CN111462045B - Method for detecting defects of catenary support assembly - Google Patents
Method for detecting defects of catenary support assembly Download PDFInfo
- Publication number
- CN111462045B CN111462045B CN202010150298.XA CN202010150298A CN111462045B CN 111462045 B CN111462045 B CN 111462045B CN 202010150298 A CN202010150298 A CN 202010150298A CN 111462045 B CN111462045 B CN 111462045B
- Authority
- CN
- China
- Prior art keywords
- base
- image
- catenary
- cable
- detection
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 57
- 238000009434 installation Methods 0.000 claims abstract description 17
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 7
- 238000003672 processing method Methods 0.000 claims abstract description 6
- 238000010586 diagram Methods 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 5
- 235000009508 confectionery Nutrition 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 8
- 239000012212 insulator Substances 0.000 description 4
- 230000008030 elimination Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 239000000725 suspension Substances 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003137 locomotive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010292 electrical insulation Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- 210000000707 wrist Anatomy 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/168—Segmentation; Edge detection involving transform domain methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- 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]
Abstract
The invention discloses a method for detecting defects of a catenary support assembly, which comprises the following steps: step 1: constructing a data set of a catenary base and a stay wire hook of the contact network; step 2: performing target positioning by adopting an Faster RCNN convolutional neural network to obtain a positioning result of a catenary base and a diagonal line hook of the contact network; and step 3: obtaining a candidate area image of the stay cable according to the positioning result and the structural information of the catenary carrier cable base and the stay cable hook; and 4, step 4: positioning the diagonal cable candidate area image by using Hough transform to obtain a positioning result of the diagonal cable, and detecting the loosening defect of the diagonal cable according to a straight line detection result; and 5: carrying out installation defect detection on the carrier cable base according to an image processing method and a detection result; the invention improves the efficiency and the precision of component detection, can effectively detect whether the inclined stay wire has loosening fault, has higher detection efficiency and simplifies the difficulty of fault detection.
Description
Technical Field
The invention relates to the technical field of high-speed rail image intelligent detection, in particular to a method for detecting defects of a catenary support assembly.
Background
With the more prominent advantages of high-speed railways, countries around the world are building a great number of railways. The railway foundation mainly comprises two parts: catenary systems and railway systems. The catenary system is primarily responsible for the power supply of high-speed locomotives and includes a number of support components, such as insulators, stable arms, support wire hooks, and the like. These support assemblies are used to carry mechanical loads, electrical insulation, and the like. However, due to the high speed movement of the locomotive and the external environment, the catenary support assembly may lose parts, cause parts to loosen, develop cracks, etc., which may pose a significant threat to the safe operation of the high speed train.
At present, the detection method for the state defect of the contact network parts at home and abroad mainly comprises the following steps: visual inspection, laser testing, eddy current, ultrasonic, and the like. The detection methods all achieve certain effects, but many methods have the problems of inaccurate measurement, high danger, complex operation, expensive and heavy equipment, heavy detection task, poor anti-interference capability and the like. The non-contact bow net detection technology based on the image processing technology can realize development of a bow net detection device which does not interfere driving safety, and the used equipment has strong expansibility, realizes automatic identification of bow net parameters and faults, and has numerous advantages. Zhang Guinan proposes a high-speed railway pole insulator detection and identification method based on Contour Transformation (CT) and a Chan-Vese model. And the rod-shaped insulator is positioned by adopting a deformable part model. The Yanghong plum uses template matching surf to detect insulator faults. As computer computing power and information gathering power have increased, many algorithms based on deep learning have been proposed. Liukai et al adopt fast RCNN to detect the damage of carrier cable base. Wangli et al have designed a high detection accuracy network for detecting whether equipotential lines are loose. Liu, et al, employs a technique of deep separable convolution in combination with a target detection network to detect dropper faults. The detection methods based on deep learning show high detection speed and high detection precision, but few people put forward corresponding methods for the faults of the inclined stay wires, and in such a case, a quick and accurate target positioning and defect detection method for the catenary support assembly is particularly important.
Disclosure of Invention
The invention provides a method for detecting defects of a suspension chain support assembly, which can realize quick detection of the installation state of a carrier cable base and the loosening fault of a stay cable, aiming at the problems in the prior art.
The technical scheme adopted by the invention is as follows:
a method for detecting defects of a catenary support assembly comprises the following steps:
step 1: constructing a data set of a catenary base and a stay wire hook of the contact network;
and 2, step: performing target positioning by adopting an Faster RCNN convolutional neural network to obtain a positioning result of a catenary base and a diagonal line hook of the contact network;
and step 3: obtaining a candidate area image of the stay cable according to the positioning result in the step 2 and the structural information of the catenary carrier cable base and the stay cable hook;
and 4, step 4: positioning the diagonal cable candidate area image obtained in the step 3 by using Hough transform to obtain a positioning result of the diagonal cable, and detecting the loosening defect of the diagonal cable according to a straight line detection result;
and 5: and (4) carrying out installation defect detection on the carrier cable base obtained in the step (2) according to the image processing method and the detection result in the step (4).
Further, the specific process of step 2 is as follows:
s11: performing convolution operation on an input image to obtain a characteristic diagram;
s12: extracting an area of interest (RoI) through an area proposal network;
s13: and classifying and positioning the RoI.
Further, the specific process of step 3 is as follows:
s21: obtaining the relative positions of a catenary carrier cable base and a stay cable hook of the contact network according to a fast RCNN positioning result;
s22: and intercepting the candidate area image where the inclined pull line is positioned according to the coordinates and the relative position of the prediction frame.
Further, the specific process of step 4 is as follows:
s31: binarizing the candidate area image where the diagonal wires are located, which is obtained in the step 3;
s32: extracting the edge of the binary image through a Candy algorithm, and detecting a horizontal cantilever by using Hough transform; rotating the carrier cable base to the horizontal direction according to the linear detection result and the angle of the horizontal cantilever;
s33: limiting Hough transformation theta angles, and selecting theta angle peak value distribution of n bits before statistic ranking according to Hough transformation results; if the standard deviation of the angle theta is smaller than a set threshold value and the peak value number is larger than the set threshold value, the inclined stay wire is normal, otherwise, the inclined stay wire is loose.
Further, the specific process of step 5 is as follows:
s41: converting the catenary base image into an original gray histogram;
s42: carrying out binarization, expansion, corrosion and filling processing on the original gray level histogram in the step S41 in sequence to eliminate the background;
s43: determining the opening direction of the carrier cable base according to a pulse signal generated by scanning along the horizontal direction;
s44: and (4) according to the opening direction of the catenary base obtained in the step (S43) and the stay cable detection direction determined in the step (4), if the two directions are consistent, the installation of the catenary base is correct, and if not, the installation of the part is defective.
The invention has the beneficial effects that:
(1) according to the invention, the bad states of the catenary base and the inclined stay wires of the high-speed rail contact network are detected through the deep convolutional neural network and the image processing method, the catenary support components (the catenary base and the inclined stay wire hooks) can be rapidly and accurately detected, meanwhile, the candidate areas of the inclined stay wires are rapidly extracted by utilizing the component structure relationship, and the component detection efficiency and precision are improved;
(3) according to the structural characteristics of the inclined stay wires, the Hough change characteristic of the straight line is combined with the structure of the inclined stay wires, so that whether the inclined stay wires are loosened or not can be effectively detected;
(3) the method can effectively detect the mounting fault of the carrier cable base and the loosening fault of the stay cable, has higher correct detection efficiency and simplifies the difficulty of fault detection.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
Fig. 2 is a schematic diagram of on-site acquisition of images of a high-speed railway catenary support and suspension device according to an embodiment of the invention.
Fig. 3 is a diagram of the positions of the messenger base and diagonal hooks located by the fast RCNN convolutional neural network of an embodiment of the present invention.
FIG. 4 is a diagram of a diagonal drawing area and a diagram of a diagonal drawing positioning result according to an embodiment of the present invention.
FIG. 5 is a horizontal wrist rotation diagram according to an embodiment of the present invention.
Fig. 6 is a gray level histogram with background removed according to an embodiment of the present invention.
FIG. 7 is a diagram of the embodiment of the present invention after pretreatment such as binarization, etching, expansion, etc.
FIG. 8 is a schematic diagram and a result diagram of an angle-based fast detection method in an embodiment of the present invention.
Fig. 9 is a graph of hough transform results of diagonal cables in the embodiment of the present invention.
FIG. 10 is a graph showing the peak profile of Theta in an example of the present invention.
Fig. 11 is a schematic view of messenger base installation defect detection in an embodiment of the present invention.
Fig. 12 is an exemplary diagram of a catenary base installation defect detection result in an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments.
As shown in fig. 1, a method for detecting defects of a catenary support assembly includes the following steps:
step 1: constructing a data set of a catenary base and a stay wire hook of the contact network;
a special train comprehensive train inspection vehicle is adopted to image the high-speed railway contact net supporting and hanging device, and a data set of a contact net carrier cable base and a diagonal cable hook is established.
Step 2: performing target positioning by adopting an Faster RCNN convolutional neural network to obtain a positioning result of a catenary base and a diagonal line hook of the contact network;
the specific process is as follows:
s11: performing convolution operation on an input image to obtain a characteristic diagram;
s12: extracting a Region of interest RoI (RoI, Region of Interests) through a Region Proposal Network (RPN, Region promosial Network);
s13: and classifying and positioning the RoI.
And 3, step 3: obtaining a candidate area image of the stay cable according to the positioning result in the step 2 and the structural information of the catenary carrier cable base and the stay cable hook;
the specific process is as follows:
s21: obtaining the relative positions of a catenary carrier cable base and a stay cable hook of the contact network according to a fast RCNN positioning result;
s22: and intercepting the candidate area image where the inclined pull line is positioned according to the coordinates and the relative position of the prediction frame.
And 4, step 4: positioning the diagonal cable candidate area image obtained in the step 3 by using Hough transform to obtain a positioning result of the diagonal cable, and detecting the loosening defect of the diagonal cable according to a straight line detection result;
the specific process is as follows:
to facilitate analysis of the direction of the carrier wire base opening, the image should be rotated to horizontal according to the angle of the horizontal cantilever.
S31: binarizing the candidate area image where the diagonal wires are located, which is obtained in the step 3;
s32: extracting the edge of the binary image through a Candy algorithm, and detecting a horizontal cantilever by using Hough transform; and rotating the carrier cable base to the horizontal direction according to the linear detection result and the angle of the horizontal cantilever.
In order to improve the diagonal detection speed and the detection precision, a rapid Hough transform detection scheme based on a candidate region is provided; according to the structural information of the supporting wire assembly, the angle of the supporting wire is bound to be within the connecting wire angle range of the carrier cable base and the stay wire hook. And (3) restricting and limiting the value range of the Hough transform theta angle by using the candidate area obtained in the step (3), thereby eliminating the interference of other angle straight lines and ensuring the accuracy and efficiency of detection.
S33: limiting Hough transformation theta angles, and selecting theta angle peak value distribution of n-th-before-ranking statistics (five-before-ranking statistics in the embodiment) according to Hough transformation results; if the standard deviation of the angle theta is smaller than a set threshold value and the peak value number is larger than the set threshold value, the inclined stay wire is normal, otherwise, the inclined stay wire is loose. Theoretically, the straighter the line segment is, the smaller the angle fluctuation is, and the peak value number reaches a certain range, so that whether the detection straight line is bent or not can be judged. Therefore, the standard deviation and the peak number of Theta angle are used as indexes for detecting the loosening defect. If the standard deviation is less than 1 and the number of peaks is greater than 6000, the diagonal is determined to be normal, otherwise, the diagonal is determined to be a loosening defect.
And 5: and (4) carrying out installation defect detection on the carrier cable base obtained in the step (2) according to the image processing method and the detection result in the step (4).
The specific process is as follows:
s41: converting the catenary base image into an original gray level histogram; for the obtained catenary base image, the original gray histogram can be obtained by the following formula:
the median pixel of the image is calculated by:
wherein, I(i,j)Is the gray value of the image pixel, L represents the gray level, (M, N) represents the size of the image, and Rank () represents the ranking function of the image gray values. And setting the pixel lower than the median pixel of the image to be 0 to obtain the image with the background interference eliminated.
S42: carrying out binarization, expansion, corrosion and filling processing on the original gray level histogram in the step S41 in sequence to eliminate the background;
s43: determining the opening direction of the carrier cable base according to a pulse signal generated by scanning along the horizontal direction;
the defect of reverse installation of the carrier cable base can be detected by scanning along the horizontal direction to generate pulse signals. First, the messenger base is mounted on the horizontal cantilever so the image begins to scan down the central axis a of the horizontal cantilever. When the direction of the opening of the fixed hook of the carrier cable base is on the left side, firstly, a pulse signal appears at the position B, then, scanning is continued, and then, two pulse signals appear at the positions A and B. Otherwise, the detected opening direction is to the right. Thus, from this characteristic, the direction of the messenger base positioning hook can be determined. And (4) judging the installation defect fault of the carrier cable base according to the determined opening direction of the carrier cable base and the diagonal cable detection direction determined in the step (4). If the direction of the two is consistent, the installation of the catenary base is correct, otherwise, the component is installed wrongly and is installed reversely.
S44: and (4) according to the opening direction of the catenary base obtained in the step (S43) and the stay cable detection direction determined in the step (4), if the two directions are consistent, the installation of the catenary base is correct, and if not, the installation of the part is defective.
Fig. 2 is a schematic diagram of the image of the high-speed rail contact net suspension device collected on site. Fig. 3 is a diagram of a messenger base and a stay wire hook positioned using the fast RCNN convolutional neural network. The diagonal positioning result is obtained from hough transform or the like, as shown in fig. 4.
The catenary base image is rotated, firstly, the image is binarized, then, the edge of the binarized image is extracted through the Candy algorithm, the horizontal cantilever is detected through Hough transformation, and then, the catenary base is rotated to the horizontal direction according to the detection result, as shown in fig. 5.
Background elimination of the carrier cable base, setting pixels lower than the median pixels of the image to be 0, and obtaining the image with the background eliminated, wherein the result is shown in fig. 6; wherein a is a gray level histogram before background elimination, and b is a gray level histogram after background elimination.
After image preprocessing, binarization, erosion and expansion processing, the image result is shown in fig. 7.
And (3) detecting the looseness of the pull-down wire, and providing a quick detection method based on Hough transform according to a certain angle range of the distribution of the inclined pull wires. As shown in fig. 8. Fig. 9 shows the hough transform result of the diagonal cable, and it can be determined whether the diagonal cable is in a loose state as shown in fig. 10 from the peak distribution result of theta.
The catenary base installation defect detection can generate different pulse results according to different opening directions of the catenary, and provides a detection method of the installation defect, and a schematic diagram of the detection method is shown in fig. 11. Fig. 12 shows an exemplary graph of the results of the mounting defect detection.
The invention detects the bad states of the catenary base and the stay cable of the high-speed rail contact network by a deep convolution neural network and an image processing method. The catenary supporting component (the carrier cable base and the inclined stay wire hook) can be detected quickly and accurately. Meanwhile, by utilizing the component structure relationship, the diagonal wire candidate area is extracted quickly, and the component detection efficiency and precision are improved. According to the structural characteristics of the inclined stay wires, the Hough change characteristics of the straight line and the structure of the inclined stay wires are combined, and whether the inclined stay wires are loosened or not can be effectively detected. The method can effectively detect the mounting fault of the carrier cable base and the loosening fault of the inclined pull wire, has higher correct detection rate and simplifies the difficulty of fault detection.
Claims (1)
1. A method for detecting defects of a catenary support assembly is characterized by comprising the following steps:
step 1: constructing a data set of a catenary base and a stay wire hook of the contact network;
step 2: performing target positioning by adopting an Faster RCNN convolutional neural network to obtain a positioning result of a catenary base and a diagonal line hook of the contact network;
s21: performing convolution operation on an input image to obtain a characteristic diagram;
s22: extracting an area of interest (RoI) through an area proposal network;
s23: classifying and positioning the RoI;
and step 3: obtaining a candidate area image of the stay cable according to the positioning result in the step 2 and the structural information of the catenary carrier cable base and the stay cable hook;
s31: obtaining the relative positions of a catenary carrier cable base and a stay cable hook of the contact network according to a fast RCNN positioning result;
s32: intercepting a candidate area image where the inclined stay wire is located according to the coordinates and the relative position of the prediction frame;
and 4, step 4: positioning the diagonal cable candidate area image obtained in the step 3 by using Hough transform to obtain a positioning result of the diagonal cable, and detecting the loosening defect of the diagonal cable according to a straight line detection result;
s41: binarizing the candidate area image where the diagonal wires are located, which is obtained in the step 3;
s42: extracting the edge of the binary image through a Candy algorithm, and detecting a horizontal cantilever by using Hough transform; rotating the carrier cable base to the horizontal direction according to the linear detection result and the angle of the horizontal cantilever;
s43: limiting Hough transformation theta angles, and selecting theta angle peak value distribution of n-bit positions before statistic ranking according to Hough transformation results; if the standard deviation of the angle theta is smaller than a set threshold value and the peak value number is larger than the set threshold value, the inclined stay wire is normal, otherwise, the inclined stay wire is loose;
and 5: carrying out installation defect detection on the carrier cable base obtained in the step 2 according to the image processing method and the detection result in the step 4;
s51: converting the catenary base image into an original gray level histogram; for the obtained catenary base image, the original gray histogram is obtained by the following formula:
the median pixel of the image is calculated by:
wherein, I(i,j)The gray value of an image pixel is obtained, L represents the gray level, (M, N) represents the size of the image, Rank () represents the sorting function of the image gray value, the pixel lower than the median pixel of the image is set as 0, and the image with background interference eliminated is obtained;
s52: carrying out binarization, expansion, corrosion and filling processing on the original gray level histogram in the step S51 in sequence to eliminate the background;
s53: determining the opening direction of the carrier cable base according to a pulse signal generated by scanning along the horizontal direction;
s54: according to the opening direction of the catenary base obtained in the step S53 and the diagonal cable detection direction determined in the step 4, if the directions of the opening direction and the diagonal cable detection direction are consistent, the installation of the catenary base is correct; otherwise, the messenger base is installed incorrectly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010150298.XA CN111462045B (en) | 2020-03-06 | 2020-03-06 | Method for detecting defects of catenary support assembly |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010150298.XA CN111462045B (en) | 2020-03-06 | 2020-03-06 | Method for detecting defects of catenary support assembly |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111462045A CN111462045A (en) | 2020-07-28 |
CN111462045B true CN111462045B (en) | 2022-07-01 |
Family
ID=71684183
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010150298.XA Expired - Fee Related CN111462045B (en) | 2020-03-06 | 2020-03-06 | Method for detecting defects of catenary support assembly |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111462045B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111986174A (en) * | 2020-08-17 | 2020-11-24 | 深圳市商汤科技有限公司 | Defect detection method, defect detection device, electronic equipment and computer storage medium |
CN112132820A (en) * | 2020-09-29 | 2020-12-25 | 江苏新绿能科技有限公司 | Catenary positioning pipe stay cable fault detection method based on YOLOv2 algorithm |
CN112801989A (en) * | 2021-02-02 | 2021-05-14 | 西南交通大学 | Contact net diagonal line fault automatic detection method based on image enhancement processing |
CN112985263B (en) * | 2021-02-09 | 2022-09-23 | 中国科学院上海微系统与信息技术研究所 | Method, device and equipment for detecting geometrical parameters of bow net |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106340019A (en) * | 2016-08-31 | 2017-01-18 | 西南交通大学 | Method for detecting adverse state of high-speed rail overhead line system inclined cable fixing hook |
CN106446934A (en) * | 2016-08-31 | 2017-02-22 | 西南交通大学 | High speed rail overhead contact system carrier cable seat support pedestal detection method based on HOG (Histogram) features |
CN106485701A (en) * | 2016-09-26 | 2017-03-08 | 成都交大光芒科技股份有限公司 | Based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image |
CN106919978A (en) * | 2017-01-18 | 2017-07-04 | 西南交通大学 | A kind of high ferro contact net support meanss parts recognition detection method |
CN107154034A (en) * | 2016-03-03 | 2017-09-12 | 成都交大光芒科技股份有限公司 | The condition detection method and system of a kind of high ferro contact net lateral conductor location hook |
CN108734687A (en) * | 2017-04-21 | 2018-11-02 | 游诚曦 | A kind of lateral conductor does not stress defect identification method and device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9796400B2 (en) * | 2013-11-27 | 2017-10-24 | Solfice Research, Inc. | Real time machine vision and point-cloud analysis for remote sensing and vehicle control |
-
2020
- 2020-03-06 CN CN202010150298.XA patent/CN111462045B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107154034A (en) * | 2016-03-03 | 2017-09-12 | 成都交大光芒科技股份有限公司 | The condition detection method and system of a kind of high ferro contact net lateral conductor location hook |
CN106340019A (en) * | 2016-08-31 | 2017-01-18 | 西南交通大学 | Method for detecting adverse state of high-speed rail overhead line system inclined cable fixing hook |
CN106446934A (en) * | 2016-08-31 | 2017-02-22 | 西南交通大学 | High speed rail overhead contact system carrier cable seat support pedestal detection method based on HOG (Histogram) features |
CN106485701A (en) * | 2016-09-26 | 2017-03-08 | 成都交大光芒科技股份有限公司 | Based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image |
CN106919978A (en) * | 2017-01-18 | 2017-07-04 | 西南交通大学 | A kind of high ferro contact net support meanss parts recognition detection method |
CN108734687A (en) * | 2017-04-21 | 2018-11-02 | 游诚曦 | A kind of lateral conductor does not stress defect identification method and device |
Non-Patent Citations (3)
Title |
---|
Detection Approach Based on an Improved Faster RCNN for Brace Sleeve Screws in High-Speed Railways;Zhigang Liu等;《IEEE Transactions on Instrumentation and Measurement》;20190913;第4395 - 4403页 * |
图像处理在接触网吊弦缺陷检测中的应用;徐钥斌;《cnki优秀硕士学位论文全文库 信息科技辑》;20181015;第I138-726页 * |
面向高铁接触网缺陷检测的智能图像处理关键技术研究;张子健;《cnki优秀硕士学位论文全文库 工程科技Ⅱ辑》;20190815;第C033-43页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111462045A (en) | 2020-07-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111462045B (en) | Method for detecting defects of catenary support assembly | |
CN105652154B (en) | Contact Running State security auditing system | |
CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
CN104318582B (en) | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network | |
CN111814686A (en) | Vision-based power transmission line identification and foreign matter invasion online detection method | |
CN106485694B (en) | A kind of high iron catenary double-jacket tube connector six-sided nut based on cascade classifier falls off defective mode detection method | |
CN105158257A (en) | Sliding plate measurement method and device | |
CN105654461A (en) | Machine vision detection method for fracture of multi-bundle conductor spacer | |
CN111402215B (en) | Contact net insulator state detection method based on robust principal component analysis method | |
CN105354589A (en) | Method and system for intelligently identifying insulator crack in catenary image | |
CN111402214A (en) | Neural network-based automatic detection method for breakage defect of catenary dropper current-carrying ring | |
CN109523543B (en) | Method for detecting broken strands of conducting wires based on edge distance | |
CN111754465A (en) | Insulator positioning and string drop detection method | |
CN114241364A (en) | Method for quickly calibrating foreign object target of overhead transmission line | |
CN108537170A (en) | A kind of power equipment firmware unmanned plane inspection pin missing detection method | |
CN112560634A (en) | Method and system for rapidly detecting and positioning power line insulator based on field image | |
CN110288571A (en) | A kind of high iron catenary insulator method for detecting abnormality based on image procossing | |
CN110782411B (en) | Anti-vibration hammer slip identification method based on image processing | |
CN113657258A (en) | Contact network fault identification system and method based on image processing | |
CN112288717A (en) | Method for detecting foreign matters on side part of motor train unit train | |
CN111260631B (en) | Efficient rigid contact line structure light bar extraction method | |
CN116704416A (en) | Automatic extraction method and system for mechanical characteristics of high-voltage circuit breaker | |
CN116071306A (en) | Machine vision detection method for riveting defect of rolling bearing retainer | |
CN114030395A (en) | Method and system for detecting foreign matters in contact suspension string area | |
CN110223346B (en) | Shape prior-based multi-insulator positioning method |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220701 |