CN110954536B - Online measuring device and method for carbon content of fly ash - Google Patents
Online measuring device and method for carbon content of fly ash Download PDFInfo
- Publication number
- CN110954536B CN110954536B CN201911218193.7A CN201911218193A CN110954536B CN 110954536 B CN110954536 B CN 110954536B CN 201911218193 A CN201911218193 A CN 201911218193A CN 110954536 B CN110954536 B CN 110954536B
- Authority
- CN
- China
- Prior art keywords
- fly ash
- carbon content
- tray
- computer
- cyclone separator
- 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.)
- Active
Links
- 239000010881 fly ash Substances 0.000 title claims abstract description 254
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 102
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 102
- 238000000034 method Methods 0.000 title abstract description 29
- 238000005070 sampling Methods 0.000 claims abstract description 57
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 238000002485 combustion reaction Methods 0.000 claims description 32
- 230000003287 optical effect Effects 0.000 claims description 28
- 239000003245 coal Substances 0.000 claims description 27
- 238000005259 measurement Methods 0.000 claims description 27
- 238000007790 scraping Methods 0.000 claims description 24
- 238000010926 purge Methods 0.000 claims description 23
- 238000004458 analytical method Methods 0.000 claims description 17
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 14
- 239000003546 flue gas Substances 0.000 claims description 14
- 238000009666 routine test Methods 0.000 claims description 14
- 238000004140 cleaning Methods 0.000 claims description 13
- 239000002245 particle Substances 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 239000007789 gas Substances 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 5
- 230000008020 evaporation Effects 0.000 claims description 5
- 238000001704 evaporation Methods 0.000 claims description 5
- 229910052760 oxygen Inorganic materials 0.000 claims description 5
- 239000001301 oxygen Substances 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 8
- 239000000463 material Substances 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 230000006872 improvement Effects 0.000 description 5
- 239000007921 spray Substances 0.000 description 5
- 230000007787 long-term memory Effects 0.000 description 4
- 238000000691 measurement method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000000877 morphologic effect Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 3
- 238000010977 unit operation Methods 0.000 description 3
- 238000003556 assay Methods 0.000 description 2
- 238000007664 blowing Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000005357 flat glass Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000000178 monomer Substances 0.000 description 2
- 239000002893 slag Substances 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 239000012780 transparent material Substances 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000011325 microbead Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000001590 oxidative effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/02—Devices for withdrawing samples
- G01N1/22—Devices for withdrawing samples in the gaseous state
- G01N1/2202—Devices for withdrawing samples in the gaseous state involving separation of sample components during sampling
- G01N1/2211—Devices for withdrawing samples in the gaseous state involving separation of sample components during sampling with cyclones
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/02—Devices for withdrawing samples
- G01N1/22—Devices for withdrawing samples in the gaseous state
- G01N1/2247—Sampling from a flowing stream of gas
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/02—Devices for withdrawing samples
- G01N1/22—Devices for withdrawing samples in the gaseous state
- G01N1/2247—Sampling from a flowing stream of gas
- G01N1/2258—Sampling from a flowing stream of gas in a stack or chimney
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/02—Devices for withdrawing samples
- G01N1/22—Devices for withdrawing samples in the gaseous state
- G01N1/2247—Sampling from a flowing stream of gas
- G01N2001/225—Sampling from a flowing stream of gas isokinetic, same flow rate for sample and bulk gas
-
- 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
- G01N2021/8411—Application to online plant, process monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Sampling And Sample Adjustment (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to an online measuring device and method for carbon content of fly ash, and belongs to the technical field of detection. The fly ash constant-speed sampling system comprises a sampling gun, a cyclone separator, an ejector, a flow controller, an exhaust pipe, an anti-blocking backrest pipe, a differential pressure transmitter and a blanking valve, wherein one end of the sampling gun is positioned in a flue, the other end of the sampling gun is connected with the cyclone separator, the blanking valve is arranged at the lower end of the cyclone separator, the upper end of the cyclone separator is connected with the ejector, the ejector is connected with the flow controller, one end of the exhaust pipe is connected with the flow controller, the other end of the exhaust pipe is positioned in the flue, the differential pressure transmitter is connected with the flow controller, one end of the anti-blocking backrest pipe is connected with the differential pressure transmitter, and the other end of the anti-blocking backrest pipe is positioned in the flue.
Description
Technical Field
The invention relates to an online measuring device and method for carbon content of fly ash, and belongs to the technical field of detection.
Background
Coal is the main primary energy source in China, a coal-fired boiler is the main mode and equipment for coal utilization, and the coal-fired boiler has very wide application in industries such as power generation, cement, steel, chemical industry and the like. Boiler efficiency is a main technical index for measuring the performance and economy of a coal-fired boiler. Coal burnout is one of the main factors affecting boiler efficiency. The higher the burnout of the coal, the more fully the chemical energy of the coal is released, and the higher the boiler efficiency. The coal burnout is directly reflected on the carbon content of fly ash and slag. In a pulverized coal furnace (in the form of a boiler with the largest ratio among coal-fired boilers), the amount of fly ash generated is much larger than that of slag, so that the carbon content of the fly ash becomes a key index reflecting the combustion efficiency of the boiler.
The carbon content of the fly ash can be measured through a loss on ignition test, which is the most direct and accurate measurement method. However, the method needs to be detected in a laboratory after sampling, has complex flow, long time consumption and manual operation, and is difficult to meet urgent demands of industrial production on measurement frequency, automation and the like.
The carbon content of the fly ash can be reflected in the aspects of the color depth of the fly ash, the morphology of fly ash particles and the like. Generally, the higher the carbon content of the fly ash, the darker the fly ash color (larger gray scale), and the higher the ratio of coke particles to irregularly shaped particles in the composition of fly ash particles, and the lower the ratio of spherical microbeads. This provides a physical basis for (indirect) measurement of the carbon content of fly ash by image detection and recognition. The invention is based on this principle.
The patent of the method for measuring the carbon content of the fly ash of the coal-fired boiler and the kiln and the online detection device (patent No. CN200310109638, in an unauthorized state) provides a method for measuring the carbon content of the fly ash by using the gray value of the fly ash, but the information of the morphology of fly ash particles and the like is not considered, the relation between the gray value and the carbon content of the fly ash is required to be manually calibrated in advance, and the measurement accuracy of uncalibrated coal types is difficult to ensure and cannot adapt to the situation that the coal types and the coal qualities of the existing coal-fired boiler are changeable.
The invention utilizes the detail information such as the microcosmic appearance of the fly ash particles, and the like to detect the gray level from more dimensions, the accuracy and the robustness of the method are improved, the technology can perform online self-learning and self-calibration, and the current burning coal type is used as one of input parameters through an informatization means, so that the invention can be suitable for detecting the carbon content of the fly ash under various burning coal types.
At present, the measurement of the carbon content of the fly ash of the coal-fired boiler mainly comprises two means, namely, sampling and sending the fly ash to a laboratory for loss on ignition test, continuously oxidizing the fly ash in a high-temperature environment, measuring the lost mass of the fly ash, calculating the ratio of the lost mass to the mass before loss on ignition, and obtaining the carbon content of the fly ash, and secondly, carrying out online measurement by a microwave method, collecting a fly ash sample from a tail flue of the boiler through a sampling device, and calculating the carbon content of the fly ash based on the quantitative rule that the microwave absorptivity is influenced by the carbon content of the fly ash. The former has the disadvantages of a large number of processes, long time consumption and serious dependence on manual operation, and the latter has the disadvantages of large influence on coal types and high cost.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide the fly ash carbon content online measurement device and method with reasonable structural design.
The invention solves the problems by adopting the following technical scheme: the fly ash carbon content online measurement device comprises a flue, a fly ash constant-speed sampling system, an image shooting analysis system and a fly ash cleaning and collecting system, wherein the flue is connected with the fly ash constant-speed sampling system, the fly ash cleaning and collecting system is positioned below the fly ash constant-speed sampling system, and the fly ash constant-speed sampling system is matched with the image shooting analysis system, and the device is structurally characterized in that: the fly ash constant-speed sampling system comprises a sampling gun, a cyclone separator, an ejector, a flow controller, an exhaust pipe, an anti-blocking type backrest pipe, a differential pressure transmitter and a blanking valve, wherein one end of the sampling gun is positioned in a flue, the other end of the sampling gun is connected with the cyclone separator, the blanking valve is arranged at the lower end of the cyclone separator, the upper end of the cyclone separator is connected with the ejector, the ejector is connected with the flow controller, one end of the exhaust pipe is connected with the flow controller, the other end of the exhaust pipe is positioned in the flue, the differential pressure transmitter is connected with the flow controller, one end of the anti-blocking type backrest pipe is connected with the differential pressure transmitter, and the other end of the anti-blocking type backrest pipe is positioned in the flue.
Further, the ejector comprises a compressed air source, an ejector body and a compressed air jet nozzle, the upper end of the cyclone separator is connected with the ejector body, the ejector body is connected with the flow controller, and the ejector body is connected with the compressed air source through the compressed air jet nozzle.
Further, the image shooting analysis system comprises a telescopic device, a telescopic rod, a tray, a standard color plate, an optical camera, a microscopic camera, a computer and a workbench, wherein the telescopic rod is arranged on the telescopic device, the tray is connected with the telescopic rod and matched with the workbench, the standard color plate is arranged on the workbench, the optical camera and the microscopic camera are respectively located above and below the workbench, and the optical camera and the microscopic camera are connected with the computer.
Further, the image shooting analysis system further comprises an upper light source, a lower light source and a data cable, wherein the upper light source and the lower light source are respectively positioned above and below the workbench, and the optical camera and the microscopic camera are connected with the computer through the data cable.
Further, the fly ash cleaning and collecting system comprises a scraping plate, a compressed air purging device and a hopper, wherein the hopper is positioned below the blanking valve, and the scraping plate and the compressed air purging device are matched with the tray.
Further, the tray is a transparent carrier.
Further, another technical object of the present invention is to provide a measuring method of the fly ash carbon content on-line measuring device.
The technical purpose of the invention is achieved by the following technical scheme.
A measuring method of an online measuring device for the carbon content of fly ash is characterized in that: the measuring method comprises the following steps:
a) Collecting a fly ash sample from the flue gas by constant-speed sampling, and preprocessing the fly ash sample to form a fly ash sample with a flat surface on a transparent tray;
b) Respectively obtaining a general image and a microscopic image of the fly ash sample by adopting conventional photographing and microscopic photographing;
c) Analyzing, processing and identifying the fly ash image based on technologies such as image detection, machine vision and the like to obtain characteristic parameters of the fly ash;
d) Obtaining characteristic parameters of boiler combustion from a unit operation database;
f) Obtaining a carbon content measurement value of a fly ash sample from daily routine tests of a unit, and establishing a correlation model of the carbon content measurement value and characteristic parameters (fly ash characteristic parameters and boiler combustion characteristic parameters) through means of machine learning and the like;
g) And f) using the established association model and taking the characteristic parameters of the steps c) and d) as model input to calculate the carbon content of the fly ash, thereby realizing online measurement.
Further, the measuring method comprises a step e) between steps d) and f),
e) C, obtaining a carbon content measurement value of the fly ash samples in the same batch by adopting a conventional assay means, calibrating the characteristic parameters obtained in the steps c and d, and establishing a correlation model of the characteristic parameters and the carbon content of the fly ash;
g) And c) using the association model established in e) or f), taking the characteristic parameters of the steps c) and d) as model input, measuring and calculating the carbon content of the fly ash, and realizing online measurement.
Wherein step e) is not necessary.
Compared with the prior art, the invention has the following advantages: the fly ash carbon content online measuring device improves the accuracy and the working efficiency. The invention aims to realize the automatic on-line detection of the carbon content of the fly ash with high accuracy, high adaptability and high technical economy based on means and algorithms such as image detection, machine learning and the like. The measured value of the carbon content of the fly ash is obtained from the routine test of the unit, and the machine algorithm and the model are trained, so that the self-learning and continuous improvement of the machine are realized. Conventional photographing and microscopic photographing are performed on the same fly ash sample, so that the photographed pictures have sample consistency. The microscopic photographing is carried out on the contact surface of the fly ash sample and the transparent carrier (tray), so that a microscopic photograph with higher quality (higher focusing quality and consistent depth of field in a photographing area) can be obtained.
Drawings
FIG. 1 is a schematic diagram of an on-line measuring device for the carbon content of fly ash according to an embodiment of the invention.
FIG. 2 is a schematic diagram of an online measurement method of the carbon content of fly ash according to an embodiment of the invention.
In the figure: a flue 1, a fly ash constant-speed sampling system 2, an image shooting analysis system 3, a fly ash cleaning and collecting system 4,
The sampling gun 2-1, the cyclone separator 2-2, the compressed air source 2-3, the ejector 2-4, the ejector body 2-5, the compressed air jet spray pipe 2-6, the flow controller 2-7, the exhaust pipe 2-8, the anti-blocking backrest pipe 2-9, the differential pressure transmitter 2-10, the blanking valve 2-11,
The telescopic device 3-1, the telescopic rod 3-2, the tray 3-3, the standard color plate 3-4, the optical camera 3-5, the upper light source 3-6, the microscopic camera 3-7, the lower light source 3-8, the data cable 3-9, the computer 3-10, the workbench 3-11,
A scraper 4-1, a compressed air purging device 4-2 and a hopper 4-3.
Detailed Description
The present invention will be described in further detail by way of examples with reference to the accompanying drawings, which are illustrative of the present invention and not limited to the following examples.
Referring to fig. 1-2, it should be understood that the structures, proportions, sizes, etc. shown in the drawings attached hereto are merely used in conjunction with the disclosure of the present specification and should not be construed as limiting the scope of the present invention, which is defined by the appended claims, and any structural modifications, proportional changes, or adjustments of size, which may fall within the scope of the present disclosure without affecting the efficacy or achievement of the present invention. In the meantime, if the terms such as "upper", "lower", "left", "right", "middle" and "a" are used in the present specification, they are merely for convenience of description, but are not intended to limit the scope of the present invention, and the relative relation changes or modifications are considered to be within the scope of the present invention without substantial modification of the technical content.
Example 1.
The online measuring device for the carbon content of the fly ash in the embodiment comprises a flue 1, a fly ash constant-speed sampling system 2, an image shooting analysis system 3 and a fly ash cleaning and collecting system 4, wherein the flue 1 is connected with the fly ash constant-speed sampling system 2, the fly ash cleaning and collecting system 4 is positioned below the fly ash constant-speed sampling system 2, and the fly ash constant-speed sampling system 2 is matched with the image shooting analysis system 3.
The fly ash constant-speed sampling system 2 in the embodiment comprises a sampling gun 2-1, a cyclone separator 2-2, an ejector 2-4, a flow controller 2-7, an exhaust pipe 2-8, an anti-blocking type backrest pipe 2-9, a differential pressure transmitter 2-10 and a blanking valve 2-11, wherein one end of the sampling gun 2-1 is positioned in a flue 1, the other end of the sampling gun 2-1 is connected with the cyclone separator 2-2, the blanking valve 2-11 is installed at the lower end of the cyclone separator 2-2, the upper end of the cyclone separator 2-2 is connected with the ejector 2-4, the ejector 2-4 is connected with the flow controller 2-7, one end of the exhaust pipe 2-8 is connected with the flow controller 2-7, the other end of the exhaust pipe 2-8 is positioned in the flue 1, the differential pressure transmitter 2-10 is connected with the flow controller 2-7, one end of the anti-blocking type backrest pipe 2-9 is connected with the differential pressure transmitter 2-10, and the other end of the anti-blocking type backrest pipe 2-9 is positioned in the flue 1.
The ejector 2-4 in the embodiment comprises a compressed air source 2-3, an ejector body 2-5 and a compressed air jet spray pipe 2-6, wherein the upper end of the cyclone separator 2-2 is connected with the ejector body 2-5, the ejector body 2-5 is connected with a flow controller 2-7, and the ejector body 2-5 is connected with the compressed air source 2-3 through the compressed air jet spray pipe 2-6.
The image capturing and analyzing system 3 in this embodiment includes a telescopic device 3-1, a telescopic rod 3-2, a tray 3-3, a standard color plate 3-4, an optical camera 3-5, an upper light source 3-6, a micro camera 3-7, a lower light source 3-8, a data cable 3-9, a computer 3-10 and a workbench 3-11, the telescopic rod 3-2 is mounted on the telescopic device 3-1, the tray 3-3 is connected with the telescopic rod 3-2, the tray 3-3 is matched with the workbench 3-11, the standard color plate 3-4 is arranged on the workbench 3-11, the optical camera 3-5 and the micro camera 3-7 are respectively located above and below the workbench 3-11, the optical camera 3-5 and the micro camera 3-7 are respectively connected with the computer 3-10, and the upper light source 3-6 and the lower light source 3-8 are respectively located above and below the workbench 3-11, and the optical camera 3-5 and the micro camera 3-7 are respectively connected with the computer 3-10 through the data cable 3-9.
The fly ash cleaning and collecting system 4 in the embodiment comprises a scraping plate 4-1, a compressed air purging device 4-2 and a hopper 4-3, wherein the hopper 4-3 is positioned below a blanking valve 2-11, the scraping plate 4-1 and the compressed air purging device 4-2 are matched with a tray 3-3, and the tray 3-3 is a transparent carrier.
The measuring method of the fly ash carbon content online measuring device in the embodiment comprises the following steps:
a) Collecting a fly ash sample from the flue gas by constant-speed sampling, and preprocessing the fly ash sample to form a fly ash sample with a flat surface on a transparent tray;
b) Respectively obtaining a general image and a microscopic image of the fly ash sample by adopting conventional photographing and microscopic photographing;
c) Analyzing, processing and identifying the fly ash image based on technologies such as image detection, machine vision and the like to obtain characteristic parameters of the fly ash;
d) Obtaining characteristic parameters of boiler combustion from a unit operation database;
f) Obtaining a carbon content measurement value of a fly ash sample from daily routine tests of a unit, and establishing a correlation model of the carbon content measurement value and characteristic parameters (fly ash characteristic parameters and boiler combustion characteristic parameters) through means of machine learning and the like;
g) And f) using the established association model and taking the characteristic parameters of the steps c) and d) as model input to calculate the carbon content of the fly ash, thereby realizing online measurement.
Working principle: the method comprises the steps of sampling fly ash at constant speed, acquiring a fly ash sample, shooting and storing a fly ash image (comprising a conventional image and a microscopic image), acquiring the fly ash image and morphological characteristics based on an image detection technology and a machine vision technology, establishing a fly ash carbon content prediction model based on a machine learning algorithm, self-learning and actually measuring and calculating.
The fly ash constant-speed sampling system 2 utilizes a sampling gun 2-1 to extract flue gas flow from a flue 1 at a constant speed, fly ash in the flow is separated by a cyclone separator 2-2, exhaust gas is returned to the flue 1 through an exhaust pipe 2-8, and the gas flow of the fly ash constant-speed sampling system 2 is provided by an ejector 2-4 (the ejector 2-4 consists of a compressed air source 2-3, an ejector body 2-5 and a compressed air jet pipe 2-6); the flow rate of the flue gas is measured by a flue gas flow rate measuring device consisting of an anti-blocking backrest pipe 2-9 and a differential pressure transmitter 2-10 and is transmitted to a flow controller 2-7 by an electrical signal.
The captured fly ash is collected at the lower part of the cyclone separator 2-2, the blanking valve 2-11 can control blanking of the fly ash to enable the fly ash to fall on the tray 3-3 to form a material pile, then the tray 3-3 translates under the control of the telescopic device 3-1 and passes through the lower part of the scraping plate 4-1, the lower edge of the scraping plate 4-1 is parallel and slightly higher than the tray 3-3, when the tray 3-3 carries the fly ash to pass through the lower part of the scraping plate, the material pile is scraped by the scraping plate 4-1 to form a flat upper surface, and then the tray 3-3 continues to translate to the lower part of the optical camera 3-5 of the observation area and the upper part of the microscopic camera 3-7; the tray 3-3 is made of transparent materials, and is respectively irradiated by the upper light source 3-6, a profile image is shot by the optical camera 3-5, a microscopic image is shot by the microscopic camera 3-7 under the irradiation of the lower light source 3-8, and the image is transmitted to the computer 3-10 for storage, processing and analysis through the data cable 3-9; finally, the tray 3-3 is translated to the lower part of the blanking valve 2-11 again under the control of the telescopic device 3-1, and before blanking again, the upper surface and the lower surface of the tray 3-3 are purged by the compressed air purging device 4-2 so as to remove fly ash on the surface, and the continuous automatic measurement can be realized by repeating the above processes.
The hopper 4-3 is used for collecting fly ash scattered during blanking, scraping and blowing.
The photographing of the optical camera 3-5 and the microscopic camera 3-7 is controlled by the computer 3-10, and both have an auto-focusing function.
The standard color plate 3-4 is used for white balance correction of the image photographed by the optical camera 3-5.
The preferred magnification of the microscope cameras 3-7 is 5x-500x.
As an alternative, the ejector 2-4 may be replaced by a centrifugal fan or a vacuum pump, etc., and the anti-blocking backrest pipe 2-9 may be replaced by a hot wire anemometer or a double venturi velocimeter, etc.
The processes of processing, analyzing and measuring carbon content of the overview image and the microscopic image by the computer 3-10 and the internal algorithm are as follows:
1. obtaining fly ash samples
2. Obtaining characteristic parameters of fly ash samples based on image recognition
2.1 image analysis of the overview image to obtain Gray parameters
2.2, carrying out image recognition and analysis on the microscopic image to obtain morphological characteristic parameters (particle size, slenderness ratio, color and the like) of a certain number of monomer fly ash particles
3. Obtaining the accurate value of the carbon content of the fly ash
3.1, obtaining the carbon content of the fly ash in the same batch in the step 2 (called a calibration reference value) based on the traditional standard measurement method of the carbon content of the fly ash, wherein the step is only carried out when the association relation between the carbon content of the fly ash and the characteristic parameter is required to be calibrated specifically;
3.2, obtaining a factory-level benchmark value of the fly ash carbon content from daily routine tests of the boiler (the fly ash carbon content tests are routine operations, but the test frequency is not high);
3.3, inputting the calibration reference value and the plant-level reference value of the carbon content of the fly ash into a database of a machine learning algorithm of the computer 3-10 together with the fly ash characteristic parameter obtained in the step 2 and the boiler combustion characteristic parameter (coal quality, pulverized coal fineness, furnace temperature, exhaust gas oxygen content, boiler evaporation amount and the like) data obtained from a plant-level information system (such as a plant-level information monitoring system (SIS);
4. repeating steps 1, 2 and 3 under different working conditions such as coal quality, pulverized coal fineness, combustion conditions and the like, and establishing a database with enough samples and enough working conditions
5. Building a correlation model of the carbon content of the fly ash and characteristic parameters through related algorithms such as machine learning and the like:
5.1, establishing a correlation model based on a calibration reference value of the carbon content of the fly ash and a fly ash characteristic parameter and a boiler combustion characteristic parameter (the step is only carried out in a calibration stage);
5.2, building a correlation model based on plant-level reference values of the carbon content of the fly ash, fly ash characteristic parameters and boiler combustion characteristic parameters, wherein the step can be continuously performed, so that the learning process is continuous, the built correlation model can be adjusted and improved along with the change of actual operation conditions, and long-term memory (LSTM) neural network can be adopted for machine learning in the step;
5.3, description: 5.1, 5.2, steps 5.1 and 5.2 may be performed independently of each other, which is not necessary, but advantageous for improving the scientificity and accuracy of the correlation model;
6. actual measurement stage:
6.1, performing online fly ash sampling according to the step 1, and obtaining characteristic parameters of the specific fly ash sample through the step 2
6.2, obtaining the boiler combustion characteristic parameters through the factory level information system
6.3, inputting the characteristic parameters obtained in the steps 6.1 and 6.2 into the correlation model established in the step 5, and calculating to obtain the carbon content of the fly ash sample
7. Continuously improving and correcting the association model established in the step 5 through 'measurement (step 6) -feedback (step 3)':
7.1, recording the calculated value of the carbon content of the fly ash obtained in the step 6
7.2 obtaining the plant-level reference value of the carbon content of the fly ash from routine tests which are closest to the boiler operation conditions and parameters at the time of the fly ash sample collection and have the smallest time interval
The deviation of the carbon content (namely [ measuring value-factory level reference value ]) obtained by 7.1 and 7.2 is used as an error and is fed back to the step 5 to correct and improve the parameters of the algorithm and the associated model.
Taking a large and medium-sized unit of a coal-fired power plant as an example, the device is arranged outside a downstream flue of an air preheater, fly ash is collected from outlet flue gas of the air preheater, a tray 3-3 is rectangular flat glass, and the material is colorless transparent wear-resistant glass, and the device comprises the following steps:
a) The telescopic device 3-1 controls the tray 3-3 to move to the lower part of the blanking valve 2-11 (the blanking valve 2-11 is in a closed state at the moment);
b) Starting a compressed air purging device 4-2, purging the upper surface and the lower surface of the tray 3-3, wherein the purged fly ash falls into the hopper 4-3, the purging strength is gradually increased from low to high, and the purging is stopped after the duration is about 10 s;
c) The fly ash constant-speed sampling system 2 extracts air from the flue gas for 30-60s, and 1-2g of fly ash sample is obtained in a small cyclone separator 2-2;
d) The blanking valve 2-11 is opened, and the fly ash of the cyclone separator 2-2 falls onto the tray 3-3 below;
e) The telescopic device 3-1 moves the tray 3-3 to pass through the lower part of the scraping plate 4-1, the upper surface of the fly ash sample is scraped to be flat by the scraping plate 4-1, and scattered fly ash still falls into the hopper 4-3;
f) The tray 3-3 continues to move to the observation position, and the optical camera 3-5 automatically focuses the fly ash sample on the tray 3-3, shoots a profile image and transmits the profile image to the computer 3-10 under the illumination of the upper light source 3-6;
g) The upper light source 3-6 is turned off, the lower light source 3-8 is turned on, and the micro-camera 3-7 automatically focuses and shoots a microscopic image of the fly ash sample on the tray 3-3 under the illumination of the lower light source 3-8 and transmits the microscopic image to the computer 3-10;
h) C, analyzing, processing and identifying the fly ash images obtained in the steps f and g by a computer 3-10 to obtain fly ash characteristic parameters;
i) The computer 3-10 obtains the boiler combustion characteristic parameters (coal quality, pulverized coal fineness, furnace temperature, exhaust gas oxygen content, boiler evaporation capacity and the like) from the factory level information system;
j) Repeating (a-i) again at intervals of 3mins after the steps are completed;
k) The accumulated fly ash in the hopper 4-3 is collected at intervals of 15mins and is subjected to routine test of the carbon content of the fly ash, and the obtained carbon content data of the fly ash is input into the computer 3-10 (the step belongs to an unnecessary calibration stage);
l) the computer 3-10 obtains routine test data of the carbon content of the fly ash from the factory level information system;
m) learning and improvement of model: the computer 3-10 takes the fly ash characteristic parameters (obtained in step h), the boiler combustion characteristic parameters (obtained in step i) and the actual value of the fly ash carbon content (obtained in step k and/or step l) which are gradually accumulated along with time as known parameters, carries out supervised learning based on machine learning means such as a neural network and the like, and establishes or improves the association model of the fly ash characteristic parameters, the boiler combustion characteristic parameters and the fly ash carbon content;
n) prediction (calculation) of fly ash carbon content: the computer 3-10 predicts the carbon content of the fly ash and outputs the numerical value by taking the fly ash characteristic parameter (obtained in the step h) and the boiler combustion characteristic parameter (obtained in the step i) as the input parameters of the correlation model established in the step m;
step m requires more than hundreds of hours of machine set operation to complete the learning process, the prediction accuracy reaches a higher level, and then the model enters a self-learning and continuous improvement stage (long-term memory LSTM neural network can be adopted for machine learning at the moment);
p) in steps m and n, boiler combustion characteristics are not necessary;
q) step k is not necessary, but step k can speed up the building of the correlation model, without step k, a longer learning process (step o) is required to build the correlation model.
Example 2.
The online measuring device for the carbon content of the fly ash in the embodiment comprises a flue 1, a fly ash constant-speed sampling system 2, an image shooting analysis system 3 and a fly ash cleaning and collecting system 4, wherein the flue 1 is connected with the fly ash constant-speed sampling system 2, the fly ash cleaning and collecting system 4 is positioned below the fly ash constant-speed sampling system 2, and the fly ash constant-speed sampling system 2 is matched with the image shooting analysis system 3.
The fly ash constant-speed sampling system 2 in the embodiment comprises a sampling gun 2-1, a cyclone separator 2-2, an ejector 2-4, a flow controller 2-7, an exhaust pipe 2-8, an anti-blocking type backrest pipe 2-9, a differential pressure transmitter 2-10 and a blanking valve 2-11, wherein one end of the sampling gun 2-1 is positioned in a flue 1, the other end of the sampling gun 2-1 is connected with the cyclone separator 2-2, the blanking valve 2-11 is installed at the lower end of the cyclone separator 2-2, the upper end of the cyclone separator 2-2 is connected with the ejector 2-4, the ejector 2-4 is connected with the flow controller 2-7, one end of the exhaust pipe 2-8 is connected with the flow controller 2-7, the other end of the exhaust pipe 2-8 is positioned in the flue 1, the differential pressure transmitter 2-10 is connected with the flow controller 2-7, one end of the anti-blocking type backrest pipe 2-9 is connected with the differential pressure transmitter 2-10, and the other end of the anti-blocking type backrest pipe 2-9 is positioned in the flue 1.
The ejector 2-4 in the embodiment comprises a compressed air source 2-3, an ejector body 2-5 and a compressed air jet spray pipe 2-6, wherein the upper end of the cyclone separator 2-2 is connected with the ejector body 2-5, the ejector body 2-5 is connected with a flow controller 2-7, and the ejector body 2-5 is connected with the compressed air source 2-3 through the compressed air jet spray pipe 2-6.
The image capturing and analyzing system 3 in this embodiment includes a telescopic device 3-1, a telescopic rod 3-2, a tray 3-3, a standard color plate 3-4, an optical camera 3-5, an upper light source 3-6, a micro camera 3-7, a lower light source 3-8, a data cable 3-9, a computer 3-10 and a workbench 3-11, the telescopic rod 3-2 is mounted on the telescopic device 3-1, the tray 3-3 is connected with the telescopic rod 3-2, the tray 3-3 is matched with the workbench 3-11, the standard color plate 3-4 is arranged on the workbench 3-11, the optical camera 3-5 and the micro camera 3-7 are respectively located above and below the workbench 3-11, the optical camera 3-5 and the micro camera 3-7 are respectively connected with the computer 3-10, and the upper light source 3-6 and the lower light source 3-8 are respectively located above and below the workbench 3-11, and the optical camera 3-5 and the micro camera 3-7 are respectively connected with the computer 3-10 through the data cable 3-9.
The fly ash cleaning and collecting system 4 in the embodiment comprises a scraping plate 4-1, a compressed air purging device 4-2 and a hopper 4-3, wherein the hopper 4-3 is positioned below a blanking valve 2-11, the scraping plate 4-1 and the compressed air purging device 4-2 are matched with a tray 3-3, and the tray 3-3 is a transparent carrier.
The measuring method of the fly ash carbon content online measuring device in the embodiment comprises the following steps:
a) Collecting a fly ash sample from the flue gas by constant-speed sampling, and preprocessing the fly ash sample to form a fly ash sample with a flat surface on a transparent tray;
b) Respectively obtaining a general image and a microscopic image of the fly ash sample by adopting conventional photographing and microscopic photographing;
c) Analyzing, processing and identifying the fly ash image based on technologies such as image detection, machine vision and the like to obtain characteristic parameters of the fly ash;
d) Obtaining characteristic parameters of boiler combustion from a unit operation database;
e) C, obtaining a carbon content measurement value of the fly ash samples in the same batch by adopting a conventional assay means, calibrating the characteristic parameters obtained in the steps c and d, and establishing a correlation model of the characteristic parameters and the carbon content of the fly ash;
f) Obtaining a carbon content measurement value of a fly ash sample from daily routine tests of a unit, and establishing a correlation model of the carbon content measurement value and characteristic parameters (fly ash characteristic parameters and boiler combustion characteristic parameters) through means of machine learning and the like;
g) And c) using the association model established in e) or f), taking the characteristic parameters of the steps c) and d) as model input, measuring and calculating the carbon content of the fly ash, and realizing online measurement.
Working principle: the method comprises the steps of sampling fly ash at constant speed, acquiring a fly ash sample, shooting and storing a fly ash image (comprising a conventional image and a microscopic image), acquiring the fly ash image and morphological characteristics based on an image detection technology and a machine vision technology, establishing a fly ash carbon content prediction model based on a machine learning algorithm, self-learning and actually measuring and calculating.
The fly ash constant-speed sampling system 2 utilizes a sampling gun 2-1 to extract flue gas flow from a flue 1 at a constant speed, fly ash in the flow is separated by a cyclone separator 2-2, exhaust gas is returned to the flue 1 through an exhaust pipe 2-8, and the gas flow of the fly ash constant-speed sampling system 2 is provided by an ejector 2-4 (the ejector 2-4 consists of a compressed air source 2-3, an ejector body 2-5 and a compressed air jet pipe 2-6); the flow rate of the flue gas is measured by a flue gas flow rate measuring device consisting of an anti-blocking backrest pipe 2-9 and a differential pressure transmitter 2-10 and is transmitted to a flow controller 2-7 by an electrical signal.
The captured fly ash is collected at the lower part of the cyclone separator 2-2, the blanking valve 2-11 can control blanking of the fly ash to enable the fly ash to fall on the tray 3-3 to form a material pile, then the tray 3-3 translates under the control of the telescopic device 3-1 and passes through the lower part of the scraping plate 4-1, the lower edge of the scraping plate 4-1 is parallel and slightly higher than the tray 3-3, when the tray 3-3 carries the fly ash to pass through the lower part of the scraping plate, the material pile is scraped by the scraping plate 4-1 to form a flat upper surface, and then the tray 3-3 continues to translate to the lower part of the optical camera 3-5 of the observation area and the upper part of the microscopic camera 3-7; the tray 3-3 is made of transparent materials, and is respectively irradiated by the upper light source 3-6, a profile image is shot by the optical camera 3-5, a microscopic image is shot by the microscopic camera 3-7 under the irradiation of the lower light source 3-8, and the image is transmitted to the computer 3-10 for storage, processing and analysis through the data cable 3-9; finally, the tray 3-3 is translated to the lower part of the blanking valve 2-11 again under the control of the telescopic device 3-1, and before blanking again, the upper surface and the lower surface of the tray 3-3 are purged by the compressed air purging device 4-2 so as to remove fly ash on the surface, and the continuous automatic measurement can be realized by repeating the above processes.
The hopper 4-3 is used for collecting fly ash scattered during blanking, scraping and blowing.
The photographing of the optical camera 3-5 and the microscopic camera 3-7 is controlled by the computer 3-10, and both have an auto-focusing function.
The standard color plate 3-4 is used for white balance correction of the image photographed by the optical camera 3-5.
The preferred magnification of the microscope cameras 3-7 is 5x-500x.
As an alternative, the ejector 2-4 may be replaced by a centrifugal fan or a vacuum pump, etc., and the anti-blocking backrest pipe 2-9 may be replaced by a hot wire anemometer or a double venturi velocimeter, etc.
The processes of processing, analyzing and measuring carbon content of the overview image and the microscopic image by the computer 3-10 and the internal algorithm are as follows:
1. obtaining fly ash samples
2. Obtaining characteristic parameters of fly ash samples based on image recognition
2.1 image analysis of the overview image to obtain Gray parameters
2.2, carrying out image recognition and analysis on the microscopic image to obtain morphological characteristic parameters (particle size, slenderness ratio, color and the like) of a certain number of monomer fly ash particles
3. Obtaining the accurate value of the carbon content of the fly ash
3.1, obtaining the carbon content of the fly ash in the same batch in the step 2 (called a calibration reference value) based on the traditional standard measurement method of the carbon content of the fly ash, wherein the step is only carried out when the association relation between the carbon content of the fly ash and the characteristic parameter is required to be calibrated specifically;
3.2, obtaining a factory-level benchmark value of the fly ash carbon content from daily routine tests of the boiler (the fly ash carbon content tests are routine operations, but the test frequency is not high);
3.3, inputting the calibration reference value and the plant-level reference value of the carbon content of the fly ash into a database of a machine learning algorithm of the computer 3-10 together with the fly ash characteristic parameter obtained in the step 2 and the boiler combustion characteristic parameter (coal quality, pulverized coal fineness, furnace temperature, exhaust gas oxygen content, boiler evaporation amount and the like) data obtained from a plant-level information system (such as a plant-level information monitoring system (SIS);
4. repeating steps 1, 2 and 3 under different working conditions such as coal quality, pulverized coal fineness, combustion conditions and the like, and establishing a database with enough samples and enough working conditions
5. Building a correlation model of the carbon content of the fly ash and characteristic parameters through related algorithms such as machine learning and the like:
5.1, establishing a correlation model based on a calibration reference value of the carbon content of the fly ash and a fly ash characteristic parameter and a boiler combustion characteristic parameter (the step is only carried out in a calibration stage);
5.2, building a correlation model based on plant-level reference values of the carbon content of the fly ash, fly ash characteristic parameters and boiler combustion characteristic parameters, wherein the step can be continuously performed, so that the learning process is continuous, the built correlation model can be adjusted and improved along with the change of actual operation conditions, and long-term memory (LSTM) neural network can be adopted for machine learning in the step;
5.3, description: 5.1, 5.2, steps 5.1 and 5.2 may be performed independently of each other, which is not necessary, but advantageous for improving the scientificity and accuracy of the correlation model;
6. actual measurement stage:
6.1, performing online fly ash sampling according to the step 1, and obtaining characteristic parameters of the specific fly ash sample through the step 2
6.2, obtaining the boiler combustion characteristic parameters through the factory level information system
6.3, inputting the characteristic parameters obtained in the steps 6.1 and 6.2 into the correlation model established in the step 5, and calculating to obtain the carbon content of the fly ash sample
7. Continuously improving and correcting the association model established in the step 5 through 'measurement (step 6) -feedback (step 3)':
7.1, recording the calculated value of the carbon content of the fly ash obtained in the step 6
7.2 obtaining the plant-level reference value of the carbon content of the fly ash from routine tests which are closest to the boiler operation conditions and parameters at the time of the fly ash sample collection and have the smallest time interval
The deviation of the carbon content (namely [ measuring value-factory level reference value ]) obtained by 7.1 and 7.2 is used as an error and is fed back to the step 5 to correct and improve the parameters of the algorithm and the associated model.
Taking a large and medium-sized unit of a coal-fired power plant as an example, the device is arranged outside a downstream flue of an air preheater, fly ash is collected from outlet flue gas of the air preheater, a tray 3-3 is rectangular flat glass, and the material is colorless transparent wear-resistant glass, and the device comprises the following steps:
a) The telescopic device 3-1 controls the tray 3-3 to move to the lower part of the blanking valve 2-11 (the blanking valve 2-11 is in a closed state at the moment);
b) Starting a compressed air purging device 4-2, purging the upper surface and the lower surface of the tray 3-3, wherein the purged fly ash falls into the hopper 4-3, the purging strength is gradually increased from low to high, and the purging is stopped after the duration is about 10 s;
c) The fly ash constant-speed sampling system 2 extracts air from the flue gas for 30-60s, and 1-2g of fly ash sample is obtained in a small cyclone separator 2-2;
d) The blanking valve 2-11 is opened, and the fly ash of the cyclone separator 2-2 falls onto the tray 3-3 below;
e) The telescopic device 3-1 moves the tray 3-3 to pass through the lower part of the scraping plate 4-1, the upper surface of the fly ash sample is scraped to be flat by the scraping plate 4-1, and scattered fly ash still falls into the hopper 4-3;
f) The tray 3-3 continues to move to the observation position, and the optical camera 3-5 automatically focuses the fly ash sample on the tray 3-3, shoots a profile image and transmits the profile image to the computer 3-10 under the illumination of the upper light source 3-6;
g) The upper light source 3-6 is turned off, the lower light source 3-8 is turned on, and the micro-camera 3-7 automatically focuses and shoots a microscopic image of the fly ash sample on the tray 3-3 under the illumination of the lower light source 3-8 and transmits the microscopic image to the computer 3-10;
h) C, analyzing, processing and identifying the fly ash images obtained in the steps f and g by a computer 3-10 to obtain fly ash characteristic parameters;
i) The computer 3-10 obtains the boiler combustion characteristic parameters (coal quality, pulverized coal fineness, furnace temperature, exhaust gas oxygen content, boiler evaporation capacity and the like) from the factory level information system;
j) Repeating (a-i) again at intervals of 3mins after the steps are completed;
k) The accumulated fly ash in the hopper 4-3 is collected at intervals of 15mins and is subjected to routine test of the carbon content of the fly ash, and the obtained carbon content data of the fly ash is input into the computer 3-10 (the step belongs to an unnecessary calibration stage);
l) the computer 3-10 obtains routine test data of the carbon content of the fly ash from the factory level information system;
m) learning and improvement of model: the computer 3-10 takes the fly ash characteristic parameters (obtained in step h), the boiler combustion characteristic parameters (obtained in step i) and the actual value of the fly ash carbon content (obtained in step k and/or step l) which are gradually accumulated along with time as known parameters, carries out supervised learning based on machine learning means such as a neural network and the like, and establishes or improves the association model of the fly ash characteristic parameters, the boiler combustion characteristic parameters and the fly ash carbon content;
n) prediction (calculation) of fly ash carbon content: the computer 3-10 predicts the carbon content of the fly ash and outputs the numerical value by taking the fly ash characteristic parameter (obtained in the step h) and the boiler combustion characteristic parameter (obtained in the step i) as the input parameters of the correlation model established in the step m;
step m requires more than hundreds of hours of machine set operation to complete the learning process, the prediction accuracy reaches a higher level, and then the model enters a self-learning and continuous improvement stage (long-term memory LSTM neural network can be adopted for machine learning at the moment);
p) in steps m and n, boiler combustion characteristics are not necessary;
q) step k is not necessary, but step k can speed up the building of the correlation model, without step k, a longer learning process (step o) is required to build the correlation model.
In addition, it should be noted that the specific embodiments described in the present specification may vary from part to part, from name to name, etc., and the above description in the present specification is merely illustrative of the structure of the present invention. All equivalent or simple changes of the structure, characteristics and principle according to the inventive concept are included in the protection scope of the present patent. Those skilled in the art may make various modifications or additions to the described embodiments or substitutions in a similar manner without departing from the scope of the invention as defined in the accompanying claims.
Claims (3)
1. The online detection method for the carbon content of the fly ash is characterized by comprising the following steps of:
a) The telescopic device (3-1) controls the transparent tray (3-3) to move to the lower part of the blanking valve (2-11), and the blanking valve (2-11) is in a closed state at the moment;
b) Starting a compressed air purging device (4-2), purging the upper surface and the lower surface of the tray (3-3), wherein the purged fly ash falls into the hopper (4-3), the purging strength is gradually increased from low to high, and the purging is stopped after the duration is about 10 s;
c) The constant-speed sampling system (2) for fly ash extracts air from the flue gas for 30-60s, and 1-2g of fly ash sample is obtained in a small cyclone separator (2-2);
d) The blanking valve (2-11) is opened, and the fly ash of the cyclone separator (2-2) falls onto the tray (3-3) below;
e) The telescopic device (3-1) moves the tray (3-3) to pass through the lower part of the scraping plate (4-1), the upper surface of the fly ash sample is scraped by the scraping plate (4-1) and scattered fly ash still falls into the hopper (4-3);
f) The tray (3-3) continues to move to an observation position, and the optical camera (3-5) automatically focuses and shoots a profile image on the fly ash sample on the tray (3-3) under the illumination of the upper light source (3-6) and transmits the profile image to the computer (3-10);
g) The upper light source (3-6) is closed, the lower light source (3-8) is opened, and the microscopic camera (3-7) automatically focuses and shoots microscopic images of the fly ash sample on the tray (3-3) under the illumination of the lower light source (3-8) and transmits the microscopic images to the computer (3-10);
h) F, analyzing, processing and identifying the fly ash images obtained in the steps f and g by a computer (3-10) to obtain fly ash characteristic parameters; the fly ash characteristic parameters comprise particle size, slenderness ratio and color;
i) The computer (3-10) obtains the boiler combustion characteristic parameters from the factory level information system; the boiler combustion characteristic parameters comprise coal quality, pulverized coal fineness, furnace temperature, exhaust gas oxygen content and boiler evaporation capacity;
j) Repeating the steps (a-i) again at intervals of 3mins after the steps are completed;
k) The accumulated fly ash in the hopper (4-3) is collected at 15mins intervals and is subjected to routine test of the carbon content of the fly ash, and the obtained data of the carbon content of the fly ash is input into the computer (3-10);
l) the computer (3-10) obtains routine test data of the carbon content of the fly ash from the factory level information system;
m) the computer (3-10) takes the fly ash characteristic parameter, the boiler combustion characteristic parameter and the fly ash carbon content actual value which are gradually accumulated along with time as known parameters, carries out supervised learning based on a neural network, and establishes or improves a correlation model of the fly ash characteristic parameter, the boiler combustion characteristic parameter and the fly ash carbon content;
n) prediction of fly ash carbon content: and d, the computer (3-10) predicts the carbon content of the fly ash by taking the fly ash characteristic parameter and the boiler combustion characteristic parameter as input parameters of the correlation model established in the step m and outputs a numerical value to realize online measurement.
2. A fly ash carbon content online detection device for performing the online detection method of fly ash carbon content according to claim 1, comprising a flue (1), a fly ash isovelocity sampling system (2), an image capturing analysis system (3) and a fly ash cleaning and collecting system (4), wherein the flue (1) is connected with the fly ash isovelocity sampling system (2), the fly ash cleaning and collecting system (4) is located below the fly ash isovelocity sampling system (2), and the fly ash isovelocity sampling system (2) is matched with the image capturing analysis system (3), and the online detection method is characterized in that: the fly ash constant-speed sampling system (2) comprises a sampling gun (2-1), a cyclone separator (2-2), an ejector (2-4), a flow controller (2-7), an exhaust pipe (2-8), an anti-blocking backrest pipe (2-9), a differential pressure transmitter (2-10) and a blanking valve (2-11), wherein one end of the sampling gun (2-1) is positioned in a flue (1), the other end of the sampling gun (2-1) is connected with the cyclone separator (2-2), the blanking valve (2-11) is arranged at the lower end of the cyclone separator (2-2), the upper end of the cyclone separator (2-2) is connected with the ejector (2-4), the ejector (2-4) is connected with the flow controller (2-7), one end of the exhaust pipe (2-8) is connected with the flow controller (2-7), the other end of the exhaust pipe (2-8) is positioned in the flue (1), the differential pressure transmitter (2-10) is connected with the flow controller (2-7), the anti-blocking backrest pipe (2-9) is connected with the differential pressure transmitter (2-7), the other end of the anti-blocking backrest pipe (2-9) is positioned in the flue (1); the image shooting analysis system (3) comprises a telescopic device (3-1), a telescopic rod (3-2), a tray (3-3), a standard color plate (3-4), an optical camera (3-5), a microscopic camera (3-7), a computer (3-10) and a workbench (3-11), wherein the telescopic rod (3-2) is arranged on the telescopic device (3-1), the tray (3-3) is connected with the telescopic rod (3-2), the tray (3-3) is matched with the workbench (3-11), the standard color plate (3-4) is arranged on the workbench (3-11), the optical camera (3-5) and the microscopic camera (3-7) are respectively arranged above and below the workbench (3-11), and the optical camera (3-5) and the microscopic camera (3-7) are connected with the computer (3-10); the fly ash cleaning and collecting system (4) comprises a scraping plate (4-1), a compressed air purging device (4-2) and a hopper (4-3), wherein the hopper (4-3) is positioned below a blanking valve (2-11), and the scraping plate (4-1) and the compressed air purging device (4-2) are matched with a tray (3-3); the image shooting analysis system (3) further comprises an upper light source (3-6), a lower light source (3-8) and a data cable (3-9), wherein the upper light source (3-6) and the lower light source (3-8) are respectively positioned above and below the workbench (3-11), and the optical camera (3-5) and the microscopic camera (3-7) are connected with the computer (3-10) through the data cable (3-9); the tray (3-3) is a transparent carrier.
3. The fly ash carbon content online measurement device according to claim 2, wherein: the ejector (2-4) comprises a compressed air source (2-3), an ejector body (2-5) and a compressed air jet nozzle (2-6), wherein the upper end of the cyclone separator (2-2) is connected with the ejector body (2-5), the ejector body (2-5) is connected with a flow controller (2-7), and the ejector body (2-5) is connected with the compressed air source (2-3) through the compressed air jet nozzle (2-6).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911218193.7A CN110954536B (en) | 2019-12-03 | 2019-12-03 | Online measuring device and method for carbon content of fly ash |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911218193.7A CN110954536B (en) | 2019-12-03 | 2019-12-03 | Online measuring device and method for carbon content of fly ash |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110954536A CN110954536A (en) | 2020-04-03 |
| CN110954536B true CN110954536B (en) | 2024-02-09 |
Family
ID=69979548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911218193.7A Active CN110954536B (en) | 2019-12-03 | 2019-12-03 | Online measuring device and method for carbon content of fly ash |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110954536B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114965164A (en) * | 2022-06-02 | 2022-08-30 | 连云港同顺电力节能设备有限公司 | Power production fly ash monitoring system, method and storage medium |
| CN115683751A (en) * | 2022-10-31 | 2023-02-03 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Device and method for synchronizing fly ash sampling and rapid detection of fly ash conveying system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1992008965A1 (en) * | 1990-11-13 | 1992-05-29 | Powergen Plc | Method and apparatus for measurement of carbon in ash |
| DE10211410A1 (en) * | 2002-03-15 | 2003-10-02 | Rag Ag | Determination of the slag content in coal by passing a sample through a measurement path in which both particle size distribution and average gray value of reflected light are determined and then used to determine slag content |
| 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 |
| CN201965095U (en) * | 2011-01-06 | 2011-09-07 | 长沙市亿泰科技有限公司 | Online monitoring device for carbon content in fly ash |
| CN102778538A (en) * | 2012-07-06 | 2012-11-14 | 广东电网公司电力科学研究院 | Soft measuring method based on improved SVM (Support Vector Machine) for measuring boiler unburned carbon content in fly ash |
| CN202886143U (en) * | 2012-11-26 | 2013-04-17 | 山东电力集团公司电力科学研究院 | Permanent flying ash sampling device of coal-fired boiler |
| CN103822880A (en) * | 2014-02-26 | 2014-05-28 | 清华大学 | Method and system for measuring fly ash carbon content |
| CN204202951U (en) * | 2014-11-13 | 2015-03-11 | 东方电气集团东方锅炉股份有限公司 | Online constant speed flyash sampler |
| 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 |
| CN107133460A (en) * | 2017-04-26 | 2017-09-05 | 中国能源建设集团广东省电力设计研究院有限公司 | A kind of online dynamic prediction method of boiler flyash carbon content |
| CN107356598A (en) * | 2017-06-08 | 2017-11-17 | 中国计量大学 | Ash content carbon online test method based on digital image processing techniques |
| CN211927711U (en) * | 2019-12-03 | 2020-11-13 | 华电电力科学研究院有限公司 | Fly ash carbon content on-line measuring device |
-
2019
- 2019-12-03 CN CN201911218193.7A patent/CN110954536B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1992008965A1 (en) * | 1990-11-13 | 1992-05-29 | Powergen Plc | Method and apparatus for measurement of carbon in ash |
| DE10211410A1 (en) * | 2002-03-15 | 2003-10-02 | Rag Ag | Determination of the slag content in coal by passing a sample through a measurement path in which both particle size distribution and average gray value of reflected light are determined and then used to determine slag content |
| 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 |
| CN201965095U (en) * | 2011-01-06 | 2011-09-07 | 长沙市亿泰科技有限公司 | Online monitoring device for carbon content in fly ash |
| CN102778538A (en) * | 2012-07-06 | 2012-11-14 | 广东电网公司电力科学研究院 | Soft measuring method based on improved SVM (Support Vector Machine) for measuring boiler unburned carbon content in fly ash |
| CN202886143U (en) * | 2012-11-26 | 2013-04-17 | 山东电力集团公司电力科学研究院 | Permanent flying ash sampling device of coal-fired boiler |
| CN103822880A (en) * | 2014-02-26 | 2014-05-28 | 清华大学 | Method and system for measuring fly ash carbon content |
| CN204202951U (en) * | 2014-11-13 | 2015-03-11 | 东方电气集团东方锅炉股份有限公司 | Online constant speed flyash sampler |
| 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 |
| CN107133460A (en) * | 2017-04-26 | 2017-09-05 | 中国能源建设集团广东省电力设计研究院有限公司 | A kind of online dynamic prediction method of boiler flyash carbon content |
| CN107356598A (en) * | 2017-06-08 | 2017-11-17 | 中国计量大学 | Ash content carbon online test method based on digital image processing techniques |
| CN211927711U (en) * | 2019-12-03 | 2020-11-13 | 华电电力科学研究院有限公司 | Fly ash carbon content on-line measuring device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110954536A (en) | 2020-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN211927711U (en) | Fly ash carbon content on-line measuring device | |
| CN105956618B (en) | Converter steelmaking blowing state identification system and method based on image dynamic and static characteristics | |
| CN110954536B (en) | Online measuring device and method for carbon content of fly ash | |
| WO2021073351A1 (en) | Quantitative evaluation method for pyrolysis activation energy of graded diesel engine particle | |
| CN101413892B (en) | Flyash ingredient on-line detection device based on laser induce plasma analysis technology | |
| CN109737898B (en) | System for realizing online test of high-temperature corrosion of water-cooled wall | |
| CN104502156A (en) | Sampling system for atmospheric pollutants discharged by civil cooking range | |
| CN102095733A (en) | Machine vision-based intelligent detection method for surface defect of bottle cap | |
| CN107589053A (en) | Automatic sampling fineness of pulverized coal On-line Measuring Method and measurement apparatus | |
| CN205845067U (en) | The pneumatic steelmaking blowing state recognition system of static nature is moved based on image | |
| CN104502284A (en) | Online detection device for carbon content in flue dust of coal fired power plant | |
| CN109492708A (en) | Missing data interpolating method is detected in a kind of pipe leakage based on LS-KNN | |
| CN112163350B (en) | Real-time on-line soft measurement system and method for pulverized coal fineness of double models of pulverizing system | |
| CN101858591A (en) | Diagnosis and prevention system and method of high temperature corrosion state of boiler water cooled wall | |
| CN101949865B (en) | Method for optimizing Parsytec on-line surface defect detection system | |
| CN111289697A (en) | CEMS running state monitoring and data false identification method and system | |
| CN116989335B (en) | Online tracking analysis method and system before garbage is burned in furnace | |
| CN112649332A (en) | Power plant coal particle size distribution online detection device and method | |
| CN107860715B (en) | Method for detecting carbon content of boiler slag | |
| CN1542432A (en) | Method for measuring carbon content in coal-burning boiler and kiln fly ash and on line detection apparatus therefor | |
| CN207570974U (en) | Automatic sampling fineness of pulverized coal on-line measurement device | |
| JP7308016B2 (en) | Waste quality estimation system and method, and waste storage facility | |
| CN113608506B (en) | Intelligent detection device for alumina operation index | |
| CN114549995A (en) | Method and system for identifying raw materials running in kiln | |
| CN107356598A (en) | Ash content carbon online test method based on digital image processing techniques |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |