CN103308593A - Defect intelligent identification detection system for magnetic powder welding flaw detection - Google Patents
Defect intelligent identification detection system for magnetic powder welding flaw detection Download PDFInfo
- Publication number
- CN103308593A CN103308593A CN 201210057960 CN201210057960A CN103308593A CN 103308593 A CN103308593 A CN 103308593A CN 201210057960 CN201210057960 CN 201210057960 CN 201210057960 A CN201210057960 A CN 201210057960A CN 103308593 A CN103308593 A CN 103308593A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- detection
- defect
- parameter
- 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
Images
Abstract
The invention discloses a defect intelligent identification detection system for magnetic powder welding flaw detection. In the system, a man-machine interface module coordinates all the works of all modules to make the system run in an ordered manner, is the control center of the system, and controls the image acquisition, processing, display, alarming, communication and the like, a friendly interface is a very important design portion of the system, and the above works are completed by the man-machine interface module. An image acquisition module, a processing module and a display alarming module are the most basic and core portions, and realize the detection work of the crack defects of a workpiece under the coordinative control of the man-machine interface module.
Description
Technical field
The present invention relates to a kind of magnetic welding flaw detection nondestructive detection system, particularly a kind of defect intelligent identification detection system of magnetic welding flaw detection.
Background technology
By in magnetic welding fault detection system, introducing image processing techniques, the surface of the work image of taking is processed, can realize the automatic detection identification of defective, the intellectuality of realization system, the defective of having avoided the human factors such as eye-observation fatigue to cause is judged by accident, is failed to judge, reduce labor intensity, can also guarantee to differentiate defective in quantity, size and locational consistance, improve the accuracy and the reliability that detect.
The defect image recognition system of perfect in shape and function mainly is comprised of following part: image pre-service, image segmentation, feature extraction and defect recognition.By the image scene that gathers is analyzed, can carry out pre-service to image by methods such as gray scale transformation, image smoothing, edge sharpenings, to improve original image quality, be conducive to subsequent processes, use appropriate algorithm to cut apart to pretreated image, and extract features relevant and carry out the identification of defective.
Yet the complicacy of surface of the work image, the weak signal of crackle are so that there are many insoluble problems in this research.
For these problems that exist in the magnetic welding detection defects recognition system, need to further study the performance characteristic of soldered flaw detection workpiece (workpiece is train wheel in the native system) surface image, analyzing defect, false defect and background different manifestations feature and the external environment in image, the impact that the factors such as workpiece motion s cause imaging, study on this basis suitable Processing Algorithm, and with algorithm application in image processing module, finish the image processing techniques research of magnetic welding flaw detection intelligent identification detection system, make system satisfy the online purpose that detects in real time defect recognition, and reach the requirement of high discrimination.Gordian technique wherein has: the workpiece image analytical technology; Surface Flaw and false defect Signature Analysis Techique; Workpiece image cutting techniques under the complex environment; The recognition technology of workpiece, defect.
Summary of the invention
The object of the present invention is to provide a kind of defect intelligent identification detection system of magnetic welding flaw detection, it mainly is comprised of the communication module of image capture module, processing module, human-machine interface module, display alarm module and system and rotating platform control system.
The technical scheme of the object of the invention is:
A kind of defect intelligent identification detection system of magnetic welding flaw detection, this detection system is used for the magnetic welding flaw detection of railway wheel, carry out online in real time detection, comprise image capture module, image processing module, human-machine interface module, display alarm module and the communication module that communicates with rotating platform control system.
The method that system of the present invention examines the identification survey may further comprise the steps:
During for the first time start operation, in the test piece of surface of the work attach both standard crackle, gather the test piece image by CCD, observation shows and treatment effect, adjusts the CCD parameter, comprises time shutter, gain, until obtain satisfied effect;
After the CCD parameter adjustment was finished, start operation next time just can be adopted the parameter after the adjustment;
Formally carry out surface defects detection, gather the surface of the work image by CCD, view data is stored among the Memory1, wait until subsequent processes and show and use;
Image processing module is processed the image among the Memory1, and result is stored among the Memory2, comprises defective locations and feature, and whether defective information passes to the parameter control module with surface of the work; The parameter control module shows and alarm module according to the output control of image processing module, finishes last display alarm; After said process is finished, wait for next workpiece, the duplicate detection step.
The processing procedure of image processing module of the present invention comprises pre-service, cuts apart, the step of feature extraction, defect recognition and result's output; At first, carry out image segmentation, cut apart finish after, on the basis of analyzing the crack defect feature, extract the feature of the connected domain of cutting apart rear image, these features input identification modules, finish the identification of crack defect, export at last recognition result.
The present invention compared with prior art, its remarkable advantage:
(1) improvement of partitioning algorithm.Being based upon on the reasonable assumption to the crackle defect characteristic based on the partitioning algorithm of multiple piecemeal extreme value, having utilized the priori to crack defect, is the good partitioning algorithm of a kind of effect.
(2) system operating mode is improved (employing stepper motor), algorithm is improved (increasing Grad information in feature) afterwards, the other problem that system runs into, cause the problems such as false-alarm such as kinetic image blur, imaging region selection, pseudo-Signal of Cracks, obtained good solution.
Below in conjunction with accompanying drawing the present invention is described in further detail.
Four description of drawings
The defect intelligent identification detection system block diagram of Fig. 1 magnetic welding flaw detection
Fig. 2 working-flow figure
Five embodiments
A kind of defect intelligent identification detection system of magnetic welding flaw detection is used for online the detection in real time of the magnetic welding flaw detection of railway wheel, mainly the communication module by image capture module, processing module, human-machine interface module, display alarm module and system and rotating platform control system forms, and the functional block diagram of system as shown in Figure 1.
System work process is as follows: during for the first time start operation, in the test piece of surface of the work attach both standard crackle, gather the test piece image by CCD, observation shows and treatment effect, adjusts CCD parameter (such as time shutter, gain etc.) until obtain satisfied effect; After the CCD parameter adjustment was finished, start operation next time just can be adopted the parameter after the adjustment, need not each start and all carries out the parameter setting; Formally carry out surface defects detection, gather the surface of the work image by CCD, view data is stored among the Memory1, wait until subsequent processes and show and use; Processing module is processed the image among the Memory1, result (such as defective locations, feature etc.) is stored among the Memory2, and whether defective information passes to the parameter control module with surface of the work; The parameter control module shows and alarm module according to the output control of processing module, finishes last display alarm; After said process is finished, wait for next workpiece, the duplicate detection step.
The workflow of system is considered the actual conditions on the workpiece sensing streamline as shown in Figure 2, and actual workflow is as follows:
(1) the i.e. operation of start detects software, enters the last time default setting of test, and default setting comprises camera parameter (brightness, gain, time shutter etc.), process module parameter (crackle alarm threshold, actual treatment zone etc.).
(2) workpiece is waited in parameter setting (with A1 type test piece testing condition, such as uviol lamp light intensity, MPI fluorescent magnetic particles lamp utility appliance, arranging according to practical work piece of camera parameter, process module parameter detects the needs setting).
When (3) workpiece arrived, " image acquisition is finished " message of this position can trigger the Electric Machine Control program and send " turntable rotation " instruction, turn to the next position after, " image acquisition preparation " instruction of Electric Machine Control procedure triggers reposition.
(4) image acquisition, demonstration.System triggers the surface image that 4 road cameras gather respectively the workpiece diverse location after receiving " image acquisition preparation " instruction of Electric Machine Control program transmission, and system sends the message of " image acquisition is complete " to the Electric Machine Control program.After the Electric Machine Control program received the message of " image acquisition is complete ", the control turntable began to rotate, and after stopping operating, the Electric Machine Control program sends the message of " can gather image " to native system.After system receives this message, repeat said process.So circulation is 8 times, stores in the storer at 8 diverse locations collection workpiece images and with the image information that collects, and shows simultaneously.
(5) the backstage image is processed.Gather image and only need to spend seldom CPU time, system is in the backstage reading images and process, and image and defect information store for playback and show after will processing.
(6) result shows, reports to the police.If detect crack defect, then send warning message.
(7) suspicious picture playback shows.System provides the function of the suspicious picture of playback for operating personnel, after finishing dealing with, operating personnel can access as required result and show, for manual observation.
Wait for next workpiece.After 8 width of cloth images of 4 road cameras were all finished dealing with, system sent the message of " waiting for next workpiece " to the turntable control program, allow the arrival of next workpiece.Forward step (3) to, begin the detection of next workpiece.
Claims (3)
1. a magnetic welds the defect intelligent identification detection system of flaw detection, it is characterized in that: this detection system is used for the magnetic welding flaw detection of railway wheel, carry out online in real time detection, comprise image capture module, image processing module, human-machine interface module, display alarm module and the communication module that communicates with rotating platform control system.
2. a kind of magnetic according to claim 1 welds the defect intelligent identification detection system of flaw detection, it is characterized in that system examines the method for identifying survey and may further comprise the steps:
During for the first time start operation, in the test piece of surface of the work attach both standard crackle, gather the test piece image by CCD, observation shows and treatment effect, adjusts the CCD parameter, comprises time shutter, gain, until obtain satisfied effect;
After the CCD parameter adjustment was finished, start operation next time just can be adopted the parameter after the adjustment;
Formally carry out surface defects detection, gather the surface of the work image by CCD, view data is stored among the Memory1, wait until subsequent processes and show and use;
Image processing module is processed the image among the Memory1, and result is stored among the Memory2, comprises defective locations and feature, and whether defective information passes to the parameter control module with surface of the work; The parameter control module shows and alarm module according to the output control of image processing module, finishes last display alarm; After said process is finished, wait for next workpiece, the duplicate detection step.
3. the defect intelligent identification detection system of a kind of magnetic welding flaw detection according to claim 1 is characterized in that: the processing procedure of image processing module comprises pre-service, cuts apart, the step of feature extraction, defect recognition and result's output; At first, carry out image segmentation, cut apart finish after, on the basis of analyzing the crack defect feature, extract the feature of the connected domain of cutting apart rear image, these features input identification modules, finish the identification of crack defect, export at last recognition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201210057960 CN103308593A (en) | 2012-03-07 | 2012-03-07 | Defect intelligent identification detection system for magnetic powder welding flaw detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201210057960 CN103308593A (en) | 2012-03-07 | 2012-03-07 | Defect intelligent identification detection system for magnetic powder welding flaw detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103308593A true CN103308593A (en) | 2013-09-18 |
Family
ID=49134045
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201210057960 Pending CN103308593A (en) | 2012-03-07 | 2012-03-07 | Defect intelligent identification detection system for magnetic powder welding flaw detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103308593A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106881462A (en) * | 2017-01-23 | 2017-06-23 | 华中科技大学 | A kind of on-line checking for selective laser fusing forming defects and optimization system |
| CN108844965A (en) * | 2018-07-04 | 2018-11-20 | 武汉黎赛科技有限责任公司 | Defect image acquires display system, method, apparatus, computer and storage medium |
| CN112229899A (en) * | 2020-09-29 | 2021-01-15 | 深圳市人工智能与机器人研究院 | Defect detection method of ferromagnetic component and related equipment |
| CN112345547A (en) * | 2020-10-29 | 2021-02-09 | 东方蓝天钛金科技有限公司 | Fluorescent inspection visual data processing system based on MES and processing method thereof |
| CN112508891A (en) * | 2020-11-27 | 2021-03-16 | 济宁鲁科检测器材有限公司 | AI intelligent defect identification magnetic powder flaw detection system based on mobile phone and method thereof |
| CN112601938A (en) * | 2018-04-17 | 2021-04-02 | 伊利诺斯工具制品有限公司 | System and method for non-destructive testing using custom quality control tasks |
-
2012
- 2012-03-07 CN CN 201210057960 patent/CN103308593A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106881462A (en) * | 2017-01-23 | 2017-06-23 | 华中科技大学 | A kind of on-line checking for selective laser fusing forming defects and optimization system |
| CN112601938A (en) * | 2018-04-17 | 2021-04-02 | 伊利诺斯工具制品有限公司 | System and method for non-destructive testing using custom quality control tasks |
| US11867774B2 (en) | 2018-04-17 | 2024-01-09 | Illinois Tool Works Inc. | Systems and methods to use customized quality control tasks for non-destructive testing |
| CN108844965A (en) * | 2018-07-04 | 2018-11-20 | 武汉黎赛科技有限责任公司 | Defect image acquires display system, method, apparatus, computer and storage medium |
| CN112229899A (en) * | 2020-09-29 | 2021-01-15 | 深圳市人工智能与机器人研究院 | Defect detection method of ferromagnetic component and related equipment |
| CN112345547A (en) * | 2020-10-29 | 2021-02-09 | 东方蓝天钛金科技有限公司 | Fluorescent inspection visual data processing system based on MES and processing method thereof |
| CN112508891A (en) * | 2020-11-27 | 2021-03-16 | 济宁鲁科检测器材有限公司 | AI intelligent defect identification magnetic powder flaw detection system based on mobile phone and method thereof |
| CN112508891B (en) * | 2020-11-27 | 2022-07-22 | 济宁鲁科检测器材有限公司 | AI intelligent defect identification magnetic powder flaw detection system based on mobile phone and method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022062812A1 (en) | Screen defect detection method, apparatus, and electronic device | |
| CN103308593A (en) | Defect intelligent identification detection system for magnetic powder welding flaw detection | |
| CN102590330A (en) | Image processing-based magnetic particle inspection defect intelligent identification detection system | |
| CA3098154A1 (en) | System and method for performing automated analysis of air samples | |
| CN101509766B (en) | On-line detecting method for spring end plane angle by machine vision system | |
| CN108760747A (en) | A kind of 3D printing model surface defect visible detection method | |
| CN103808730B (en) | Engine cam component surface defect inspection method | |
| CN103785622B (en) | Based on the part method for sorting of the part sorting equipment of machine vision | |
| CN103020590B (en) | A kind of vehicle identification system based on three-dimensional model and images match and method thereof | |
| CN205538710U (en) | Inductance quality automatic check out system based on machine vision | |
| CN109060826B (en) | Wind-powered electricity generation blade detection device that does not shut down | |
| WO2012027869A1 (en) | Online quality detection method for closure assembly | |
| CN110441316B (en) | Battery surface defect detection method and detection system | |
| CN104614379A (en) | Plate surface defect detection system and method | |
| CN102901735B (en) | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer | |
| CN112115927A (en) | Intelligent machine room equipment identification method and system based on deep learning | |
| CN104535589A (en) | Online detection method and device for low-voltage current mutual inductor | |
| CN103983426A (en) | Optical fiber defect detecting and classifying system and method based on machine vision | |
| CN109507205A (en) | A kind of vision detection system and its detection method | |
| CN104048966A (en) | Big-law-based cloth cover defect detection and classification method | |
| CN116228651A (en) | Cloth defect detection method, system, equipment and medium | |
| CN103091330A (en) | Copper strip surface defect identifying device for simulating human visual perception mechanism and method thereof | |
| CN103674970B (en) | A kind of automatic testing method producing band in batches | |
| CN207081666U (en) | A kind of zipper detecting device based on machine vision | |
| CN111105413B (en) | Intelligent spark plug appearance defect detection system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130918 |