CN108073651A - The processing method of the automatic slab FQC picture materials of identification in real time - Google Patents
The processing method of the automatic slab FQC picture materials of identification in real time Download PDFInfo
- Publication number
- CN108073651A CN108073651A CN201611030054.8A CN201611030054A CN108073651A CN 108073651 A CN108073651 A CN 108073651A CN 201611030054 A CN201611030054 A CN 201611030054A CN 108073651 A CN108073651 A CN 108073651A
- Authority
- CN
- China
- Prior art keywords
- slab
- fqc
- image
- identification
- automatic
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Abstract
The invention discloses a kind of processing methods of the automatic slab FQC picture materials of identification in real time, comprise the following steps:Step 1, the real-time Dynamical capture of slab FQC images;Step 2, the identification of slab FQC graphic services;Step 3, slab FQC Image Information Processings and association analysis.The present invention improves the degree of automation of production process, liberates labour productive forces;Missing inspection, the situation of flase drop are largely avoided, improves detection efficiency;It has a extensive future.
Description
Technical field
The present invention relates to a kind of processing method of picture material, more particularly to a kind of automatic FQC figures of identification slab in real time
As the processing method of content.
Background technology
So-called slab refers mainly to what is produced with four-roller heavy plate mill, and thicker hot rolled steel plate, it is the one of metallurgical industry
A staple product.Various in style, the different properties of slab, quality requirement is high, has a wide range of application, no matter in economic construction or state
Slab is all be unable to do without in anti-construction.Thus countries in the world are all using the kind of slab, quality as one national steel and iron industry of measurement
The scale of level of aggregation.
Quality management and quality examination occupy critically important status in Heavy plate production.Since oil crisis, to slab matter
Amount requirement further improves, and slab is almost by user's contract, and order is produced one by one.The contract of slab, which removes, to expire
Outside sufficient standard, the also additional particular/special requirement of most of contracts.Heavy plate production process is more and complicated, and the quality management of slab is used with each
Based on process quality management, it is related to the consistent quality management mode from steel-making to the full process of product export.
FQC (Final Quality Control, final mass control) manufacturing process final inspection verification is also referred to as completed
Product examine examination card.FQC is the quality status for slab in itself, including:Appearance test (bubble, protrusion, scratch etc.), size
It measures, performance test (physical/chemical properties of material, electrical characteristic, mechanical property, operation control), carries out comprehensively and last
Inspection and test once, purpose are ensuring that product meets shipment specification requirement or even meet the requirement in client's use.
For Thick Plate Plant for FQC images using the mode manually judged, being not achieved through artificial detection glacing flatness will at present
It asks, is sent by the traversing reconditioning rack after cutting or traversing crane to carrying out cold rectify on cold straightener.According to the requirement of order steel plate,
To needing the steel plate of temperature correction, it is straight that band temperature correction can be carried out in 250~400 DEG C of temperature.Steel can be eliminated by cold rectify to greatest extent
Plate is in the various flatness defects for cooling down with being likely to occur in shear history.But this judge that the mode of FQC images is deposited by human eye
In following deficiency:Since human eye is easily tired, it is impossible to carry out long-time inspection, can only follow one's inclinations inspection, easily come out missing inspection situation;
It can not carry out accurate, timely automatic judgement;Data message contained by FQC images can not be filed and be transferred;It cannot
The adjustment of technological parameter is targetedly carried out, slab quality can not provide better decision support in order to control.
Therefore, this patent proposes a kind of automatic identification slab FQC picture materials in real time and the method for processing to substitute people
Work identification decision by carrying out automated graphics identification, information included in extraction and processing image to FQC images, and carries out
Automatic archiving stores, and simplifies inspection action and review time, avoids inspection personnel's missing inspection, flase drop, improves detection efficiency, be simultaneously
It improves slab quality and data basis is provided.
The content of the invention
The technical problems to be solved by the invention are to provide a kind of processing side of the automatic slab FQC picture materials of identification in real time
Method, which raises the degree of automation of production process, liberate labour productive forces;Missing inspection, the situation of flase drop are largely avoided, is improved
Detection efficiency;It has a extensive future.
The present invention is to solve above-mentioned technical problem by following technical proposals:A kind of automatic identification slab FQC in real time
The processing method of picture material, comprises the following steps:
Step 1, the real-time Dynamical capture of slab FQC images;
Step 2, the identification of slab FQC graphic services;
Step 3, slab FQC Image Information Processings and association analysis.
Preferably, the step 1 comprises the following steps:Automatically backstage according to setting frequency real-time dynamicly to refer to
Fixed production process cut deal FQC graphic interfaces are captured.
Preferably, the step 2 comprises the following steps:
Step 2 11 defines business recognition rule, according to usage scenario and demand, for each type of picture, needs
A recognition rule text file is wanted, records the type and location information of each identification item;
Step 2 12, according to recognition rule file, using OCR and image processing techniques, a set of image of independent development
Identification software calls the image recognition software to carry out automatic identification to FQC images.
Preferably, the step 3 comprises the following steps:
The result of identification is stored in corresponding database, including structural data and unstructured figure by step 3 11
As data;If there is the rule of Type=2 in recognition rule file, by crawl figure at the rectangle frame position specified in the picture
Picture;The rectangle frame should be slightly bigger than maximum image, and for software by the size according to real image, automatic cutting cuts the extra portion of surrounding
Point, and image is stored in<PlateID>In _ image.png files;
Step 3 12, unstructured image data<PlateID>_ image.png is according to numerical value, by image data structure
Change, obtain the FQC numeric datas of every block of slab, the merging and statistical disposition of a plurality of data are carried out on the basis of motherboard ID, including
Min, Max, Sum, Mean, Range, Standard Deviation, CV so that data that treated are as influence slab quality
Correlative factor;
Step 3 13, the structural data that treated FQC picture structures data and step 3 11 is identified
Directly as influence slab quality correlative factor, with Heavy plate production manufacture other process datas be associated, analyze its with
The correlation of slab quality problems provides decision support to improve slab quality.
The positive effect of the present invention is:The present invention to slab FQC images by carrying out automatic identification, in image
Comprising data message handled and stored, the existing judgement to FQC images is promoted to computer by artificial judgment
Automatic decision;The degree of automation of production process is improved, liberates labour productive forces;Missing inspection, the situation of flase drop are largely avoided,
Improve detection efficiency;Data basis and analytical factor are provided for the analysis of follow-up slab quality intelligent, adapts to the need of wisdom manufacture
It will;This method comes into operation in Baogang Stocks Trading Co.'s Thick Plate Plant, and application effect is very good;At present, domestic most manufacture enterprises
Industry is still all manual type in terms of FQC images and processing to judge, verification and measurement ratio is low and can not be provided for follow-up intellectual analysis
Data basis, therefore the technology has a extensive future.
Description of the drawings
Fig. 1 is the flow diagram of the processing method of the automatic slab FQC picture materials of identification in real time of the present invention.
Fig. 2 is the flow diagram of step 2 in the present invention.
Fig. 3 is the flow diagram of step 3 in the present invention.
Specific embodiment
Present pre-ferred embodiments are provided below in conjunction with the accompanying drawings, with the technical solution that the present invention will be described in detail.
As shown in Figure 1, the place of automatic slab FQC (the manufacturing process final inspection verification) picture material of identification in real time of the present invention
Reason method comprises the following steps:
Step 1, the real-time Dynamical capture of slab FQC images;
Step 2, the identification of slab FQC graphic services;
Step 3, slab FQC Image Information Processings and association analysis.
The step 1 comprises the following steps:Automatically on backstage according to the frequency of setting real-time dynamicly to specified production
Process cut deal FQC graphic interfaces are captured.
As shown in Fig. 2, the step 2 comprises the following steps:
Step 2 11 defines business recognition rule, according to usage scenario and demand, for each type of picture, needs
A recognition rule text file is wanted, records the type and location information of each identification item;
Step 2 12 according to recognition rule file, utilizes OCR (Optical Character Recognition, light
Learn character recognition) and image processing techniques, a set of image recognition software of independent development calls the image recognition software to FQC
Image carries out automatic identification.
As shown in figure 3, the step 3 comprises the following steps:
The result of identification is stored in corresponding database, including structural data and unstructured figure by step 3 11
As data;If there is the rule of Type=2 (i.e. image-capture) in recognition rule file, the rectangle frame position that will specify in the picture
Put place's crawl image;The rectangle frame should be slightly bigger than maximum image, and the size according to real image, automatic cutting are cut four by software
The part of Zhou Duoyu, and image is stored in "<PlateID>In _ image.png " files;
Step 3 12, unstructured image data "<PlateID>_ image.png " is according to numerical value, by image data knot
Structure, obtains the FQC numeric datas of every block of slab, and the merging and statistical disposition of a plurality of data are carried out on the basis of motherboard ID, bag
Include Min (minimum), Max (maximum), Sum (summation), Mean (average), Range (Max-Min, scope), Standard
Deviation (SD, standard deviation), CV (Mean/SD.) so that data that treated are as the correlative factor for influencing slab quality;
Step 3 13, the structural data that treated FQC picture structures data and step 3 11 is identified
Directly as the correlative factor for influencing slab quality, other process data (heating furnace data, rolling numbers with Heavy plate production manufacture
According to) be associated, its correlation with slab quality problems is analyzed, decision support is provided to improve slab quality.
To the real-time Dynamical capture of slab FQC images, by defining image recognition rule, slab FQC images are carried out automatic
Identification, is then handled and is stored to data message included in image, and number is provided for the analysis of slab influencing factors of quality
According to basis and association analysis factor, the needs that wisdom manufactures are adapted to.
The present invention substantially increases the work efficiency of judgement personnel, and provides data for Analysis of Thick influencing factors of quality
Support.
By taking slab temperature distribution image as an example, the specific implementation process is as follows:
Ensure live FQC monitoring interconnection plane, identification software client is disposed on monitoring equipment, in FQC acquisition servers portion
Server-side is affixed one's name to, establishes operation task, operation temperature distributed image screen capture;
Temperature recognition rule text file is defined, calls the image recognition software of independent research to the Temperature Distribution that captures
Image carries out automatic identification, and form is as follows:OCR.exe<Recognition rule filename><Image file name to be identified>, after operation,
Automatic upload in real time is written in DB2 by structural data, and automatic identification is generated .png files by temperature pattern;
According to the numerical value that legend color in the .png files of generation represents, by image data structure, every block of slab is obtained
Temperature profile data, temperature data length direction is divided into 10 deciles, i.e. width is 9 passages, length direction
For 11 passage, difference is done respectively by length direction and width into trip temperature to every block of slab, expands temperature difference variation per minute,
Then the merging and statistical disposition of a plurality of data are carried out, including Min, Max, Sum, Mean, Range (Max-Min), Standard
Deviation (SD.), CV (Mean/SD.) so that one piece of slab motherboard only has a record;
Above by the data parsed directly as the correlative factor for influencing slab quality, with Heavy plate production manufacture
Other process datas are associated, and such as heating furnace data, rolling data, analyze its correlation with slab quality problems.
The main path of the present invention is that slab FQC picture materials are identified, extracted and handled, particular content into row information
Including:
Slab FQC images are that finished product carries out the quality inspection technique before cold rectify, by the judgement to FQC images, to sentence
Whether the disconnected slab needs to carry out cold rectify, if meets customer requirement;
Slab FQC images are currently by manually judging, can not realize that system judges automatically, comprising data message
Also it can not file in real time, store with transferring;
The judgement result of slab FQC images directly affects cold strong cost and the quality of slab, but manually judges to be present with
Missing inspection, flase drop, Detection accuracy can not improve slab quality than relatively low;
The data message and its correlation process method that slab FQC images are included, currently without relatively good method, cause
Its data can not analyze its correlation with slab quality as correlative factor, can not provide decision-making branch to improve slab quality
It holds;
Exactly more than rule directly determines the difficulty of the identification of slab FQC images and processing and leads to not significantly carry
The reason for high slab quality, this patent propose a kind of automatic identification slab FQC picture materials in real time and the method for processing.Pass through
To the real-time Dynamical capture of slab FQC images, by defining image recognition rule, automatic identification is carried out to slab FQC images, then
Data message included in image is handled and stored, the existing judgement to FQC images is promoted by artificial judgment
For computer automatic decision, the degree of automation of production process is on the one hand improved, liberates labour productive forces;On the other hand significantly
Missing inspection, the situation of flase drop are avoided, detection efficiency is improved, while data basis and pass is provided for the analysis of slab influencing factors of quality
Join analytical factor, adapt to the needs of wisdom manufacture.If promoting and applying, it is related in manufacturing process at the automatic identification and data of image
The technique of reason can be used, remarkable in economical benefits.
Particular embodiments described above, the technical issues of to the solution of the present invention, technical solution and advantageous effect carry out
It is further described, it should be understood that the above is only a specific embodiment of the present invention, is not limited to
The present invention, within the spirit and principles of the invention, any modification, equivalent substitution, improvement and etc. done should be included in this
Within the protection domain of invention.
Claims (4)
1. a kind of processing method of the automatic slab FQC picture materials of identification in real time, which is characterized in that it comprises the following steps:
Step 1, the real-time Dynamical capture of slab FQC images;
Step 2, the identification of slab FQC graphic services;
Step 3, slab FQC Image Information Processings and association analysis.
2. the processing method of the automatic slab FQC picture materials of identification in real time as described in claim 1, which is characterized in that described
Step 1 comprises the following steps:Automatically on backstage according to the frequency of setting real-time dynamicly to specified production process cut deal
FQC graphic interfaces are captured.
3. the processing method of the automatic slab FQC picture materials of identification in real time as described in claim 1, which is characterized in that described
Step 2 comprises the following steps:
Step 2 11 defines business recognition rule, according to usage scenario and demand, for each type of picture, it is necessary to one
A recognition rule text file records the type and location information of each identification item;
Step 2 12, according to recognition rule file, using OCR and image processing techniques, a set of image identification of independent development
Software calls the image recognition software to carry out automatic identification to FQC images.
4. the processing method of the automatic slab FQC picture materials of identification in real time as described in claim 1, which is characterized in that described
Step 3 comprises the following steps:
The result of identification is stored in corresponding database, including structural data and unstructured picture number by step 3 11
According to;If there is the rule of Type=2 in recognition rule file, image will be captured at the rectangle frame position specified in the picture;It should
Rectangle frame should be slightly bigger than maximum image, and for software by the size according to real image, automatic cutting cuts the extra part of surrounding, and
Image is stored in<PlateID>In _ image.png files;
Step 3 12, unstructured image data<PlateID>_ image.png is according to numerical value, by image data structure,
Obtain the FQC numeric datas of every block of slab, the merging and statistical disposition of a plurality of data carried out on the basis of motherboard ID, including Min,
Max, Sum, Mean, Range, Standard Deviation, CV so that data that treated are as the phase for influencing slab quality
Pass factor;
Step 3 13, the structural data that treated FQC picture structures data and step 3 11 is identified are direct
As the correlative factor for influencing slab quality, it is associated with other process datas of Heavy plate production manufacture, analyzes itself and slab
The correlation of quality problems provides decision support to improve slab quality.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611030054.8A CN108073651A (en) | 2016-11-15 | 2016-11-15 | The processing method of the automatic slab FQC picture materials of identification in real time |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611030054.8A CN108073651A (en) | 2016-11-15 | 2016-11-15 | The processing method of the automatic slab FQC picture materials of identification in real time |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108073651A true CN108073651A (en) | 2018-05-25 |
Family
ID=62161097
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611030054.8A Pending CN108073651A (en) | 2016-11-15 | 2016-11-15 | The processing method of the automatic slab FQC picture materials of identification in real time |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108073651A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0816825A2 (en) * | 1996-06-26 | 1998-01-07 | Toshiba Engineering Corporation | Method and apparatus for inspecting streak |
CN1652120A (en) * | 2005-02-24 | 2005-08-10 | 上海交通大学 | Plasticity forming technique regulation obtaining method based on numerical value simulation and policy-making tree algorithm |
CN101556251A (en) * | 2009-05-08 | 2009-10-14 | 西安理工大学 | CTP plate making quality testing method based on digital signal processor |
CN103163141A (en) * | 2011-12-14 | 2013-06-19 | 鞍钢股份有限公司 | Strip steel surface on-line inspection system and method based on embedded image processing system |
CN103593670A (en) * | 2013-10-14 | 2014-02-19 | 浙江工业大学 | Copper sheet and strip surface defect detection method based on-line sequential extreme learning machine |
CN103632368A (en) * | 2013-11-29 | 2014-03-12 | 苏州有色金属研究院有限公司 | Metal plate strip surface image defect merging method |
CN104616275A (en) * | 2013-11-04 | 2015-05-13 | 北京兆维电子(集团)有限责任公司 | Defect detecting method and defect detecting device |
CN105092593A (en) * | 2015-08-27 | 2015-11-25 | 张小磊 | Steel plate defect detection method based on high-intensity illumination |
CN105136810A (en) * | 2015-08-27 | 2015-12-09 | 张小磊 | Steel plate defect detecting platform based on high-strength lighting |
CN106093053A (en) * | 2016-07-25 | 2016-11-09 | 天津松洋金属制品有限公司 | A kind of Surface Defects in Steel Plate detection device |
-
2016
- 2016-11-15 CN CN201611030054.8A patent/CN108073651A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0816825A2 (en) * | 1996-06-26 | 1998-01-07 | Toshiba Engineering Corporation | Method and apparatus for inspecting streak |
CN1652120A (en) * | 2005-02-24 | 2005-08-10 | 上海交通大学 | Plasticity forming technique regulation obtaining method based on numerical value simulation and policy-making tree algorithm |
CN101556251A (en) * | 2009-05-08 | 2009-10-14 | 西安理工大学 | CTP plate making quality testing method based on digital signal processor |
CN103163141A (en) * | 2011-12-14 | 2013-06-19 | 鞍钢股份有限公司 | Strip steel surface on-line inspection system and method based on embedded image processing system |
CN103593670A (en) * | 2013-10-14 | 2014-02-19 | 浙江工业大学 | Copper sheet and strip surface defect detection method based on-line sequential extreme learning machine |
CN104616275A (en) * | 2013-11-04 | 2015-05-13 | 北京兆维电子(集团)有限责任公司 | Defect detecting method and defect detecting device |
CN103632368A (en) * | 2013-11-29 | 2014-03-12 | 苏州有色金属研究院有限公司 | Metal plate strip surface image defect merging method |
CN105092593A (en) * | 2015-08-27 | 2015-11-25 | 张小磊 | Steel plate defect detection method based on high-intensity illumination |
CN105136810A (en) * | 2015-08-27 | 2015-12-09 | 张小磊 | Steel plate defect detecting platform based on high-strength lighting |
CN106093053A (en) * | 2016-07-25 | 2016-11-09 | 天津松洋金属制品有限公司 | A kind of Surface Defects in Steel Plate detection device |
Non-Patent Citations (2)
Title |
---|
夏承亮 等: "板材表面质量在线检测方法概述", 《工业计量》 * |
王凯茹 等: "基于大数据技术的钢铁全产线质量控制系统", 《冶金自动化》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN100468246C (en) | Real time monitoring system for production processes and monitoring method | |
KR102021944B1 (en) | Method for managing steel quality and system | |
CN110781930A (en) | User portrait grouping and behavior analysis method and system based on log data of network security equipment | |
Brandenburger et al. | Big data solution for quality monitoring and improvement on flat steel production | |
CN103279883A (en) | Electronic-payment transaction risk control method and system | |
CN109978835B (en) | Online assembly defect identification system and method thereof | |
CN105574593B (en) | Track state static detection and control system and method based on cloud computing and big data | |
CN109344719A (en) | Substation equipment information query method based on augmented reality and intelligent glasses | |
CN107578160A (en) | Construction personnel's real-name management method | |
WO2016169499A1 (en) | Random anti-counterfeiting marker-based anti-counterfeiting system, and anti-counterfeiting method therefor | |
JP4757729B2 (en) | Manufacturing load prediction apparatus, manufacturing load prediction method, computer program, and computer-readable storage medium | |
CN107645709A (en) | A kind of method and device for determining personal information | |
CN111611487A (en) | Stock information application analysis system | |
CN106447157A (en) | Product testing and supervision method and monitoring system thereof | |
CN103942547A (en) | Online and real-time printing detection method for intelligent card issuing system | |
CN115937101A (en) | Quality detection method, device, equipment and storage medium | |
CN204496264U (en) | Middle plate finishing area secondary tracking means | |
CN108073651A (en) | The processing method of the automatic slab FQC picture materials of identification in real time | |
CN107798137A (en) | A kind of multi-source heterogeneous data fusion architecture system based on additive models | |
KR101671890B1 (en) | apparatus for analyzing business traction information and method fornalyzing business traction information | |
CN109492780B (en) | Repair tracking method, device and system for repaired parts | |
CN110322218A (en) | Intelligent society insurance business operation and monitoring method and system | |
CN108921433A (en) | Quantitative risk analysis system based on business continuance | |
CN107491987A (en) | A kind of batch cost accounting system and method based on diamond product dynamic database | |
CN111970159A (en) | Centralized control system, method and device based on smart 5G energy Internet of things technology |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180525 |
|
RJ01 | Rejection of invention patent application after publication |