CN107356598A - Ash content carbon online test method based on digital image processing techniques - Google Patents
Ash content carbon online test method based on digital image processing techniques Download PDFInfo
- Publication number
- CN107356598A CN107356598A CN201710427783.5A CN201710427783A CN107356598A CN 107356598 A CN107356598 A CN 107356598A CN 201710427783 A CN201710427783 A CN 201710427783A CN 107356598 A CN107356598 A CN 107356598A
- Authority
- CN
- China
- Prior art keywords
- ash
- image
- lime
- detection
- content carbon
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The invention discloses a kind of ash content carbon online test method based on digital image processing techniques, comprise the following steps：Step 1. lime-ash image and its phosphorus content obtain；Step 2. lime-ash image procossing；Step 3. ash content carbon detection image rgb value obtains；The structure of step 4. ash content carbon BP Artificial Neural Network Prediction Models；Step 5. lime-ash sample phosphorus content detection to be measured.The present invention has the advantages that：（1）Detection process is simple, and the detection that lime-ash sample image just realizes ash content carbon need to be only obtained by image capture device；（2）Detection speed is fast, while precision is higher, is easy to extensive and is used for industry reality；（3）It is versatile, by establishing corresponding training set for other coals, the detection of ash content carbon can be realized.
Description
Technical field
The invention belongs to technical field of boiler combustion, and in particular to one kind is based on Digital Image Processing and BP ANN
The coal-burning boiler ash content carbon online test method of network technology.
Background technology
Lime-ash（The general designation of clinker and flying dust）Phosphorus content is to weigh the horizontal important indicator of boiler combustion.Too high lime-ash contains
Carbon amounts shows boiler combustion process imperfection, causes larger Mechanical adsorption, reduces the warp of boiler operatiopn
Ji property, simultaneously because the rising of Powelery Solids Emission and cause boiler heating surface abrasion aggravation, deduster and air-introduced machine operation
Power consumption increases.
Boiler slag phosphorus content is mainly obtained by laboratory calcination loss method at present, and calcination loss method is carbon containing to clinker
Time-consuming for amount detection, and boiler operatiopn operating mode is that ever-changing and coal-fired species is various, therefore calcination loss method can not be timely
Obtain boiler slag carbon content data；The detection of boiler flyash carbon content is typically completed by microwave carbonmeter, but due to actual behaviour
The measurement accuracy of microwave carbonmeter can be influenceed by flow velocity and smoke density during work, cause its measurement result excursion
It is excessive.The influence that microwave carbonmeter is blocked due to flying dust often simultaneously can not normal operation, and considerably increase operation maintenance work
Measure.Therefore for prior art, the ash content carbon detection of real-time online is realized, provides operation in time for operations staff
Data needed for optimization, it can not possibly substantially accomplish.To solve this problem, the present invention is proposed based on Digital Image Processing
With the coal-burning boiler ash content carbon online test method of BP artificial neural network technologies, BP artificial neural networks have powerful
Learning ability, good fault-tolerance, fast and accurately mathematical modeling can be established by it, and then can realized to ash content carbon
On-line monitoring.
The content of the invention
It is an object of the invention to provide a kind of coal-fired pot based on digital image processing techniques and BP artificial neural networks
Boiler ash sediment phosphorus content online test method.Efficiently solve the carbon containing quantity measuring method detection time of existing boiler is long, cost is high,
The technical problems such as complex operation.
The technical solution adopted in the present invention is：
（1）Lime-ash RGB color image obtains
Collection lime-ash sample is continuously introduced into the photographing device with white background after being ground mixing in real time, then with automatic
Image capture device is continuously shot collection lime-ash sample RGB color image.
（2）Lime-ash image procossing
Lime-ash RGB color image is converted into lime-ash gray level image, and medium filtering is carried out to lime-ash gray level image.Then use
Maximum variance between clusters enter row threshold division to lime-ash gray level image, obtain lime-ash bianry image.Finally to lime-ash RGB color figure
As carrying out image separation, R component, G components, B component image are obtained.Three width component images and lime-ash bianry image are carried out respectively
Image and computing, three width component images after computing are subjected to image and merge to obtain the ash content carbon detection for removing background area
Image.
（3）Ash content carbon detection image rgb value obtains
Image traversal is carried out to ash content carbon detection image, the region that rgb value is 255 is skipped, takes each pixel respectively
R, G, B value and R that average value is as the detection image, G, B values.
（4）Ash content carbon detection model structure based on BP artificial neural networks
Obtain the lime-ash sample image of 60 groups of difference ash content carbons, select the color of image characteristic parameter R after data normalization,
G, Y, B, g, y establish neural metwork training collection as mode input vector, ash content carbon as output vector.It is basic herein
On establish ash content carbon BP artificial neural network detection models, the input layer of detection model, hidden layer, the output layer number of plies are all
1, input layer, hidden layer, the neuron number of output layer are respectively 6,8,1.
（5）Lime-ash sample phosphorus content detection to be measured
Ash content carbon detecting system is established based on OpenCV machine vision storehouse, it is special to obtain color of image according to above-mentioned steps 1-3
Parameter R, G, Y, B, g, y are levied, brings R, G, Y, B, g, y into detection model that step 4 established, you can it is carbon containing to obtain lime-ash sample
Amount.
The invention has the advantages that：
（1）Detection process is simple, and the inspection that lime-ash sample image just realizes ash content carbon need to be only obtained by image capture device
Survey；（2）Detection speed is fast, while precision is higher, is easy to extensive and is used for industry reality；（3）It is versatile, by for other
Coal establishes corresponding training set, can realize the detection of ash content carbon.
Brief description of the drawings
The embodiment of the present invention is described in further detail below in conjunction with the accompanying drawings.
Fig. 1 is ash content carbon testing process schematic diagram of the present invention.
Fig. 2 is lime-ash image capture environment top view.
Fig. 3 is lime-ash image processing flow schematic diagram of the present invention.
Fig. 4（a）It is the RGB color image of example lime-ash sample.
Fig. 4（b）It is the gray level image of example lime-ash sample.
Fig. 4（c）It is the bianry image of example lime-ash sample.
Fig. 4（d）It is the phosphorus content detection image of example lime-ash sample.
In figure：1- white background cardboards, 2- image capture devices, 3- lime-ash samples.
Embodiment
With reference to non-limiting example, the present invention will be further described.
Ash content carbon testing process of the present invention is as shown in figure 1, of the invention with lime-ash caused by coal-burning boiler running
It is main study subject with its phosphorus content, by handling lime-ash image, based on preset lime-ash sample data and BP nerves
Network, realize it is quick, stably, accurate ash content carbon on-line checking.
（1）Lime-ash image and its phosphorus content obtain
Obtain lime-ash sample to be placed on white background cardboard, the shooting image when lime-ash sample covers camera lens substantially, such as Fig. 2 institutes
Show.Same lime-ash sample shooting image 5 times, lime-ash image save as JPG forms, and resolution ratio is 5184 × 3456.Captured
Lime-ash image such as Fig. 4（a）It is shown.
（2）Lime-ash image procossing and rgb value obtain
Lime-ash RGB color image is converted into lime-ash gray level image, lime-ash gray level image such as Fig. 4（b）It is shown.Based between maximum kind
Method splits lime-ash gray level image, realizes the separation of shooting background and lime-ash target, and carries out corresponding median filter process, obtains
Lime-ash bianry image, such as Fig. 4（c）It is shown.Separated and merged by image channel, obtain Fig. 4（d）Shown ash content carbon inspection
Altimetric image.Detection image is traveled through, ignores white portion, takes the average value conduct of the rgb value summation of each pixel respectively
The R of the detection image, G, B values.For five detection images of same lime-ash sample, each detection image R, G, B are taken respectively
With average R, G, B value as lime-ash sample image.
（3）Ash content carbon detects
Using lime-ash detection image red values R, green glow value G, gray value Y, blue light value B, green glow standard value g, grey scale value y to be defeated
Incoming vector, by the BP neural network of 60 sample datas built in input after its data normalization, the lime-ash for obtaining the sample is carbon containing
Detection limit is measured, as shown in table 1.Pass through the phosphorus content of R, G, Y, B, g, y value indirect detection ash product of lime-ash image.
15 carbon containing detection values of lime-ash sample of table
。
Claims (2)
1. a kind of ash content carbon online test method based on digital image processing techniques, it is characterised in that according to following steps
Carry out：
Step 1. lime-ash image and its phosphorus content obtain：Collection lime-ash sample is laid in white background cardboard after being ground mixing
On, then shot with image capture device perpendicular to background cardboard, obtain lime-ash sample RGB color image, and by burning
Loss on ignition method obtains the phosphorus content of lime-ash sample；
Step 2. lime-ash image procossing；
Step 3. ash content carbon detection image rgb value obtains：Image traversal is carried out to ash content carbon detection image, skipped
Rgb value is 255 region, takes R of R, G, B value and average value of each pixel as the detection image, G, B values respectively；
The structure of step 4. ash content carbon BP Artificial Neural Network Prediction Models：Select the color of image after data normalization special
Parameter R, G, Y, B, g, y are levied as mode input vector, establishes ash content carbon BP Artificial Neural Network Prediction Models；
Step 5. lime-ash sample phosphorus content detection to be measured：Ash content carbon detection image and image are obtained according to above-mentioned steps 1-3
Color characteristics parameters R, G, Y, B, g, y, bring R, G, Y, B, g, y into forecast model that step 4 established, you can obtain grey slag specimen
Product phosphorus content.
2. the ash content carbon online test method based on digital image processing techniques, its feature exist as claimed in claim 1
In：Step 2. lime-ash image procossing is as follows：First, lime-ash RGB color image is converted into lime-ash gray level image, conversion formula is：, wherein Y is lime-ash gray level image pixel gray value, and RGB is lime-ash coloured image picture
R, G, B value of vegetarian refreshments；2nd, enter row threshold division to lime-ash gray level image using maximum variance between clusters, obtain lime-ash binary map
Picture, and medium filtering is carried out to lime-ash bianry image；3rd, image separation is carried out to lime-ash RGB color image, obtained only comprising original
Image red information, green information, the R component of blue information, G components, B component image；Respectively by three width component images and ash
Slag bianry image carries out image and computing, and image will be carried out with three width component images after computing and merges to obtain removal background area
Ash content carbon detection image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710427783.5A CN107356598A (en) | 2017-06-08 | 2017-06-08 | Ash content carbon online test method based on digital image processing techniques |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710427783.5A CN107356598A (en) | 2017-06-08 | 2017-06-08 | Ash content carbon online test method based on digital image processing techniques |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107356598A true CN107356598A (en) | 2017-11-17 |
Family
ID=60272426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710427783.5A Pending CN107356598A (en) | 2017-06-08 | 2017-06-08 | Ash content carbon online test method based on digital image processing techniques |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107356598A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110954536A (en) * | 2019-12-03 | 2020-04-03 | 华电电力科学研究院有限公司 | Fly ash carbon content online measurement device and method |
| CN111476770A (en) * | 2020-04-03 | 2020-07-31 | 中冶赛迪工程技术股份有限公司 | Slag detection method, device, equipment and medium based on image processing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1542432A (en) * | 2003-11-06 | 2004-11-03 | 华北电力大学 | Method for measuring carbon content in coal-burning boiler and kiln fly ash and on line detection apparatus therefor |
| CN101949831A (en) * | 2010-08-06 | 2011-01-19 | 江苏省特种设备安全监督检验研究院淮安分院 | Method for quickly testing solid incomplete combustion heat loss of boiler and cinder carbon content colorimetric card |
| CN103267762A (en) * | 2013-05-09 | 2013-08-28 | 中国矿业大学 | Coal slurry ash online detection system based on image method, and method |
| CN104502284A (en) * | 2014-12-16 | 2015-04-08 | 西安西热锅炉环保工程有限公司 | Online detection device for carbon content in flue dust of coal fired power plant |
-
2017
- 2017-06-08 CN CN201710427783.5A patent/CN107356598A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1542432A (en) * | 2003-11-06 | 2004-11-03 | 华北电力大学 | Method for measuring carbon content in coal-burning boiler and kiln fly ash and on line detection apparatus therefor |
| CN101949831A (en) * | 2010-08-06 | 2011-01-19 | 江苏省特种设备安全监督检验研究院淮安分院 | Method for quickly testing solid incomplete combustion heat loss of boiler and cinder carbon content colorimetric card |
| CN103267762A (en) * | 2013-05-09 | 2013-08-28 | 中国矿业大学 | Coal slurry ash online detection system based on image method, and method |
| CN104502284A (en) * | 2014-12-16 | 2015-04-08 | 西安西热锅炉环保工程有限公司 | Online detection device for carbon content in flue dust of coal fired power plant |
Non-Patent Citations (2)
| Title |
|---|
| 《全国公安高等教育（本科）规划教材 刑事科学技术》: "《全国公安高等教育（本科）规划教材 刑事科学技术》", 27 February 2015, 中国人民公安大学出版社 * |
| 梁志芳 王迎娜主编: "《计算机在材料加工中的应用》", 31 March 2012, 煤炭工业出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110954536A (en) * | 2019-12-03 | 2020-04-03 | 华电电力科学研究院有限公司 | Fly ash carbon content online measurement device and method |
| CN110954536B (en) * | 2019-12-03 | 2024-02-09 | 华电电力科学研究院有限公司 | Online measuring device and method for carbon content of fly ash |
| CN111476770A (en) * | 2020-04-03 | 2020-07-31 | 中冶赛迪工程技术股份有限公司 | Slag detection method, device, equipment and medium based on image processing |
| CN111476770B (en) * | 2020-04-03 | 2023-01-31 | 中冶赛迪工程技术股份有限公司 | Slag detection method, device, equipment and medium based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110648364B (en) | Multi-dimensional space solid waste visual detection positioning and identification method and system | |
| Schmugge et al. | Crack segmentation by leveraging multiple frames of varying illumination | |
| CN104256882B (en) | Based on reconstituted tobacco ratio measuring method in the pipe tobacco of computer vision | |
| GB2542118A (en) | A method, apparatus, system, and computer readable medium for detecting change to a structure | |
| CN104198325B (en) | Stem ratio measuring method in pipe tobacco based on computer vision | |
| CN103454285A (en) | Transmission chain quality detection system based on machine vision | |
| CN103954634A (en) | Online quality detection system for printed matter | |
| CN104766097B (en) | Surface of aluminum plate defect classification method based on BP neural network and SVMs | |
| JP2018509752A5 (en) | ||
| CN106226157A (en) | Concrete structure member crevices automatic detection device and method | |
| JP2010210318A (en) | Measuring device of dust, and estimation method of generation source | |
| CN110414341A (en) | A kind of Blasting In The Open Mining heap measurement statistical method based on unmanned air vehicle technique | |
| CN117115148B (en) | Chip surface defect intelligent identification method based on 5G technology | |
| CN107356598A (en) | Ash content carbon online test method based on digital image processing techniques | |
| CN115597494B (en) | Precision detection method and system for prefabricated part preformed hole based on point cloud | |
| CN110554052A (en) | artificial board surface defect detection method and system | |
| CN106018179A (en) | Glue material surface viscosity measurement method and device based on image processing | |
| KR20210018672A (en) | Apparatus and method for providing predictive value for measurement of particulate matter concentration using a camera | |
| JP2020112483A (en) | Exterior appearance inspection system, calculation model construction method and calculation model construction program | |
| CN110954536B (en) | Online measuring device and method for carbon content of fly ash | |
| CN102735689A (en) | Paper defect detection system based on image pattern recognition | |
| JP2012108026A (en) | Detection method of foreign material-contaminated product | |
| CN116645351A (en) | Online defect detection method and system for complex scene | |
| CN107860715B (en) | Method for detecting carbon content of boiler slag | |
| CN115937555A (en) | Industrial defect detection algorithm based on standardized flow model |
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: 20171117 |
|
| RJ01 | Rejection of invention patent application after publication |