CN101699273A - Auxiliary detection device and method of image processing for on-line flaw detection of rails - Google Patents

Auxiliary detection device and method of image processing for on-line flaw detection of rails Download PDF

Info

Publication number
CN101699273A
CN101699273A CN200910236940A CN200910236940A CN101699273A CN 101699273 A CN101699273 A CN 101699273A CN 200910236940 A CN200910236940 A CN 200910236940A CN 200910236940 A CN200910236940 A CN 200910236940A CN 101699273 A CN101699273 A CN 101699273A
Authority
CN
China
Prior art keywords
rail
image
information
online
light source
Prior art date
Application number
CN200910236940A
Other languages
Chinese (zh)
Inventor
刘泽
王嵬
张广伟
Original Assignee
北京交通大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京交通大学 filed Critical 北京交通大学
Priority to CN200910236940A priority Critical patent/CN101699273A/en
Publication of CN101699273A publication Critical patent/CN101699273A/en

Links

Abstract

The invention relates to an auxiliary detection device and a method of image processing for the on-line flaw detection of rails. In the on-line running process of a train, an embedded type control system controls a light source excitation controller to enable two auxiliary light sources to irradiate the surfaces of rails, an industrial CCD line array camera collects image information at the surfaces of the rails by the control of a digital line array image collection interface, the information is transmitted to the embedded type system, and the embedded type system processes the collected rail image by an image processing technology; the flaw information and the inherent structure information of the surfaces of the rails are calculated from the processed rail image; then, the obtained flaw information of the surfaces of the rails is classified, and the flaw degree is calculated; and finally, the flaw classification and degree information is transmitted to an on-line rail flaw detection device by a communication interface, and then information integration is carried out on the transmitted information and a collection signal of the on-line rail flaw detection device, thereby reducing the interference degree of surface flaws to the on-line rail flaw detection device when detecting flaws inside the rails.

Description

A kind of Flame Image Process auxiliary detection device and method of online rail examination
Technical field
The present invention relates to a kind of Flame Image Process auxiliary detection device and method of online rail examination.
Background technology
The intrinsic geometry of rail and surface damage are very big to the testing result influence of online rail examination, make the severely injured failure detector of online rail can't distinguish the twist irregularity on rail inner core wound and rail surface and peel off the piece situation.The intrinsic geometry of rail and surface damage are not only influential to the rail examination equipment of electromagnetic principle, rail examination equipment to ultrasonic principle has considerable influence equally, because ultrasonic inspection needs sensor and rail closely connected, the degree of coupling of its surface in contact directly influences result of detection.So a problem that must solve is how to remove the influence that causes when the intrinsic geometry of rail and surface damage are surveyed the rail internal injury to online rail examination equipment.
Traditional solution is: for UT (Ultrasonic Testing), increase the coupling exposure level on ultrasonic probe and rail surface, add couplant; For electromagnetic method is the requirement surfacing, even requires surface finish.Like this, inconvenient operation not only, efficient is low, and has increased operating cost.
Summary of the invention
The Flame Image Process auxiliary detection device and the method that the purpose of this invention is to provide a kind of online rail examination, the influence that causes when online rail examination equipment being surveyed the rail internal injury with the intrinsic geometry of eliminating rail and surface damage, and improved operability, improve work efficiency, reduced operating cost.
According to an aspect of the present invention, provide a kind of Flame Image Process auxiliary detection device of online rail examination, the Flame Image Process auxiliary detection device of described online rail examination comprises: industrial CCD line array video camera, secondary light source, control cabinet; Comprise embedded system, system power supply, communication interface, light source excitation controller, linear array images acquisition interface in the control cabinet.Wherein, described industrial CCD line array video camera is connected with the linear array images acquisition interface; Secondary light source is connected with the light source excitation controller; System power supply, communication interface, light source excitation controller, digital linear array images acquisition interface are connected with embedded system respectively.
Preferably, described industrial CCD line array video camera comprises linear array charge-coupled device ccd sensor, camera lens and data transmission interface.Preferably, described control cabinet is installed on the below on train chassis.
Preferably, described embedded system comprises embedded microprocessor, constitutes the peripheral interface circuit of microprocessor system and field programmable logic array (FPLA) (FPGA) chip of auxiliary raising Digital Image Processing speed.
According to another aspect of the present invention, a kind of Flame Image Process aided detection method of online rail examination is provided, the Flame Image Process aided detection method performing step of described online rail examination comprises: the first step, in train on-line operation process, embedded control system control light source excitation controller makes two secondary light source irradiation rail surfaces, and the industrial CCD line array video camera is gathered the image information on rail surface by the control of digital linear array images acquisition interface.Second step, digital linear array images acquisition interface are transferred to embedded system with image information.The 3rd step, embedded system use image processing techniques that the rail image that collects is handled; The damage information and the inherent structure information on statistics rail surface the rail image after handling.The 4th step, embedded system is further classified the rail surface damage information that is obtained and degree of injury calculates.The 5th the step, embedded system will damage classified information and degree of injury information is transferred to online rail failure sniffer by communication interface.The 6th step, embedded system institute's information transmitted and online rail failure sniffer acquired signal are carried out information fusion, thereby reduce the annoyance level that is subjected to surface damage when online rail failure sniffer detects the rail internal injury.
Preferably, the image processing techniques in described the 3rd step comprises rail rail gap recognition technology and rail surface defects recognition technology, and the information fusion in described the 6th step is handled and comprised weighting fusion method and system function fusion method.
The present invention obtains the information on rail surface with the method for video identification, uses the information fusion of these information and severely injured acquisition sensor then, thereby the information that reduces surface imperfection is disturbed.
Beneficial effect of the present invention is: used linear array CCD image acquisition technique, digital image processing techniques and information fusion method, solved the problem that is subjected to the intrinsic geometry of track when online rail examination device is surveyed the rail inherent vice and shows the interference of defective, made online rail examination device can directly export the severely injured situation of rail that track traffic is had big potential hazard.The advantage of high speed rail inspection technique is onlinely to use, can in time find severely injured rail, so there is important use to be worth, but because high speed rail failure detector need be equipped on the train of high-speed cruising, so its sensing mode must adopt non-contacting mode, it is inner severely injured that this mode is responded to rail, is very easy to be subjected to the influence of intrinsic geometry of rail and surface damage, and the Flame Image Process householder method of online rail examination efficiently solves this difficult problem.
Description of drawings
Fig. 1 is the overall construction drawing of the Flame Image Process auxiliary detection device of online rail examination of the present invention.
Fig. 2 is the installation site and the connection diagram of the Flame Image Process auxiliary detection device of online rail examination.
Embodiment
Details are as follows to embodiments of the invention below in conjunction with accompanying drawing:
As shown in Figure 1, a kind of Flame Image Process auxiliary detection device of online rail examination comprises industrial CCD line array video camera 206, secondary light source 207,208, control cabinet 107; Comprise embedded system 204, system power supply 202, communication interface 201, light source excitation controller 203, digital linear array images acquisition interface 205 in the control cabinet.Wherein, described industrial CCD line array video camera 206 is connected with linear array images acquisition interface 205; Secondary light source 207,208 is connected with light source excitation controller 203; System power supply 202, communication interface 201, light source excitation controller 203, digital linear array images acquisition interface 205 are connected with embedded system 204 respectively.Wherein:
Industrial CCD line array video camera 206: be used to gather intrinsic geometry information of rail and surface imperfection information, use the linear array acquisition mode, gather the digital image information that is obtained and be transferred to digital linear array images acquisition interface 205 by telecommunication cable 307.
Secondary light source 207,208: the auxiliary light filling when being used to industrial CCD line array video camera 206 that images acquired is provided, use highlighted led array as light source.Be connected with 307 by lead 306 with light source excitation controller 203.
Control cabinet 107: be connected with the train chassis, inside comprises embedded system 204, system power supply 202, communication interface 201, light source excitation controller 203, digital linear array images acquisition interface 205.
Embedded system 204: be used to control image acquisition, processing and information output, inside comprises embedded microprocessor, Flame Image Process on-site programmable gate array FPGA chip.Be connected by lead 302 with communication interface 201; Be connected by lead 303 with light source excitation controller 203; Be connected by lead 304 with digital linear array images acquisition interface 205.
System power supply 202: for each electronic equipment in the cabinet of control, secondary light source 207 and 208 and industrial CCD line array video camera 206 power supply is provided.
Communication interface 201: be used for the output of the fusion information that obtains after the Flame Image Process.
Light source excitation controller 203: under the control of embedded system 204, output control signal, the light intensity of regulating secondary light source 207,208.
Numeral linear array images acquisition interface 205: the output digital image information that is used to transmit industrial CCD line array video camera 206.
Fig. 2 is installation site and the connection diagram of device of the present invention in the train bottom, and in Fig. 2, control cabinet 107, online rail failure sniffer 104 are connected with railway car 101 with image Auxiliary Processing Unit 105; Image Auxiliary Processing Unit 105 be installed on train wheel 102 and bogie 103 near, near a side of center compartment.Wherein:
Railway car 101: being the installation carrier of the Flame Image Process auxiliary detection device of described a kind of online rail examination, can be passenger car or freight compartment.
Wheel 102: be train wheel, diagram is in order to illustrate the installation site of Flame Image Process auxiliary detection device of described a kind of online rail examination herein.
Bogie 103: the link that is wheel and compartment.
Online rail failure sniffer 104: being to finish the device that rail failure is surveyed when being used for the train on-line operation, is the Flame Image Process auxiliary detection device output intrinsic geometry of rail of described a kind of online rail examination and the receiving trap of surface damage information.
Image Auxiliary Processing Unit 105: the i.e. Flame Image Process auxiliary detection device of described online rail examination.
Rail 106: the employed steel track of track traffic generally has manganese steel to make.
In Fig. 3, a kind of Flame Image Process aided detection method of online rail examination, it is as follows that it implements process description:
1) system initialization is provided with embedded system 204 running parameters, by light source excitation controller 203 excitation secondary light sources 207 and 208.
2) by digital linear array images acquisition interface 205 acquisition rate and the linear resolution of industrial CCD line array video camera 206 are set by embedded system 204, industrial CCD line array video camera 206 begins to gather the image information on rail surface.
3) industrial CCD line array video camera 206 is exported the linear array pixel data continuously, and embedded system 204 synthesizes consecutive image with the linear array pixel sequence, and is grouped into face battle array gray level image.
4) the face system of battle formations picture after will dividing into groups is parallel carries out two kinds of computings: identification rail gap and rail level defect analysis.Wherein the rail gap recognition methods comprises: the face system of battle formations after the grouping is as rim detection, and image column is to the gray average vector calculation, and image column is calculated the rail gap information extraction to gray average vector first order derivative and second derivative; The rail level defect analysis comprises: the face system of battle formations image intensifying after the grouping is handled, image smoothing, and the image threshold processing, image boundary suppresses, and calculates rail surface damage degree information.
5) information classification of rail surface image and degree of injury calculate.
6) export to online rail failure sniffer by communication interface 201, return step 3 circular treatment then.

Claims (7)

1. the Flame Image Process auxiliary detection device of an online rail examination, it is characterized in that: described pick-up unit comprises: industrial CCD line array video camera (206), secondary light source (207,208), control cabinet (107); Comprise embedded system (204), system power supply (202), communication interface (201), light source excitation controller (203), digital linear array images acquisition interface (205) in the control cabinet, described industrial CCD line array video camera (206) is connected with linear array images acquisition interface (205); Secondary light source (207,208) is connected with light source excitation controller (203); System power supply (202), communication interface (201), light source excitation controller (203), digital linear array images acquisition interface (205) are connected with embedded system (204) respectively.
2. the Flame Image Process auxiliary detection device of online rail examination according to claim 1, it is characterized in that: described control cabinet (107) is installed on the train bottom, control cabinet (107) is near a side mounting industrial CCD line array video camera (206) and the secondary light source (207,208) of rail.
3. the Flame Image Process auxiliary detection device of online rail examination according to claim 1, it is characterized in that: described embedded system (204) is made of embedded microprocessor and field programmable logic array (FPLA) FPGA.
4. the Flame Image Process aided detection method of an online rail examination, it is characterized in that: described detection method comprises the steps:
1) system initialization is provided with embedded system (204) running parameter, by light source excitation controller (203) excitation secondary light source (207,208);
2) by digital linear array images acquisition interface (205) acquisition rate and the linear resolution of industrial CCD line array video camera (206) are set by embedded system (204), industrial CCD line array video camera (206) begins to gather the image information on rail surface;
3) industrial CCD line array video camera (206) is exported the linear array pixel data continuously, and embedded system (204) synthesizes consecutive image with the linear array pixel sequence, and is grouped into face battle array gray level image;
4) the face system of battle formations picture after will dividing into groups is parallel carries out two kinds of computings: identification rail gap and rail level defect analysis, wherein, the rail gap recognition methods comprises: the face system of battle formations after the grouping is as rim detection, image column is to the gray average vector calculation, image column is calculated the rail gap information extraction to gray average vector first order derivative and second derivative; The rail level defect analysis comprises: the face system of battle formations image intensifying after the grouping is handled, image smoothing, and the image threshold processing, image boundary suppresses, and calculates rail surface damage degree information;
5) information classification of rail surface image and degree of injury calculate;
6) export to online rail failure sniffer by communication interface (201), return step 3 circular treatment then.
5. the Flame Image Process aided detection method of online rail examination according to claim 4, it is characterized in that: described industrial CCD line array video camera (206) is exported the linear array pixel data continuously, be meant the image information of industrial CCD line array video camera (206) with the rail surface of train operation online acquisition, acquisition mode is the linear array form.
6. the Flame Image Process aided detection method of online rail examination according to claim 4, it is characterized in that: described rail surface damage information comprises pitting, scalelike mark and the crackle on rail surface.
7. the Flame Image Process aided detection method of online rail examination according to claim 4 is characterized in that: described online rail failure sniffer comprises based on the online rail examination device of electromagnetic method with based on the online rail examination device of ultrasonic technology.
CN200910236940A 2009-10-29 2009-10-29 Auxiliary detection device and method of image processing for on-line flaw detection of rails CN101699273A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN200910236940A CN101699273A (en) 2009-10-29 2009-10-29 Auxiliary detection device and method of image processing for on-line flaw detection of rails

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN200910236940A CN101699273A (en) 2009-10-29 2009-10-29 Auxiliary detection device and method of image processing for on-line flaw detection of rails

Publications (1)

Publication Number Publication Date
CN101699273A true CN101699273A (en) 2010-04-28

Family

ID=42147736

Family Applications (1)

Application Number Title Priority Date Filing Date
CN200910236940A CN101699273A (en) 2009-10-29 2009-10-29 Auxiliary detection device and method of image processing for on-line flaw detection of rails

Country Status (1)

Country Link
CN (1) CN101699273A (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AT509607A4 (en) * 2010-12-13 2011-10-15 Ait Austrian Inst Technology Method and device for detecting surface failures
CN102438356A (en) * 2011-09-20 2012-05-02 株洲南车时代电气股份有限公司 Light source regulating device and method
CN102507587A (en) * 2011-09-20 2012-06-20 株洲南车时代电气股份有限公司 Perambulated inspection system and method
CN102565068A (en) * 2011-12-12 2012-07-11 关持循 Steel rail damage automatic detection device
CN103884719A (en) * 2012-12-21 2014-06-25 鞍钢股份有限公司 Image acquisition and preprocessing method based on embedded steel plate surface quality detection system
CN104237381A (en) * 2014-10-15 2014-12-24 北京新联铁科技股份有限公司 Steel rail flaw-detection method based on laser ultrasonic and high-speed photography image fusion
CN104792789A (en) * 2015-04-08 2015-07-22 上海常良智能科技有限公司 Chemical fiber paper tube appearance detection device and method
CN106290379A (en) * 2016-08-30 2017-01-04 哈尔滨工业大学(威海) Rail surface defects based on Surface scan camera detection device and method
CN107727660A (en) * 2017-10-13 2018-02-23 浙江树人学院 Rail surface defects detecting system and method based on machine vision and impulse eddy current
CN108416766A (en) * 2018-01-31 2018-08-17 浙江理工大学 Bilateral incidence type light guide plate defective vision detection method
CN109490416A (en) * 2018-12-10 2019-03-19 上海市东方海事工程技术有限公司 A kind of weld joint recognition method applied to double rail type rail examination
CN110987942A (en) * 2019-12-04 2020-04-10 联想(北京)有限公司 Electronic device and machine vision system

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AT509607A4 (en) * 2010-12-13 2011-10-15 Ait Austrian Inst Technology Method and device for detecting surface failures
AT509607B1 (en) * 2010-12-13 2011-10-15 Ait Austrian Inst Technology Method and device for detecting surface failures
CN102438356A (en) * 2011-09-20 2012-05-02 株洲南车时代电气股份有限公司 Light source regulating device and method
CN102507587A (en) * 2011-09-20 2012-06-20 株洲南车时代电气股份有限公司 Perambulated inspection system and method
CN102438356B (en) * 2011-09-20 2013-11-27 株洲时代电子技术有限公司 Light source regulating device and method
CN102507587B (en) * 2011-09-20 2013-11-27 株洲时代电子技术有限公司 Perambulated inspection system and method
CN102565068A (en) * 2011-12-12 2012-07-11 关持循 Steel rail damage automatic detection device
CN103884719A (en) * 2012-12-21 2014-06-25 鞍钢股份有限公司 Image acquisition and preprocessing method based on embedded steel plate surface quality detection system
CN104237381A (en) * 2014-10-15 2014-12-24 北京新联铁科技股份有限公司 Steel rail flaw-detection method based on laser ultrasonic and high-speed photography image fusion
CN104792789A (en) * 2015-04-08 2015-07-22 上海常良智能科技有限公司 Chemical fiber paper tube appearance detection device and method
CN106290379A (en) * 2016-08-30 2017-01-04 哈尔滨工业大学(威海) Rail surface defects based on Surface scan camera detection device and method
CN107727660A (en) * 2017-10-13 2018-02-23 浙江树人学院 Rail surface defects detecting system and method based on machine vision and impulse eddy current
CN108416766A (en) * 2018-01-31 2018-08-17 浙江理工大学 Bilateral incidence type light guide plate defective vision detection method
CN109490416A (en) * 2018-12-10 2019-03-19 上海市东方海事工程技术有限公司 A kind of weld joint recognition method applied to double rail type rail examination
CN110987942A (en) * 2019-12-04 2020-04-10 联想(北京)有限公司 Electronic device and machine vision system

Similar Documents

Publication Publication Date Title
US9908543B2 (en) System and method for inspecting a route during movement of a vehicle system over the route
CN103144937B (en) System and method for intelligently monitoring belt-type conveyer for coal mine steel wire rope core
CN102788803B (en) On-line high-speed detection system of train wheel set tread and wheel rim and detection method thereof
Yang et al. On-line conveyor belts inspection based on machine vision
CN101893580B (en) Digital image based detection method of surface flaw of steel rail
KR101111569B1 (en) Monitering System of Railroad Facilities using Railway Vehicle
CN102129564B (en) Contact network failure detection and diagnosis method based on unmanned aerial vehicle
CN102923164B (en) High-speed rail health monitoring system based on ultrasonic guide wave and wireless network
CN106192634B (en) A kind of railroad track elastic bar fastener condition automatic detection device and method
CN204974510U (en) Food processing lines developments quality detecting and automatic grading plant of weight
CN106394606B (en) A kind of railway car wheel loses circle detection method and detection device
EP1236634A1 (en) Method and apparatus for determining track condition
CN102495078B (en) Method for detecting welding seam on basis of quantum dot infrared fluorescence display technology
CN103048330B (en) The visual sniffer of a kind of surface crack of underwater structure
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
CN204556257U (en) A kind of rolling stock rolling bearing acoustic diagnostic instrument
CN102721700B (en) System and method for high-speed detection of loosening of railway fasteners on basis of infrared thermal imaging
Aydin et al. A new contactless fault diagnosis approach for pantograph-catenary system
CN201429413Y (en) Pantograph performance on-line automatic detection system for high-speed trains
CN203376271U (en) Machine vision-based non-continuous product online detection system
CN2795852Y (en) Automatic detector for glazed tile surface property
CN104502451A (en) Method for identifying flaw of steel plate
CN101986143A (en) Machine vision belt tear detection and protective device
CN103364400A (en) Multistation intelligent syncretic bottled beer online detection device
CN103322936A (en) Wheel set size on-line monitoring method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20100428