state detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111754508A true CN111754508A (en) | 2020-10-09 |
Family
ID=72679062
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010633369.1A Pending CN111754508A (en) | 2020-07-06 | 2020-07-06 | Contact net limiting nail-stopping allowance state detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111754508A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011209227A (en) * | 2010-03-30 | 2011-10-20 | Railway Technical Research Institute | Non-destructive inspection device for electric traction material |
| US20120205419A1 (en) * | 2011-02-15 | 2012-08-16 | Intuitive Surgical Operations, Inc. | Methods and Systems for Detecting Clamping or Firing Failure |
| CN105719305A (en) * | 2016-01-25 | 2016-06-29 | 成都国铁电气设备有限公司 | Assembly falloff defect identification method and system of overhead contact system |
| CN106570857A (en) * | 2016-09-11 | 2017-04-19 | 西南交通大学 | High-speed railway overhead contact system lateral conductor fixation hook nut falling bad state detection method based on HOG features |
| WO2018037483A1 (en) * | 2016-08-23 | 2018-03-01 | 株式会社Pfu | Bound member detection device |
-
2020
- 2020-07-06 CN CN202010633369.1A patent/CN111754508A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011209227A (en) * | 2010-03-30 | 2011-10-20 | Railway Technical Research Institute | Non-destructive inspection device for electric traction material |
| US20120205419A1 (en) * | 2011-02-15 | 2012-08-16 | Intuitive Surgical Operations, Inc. | Methods and Systems for Detecting Clamping or Firing Failure |
| CN105719305A (en) * | 2016-01-25 | 2016-06-29 | 成都国铁电气设备有限公司 | Assembly falloff defect identification method and system of overhead contact system |
| WO2018037483A1 (en) * | 2016-08-23 | 2018-03-01 | 株式会社Pfu | Bound member detection device |
| CN106570857A (en) * | 2016-09-11 | 2017-04-19 | 西南交通大学 | High-speed railway overhead contact system lateral conductor fixation hook nut falling bad state detection method based on HOG features |
Non-Patent Citations (5)
| Title |
|---|
| JUNPING ZHONG 等: "A CNN-Based Defect Inspection Method for Catenary Split Pins in High-Speed Railway", 《IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT》, vol. 68, no. 8, 31 August 2019 (2019-08-31), pages 2849 - 2860, XP011734524, DOI: 10.1109/TIM.2018.2871353 * |
| 张国栋: "高速铁路接触网定位坡度问题的分析与对策", 《上海铁道科技》, no. 2017, 25 March 2017 (2017-03-25), pages 83 - 84 * |
| 王恒迪 等: "滚动轴承的缺钉、缺球及注脂定位检测系统", 《轴承》, no. 10, 5 October 2018 (2018-10-05), pages 52 - 57 * |
| 钟俊平 等: "高速铁路接触网悬挂装置开口销不良状态检测方法研究", 《铁道学报》., vol. 40, no. 6, 30 June 2018 (2018-06-30), pages 51 - 59 * |
| 魏文静 等: "垂向减振器铆钉微间隙的远场涡流检测方法研究", 《热加工工艺》, vol. 46, no. 1, 31 January 2017 (2017-01-31), pages 175 - 178 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111080634A (en) | Transformer appearance defect identification method based on inspection robot and Cascade RCNN algorithm | |
| CN108760747A (en) | A kind of 3D printing model surface defect visible detection method | |
| CN205898699U (en) | Single track box roof beam inspection device of suspension type | |
| CN113112501B (en) | Vehicle-mounted track inspection device and method based on deep learning | |
| CA3228100A1 (en) | Road surface technical condition detection method and device based on three-dimensional contour | |
| CN109740507A (en) | A kind of method of transformer equipment abnormality sensing | |
| CN110186375A (en) | Intelligent high-speed rail white body assemble welding feature detection device and detection method | |
| CN107169951B (en) | A kind of the missing detection method and system of the inclined cantilever end pipe cap based on image | |
| CN109986172A (en) | A kind of weld and HAZ method, equipment and system | |
| CN105241679A (en) | Method for detecting hidden fault of motor train unit | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN208042989U (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device | |
| CN108921844A (en) | A kind of defects of insulator detection method and device | |
| CN111754508A (en) | Contact net limiting nail-stopping allowance state detection system | |
| CN112179922A (en) | Wire and cable defect detection system | |
| CN116310294A (en) | Subway train bolt loosening detection method and device | |
| CN111028289B (en) | Method for positioning foreign matters in equipment in transformer substation based on template matching | |
| CN112801975B (en) | Binocular vision-based railway ballast inspection system and working method thereof | |
| CN114442658A (en) | Automatic inspection system for unmanned aerial vehicle of power transmission and distribution line and operation method thereof | |
| Chen et al. | Surface Defect Detection of Cable Based on Threshold Image Difference | |
| CN109631779A (en) | A kind of detection method and system that the superstructure loosening based on 3D rendering processing falls off | |
| CN113962956B (en) | Foreign matter detection method for coal conveying belt conveyor | |
| CN115810010B (en) | Train pantograph online detection method and system | |
| CN112528827B (en) | Automatic detection method for crack loss of high-speed rail contact network power supply equipment | |
| CN103714524A (en) | Automatic fusion method for cold-rolled strip steel surface images |
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 |