CN113657258A - Contact network fault identification system and method based on image processing - Google Patents
Contact network fault identification system and method based on image processing Download PDFInfo
- Publication number
- CN113657258A CN113657258A CN202110937467.9A CN202110937467A CN113657258A CN 113657258 A CN113657258 A CN 113657258A CN 202110937467 A CN202110937467 A CN 202110937467A CN 113657258 A CN113657258 A CN 113657258A
- Authority
- CN
- China
- Prior art keywords
- defect
- image
- analysis
- platform
- image processing
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000007547 defect Effects 0.000 claims abstract description 102
- 238000004458 analytical method Methods 0.000 claims abstract description 92
- 230000002159 abnormal effect Effects 0.000 claims abstract description 13
- 238000004891 communication Methods 0.000 claims abstract description 12
- 238000012423 maintenance Methods 0.000 claims abstract description 11
- 239000000284 extract Substances 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 23
- 239000012212 insulator Substances 0.000 claims description 22
- 230000003137 locomotive effect Effects 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 9
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 230000006872 improvement Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000011426 transformation method Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 9
- 239000000725 suspension Substances 0.000 description 9
- 229910052573 porcelain Inorganic materials 0.000 description 8
- 230000008859 change Effects 0.000 description 6
- 238000013475 authorization Methods 0.000 description 3
- 238000010191 image analysis Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000005672 electromagnetic field Effects 0.000 description 2
- 238000006056 electrooxidation reaction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1272—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of cable, line or wire insulation, e.g. using partial discharge measurements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses an image processing-based catenary fault identification system which comprises a defect analysis platform, and a data acquisition device and a maintenance platform which are in communication connection with the defect analysis platform, wherein the data acquisition device is used for acquiring image information of a catenary and uploading the image information to the defect analysis platform, the defect analysis platform comprises an algorithm analysis module and a defect database in communication connection with the algorithm analysis module, the algorithm analysis module extracts characteristics of a set analysis component from the image information, compares the characteristics of the set analysis component with the defect database, and when any analysis component is abnormal, the defect analysis platform generates position information by combining GPS data and a corresponding time sequence table, generates a defect report by combining the position information and the abnormal information, and uploads the defect report to the maintenance platform. The system also discloses an identification method based on the system, which can automatically identify and mark the defects, effectively improve the efficiency and accuracy of defect searching and positioning and obviously reduce the labor intensity of workers.
Description
Technical Field
The invention relates to the technical field of contact network identification, in particular to a contact network fault identification system and method based on image processing.
Background
Railway freight transportation is one of the main modes of modern transportation and is also one of the two basic modes of transportation constituting land freight transportation. It plays an important role in the whole transportation field and plays an increasingly important role. The railway transportation is slightly influenced by climate and natural conditions, and the transportation capacity and the single-vehicle loading capacity are large, so that the railway transportation has the advantages of transportation regularity and low cost. In addition to the many types of vehicles that can carry almost any commodity, there are almost no weight or volume restrictions that are comparable to road and air transportation.
The contact net is a key device of the traction power supply system of the electrified railway, and consists of a support column, a foundation thereof, a supporting device, a positioning device, a contact suspension and the like. The special characteristics of open-air setting, dynamic working, no standby along the line and the like are provided, so that the special characteristics are the weakest link in a traction power supply system, and in addition, the load on the line is changed along the movement of the electric locomotive along a contact line, so that the contact net support suspension device is easy to be influenced by the service life of the contact net support suspension device and environmental factors to generate bad states of component loosening, breakage and the like, and once a fault occurs, the normal operation of the traction power supply system is directly influenced, and even the running operation safety of a train is damaged. In order to ensure the operation order of the high-speed railway and improve the power supply safety and reliability, the overall technical specification of the high-speed railway power supply safety detection and monitoring system (6C system) is released and implemented.
The traditional manual inspection mode is very low in efficiency in the presence of large mileage, and can also interfere with the normal operation of the railway and very large safety risks. The rapid development of image recognition technology and the rapid development of camera hardware equipment, based on the high-speed camera and the image processing algorithm, the detection efficiency of electrical equipment can be greatly improved, the influence on railway operation is reduced, the safety of inspection personnel is ensured, and how to provide a high-efficiency intelligent contact network fault recognition system and method becomes the problem to be solved by the application.
Disclosure of Invention
In order to overcome the defects, the invention aims to provide a contact network fault identification method based on image processing.
In order to achieve the above purposes, the invention adopts the technical scheme that: a contact network fault identification method based on image processing is characterized in that: s1, installing an image acquisition device on a locomotive, wherein the image acquisition device shoots when passing through a position of a contact net; s2, the image acquisition device acquires image data, GPS data and a corresponding time sequence table of the contact network and transmits the acquired image data, GPS data and the corresponding time sequence table to the defect analysis platform; s3, the defect analysis platform carries out preprocessing of denoising, enhancing, segmentation clustering and fusion on image data to form a preprocessed image, and the features of a set analysis component are extracted from the preprocessed image; s4, the defect analysis platform compares the characteristics of the set analysis components with a defect database set in the defect analysis platform, and when any analysis component is abnormal, S5 is executed; and S5, the defect analysis platform generates position information by combining the GPS data and the corresponding time sequence table, generates a defect report by the position information and the abnormal information and uploads the defect report to the maintenance platform.
The invention has the beneficial effects that: based on technologies such as image analysis and image recognition, high-definition imaging is carried out on the contact network through the acquisition device, after image data are imported by the defect analysis platform, the image data are processed, feature extraction of analysis components is set, and then the image data are compared with a defect database to carry out fault recognition. The defects are automatically identified and marked, the defect searching and positioning efficiency and accuracy can be effectively improved, and the manual labor intensity is obviously reduced. The defect identification and detection aiming at the image has certain universality, is not limited by specific equipment, and enhances the expansibility of a program; through the management of the defect feature library by the Internet technology and a flexible authorization mode, the maintainability of the program is improved, and the early-stage cost is reduced to a certain extent.
Further, the setting analysis component comprises an insulator, an equipotential line and a wire clamp. The insulator, the equipotential line and the wire clamp are 3 key devices in a contact network. In the suspension of a contact net, a wire clamp is connected with a contact wire and a supporting device, bears the maximum impact force and the tension of the contact wire of a pantograph net, is the most important and weakest part, has multiple faults of looseness, falling-off and the like in actual operation, and even can cause the contact wire to fall off to cause pantograph net accidents. The insulator plays the electric isolation of the live part and the insulating part and the supporting role of the suspension device, and is the part which supports the most concentrated electric impact and mechanical stress in the suspension device. Due to the fact that the porcelain insulator works in the environments of sunshine solarization, chemical substance corrosion, strong electromagnetic field and strong mechanical stress for a long time, and factors such as material and manufacturing process level limitation of the porcelain insulator are added, the porcelain insulator is easy to age, bad states such as damage and the like caused by flashover discharge caused by thunder and lightning, dirt transfer and the like are prone to occurring, insulating performance is reduced, and breakage and net collapse are caused when the porcelain insulator is seriously broken. When the pantograph of the train passes through, the positioner is lifted to a certain extent, so that a gap is formed between the positioner and the positioner support on the positioning tube, if the equipotential line is loosened or broken, the positioner support bears large electrical impact when the gap is formed, electrochemical corrosion is caused, and the connection part of the positioner and the support is broken and separated seriously, so that the running safety is influenced.
Further, the feature extraction of the insulator is carried out based on a target recognition algorithm combining the gradient direction histogram feature quantity extraction and the SVM classifier, and the extracted features of the insulator are compared with a defect database.
Further, when the characteristics of the equipotential lines are extracted, firstly, a Canny algorithm is selected to realize edge detection; then, the real end points of the contact net positioner are positioned by carrying out collinear combination improvement on the probability Hough transformation straight line detection results, and then the local image extraction of the contact net positioning support is completed by applying an affine transformation method; and finally, utilizing closed domain contour detection to realize the feature extraction of the equipotential lines in the local image.
Further, when extracting the characteristics of the wire clamp, firstly, performing longitudinal straight line detection in each candidate area, and if no longitudinal straight line exists, not positioning the wire clamp area in the candidate area; if yes, carrying out the next judgment; and then performing shape characteristic detection, if the longitudinal straight line and the transverse straight line do not intersect, determining that the region is not a positioning wire clamp region, if the longitudinal straight line and the transverse straight line intersect, taking a circle by taking the intersection point as a circle center and 1/2 of the transverse straight line as a radius, determining that the circle has 3 intersection points with the two straight lines, determining that the circle is a T-shaped structure, determining the region as a positioning wire clamp region, and determining the coordinates of end points of the returned straight lines as the coordinates of the positioning wire clamp.
Further, the defect analysis platform also identifies the pole number on the contact net, and the contact net pole number is positioned according to the contact net position information and the gray histogram characteristics in the pole number identification; then, enhancing image information of the number plate area through self-adaption binaryzation, extracting a pole number frame through a thinning algorithm, and obtaining an accurate pole number area through linear detection and fine segmentation; and finally, optimally segmenting according to the image gray scale statistic value to accurately extract a single character image, and identifying characters to obtain the rod number digital information. The serial number of this pole can all be marked in the pole setting of contact net, discerns the pole number in the contact net and can play two effects: firstly, whether the number plate exists or not can be detected; but can quickly locate the failed vertical pole by the pole number and obtain the position of the failed vertical pole.
Further, the setting analysis part further includes an overall posture and a hard point. The overall posture of the rod can also show whether the contact with the net book has problems in appearance, such as an included angle between the rod and the rod; the angle of inclination of a certain pole book, etc. There are potential safety issues when one of these angles changes significantly and goes beyond normal standards. When the overall posture is used for feature extraction, straight lines in the preprocessed image are detected by Hough transformation, and meanwhile, included angle operation is performed by using the detected straight lines. When an electric locomotive is in operation, the contact force between a locomotive pantograph and a contact line is very complicated to change, and generally, the place causing the contact force between the locomotive pantograph and the contact line to change suddenly is called a contact hard point, which is generally called a hard point, and the place causing the contact force to change suddenly on a contact network is called a contact network hard point. And when the hard points are subjected to feature extraction, detecting straight lines in the preprocessed images by adopting a Hough transformation detection principle, evaluating the sizes of bulges in the straight lines, and comparing the values of the bulges with given threshold values in a defect database.
Further, the image acquisition device is a camera, the angle of the camera is 45 degrees, and the lens of the camera faces the contact net.
The invention further discloses a contact network fault identification system based on image processing.
In order to achieve the above purposes, the invention adopts the technical scheme that: the utility model provides a contact net fault identification system based on image processing, includes defect analysis platform and with defect analysis platform communication connection's data acquisition device and maintenance platform, data acquisition device is used for gathering the image information of contact net and uploads to defect analysis platform, defect analysis platform includes algorithm analysis module and the defect database with algorithm analysis module communication connection, algorithm analysis module draws the characteristic of setting for analysis component to graphical information, set for analysis component's characteristic and defect database and compare, when arbitrary analysis component is unusual, the defect analysis platform combines to generate positional information with GPS data and the time sequence table that corresponds to generate the defect report with positional information and unusual information and upload to maintenance platform.
Based on technologies such as image analysis and image recognition, high-definition imaging is carried out on the contact network through the acquisition device, after image data are imported by the defect analysis platform, the image data are processed, feature extraction of analysis components is set, and then the image data are compared with a defect database to carry out fault recognition. The defects are automatically identified and marked, the defect searching and positioning efficiency and accuracy can be effectively improved, and the manual labor intensity is obviously reduced. The defect identification and detection aiming at the image has certain universality, is not limited by specific equipment, and enhances the expansibility of a program; through the management of the defect feature library by the Internet technology and a flexible authorization mode, the maintainability of the program is improved, and the early-stage cost is reduced to a certain extent. And feature training is carried out aiming at newly identified defects, so that a feature library is continuously enriched, and the intelligence of the system is continuously improved.
Further, the defect analysis platform further comprises a mass data sample library, the algorithm analysis module can store the extracted characteristics of the set analysis component as a sample into the mass data sample library, the mass data sample library is further in communication connection with the defect database, and the mass data sample library can update the sample in the mass data sample library into the defect database. The mass data sample library is uniformly managed by adopting the internet technology, functions of issuing, uploading, counting and the like of the mass data sample library are provided, and the system is stronger in subsequent expansion and the like by adopting a big data mode.
Drawings
FIG. 1 is a system block diagram of an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a catenary in an embodiment of the invention;
FIG. 3 is a schematic diagram illustrating the effect of extracting and identifying the insulator characteristics according to the embodiment of the present invention;
FIG. 4 is a diagram illustrating the effect of equipotential line feature extraction and identification according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of the effect of characteristic extraction and identification of the wire clamp in the embodiment of the invention;
fig. 6 is a schematic diagram illustrating the effect of hard point feature extraction and identification in the embodiment of the present invention.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention easier to understand by those skilled in the art, and thus will clearly and clearly define the scope of the invention.
Examples
Referring to fig. 1-6, a method for identifying a fault of a contact network based on image processing includes the following steps:
the method comprises the following steps that firstly, an image acquisition device is installed on a locomotive, and the image acquisition device shoots when passing through the position of a contact net. The image acquisition device is a camera, the angle of camera installation is 45 degrees for raising, the camera lens of camera is towards the contact net. Aiming at the running speed of the train and the position and distance of a contact net for shooting, the frame rate of a selected camera is 60fps, the focal length is 4mm, and the FOV is 90 degrees.
And secondly, the image acquisition device acquires the image data, the GPS data and the corresponding time sequence list of the contact network and transmits the acquired image data, the GPS data and the corresponding time sequence list to the defect analysis platform.
And thirdly, the defect analysis platform carries out preprocessing of denoising, enhancing, segmentation clustering and fusion on the image data to form a preprocessed image, and the features of the set analysis component are extracted from the preprocessed image. The setting and analyzing part comprises an insulator, an equipotential line, a wire clamp, an integral posture and a hard point.
The insulator plays the electric isolation of the live part and the insulating part and the supporting role of the suspension device, and is the part which supports the most concentrated electric impact and mechanical stress in the suspension device. Due to the fact that the porcelain insulator works in the environments of sunshine solarization, chemical substance corrosion, strong electromagnetic field and strong mechanical stress for a long time, and factors such as material and manufacturing process level limitation of the porcelain insulator are added, the porcelain insulator is easy to age, bad states such as damage and the like caused by flashover discharge caused by thunder and lightning, dirt transfer and the like are prone to occurring, insulating performance is reduced, and breakage and net collapse are caused when the porcelain insulator is seriously broken. The characteristic extraction of the insulator is carried out on the basis of a target recognition algorithm combining the gradient direction histogram characteristic quantity extraction and the SVM classifier, and the extracted characteristics of the insulator are compared with a defect database. Referring to fig. 3, a schematic diagram of the effect of the insulator feature extraction and identification is shown, wherein an abnormal portion is located at a circle.
When the pantograph of the train passes through, the positioner is lifted to a certain extent, so that a gap is formed between the positioner and the positioner support on the positioning tube, if the equipotential line is loosened or broken, the positioner support bears large electrical impact when the gap is formed, electrochemical corrosion is caused, and the connection part of the positioner and the support is broken and separated seriously, so that the running safety is influenced. When the characteristics of the equipotential lines are extracted, firstly, a Canny algorithm is selected to realize edge detection; then, the real end points of the contact net positioner are positioned by carrying out collinear combination improvement on the probability Hough transformation straight line detection results, and then the local image extraction of the contact net positioning support is completed by applying an affine transformation method; and finally, utilizing closed domain contour detection to realize the feature extraction of the equipotential lines in the local image.
In the suspension of a contact net, a wire clamp is connected with a contact wire and a supporting device, bears the maximum impact force and the tension of the contact wire of a pantograph net, is the most important and weakest part, has multiple faults of looseness, falling-off and the like in actual operation, and even can cause the contact wire to fall off to cause pantograph net accidents. When the characteristics of the wire clamp are extracted, firstly, longitudinal straight line detection is carried out in each candidate area, and if no longitudinal straight line exists, the area is not a wire clamp positioning area; if yes, carrying out the next judgment; and then performing shape characteristic detection, if the longitudinal straight line does not intersect with the transverse straight line, determining that the region is not a positioning wire clamp region, if the longitudinal straight line intersects with the transverse straight line, taking a circle by taking the intersection point as the center of the circle and 1/2 of the transverse straight line as the radius, determining that the circle has 3 intersection points with the two straight lines, determining that the circle is a T-shaped structure, determining the region as the positioning wire clamp region, and determining the coordinates of the end points of the returned straight line as the positioning line. Referring to fig. 5, a schematic diagram of the effect of the characteristic extraction and identification of the wire clamp is shown, wherein an abnormal part is arranged at a circle.
The overall posture of the rod can also show whether the contact with the net book has problems in appearance, such as an included angle between the rod and the rod; the angle of inclination of a certain pole book, etc. There are potential safety issues when one of these angles changes significantly and goes beyond normal standards. When the overall posture is used for feature extraction, straight lines in the preprocessed image are detected by Hough transformation, and meanwhile, included angle operation is performed by using the detected straight lines. When an electric locomotive is in operation, the contact force between a locomotive pantograph and a contact line is very complicated to change, and generally, the place causing the contact force between the locomotive pantograph and the contact line to change suddenly is called a contact hard point, which is generally called a hard point, and the place causing the contact force to change suddenly on a contact network is called a contact network hard point. Referring to fig. 6, a schematic diagram of the effect of hard point extraction and identification is shown, wherein an abnormal part is located at a circle.
And when the hard points are subjected to feature extraction, detecting straight lines in the preprocessed images by adopting a Hough transformation detection principle, evaluating the sizes of bulges in the straight lines, and comparing the values of the bulges with given threshold values in a defect database.
And step four, the defect analysis platform compares the characteristics of the set analysis part with a defect database set in the defect analysis platform, and when any analysis part is abnormal, the step five is executed. If no abnormity exists, the step III is returned.
The defect analysis platform further comprises a mass data sample library, the characteristics of the set analysis component can be stored into the mass data sample library as a sample, the mass data sample library is further in communication connection with the defect database, and the mass data sample library can update the samples in the mass data sample library into the defect database. The mass data sample library is uniformly managed by adopting the internet technology, functions of issuing, uploading, counting and the like of the mass data sample library are provided, and the system is stronger in subsequent expansion and the like by adopting a big data mode.
And the defect analysis platform generates position information by combining the GPS data and the corresponding time sequence table, generates a defect report by the position information and the abnormal information and uploads the defect report to the maintenance platform.
The method is based on technologies such as image analysis and image recognition, high-definition imaging is carried out on a contact network through an acquisition device, after image data are imported by a defect analysis platform, the image data are processed, feature extraction of an analysis component is set, and then the image data are compared with a defect database to carry out fault recognition. The defects are automatically identified and marked, the defect searching and positioning efficiency and accuracy can be effectively improved, and the manual labor intensity is obviously reduced. The defect identification and detection aiming at the image has certain universality, is not limited by specific equipment, and enhances the expansibility of a program; through the management of the defect feature library by the Internet technology and a flexible authorization mode, the maintainability of the program is improved, and the early-stage cost is reduced to a certain extent.
The defect analysis platform also identifies the pole number on the contact net, and the contact net pole number is positioned according to the contact net position information and the gray histogram characteristics in the pole number identification; then, enhancing image information of the number plate area through self-adaption binaryzation, extracting a pole number frame through a thinning algorithm, and obtaining an accurate pole number area through linear detection and fine segmentation; and finally, optimally segmenting according to the image gray scale statistic value to accurately extract a single character image, and identifying characters to obtain the rod number digital information. The serial number of this pole can all be marked in the pole setting of contact net, discerns the pole number in the contact net and can play two effects: firstly, whether the number plate exists or not can be detected; but can quickly locate the failed vertical pole by the pole number and obtain the position of the failed vertical pole.
The invention also discloses an image processing-based catenary fault identification system for the method, which comprises a defect analysis platform, and a data acquisition device and a maintenance platform which are in communication connection with the defect analysis platform, wherein the data acquisition device is used for acquiring image information of a catenary and uploading the image information to the defect analysis platform, the defect analysis platform comprises an algorithm analysis module and a defect database in communication connection with the algorithm analysis module, the algorithm analysis module extracts characteristics of a set analysis component from the image information, the characteristics of the set analysis component are compared with the defect database, and when any analysis component is abnormal, the defect analysis platform generates position information by combining GPS data and a corresponding time sequence table, generates a defect report by combining the position information and the abnormal information, and uploads the defect report to the maintenance platform.
The defect analysis platform further comprises a mass data sample library, the algorithm analysis module can store the extracted characteristics of the set analysis component as samples in the mass data sample library, the mass data sample library is further in communication connection with the defect database, and the mass data sample library can update the samples in the mass data sample library to the defect database. The mass data sample library is uniformly managed by adopting the internet technology, functions of issuing, uploading, counting and the like of the mass data sample library are provided, and the system is stronger in subsequent expansion and the like by adopting a big data mode. And feature training is carried out aiming at newly identified defects, so that a feature library is continuously enriched, and the intelligence of the system is continuously improved.
The above embodiments are merely illustrative of the technical concept and features of the present invention, and the present invention is not limited thereto, and any equivalent changes or modifications made according to the spirit of the present invention should be included in the scope of the present invention.
Claims (10)
1. A contact network fault identification method based on image processing is characterized in that: s1, installing an image acquisition device on a locomotive, wherein the image acquisition device shoots when passing through a position of a contact net; s2, the image acquisition device acquires image data, GPS data and a corresponding time sequence table of the contact network and transmits the acquired image data, GPS data and the corresponding time sequence table to the defect analysis platform; s3, the defect analysis platform carries out preprocessing of denoising, enhancing, segmentation clustering and fusion on image data to form a preprocessed image, and the features of a set analysis component are extracted from the preprocessed image; s4, the defect analysis platform compares the characteristics of the set analysis components with a defect database set in the defect analysis platform, and when any analysis component is abnormal, S5 is executed; and S5, the defect analysis platform generates position information by combining the GPS data and the corresponding time sequence table, generates a defect report by the position information and the abnormal information and uploads the defect report to the maintenance platform.
2. The image processing-based contact network fault identification method according to claim 1, characterized in that: the setting analysis component comprises an insulator, an equipotential line and a wire clamp.
3. The image processing-based contact network fault identification method according to claim 2, characterized in that: the characteristic extraction of the insulator is carried out on the basis of a target recognition algorithm combining the gradient direction histogram characteristic quantity extraction and the SVM classifier, and the extracted characteristics of the insulator are compared with a defect database.
4. The image processing-based contact network fault identification method according to claim 2, characterized in that: when the characteristics of the equipotential lines are extracted, firstly, a Canny algorithm is selected to realize edge detection; then, the real end points of the contact net positioner are positioned by carrying out collinear combination improvement on the probability Hough transformation straight line detection results, and then the local image extraction of the contact net positioning support is completed by applying an affine transformation method; and finally, utilizing closed domain contour detection to realize the feature extraction of the equipotential lines in the local image.
5. The image processing-based contact network fault identification method according to claim 2, characterized in that: when the characteristics of the wire clamp are extracted, firstly, longitudinal straight line detection is carried out in each candidate area, and if no longitudinal straight line exists, the area is not a wire clamp positioning area; if yes, carrying out the next judgment; and then performing shape characteristic detection, if the longitudinal straight line and the transverse straight line do not intersect, determining that the region is not a positioning wire clamp region, if the longitudinal straight line and the transverse straight line intersect, taking a circle by taking the intersection point as a circle center and 1/2 of the transverse straight line as a radius, determining that the circle has 3 intersection points with the two straight lines, determining that the circle is a T-shaped structure, determining the region as a positioning wire clamp region, and determining the coordinates of end points of the returned straight lines as the coordinates of the positioning wire clamp.
6. The image processing-based contact network fault identification method according to claim 1, characterized in that: the defect analysis platform also identifies the pole number on the contact net, and the contact net pole number is positioned according to the contact net position information and the gray histogram characteristics in the pole number identification; then, enhancing image information of the number plate area through self-adaption binaryzation, extracting a pole number frame through a thinning algorithm, and obtaining an accurate pole number area through linear detection and fine segmentation; and finally, optimally segmenting according to the image gray scale statistic value to accurately extract a single character image, and identifying characters to obtain the rod number digital information.
7. The image processing-based contact network fault identification method according to claim 1, characterized in that: the setting analysis component also comprises an integral gesture and hard points, wherein when the integral gesture is used for feature extraction, the Hough transformation is adopted to detect straight lines in the preprocessed image, and meanwhile, the detected straight lines are used for carrying out included angle operation; and when the hard points are subjected to feature extraction, detecting straight lines in the preprocessed images by adopting a Hough transformation detection principle, evaluating the sizes of bulges in the straight lines, and comparing the values of the bulges with given threshold values in a defect database.
8. The method for identifying the faults of the overhead line system based on the image processing according to any one of claims 1 to 7, wherein the method comprises the following steps: the image acquisition device is a camera, the angle of camera installation is 45 degrees for raising, the camera lens of camera is towards the contact net.
9. The utility model provides a contact net fault identification system based on image processing which characterized in that: including defect analysis platform and with defect analysis platform communication connection's data acquisition device and maintenance platform, data acquisition device is used for gathering the image information of contact net and uploads to defect analysis platform, defect analysis platform include algorithm analysis module and with algorithm analysis module communication connection's defect database, algorithm analysis module draws the characteristic of setting for the analysis component to graphical information, set for the analysis component the characteristic and carry out the comparison with the defect database, when arbitrary analysis component is unusual, defect analysis platform combines to generate positional information with GPS data and the time sequence table that corresponds to with positional information and unusual information generation defect report and upload to maintenance platform.
10. The image processing-based catenary fault identification system of claim 9, wherein: the defect analysis platform further comprises a mass data sample library, the algorithm analysis module can store the extracted characteristics of the set analysis component as samples in the mass data sample library, the mass data sample library is further in communication connection with the defect database, and the mass data sample library can update the samples in the mass data sample library to the defect database.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110937467.9A CN113657258A (en) | 2021-08-16 | 2021-08-16 | Contact network fault identification system and method based on image processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110937467.9A CN113657258A (en) | 2021-08-16 | 2021-08-16 | Contact network fault identification system and method based on image processing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113657258A true CN113657258A (en) | 2021-11-16 |
Family
ID=78491099
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110937467.9A Pending CN113657258A (en) | 2021-08-16 | 2021-08-16 | Contact network fault identification system and method based on image processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113657258A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114996258A (en) * | 2022-06-23 | 2022-09-02 | 中铁第四勘察设计院集团有限公司 | Contact network fault diagnosis method based on data warehouse |
CN117690096A (en) * | 2024-02-04 | 2024-03-12 | 成都中轨轨道设备有限公司 | Contact net safety inspection system adapting to different scenes |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102759347A (en) * | 2012-01-10 | 2012-10-31 | 广州科易光电技术有限公司 | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof |
CN104764748A (en) * | 2015-05-04 | 2015-07-08 | 成都唐源电气有限责任公司 | Method and system for positioning insulators and method and system for fault detection |
CN104794720A (en) * | 2015-05-04 | 2015-07-22 | 成都唐源电气有限责任公司 | Method and system for positioning steady ears in catenary images |
CN107895347A (en) * | 2017-07-20 | 2018-04-10 | 吉林大学 | A kind of vision self-adapting adjusting display device and method |
US20190222744A1 (en) * | 2016-09-12 | 2019-07-18 | Huawei Technologies Co., Ltd. | Image Photographing Method, Apparatus, and Terminal |
CN110135273A (en) * | 2019-04-19 | 2019-08-16 | 中铁第一勘察设计院集团有限公司 | Contact net video image cloud intellectual monitoring and fault recognition method |
CN111402241A (en) * | 2020-03-19 | 2020-07-10 | 中铁电气化局集团有限公司 | Processing method and device of contact network data, computer equipment and storage medium |
CN112288674A (en) * | 2019-07-11 | 2021-01-29 | 成都唐源电气股份有限公司 | Vehicle-mounted contact network component defect online identification method |
CN112288675A (en) * | 2019-07-11 | 2021-01-29 | 成都唐源电气股份有限公司 | Vehicle-mounted contact net component imaging processing method |
-
2021
- 2021-08-16 CN CN202110937467.9A patent/CN113657258A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102759347A (en) * | 2012-01-10 | 2012-10-31 | 广州科易光电技术有限公司 | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof |
CN104764748A (en) * | 2015-05-04 | 2015-07-08 | 成都唐源电气有限责任公司 | Method and system for positioning insulators and method and system for fault detection |
CN104794720A (en) * | 2015-05-04 | 2015-07-22 | 成都唐源电气有限责任公司 | Method and system for positioning steady ears in catenary images |
US20190222744A1 (en) * | 2016-09-12 | 2019-07-18 | Huawei Technologies Co., Ltd. | Image Photographing Method, Apparatus, and Terminal |
CN107895347A (en) * | 2017-07-20 | 2018-04-10 | 吉林大学 | A kind of vision self-adapting adjusting display device and method |
CN110135273A (en) * | 2019-04-19 | 2019-08-16 | 中铁第一勘察设计院集团有限公司 | Contact net video image cloud intellectual monitoring and fault recognition method |
CN112288674A (en) * | 2019-07-11 | 2021-01-29 | 成都唐源电气股份有限公司 | Vehicle-mounted contact network component defect online identification method |
CN112288675A (en) * | 2019-07-11 | 2021-01-29 | 成都唐源电气股份有限公司 | Vehicle-mounted contact net component imaging processing method |
CN111402241A (en) * | 2020-03-19 | 2020-07-10 | 中铁电气化局集团有限公司 | Processing method and device of contact network data, computer equipment and storage medium |
Non-Patent Citations (3)
Title |
---|
何钊: ""基于图像处理技术的腕臂式支持装置倾角自动检测研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 09, 15 September 2014 (2014-09-15) * |
杨亚明: ""基于OpenCV的绝缘子及等电位线故障状态智能识别"", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, no. 01, 15 January 2016 (2016-01-15), pages 27 * |
武翔宇: ""基于图像的接触网支柱检测与编号识别"", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 01, 15 January 2016 (2016-01-15) * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114996258A (en) * | 2022-06-23 | 2022-09-02 | 中铁第四勘察设计院集团有限公司 | Contact network fault diagnosis method based on data warehouse |
CN117690096A (en) * | 2024-02-04 | 2024-03-12 | 成都中轨轨道设备有限公司 | Contact net safety inspection system adapting to different scenes |
CN117690096B (en) * | 2024-02-04 | 2024-04-12 | 成都中轨轨道设备有限公司 | Contact net safety inspection system adapting to different scenes |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108037133B (en) | Intelligent electric power equipment defect identification method and system based on unmanned aerial vehicle inspection image | |
CN111322985B (en) | Tunnel clearance analysis method, device and system based on laser point cloud | |
CN102902974B (en) | Image based method for identifying railway overhead-contact system bolt support identifying information | |
CN110197176A (en) | Inspection intelligent data analysis system and analysis method based on image recognition technology | |
CN113657258A (en) | Contact network fault identification system and method based on image processing | |
CN109409404A (en) | A kind of high iron catenary radix saposhnikoviae bracing wire fault detection method based on deep learning | |
CN111260629A (en) | Pantograph structure abnormity detection algorithm based on image processing | |
CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
CN104764748A (en) | Method and system for positioning insulators and method and system for fault detection | |
Gao et al. | Detection and monitoring system of the pantograph-catenary in high-speed railway (6C) | |
CN111402214A (en) | Neural network-based automatic detection method for breakage defect of catenary dropper current-carrying ring | |
CN108846331B (en) | Video identification method for judging whether screw fastener of motor train unit chassis falls off or not | |
CN103745224A (en) | Image-based railway contact net bird-nest abnormal condition detection method | |
CN105741291A (en) | Method for detecting faults of equipotential lines of high-speed railway overhead line system suspension devices | |
CN104318582A (en) | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network on basis of image invariance target positioning | |
CN105354589A (en) | Method and system for intelligently identifying insulator crack in catenary image | |
Han et al. | High-speed railway rod-insulator detection using segment clustering and deformable part models | |
CN102538762A (en) | Online inspection device of high-speed railway contact network and inspection method of online inspection device as well as high-speed rail contact network detection system formed by online inspection device | |
CN112414309A (en) | High-speed rail contact line height-guiding and pull-out value inspection method based on airborne laser radar | |
CN109360188A (en) | A kind of detection method of high iron catenary equipotential line defective mode | |
CN111784656A (en) | Railway contact network fault detection method and device, electronic equipment and storage medium | |
CN111008587A (en) | Intelligent visual recognition system based on deep learning and applied to robot | |
CN108508023B (en) | Defect detection system for contact end jacking bolt in railway contact network | |
CN105528790A (en) | Transmission line small part identification method | |
CN114030395B (en) | Foreign matter detection method and system for contact suspension dropper area |
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 |