CN112001918A - AI algorithm based high-speed rail contact network equipment inspection method and system - Google Patents
AI algorithm based high-speed rail contact network equipment inspection method and system Download PDFInfo
- Publication number
- CN112001918A CN112001918A CN202011031247.1A CN202011031247A CN112001918A CN 112001918 A CN112001918 A CN 112001918A CN 202011031247 A CN202011031247 A CN 202011031247A CN 112001918 A CN112001918 A CN 112001918A
- Authority
- CN
- China
- Prior art keywords
- picture
- defect
- vehicle
- speed rail
- algorithm
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000007689 inspection Methods 0.000 title claims abstract description 25
- 230000007547 defect Effects 0.000 claims abstract description 65
- 238000012423 maintenance Methods 0.000 claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 230000002950 deficient Effects 0.000 claims description 9
- 238000012552 review Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 4
- 208000003464 asthenopia Diseases 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012212 insulator Substances 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
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening 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
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/725—Cordless telephones
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W76/00—Connection management
- H04W76/10—Connection setup
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30184—Infrastructure
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a high-speed rail contact net equipment inspection method based on an AI algorithm, which comprises the following steps: s1, carrying out picture data acquisition on a tower and a lead of the railway contact network; s2, intelligently analyzing the acquired picture data through an AI algorithm, and extracting suspected defect pictures; s3, marking and analyzing the position of the suspected defect by using an auxiliary analysis tool for the suspected defect picture, and judging whether the suspected defect picture is a defect; and S4, after the defect is judged, generating an overhaul list from the fault point information in the picture, and exporting the overhaul list to an overhaul worker for maintenance operation. According to the invention, the high-speed rail industry is enabled through an artificial intelligence technology, workers are assisted to detect the defects of the contact network, the workload is reduced, and the real-time performance of detection work is improved.
Description
Technical Field
The invention relates to the technical field of contact net detection, in particular to a high-speed rail contact net equipment inspection method and system based on an AI algorithm.
Background
The high-speed rail contact network is an important component of a high-speed rail electrical system, and bears an important power transmission task, if the contact network fails, the high-speed rail safety operation is seriously affected, a large area of delay is low, and a large number of lives and properties of people are lost, so that the prevention and the overhaul of the contact network failure by each railway administration are not lost. Therefore, related departments vigorously introduce high-speed rail maintenance vehicles, and the traditional inspection mode depending on manual inspection is gradually eliminated, so that the working environment and the working strength of maintenance personnel are greatly improved, pillar photos shot by the maintenance vehicles are centrally checked, field inspection is not needed, and field repair is only carried out after the defects are confirmed through the pictures. However, this advanced inspection method still has a large workload, taking the high-speed rail in kyu province as an example, the uplink and downlink completely complete one inspection, 400 thousands of photos can be generated, a large amount of manpower and a large amount of time are required for auditing, and the inspection center looks at the images for a long time and is easy to have visual fatigue and generate missed inspection, and besides the inspection task of the overhead contact network, other similar works exist in the inspection center, the inspection is completed at most once in a quarter with the current working efficiency, the fine-grained and high-frequency inspection for the overhead contact network is difficult, and the development of a high-speed rail safety monitoring system is seriously hindered.
The defect detection process of the contact network in the current market comprises the following steps of 1) inspecting the line by a maintenance vehicle according to a plan and taking a picture; 2) after the patrol work is completed, exporting the picture information by using a storage medium; 3) data is imported into auditing software, and the defect points are marked and stored by using a marking function provided by the software; 4) and (5) exporting the defect list, and handing over to a maintenance team for confirmation and repair.
The prior art has the following defects:
1. the image data is huge, large-scale human resources are invested, and other work is influenced;
2. the photos are continuously checked for a long time, so that visual fatigue is easy to occur, and some obvious serious defects are missed;
3. the defect analysis mode is originally inefficient, and many defects cannot be found and processed in time.
Disclosure of Invention
In order to solve the technical problems, the invention provides a high-speed rail overhead line system equipment inspection method and system based on an AI algorithm. In order to achieve the purpose, the technical scheme of the invention is as follows:
a high-speed rail contact network equipment inspection method based on an AI algorithm comprises the following steps:
s1, carrying out picture data acquisition on a tower and a lead of the railway contact network;
s2, intelligently analyzing the acquired picture data through an AI algorithm, and extracting suspected defect pictures;
s3, marking and classifying the positions of the suspected defects by using an auxiliary analysis tool for the suspected defect pictures
Analyzing and judging whether the defect exists;
and S4, after the defect is judged, generating an overhaul list from the fault point information in the picture, and exporting the overhaul list to an overhaul worker for maintenance operation.
Preferably, after S2, the method further includes the following steps: and performing frame pulling alarm on the fault point in the suspected defect picture, and prompting the corresponding fault position and fault type.
Preferably, after S3, the method further includes the following steps: and marking the pictures judged to be defective as non-defective, returning to the step S2 for rechecking, and judging whether the pictures are real defects.
Preferably, the picture data is obtained by regularly shooting towers and wires of the railway contact network through a camera array of the overhaul vehicle.
High-speed railway contact net equipment system of patrolling and examining based on AI algorithm includes: the system comprises a vehicle-mounted camera array, a vehicle-mounted video system, an auxiliary analysis server and a mobile terminal, wherein the vehicle-mounted camera array is electrically connected with the vehicle-mounted video system, the vehicle-mounted video system and the mobile terminal are in wireless communication connection with the auxiliary analysis server, wherein,
the vehicle-mounted camera array is used for collecting picture data of a tower and a lead of a railway contact network;
the vehicle-mounted video system is used for storing the picture data and uploading the picture data to an auxiliary analysis server;
the auxiliary analysis server comprises an analysis module, a detection module and a sending module, wherein,
the analysis module is used for intelligently analyzing the picture data and extracting suspected defect pictures;
the detection module is used for marking and analyzing the suspected defect picture and judging whether the picture is a defect picture;
the sending module is used for generating a maintenance list of the fault point information in the defect picture and sending the maintenance list to the mobile terminal;
and the mobile terminal is used for receiving the maintenance list for the maintenance personnel to check.
Preferably, the auxiliary analysis server further includes a review module, configured to mark the picture initially determined as a defect in the detection module as a non-defect picture, and send the non-defect picture to the analysis module for review.
Based on the technical scheme, the invention has the beneficial effects that:
1) the suspected defect data can be screened in a short time through an artificial intelligence technology, after screening is completed, the workload of workers is reduced by at least 10 times, the contact network defect detection is assisted by the workers, the workload is reduced, and the real-time performance of detection work is improved;
2) the rechecking function is used for carrying out secondary mutual inspection on the pictures which are judged as the defects for the first time, so that real defects are prevented from being missed, and the accuracy of defect detection is improved;
3) and after the defect detection is finished, generating a maintenance list in time and sending the maintenance list to a maintenance team group for maintenance, so that the maintenance efficiency is improved, and the safe operation and the driving protection of the electrified railway are realized.
Drawings
FIG. 1: the invention relates to a flow chart of a high-speed rail overhead line system equipment inspection method based on an AI algorithm;
FIG. 2: the invention discloses a structural block diagram of a high-speed rail overhead line system equipment inspection system based on an AI algorithm. In the figure, 1-vehicle camera array, 2-vehicle video system, 3-auxiliary analysis server, 301-analysis module, 302-detection module, 303-rechecking module, 304-sending module and 4-mobile terminal.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Example one
As shown in fig. 1, the method for inspecting the high-speed rail overhead line system equipment based on the AI algorithm includes the following steps:
s1, carrying out picture data acquisition on a tower and a lead of the railway contact network;
s2, intelligently analyzing the collected picture data through AI algorithm, and extracting suspected defect pictures (example)
Such as nut loosening, pin missing, dropper breaking, insulator breakage, etc.);
s3, extracting a corresponding support column number in the suspected defect picture based on machine vision, checking the suspected defect picture according to the support column number by using some auxiliary analysis tools by field workers, such as a part, a part position mark, a picture checking tool, a defect pre-marking and the like, quickly analyzing the position of the suspected defect, and judging whether the suspected defect is the defect;
and S4, after the defect is judged, generating an overhaul list from the fault point information in the picture, and exporting the overhaul list to an overhaul worker for maintenance operation.
Further, after S2, the method further includes the following steps: and performing frame pulling alarm on the fault point in the suspected defect picture, and prompting the corresponding fault position and fault type.
Further, after S3, the method further includes the following steps: and marking the pictures judged to be defective as non-defective, returning to the step S2 for rechecking, and judging whether the pictures are real defects.
Further, the picture data is obtained by regularly shooting towers and wires of the railway contact network through a camera array of the overhaul vehicle.
As shown in fig. 2, the AI algorithm-based high-speed rail catenary equipment inspection system includes: the system comprises a vehicle-mounted camera array 1, a vehicle-mounted video system 2, an auxiliary analysis server 3 and a mobile terminal 4, wherein the vehicle-mounted camera array 1 is electrically connected with the vehicle-mounted video system 2, the vehicle-mounted video system 2 and the mobile terminal 4 are in wireless communication connection with the auxiliary analysis server 3,
the vehicle-mounted camera array 1 is used for collecting picture data of a tower and a lead of a railway contact network;
the vehicle-mounted video system 2 is used for storing the picture data and uploading the picture data to an auxiliary analysis server;
the auxiliary analysis server 3 comprises an analysis module 301, a detection module 302 and a sending module 304, wherein,
the analysis module 301 is configured to perform intelligent analysis on the picture data and extract a suspected defect picture;
the detection module 302 is configured to mark and analyze the suspected defect picture, and determine whether the suspected defect picture is a defect picture;
the sending module 304 is configured to generate a maintenance list according to the fault point information determined as the defect picture, and send the maintenance list to the mobile terminal;
and the mobile terminal 4 is used for receiving the maintenance list for the maintenance personnel to check.
Further, the auxiliary analysis server further includes a review module 303, configured to mark the picture initially determined as a defect in the detection module 302 as a non-defect picture, and send the non-defect picture to the analysis module 301 for review.
The above description is only a preferred embodiment of the AI algorithm based inspection method for the high-speed rail catenary equipment disclosed in the present invention, and is not intended to limit the scope of protection of the embodiments of the present specification. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the embodiments of the present disclosure should be included in the protection scope of the embodiments of the present disclosure.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
It should also be noted that 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. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present specification are all described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Claims (6)
1. A high-speed rail overhead line system equipment inspection method based on an AI algorithm is characterized by comprising the following steps:
s1, carrying out picture data acquisition on a tower and a lead of the railway contact network;
s2, intelligently analyzing the acquired picture data through an AI algorithm, and extracting suspected defect pictures;
s3, marking and analyzing the position of the suspected defect by using an auxiliary analysis tool for the suspected defect picture, and judging whether the suspected defect picture is a defect;
and S4, after the defect is judged, generating an overhaul list from the fault point information in the picture, and exporting the overhaul list to an overhaul worker for maintenance operation.
2. The AI algorithm based high-speed rail catenary equipment inspection method according to claim 1, further comprising the following steps after S2: and performing frame pulling alarm on the fault point in the suspected defect picture, and prompting the corresponding fault position and fault type.
3. The AI algorithm based high-speed rail catenary equipment inspection method according to claim 1, further comprising the following steps after S3: and marking the pictures judged to be defective as non-defective, returning to the step S2 for rechecking, and judging whether the pictures are real defects.
4. The AI algorithm based high-speed rail catenary equipment inspection method according to claim 1, wherein the picture data is obtained by periodically shooting towers and wires of a railway catenary through a camera array of a maintenance vehicle.
5. High-speed railway contact net equipment system of patrolling and examining based on AI algorithm, its characterized in that includes: the system comprises a vehicle-mounted camera array, a vehicle-mounted video system, an auxiliary analysis server and a mobile terminal, wherein the vehicle-mounted camera array is electrically connected with the vehicle-mounted video system, the vehicle-mounted video system and the mobile terminal are in wireless communication connection with the auxiliary analysis server, wherein,
the vehicle-mounted camera array is used for collecting picture data of a tower and a lead of a railway contact network;
the vehicle-mounted video system is used for storing the picture data and uploading the picture data to an auxiliary analysis server;
the auxiliary analysis server comprises an analysis module, a detection module and a sending module, wherein,
the analysis module is used for intelligently analyzing the picture data and extracting suspected defect pictures;
the detection module is used for marking and analyzing the suspected defect picture and judging whether the picture is a defect picture;
the sending module is used for generating a maintenance list of the fault point information in the defect picture and sending the maintenance list to the mobile terminal;
and the mobile terminal is used for receiving the maintenance list for the maintenance personnel to check.
6. The AI-algorithm-based high-speed rail catenary equipment inspection system according to claim 5, wherein the auxiliary analysis server further comprises a review module for marking the picture initially determined as defective in the detection module as a non-defective picture and sending the non-defective picture to the analysis module for review.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011031247.1A CN112001918A (en) | 2020-09-27 | 2020-09-27 | AI algorithm based high-speed rail contact network equipment inspection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011031247.1A CN112001918A (en) | 2020-09-27 | 2020-09-27 | AI algorithm based high-speed rail contact network equipment inspection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112001918A true CN112001918A (en) | 2020-11-27 |
Family
ID=73475000
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011031247.1A Pending CN112001918A (en) | 2020-09-27 | 2020-09-27 | AI algorithm based high-speed rail contact network equipment inspection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112001918A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113525183A (en) * | 2021-07-29 | 2021-10-22 | 北京南凯自动化系统工程有限公司 | Railway contact net barrier cleaning system and method |
| CN114485575A (en) * | 2021-12-31 | 2022-05-13 | 中铁武汉电气化局集团有限公司 | Contact net dropper high-definition imaging device and using method thereof |
| CN114708484A (en) * | 2022-03-14 | 2022-07-05 | 中铁电气化局集团有限公司 | Pattern analysis method suitable for identifying defects |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105511495A (en) * | 2016-02-15 | 2016-04-20 | 国家电网公司 | Control method and system for intelligent unmanned aerial vehicle patrol for power line |
| CN110059631A (en) * | 2019-04-19 | 2019-07-26 | 中铁第一勘察设计院集团有限公司 | The contactless monitoring defect identification method of contact net |
| CN110197176A (en) * | 2018-10-31 | 2019-09-03 | 国网宁夏电力有限公司检修公司 | Inspection intelligent data analysis system and analysis method based on image recognition technology |
| CN111524114A (en) * | 2020-04-17 | 2020-08-11 | 哈尔滨理工大学 | Steel plate surface defect detection method based on deep learning |
| CN213182832U (en) * | 2020-09-27 | 2021-05-11 | 中铁电气化局集团有限公司 | AI algorithm-based high-speed rail contact network equipment inspection system |
-
2020
- 2020-09-27 CN CN202011031247.1A patent/CN112001918A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105511495A (en) * | 2016-02-15 | 2016-04-20 | 国家电网公司 | Control method and system for intelligent unmanned aerial vehicle patrol for power line |
| CN110197176A (en) * | 2018-10-31 | 2019-09-03 | 国网宁夏电力有限公司检修公司 | Inspection intelligent data analysis system and analysis method based on image recognition technology |
| CN110059631A (en) * | 2019-04-19 | 2019-07-26 | 中铁第一勘察设计院集团有限公司 | The contactless monitoring defect identification method of contact net |
| CN111524114A (en) * | 2020-04-17 | 2020-08-11 | 哈尔滨理工大学 | Steel plate surface defect detection method based on deep learning |
| CN213182832U (en) * | 2020-09-27 | 2021-05-11 | 中铁电气化局集团有限公司 | AI algorithm-based high-speed rail contact network equipment inspection system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113525183A (en) * | 2021-07-29 | 2021-10-22 | 北京南凯自动化系统工程有限公司 | Railway contact net barrier cleaning system and method |
| CN114485575A (en) * | 2021-12-31 | 2022-05-13 | 中铁武汉电气化局集团有限公司 | Contact net dropper high-definition imaging device and using method thereof |
| CN114708484A (en) * | 2022-03-14 | 2022-07-05 | 中铁电气化局集团有限公司 | Pattern analysis method suitable for identifying defects |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112001918A (en) | AI algorithm based high-speed rail contact network equipment inspection method and system | |
| CN110569841B (en) | Contact gateway key component target detection method based on convolutional neural network | |
| CN106771856B (en) | Electric power transmission line lightning stroke point determination method based on unmanned aerial vehicle technology | |
| CN109784138B (en) | Image datamation inspection method for unmanned transformer substation | |
| CN106327605A (en) | Inspection method | |
| CN104210500A (en) | Overhead lines suspension state detecting and monitoring device and working method thereof | |
| CN104978692A (en) | Handheld terminal collecting system | |
| CN109142978B (en) | Active monitoring method for running state of railway contact net | |
| CN110807460A (en) | Transformer substation intelligent patrol system based on image recognition and application method thereof | |
| CN104038373A (en) | Information early warning and self repairing system and method | |
| CN110942221A (en) | Transformer substation fault rapid repairing method based on Internet of things | |
| CN213182832U (en) | AI algorithm-based high-speed rail contact network equipment inspection system | |
| CN111509840A (en) | Wireless cluster visualization system and method based on power grid safety operation and maintenance | |
| CN115131505A (en) | Multi-system fusion's of transformer substation panorama perception system | |
| CN104902223A (en) | Fault monitoring system of power line | |
| CN110597130A (en) | Unattended substation remote information acquisition system | |
| CN112884174A (en) | Daily maintenance information management method and system for road | |
| CN112614245A (en) | Environmental sanitation operation vehicle monitoring and checking method based on GPS positioning | |
| CN105574872B (en) | The detection method of rail clip based on computer picture and visual identity | |
| CN116631087A (en) | Unmanned aerial vehicle-based electric power inspection system | |
| CN112150662A (en) | Power system inspection communication system and power system inspection method | |
| CN115880803A (en) | Intelligent inspection system and method | |
| CN113449767B (en) | Multi-image fusion transformer substation equipment abnormity identification and positioning method | |
| CN210428558U (en) | Intelligent auxiliary system for power optical cable inspection line | |
| CN112132819A (en) | Communication network management monitoring method based on artificial intelligence |
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 |