CN112999834B - Machine vision system and method for monitoring health state of slurry of absorption tower of coal-fired power plant - Google Patents
Machine vision system and method for monitoring health state of slurry of absorption tower of coal-fired power plant Download PDFInfo
- Publication number
- CN112999834B CN112999834B CN202110128259.4A CN202110128259A CN112999834B CN 112999834 B CN112999834 B CN 112999834B CN 202110128259 A CN202110128259 A CN 202110128259A CN 112999834 B CN112999834 B CN 112999834B
- Authority
- CN
- China
- Prior art keywords
- slurry
- absorption tower
- phase
- dilute phase
- monitoring module
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/46—Removing components of defined structure
- B01D53/48—Sulfur compounds
- B01D53/50—Sulfur oxides
- B01D53/501—Sulfur oxides by treating the gases with a solution or a suspension of an alkali or earth-alkali or ammonium compound
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/346—Controlling the process
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/74—General processes for purification of waste gases; Apparatus or devices specially adapted therefor
- B01D53/77—Liquid phase processes
- B01D53/78—Liquid phase processes with gas-liquid contact
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Analytical Chemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Treating Waste Gases (AREA)
Abstract
The invention relates to a system and a method for monitoring the health state of slurry in an absorption tower, belonging to the field of limestone-gypsum wet flue gas desulfurization in a coal-fired power plant. The monitoring system comprises a dilute phase industrial vision monitoring module, a dilute phase secondary fluid pump, a concentrated phase industrial vision monitoring module, an absorption tower, a circulating pump, a cleaning water pump, a high-efficiency liquid-solid separator, a dilute phase ball valve and a waste liquid pool, wherein the circulating pump is matched with one side of the absorption tower, the discharge end of the absorption tower is connected with the high-efficiency liquid-solid separator, the dilute phase ball valve is arranged at the outlet of the high-efficiency liquid-solid separator, and slurry dilute phase and slurry concentrated phase are respectively communicated with the dilute phase industrial vision monitoring module and the concentrated phase industrial vision monitoring module and are respectively conveyed to a downstream area through the dilute phase secondary fluid pump and the concentrated phase secondary fluid pump. The system of the invention has reasonable design, adopts machine vision to replace human eye observation to carry out continuous and on-line analysis on the treated slurry, effectively shortens the monitoring time, reduces the labor intensity and improves the measurement accuracy.
Description
Technical Field
The invention relates to a system and a method, in particular to a machine vision system and a machine vision method for monitoring the health state of slurry of an absorption tower of a coal-fired power plant, belonging to the field of limestone-gypsum wet flue gas desulfurization of the coal-fired power plant.
Background
More than 90% of large coal-fired power plants in China adopt a limestone-gypsum wet desulphurization process to realize ultralow emission of sulfur dioxide. The wet desulphurization process system has the advantages of high desulphurization efficiency and strong adaptability to coal types and loads, but also has the defects of complex physicochemical process and process flow, high difficulty in state monitoring and optimization control, and frequent occurrence of operation deviation from the optimal state or even faults and abnormity.
Limestone is one of the most key raw materials of a limestone-gypsum wet desulphurization process system, and the state of the limestone in a slurry pond can reflect whether a desulphurization system operates normally. When the slurry poisoning phenomenon occurs in the absorption tower, the color and the shape of the slurry in the slurry pool may also be changed. For example, the slurry of the absorption tower is milky white in color under normal conditions, is obviously layered after standing for a period of time, the upper layer is clear and light, when the slurry is abnormal, the slurry is grayish black in color, and the slurry is not obviously changed after standing for a period of time. Therefore, the internal operating state of the absorption tower can be determined to a certain extent by directly sampling and analyzing the slurry in the absorption tower.
At present, the slurry in the absorption tower is directly sent to a laboratory of a power plant for treatment (standing sedimentation or centrifugal layering). Then the slurry state of the absorption tower is determined by means of chemical component analysis. This work is time consuming, which results in the operator losing the gold opportunity for rescuing the absorption tower equipment to operate, resulting in very high disposal cost after determining the device abnormality. The sampled slurry is observed by naked eyes, so that the sampled slurry has high randomness and poor resolution, and can not be used for quantifying the abnormal state standard.
Although the chemical components cannot be visually perceived by people, the chemical detection means is complex and time-consuming, and the abnormality of the slurry is reflected on the change of the physical characteristics. The change in slurry composition is first reflected directly as a color change, e.g., the slurry tends to be gray/black when more fly ash or oil is mixed in. Secondly, the serous fluid in a normal state is obviously layered after standing for a period of time, the upper layer is clear and has lighter color, the lower layer is precipitated solid particles and has darker color, and the serous fluid in an abnormal state is not precipitated and is not layered after standing for a long time.
At present, the slurry monitoring adopts the measures of manual on-site inspection visual inspection, remote video monitoring manual visual inspection, on-site sampling and laboratory test. The visual observation means is restricted by the human's energy and mental power and cannot be continuously performed on-line. The means of testing after on-site sampling has high accuracy and good repeatability, but consumes long time and can only be implemented discontinuously. Therefore, if a set of slurry continuous on-line monitoring system can be designed, and the machine vision is used for replacing the visual observation and judgment of people, the monitoring time can be effectively shortened, and the measurement accuracy can be improved.
The Chinese patent with publication number CN211553459U, whose publication number is 09/22 in 2020, discloses a utility model named as "a continuous monitoring sampling probe rod for wet flue gas desulfurization"; the patent aims at carrying out on-line monitoring on waste gas after wet desulphurization in coking production.
The invention discloses an invention patent named as a denitration speed field on-line dynamic adjustable flow system and method in Chinese patent with publication number CN108636102A, which is published as 10, 12 and 2018.
However, the above patent applications all belong to the field of nitrogen oxide removal, and no report of monitoring the health state of wet slurry based on a machine vision technology is found; it also has the above-mentioned drawbacks.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides the machine vision-based coal-fired power plant absorption tower slurry health state monitoring system and method which have reasonable system design, are stable and reliable, adopt machine vision to replace human eye observation to carry out continuous and on-line analysis on the treated slurry, effectively shorten the monitoring time, reduce the labor intensity and improve the measurement accuracy.
The technical scheme adopted by the invention for solving the problems is as follows: this coal fired power plant's absorption tower thick liquid health status monitoring system of machine vision, including absorption tower, circulating pump, sample main valve, washing water pump, high-efficient liquid-solid separator, dilute phase ball valve and waste liquid pond, the supporting circulating pump in absorption tower one side, the absorption tower discharge end links to each other with high-efficient liquid-solid separator, and through setting up sample main valve control flow, the export of high-efficient liquid-solid separator sets up dilute phase ball valve, its characterized in that on the way: the system also comprises a dilute-phase industrial vision monitoring module, a dilute-phase secondary fluid pump, a concentrated-phase secondary fluid pump and a concentrated-phase industrial vision monitoring module, wherein a slurry dilute phase is separated from an overflow port outlet of the high-efficiency liquid-solid separator, a slurry concentrated phase is separated from a bottom flow port of the high-efficiency liquid-solid separator, the slurry dilute phase and the slurry concentrated phase are respectively communicated with the dilute-phase industrial vision monitoring module and the concentrated-phase industrial vision monitoring module and are respectively conveyed to a downstream area through the dilute-phase secondary fluid pump and the concentrated-phase secondary fluid pump, and slurry in the downstream area is pumped back into a slurry pool of the absorption tower or flows into a waste liquid pool as required.
Preferably, the system also comprises a first industrial camera and a second industrial camera which have the same structures, and one sides of the dilute-phase industrial vision monitoring module and the dense-phase industrial vision monitoring module are correspondingly provided with the first industrial camera and the second industrial camera which are matched with each other.
Preferably, the dilute-phase industrial vision monitoring module and the concentrated-phase industrial vision monitoring module respectively comprise a light source, a camera bellows, a duckbill, an observation window, a receiving port and a second industrial camera, wherein the light source, the duckbill, the observation window, the receiving port and the second industrial camera are all arranged in the camera bellows, the light source is the only light source in the module, the duckbill flattens and bundles fluid of the high-efficiency liquid-solid separator, the receiving port is used for receiving the fluid flowing out of the duckbill, the fluid between the receiving port and the duckbill is not in contact with a wall surface and is used for observation of the second industrial camera, and the observation window is arranged between the duckbill and the receiving port.
Preferably, the monitoring system further comprises a waste liquid branch valve, and the waste liquid branch valve is arranged on the waste liquid pool branch.
The invention also provides a machine vision method for the system for monitoring the health state of the slurry of the absorption tower of the coal-fired power plant, which is characterized by comprising the following steps: the method comprises the following steps:
(S1) separating the material under the condition of unknown health information of the slurry of the absorption tower into two streams of thin and thin phases and thick phases through a high-efficiency liquid-solid separator; inputting the information characteristics of the thin and thick fluid into a mapping model, and outputting the calculated health state of the slurry of the absorption tower by the mapping model;
(S2) the slurry quality evaluation algorithm module judges whether the slurry health degree is normal or abnormal according to the combination of the color characteristics of the materials and the slurry property information, the dilute phase and dense phase health indexes meet/exceed the related technical standards and the specified limits, and the slurry quality in the absorption tower is judged to be normal/abnormal;
(S3) the user service module presents the material image, color characteristics, and absorption tower slurry quality assessment result information to the user through a graphical interface, and provides user interaction functions including (but not limited to) retrieval and storage of images and data.
Preferably, the mapping model in (S1) of the present invention is established by a machine learning method to estimate the health status of the slurry based on the color characteristics of the slurry.
Preferably, the color feature in (S2) of the present invention determines whether the image is abnormal by obtaining the gray-scale value/RGB component ratio/HSV component ratio of the image.
Preferably, in the user service module (S3) of the present invention, the carrier is a computer, and when the slurry quality is abnormal, the user is reminded by a software box, a sound, or a light-word plate.
Compared with the prior art, the invention has the following advantages and effects: (1) compared with the traditional absorption tower slurry assay means, the method has the advantages that the absorption tower slurry analysis is continuous and on-line analysis; the method adopts machine vision to replace human eye observation to analyze the treated slurry; the method utilizes the information of slurry turbidity degree, color and the like, and judges the slurry state of the absorption tower according to the image information obtained by machine vision, so as to judge the internal operation state of the absorption tower; (2) the uninterrupted sampling of the high-efficiency liquid-solid separator can meet the time response requirement of continuous on-line measurement, and the monitoring time can be effectively shortened; meanwhile, compared with visual observation, the quantitative standard can be formulated to judge the slurry state of the absorption tower in the absorption tower more accurately and professionally; (3) the application can effectively save the workload of the working personnel and shorten the abnormal time of the equipment, thereby contributing to the economic benefit and the environmental protection of the power plant.
Drawings
FIG. 1 is a flow chart of a system for health status detection of absorber tower slurry according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of an industrial vision monitoring module arrangement according to an embodiment of the invention.
FIG. 3 is a graph showing the correlation between the gray scale values of the dilute phase and the concentrated phase and the health of the slurry according to the embodiment of the present invention.
FIG. 4 is a flow chart of a pipeline cleaning module according to an embodiment of the invention.
In the figure: the system comprises an absorption tower 1, a circulating pump 2, a sampling main valve 3, a cleaning water pump 4, a high-efficiency liquid-solid separator 5, a dilute phase ball valve 6, a first industrial camera 7, a dilute phase industrial vision monitoring module 8, a dilute phase secondary fluid pump 9, a waste liquid branch valve 10, a waste liquid pool 11, a concentrated phase secondary fluid pump 12 and a concentrated phase industrial vision monitoring module 13; a second industrial camera 14, a light source 14A, a dark box 14B, a duckbill 14C, an observation window 14D and a receiving opening 14E.
Detailed Description
The present invention will be described in further detail below by way of examples with reference to the accompanying drawings, which are illustrative of the present invention and are not to be construed as limiting the present invention.
Examples are given.
Referring to fig. 1 to 4, the system for monitoring the slurry health state of the absorption tower of the coal-fired power plant with machine vision in this embodiment includes an absorption tower 1, a circulating pump 2, a sampling main valve 3, a cleaning water pump 4, a high-efficiency liquid-solid separator 5, a dilute phase ball valve 6, a waste liquid tank 11, a dilute phase industrial vision monitoring module 8, a dilute phase secondary fluid pump 9, a concentrated phase secondary fluid pump 12 and a concentrated phase industrial vision monitoring module 13, the circulating pump 2 is matched with one side of the absorption tower 1, the discharge end of the absorption tower 1 is connected with the high-efficiency liquid-solid separator 5, the flow rate is controlled by arranging the sampling main valve 3 on a branch, the dilute phase ball valve 6 is arranged at the outlet of the high-efficiency liquid-solid separator 5, the slurry dilute phase is separated from the overflow outlet of the high-efficiency liquid-solid separator 5, the slurry concentrated phase is separated from the bottom flow port of the high-efficiency liquid-solid separator 5, and the slurry phase are respectively communicated with the dilute phase industrial vision monitoring module 8 and the concentrated phase industrial vision monitoring module 13, then the slurry is respectively conveyed to a downstream area through a dilute phase secondary fluid pump 9 and a concentrated phase secondary fluid pump 12, and the slurry in the downstream area is pumped back into the slurry pool of the absorption tower 1 or flows into a waste liquid pool 11 according to requirements; the waste liquid branch valve 10 is arranged on a branch of the waste liquid pool 11.
The first industrial camera 7 and the second industrial camera 14 of the embodiment have the same structure, and the first industrial camera 7 and the second industrial camera 14 which are matched with each other are correspondingly arranged on one side of the dilute-phase industrial vision monitoring module 8 and one side of the dense-phase industrial vision monitoring module 13.
The dilute-phase industrial vision monitoring module 8 and the concentrated-phase industrial vision monitoring module 13 in this embodiment each include a light source 14A, a dark box 14B, a duckbill 14C, an observation window 14D, a receiving port 14E, and a second industrial camera 14, the light source 14A, the duckbill 14C, the observation window 14D, the receiving port 14E, and the second industrial camera 14 are all disposed in the dark box 14B, the light source 14A is the only light source in the module, the duckbill 14C flattens and bundles the fluid of the high-efficiency liquid-solid separator 5, the receiving port 14E is used for receiving the fluid flowing out from the duckbill 14C, the fluid between the receiving port 14E and the duckbill 14C does not contact with a wall surface and is used for observation by the second industrial camera 14, and the observation window 14D is disposed between the duckbill 14C and the receiving port 14E.
The embodiment is applied to an absorption tower desulfurization system and mainly comprises a fluid image acquisition module, a data analysis module, a pipeline cleaning module and a high-efficiency liquid-solid separator 5. Compared with the traditional absorption tower slurry assay mode, the absorption tower slurry analysis is continuous and on-line; adopting machine vision to replace human eye observation to analyze the treated slurry; and judging the state of the slurry in the absorption tower by using the image information obtained by machine vision according to the information such as the turbidity degree, color and the like of the slurry, and further judging the internal operation state of the absorption tower.
In this embodiment, the output of the image analysis module is used as an input condition, and the evaluation result of the slurry quality of the absorption tower is output by the slurry health online evaluation method.
The pipeline cleaning module of the embodiment extracts image characteristics and feedback of information of the fluid measuring instrument through the front-end industrial camera, clear water or detergent is manually or automatically introduced from the bypass at regular intervals, and a main path inlet pipeline valve is in a closed state when the pipeline is cleaned.
The data analysis module of the embodiment mainly comprises image recording, image processing and fault diagnosis at the front end; shooting image data of the slurry of the absorption tower through a front-end camera, processing the shot slurry image by using a program, and carrying out expert diagnosis on the fault type in the absorption tower according to the processing result.
In the high-efficiency liquid-solid separator 5 of the embodiment, two phases of slurry in the absorption tower are separated in a centrifugal separation mode; the separator structure can be a hydraulic cyclone device based on the free vortex principle, and can also be a dynamic centrifugal separation device based on the forced vortex principle.
The online evaluation method for the health state of the slurry in the embodiment calculates the health state of the slurry according to the color characteristics of the material, and is realized by the following steps:
(1) under the stable working condition, slurry is extracted from the absorption tower through a pump and is separated into two streams of fluid, namely a dilute phase and a thick phase, through a high-efficiency separator.
(2) The image acquisition module captures a material image, and the image analysis module analyzes the image to obtain the color characteristics of the material.
(3) Sampling the material, testing to obtain the slurry components, and evaluating the health state of the slurry.
(4) And (3) adjusting working conditions to change the components of the slurry in the absorption tower, repeating the steps (1) to (2), and establishing a data set of the color characteristics of the materials and the health state of the corresponding slurry.
(5) And (4) based on the data set in the step (4), adopting a machine learning method to establish a mapping model for calculating the health state of the slurry according to the color characteristics of the slurry.
(6) And (4) inputting the material information characteristics under the condition of unknown absorption tower slurry health information into the mapping model in the step (5), and outputting the calculated absorption tower slurry health state by the mapping model.
The slurry health state monitoring system of the embodiment works according to the following steps:
(S1) separating the material under the condition of unknown health information of the slurry of the absorption tower into two flows of a thin phase and a thick phase through a high-efficiency centrifugal separator. Inputting the information characteristics of the thin and thick fluid into the mapping model in the step (5), and outputting the health state of the slurry of the absorption tower by the mapping model.
(S2) the pulp quality evaluation algorithm module of the absorption tower judges whether the pulp health degree is normal or abnormal according to the color characteristic information of the materials in a combined manner, the dilute phase and dense phase health indexes meet/exceed the related technical standards and the specified limits, and the pulp quality in the absorption tower is judged to be normal/abnormal.
(S3) the user service module presents information such as material images, color characteristics, quality evaluation results of absorption tower slurry and the like to the user through a graphical interface, and provides user interaction functions including (but not limited to) retrieval, storage and the like of images and data.
The mapping model in this embodiment (S1) is established by a machine learning method to estimate the health status of the slurry based on the color characteristics of the slurry.
In the color feature in this embodiment (S2), whether the image is abnormal is determined by the obtained image gray-scale value size/RGB component ratio/HSV component ratio.
In the user service module of this embodiment (S3), the carrier is a computer, and when the slurry quality is abnormal, the user is reminded by means of a software box, a sound, a light word plate, and the like.
The technical principle of the embodiment is as follows: limestone is one of the most key raw materials of a limestone-gypsum wet desulphurization process system, and the state of the limestone in a slurry pond can reflect whether a desulphurization system operates normally. When the slurry poisoning phenomenon occurs in the absorption tower, the color and the shape of the slurry in the slurry pool may also be changed. For example, the color of the slurry is milky white under normal conditions, the slurry is obviously layered after standing for a period of time, the upper layer is clear and light, when abnormality occurs, the color of the slurry is grayish black, and the slurry is not obviously changed after standing for a period of time. Therefore, the internal operating state of the absorption tower can be determined to a certain extent by directly sampling and analyzing the slurry in the absorption tower. And whether the traditional slurry is normally tested by a laboratory manually or observed by eyes, uninterrupted implementation is difficult due to the limitation of manpower, objective evaluation standards are lacked, and the invention has the advantage of continuous and automatic monitoring.
Example 1:
coal quality of a certain plant is changed frequently, load is lifted frequently, the phenomenon of sudden jump of the sulfur dioxide in the raw flue gas occurs, and the slurry poisoning of the absorption tower occurs frequently. The present embodiment realizes the health status monitoring of the slurry by the following methods:
in the process of stopping and transforming the coal-fired power generating unit, a bypass is led out from the position of an upstream pipeline of a circulating loop of the absorption tower 1 and is merged into a slurry health state detection system shown in figure 1. As shown, the system is introduced at a bypass location after discharge from the absorber column 1 and flow is controlled by a main sampling valve 3, the bypass flow being directed to a high efficiency liquid-solid separator 5 static hydrocyclone. The outlet of the overflow port of the high-efficiency liquid-solid separator 5 separates out slurry dilute phase, and the underflow port separates out slurry concentrated phase. The dilute phase and the concentrated phase respectively reach the dilute phase industrial visual monitoring module 8 and the concentrated phase industrial visual monitoring module 13. After the machine vision observation area is passed, the slurry is conveyed to a downstream area by using a pump, and the slurry in the downstream area is pumped back to the slurry tank of the absorption tower or flows into the waste liquid tank 11 according to requirements.
The dilute-phase industrial vision monitoring module 8 of the present embodiment is structured as shown in fig. 2, and includes a second industrial camera 14, a light source 14A, a dark box 14B, a duckbill 14C, an observation window 14D, and a receiving opening 14E. In order for the device status to be dark, its light source 14A is the only light source within the module. In order to take a clear image by the second industrial camera 14, the outlet of the pipeline is in a duckbill shape, so that the fluid forms a water curtain to be left. The bottom receiving port 14E is for receiving fluid from the duckbill opening. Meanwhile, in order to avoid the wall surface from being scaled when the wall surface works for a long time, the fluid in the observation area is designed not to contact the wall surface.
The industrial camera can judge whether the slurry is abnormal or not by monitoring the gray values of the dilute phase and the dense phase of the slurry in the absorption tower. When the dilute phase gray value and the concentrated phase gray value fall within the set range, the system judges the state of the slurry of the absorption tower. The normal/abnormal boundary is an equal-proportion linear function, or is adjusted in real time according to the actual situation, and when the boundary is a straight line, the set value of the proportion coefficient is related to the coal quality of the power plant, the limestone quality and the sampling illumination. When the illumination is insufficient or the interference of human factors is large, the normal image sample cannot be obtained by sampling, namely, the dilute phase and the dense phase are dark in color, and the size of the slurry cannot be judged at the moment. Therefore, the gray value identification area should have the minimum value, and fig. 3 shows a schematic diagram of a gray contrast-based slurry normal/abnormal judgment rule, which judges whether the slurry is healthy or not according to the dilute phase and the dense phase data measured in real time.
The working process flow of the pipeline cleaning module is shown in fig. 4, and the main effect is to avoid the influence on the precision of the measuring instrument when the pipeline is accumulated with more impurities and foreign matters. The present embodiment assumes that the response condition is a gray value abnormality. As shown in fig. 3, when the value falls in the non-slurry interval, the liquid feeding from the absorption tower is stopped, the clean water valve is opened, the water pump starts to work to remove impurities in the pipeline, and the monitoring work is continued after a period of time.
The process of this embodiment is:
(1) a photographic image of the absorption tower slurry is taken by the industrial camera of the image acquisition module.
(2) The image acquisition module transmits the image to the image analysis module, the image analysis module respectively acquires color data of the slurry through an image recognition algorithm, converts the RGB format of the color data into the HSL format, and counts to obtain the average value of each component.
(3) And (4) manually sampling the slurry of the dehydration absorption tower on site, and testing to obtain the slurry components.
(4) And (4) adjusting the working condition to enable the slurry components of the absorption tower to repeat the steps (1) to (3), and establishing a data set of the HSL components and the corresponding slurry components of the absorption tower.
(5) And (4) classifying the quantitative relation between the impurity concentration and the type by adopting an automatic machine learning tool/software based on the data set in the step (3), so as to establish a mapping model for calculating the slurry component of the absorption tower according to the color component value, and integrating the mapping model into a slurry quality evaluation algorithm module.
(6) And (3) the system enters a continuous monitoring state, namely, steps (1) to (2) are executed, the HSL obtained in the step (2) is input into a slurry quality evaluation algorithm module, the latter calculates the fault type and the strength of the slurry, compares the fault type and the strength with a slurry qualified limit value, and sets a qualified threshold value. Above the acceptable limit, the slurry is abnormal, otherwise it is acceptable (normal).
(7) The user service module reads an original image from the image acquisition module, reads a post-processing image marked with the health state of the slurry from the image analysis module, reads a slurry component calculation value and a component normal/abnormal state identifier from the slurry quality evaluation algorithm module, and presents the slurry component calculation value and the component normal/abnormal state identifier to an operator through a webpage interface to provide slurry quality monitoring information for the operator.
Example 2:
referring to embodiment 1, the difference is that a mapping model is established together with slurry state information, a separator is a dynamic centrifugal separation device, and the flow of this embodiment is as follows:
(1-3) same as in example 1, step (1-3).
(4) The density and turbidity of the slurry were measured.
(5) And (5) adjusting the working condition to enable the absorption tower slurry component, repeating the steps (1) to (4), and establishing a data set of the color numerical value, the gray value, the density and the turbidity value and the corresponding absorption tower slurry component.
(6-8) same as in example 1, step (5-7).
And will be apparent to those skilled in the art from the foregoing description.
In addition, it should be noted that the specific embodiments described in the present specification may be different in the components, the shapes of the components, the names of the components, and the like, and the above description is only an illustration of the structure of the present invention. Equivalent or simple changes in the structure, characteristics and principles of the invention are included in the protection scope of the patent. Various modifications, additions and substitutions for the specific embodiments described may be made by those skilled in the art without departing from the scope of the invention as defined in the accompanying claims.
Claims (5)
1. The utility model provides a coal fired power plant absorption tower thick liquid health status monitoring system of machine vision, includes absorption tower (1), circulating pump (2), sample main valve (3), washing water pump (4), high-efficient liquid-solid separation ware (5), dilute phase ball valve (6) and waste liquid pond (11), the supporting circulating pump (2) in absorption tower (1) one side, absorption tower (1) exit end links to each other with high-efficient liquid-solid separation ware (5), and through setting up sample main valve (3) control flow on the way, high-efficient liquid-solid separation ware (5) export sets up dilute phase ball valve (6), its characterized in that: the device is characterized by further comprising a dilute phase industrial visual monitoring module (8), a dilute phase secondary fluid pump (9), a waste liquid branch valve (10), a concentrated phase secondary fluid pump (12), a concentrated phase industrial visual monitoring module (13), a first industrial camera (7) and a second industrial camera (14) which are completely the same in structure, a slurry dilute phase is separated from an overflow port outlet of the high-efficiency liquid-solid separator (5), a slurry concentrated phase is separated from a bottom flow port of the high-efficiency liquid-solid separator (5), the slurry dilute phase and the slurry concentrated phase are respectively communicated with the dilute phase industrial visual monitoring module (8) and the concentrated phase industrial visual monitoring module (13), and are respectively conveyed to a downstream area through the dilute phase secondary fluid pump (9) and the concentrated phase secondary fluid pump (12), and slurry in the downstream area is pumped back to a slurry pool of the absorption tower (1) or flows into a waste liquid pool (11) according to requirements; the waste liquid branch valve (10) is arranged on a branch of the waste liquid pool (11); one sides of the dilute-phase industrial vision monitoring module (8) and the concentrated-phase industrial vision monitoring module (13) are correspondingly provided with a first industrial camera (7) and a second industrial camera (14) which are matched with each other; the dilute phase industrial vision monitoring module (8) and the dense phase industrial vision monitoring module (13) respectively comprise a light source (14A), a dark box (14B), a duckbill opening (14C), an observation window (14D), a receiving opening (14E) and a second industrial camera (14), the light source (14A), the duckbill (14C), the observation window (14D), the receiving port (14E) and the industrial camera II (14) are all arranged in the dark box (14B), the light source (14A) is the only light source in the module, the duckbill (14C) flattens and bundles the fluid of the high-efficiency liquid-solid separator (5), the receiving port (14E) is used for receiving the fluid flowing out of the duckbill (14C), the fluid between the receiving port (14E) and the duckbill (14C) does not contact with the wall surface, the observing window (14D) is arranged between the duckbill (14C) and the receiving opening (14E) for observing by the industrial camera II (14).
2. A method of a machine-vision coal-fired power plant absorption tower slurry health status monitoring system, which adopts the machine-vision coal-fired power plant absorption tower slurry health status monitoring system of claim 1, and is characterized in that: the method comprises the following steps:
(S1) separating the material under the condition of unknown slurry health information of a certain unknown absorption tower (1) into two streams of thin and thin phase and thick phase through a high-efficiency liquid-solid separator (5); inputting the information characteristics of the thin and thick fluid into a mapping model, and outputting the calculated health state of the slurry of the absorption tower by the mapping model;
(S2) the slurry quality evaluation algorithm module judges whether the slurry health degree is normal or abnormal according to the combination of the color characteristics of the materials and the slurry property information, the dilute phase and dense phase health indexes meet/exceed the related technical standards and the specified limits, and the slurry quality in the absorption tower is judged to be normal/abnormal;
(S3) the user service module presents the material image, the color characteristic and the absorption tower slurry quality evaluation result information to the user through a graphical interface and provides user interaction functions including image and data retrieval and storage.
3. The machine-vision coal fired power plant absorption tower slurry health monitoring system method of claim 2, further comprising: and (S1) adopting a machine learning method to establish the mapping model for estimating the health state of the slurry according to the color characteristics of the slurry.
4. The machine-vision coal fired power plant absorption tower slurry health monitoring system method of claim 2, further comprising: and (S2) judging whether the image is abnormal or not according to the acquired image gray value size/RGB component ratio/HSV component ratio.
5. The machine-vision coal fired power plant absorption tower slurry health monitoring system method of claim 2, further comprising: and the user service module in the step (S3) has a computer as a carrier, and reminds a user in a software box-flipping, sound and light word board mode when the slurry quality is abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110128259.4A CN112999834B (en) | 2021-01-29 | 2021-01-29 | Machine vision system and method for monitoring health state of slurry of absorption tower of coal-fired power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110128259.4A CN112999834B (en) | 2021-01-29 | 2021-01-29 | Machine vision system and method for monitoring health state of slurry of absorption tower of coal-fired power plant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112999834A CN112999834A (en) | 2021-06-22 |
| CN112999834B true CN112999834B (en) | 2022-05-20 |
Family
ID=76385436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110128259.4A Active CN112999834B (en) | 2021-01-29 | 2021-01-29 | Machine vision system and method for monitoring health state of slurry of absorption tower of coal-fired power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112999834B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6036955A (en) * | 1983-08-10 | 1985-02-26 | Mitsubishi Heavy Ind Ltd | Method for measuring concentration of caco3 in slurry |
| CN103885397A (en) * | 2013-12-23 | 2014-06-25 | 南宁职业技术学院 | Wet process flue gas desulphurization intelligent monitoring system and method |
| CN110132961A (en) * | 2018-02-09 | 2019-08-16 | 宝山钢铁股份有限公司 | The quickly method of gypsum lime stone and flue dust ratio in measurement desulphurization circulating slurries |
| CN209387451U (en) * | 2018-11-29 | 2019-09-13 | 北京国电龙源环保工程有限公司 | Wet desulphurization device gypsum slurries density and pH measuring device |
| CN112206640A (en) * | 2020-09-16 | 2021-01-12 | 西安热工研究院有限公司 | Limestone slurry pH value concentration fly-up detection system, method, control system and desulfurization system |
-
2021
- 2021-01-29 CN CN202110128259.4A patent/CN112999834B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6036955A (en) * | 1983-08-10 | 1985-02-26 | Mitsubishi Heavy Ind Ltd | Method for measuring concentration of caco3 in slurry |
| CN103885397A (en) * | 2013-12-23 | 2014-06-25 | 南宁职业技术学院 | Wet process flue gas desulphurization intelligent monitoring system and method |
| CN110132961A (en) * | 2018-02-09 | 2019-08-16 | 宝山钢铁股份有限公司 | The quickly method of gypsum lime stone and flue dust ratio in measurement desulphurization circulating slurries |
| CN209387451U (en) * | 2018-11-29 | 2019-09-13 | 北京国电龙源环保工程有限公司 | Wet desulphurization device gypsum slurries density and pH measuring device |
| CN112206640A (en) * | 2020-09-16 | 2021-01-12 | 西安热工研究院有限公司 | Limestone slurry pH value concentration fly-up detection system, method, control system and desulfurization system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112999834A (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2780056C (en) | An on-line macrocontaminant analyser and method | |
| CN103813863A (en) | Cleaning system | |
| CN113899752B (en) | Method for detecting crack of chain plate by adopting visual detection device for crack of inner chain plate of double-row chain scraper conveyor | |
| CN105987883A (en) | Method and system for determining sulfide content in water body | |
| CN101786675A (en) | Device and method for separating multi-parameter wastewater sources | |
| JP2006038860A (en) | Tribological debris analysis system | |
| CN111289697A (en) | CEMS running state monitoring and data false identification method and system | |
| CN112999834B (en) | Machine vision system and method for monitoring health state of slurry of absorption tower of coal-fired power plant | |
| CN214844840U (en) | Coal fired power plant absorption tower slurry health state monitoring system based on machine vision | |
| WO2019109871A1 (en) | Device and method for detecting fluid transparency | |
| CN101799394A (en) | Soft measurement method of overflow particle size distribution of hydraulic cyclone | |
| CN208334182U (en) | A kind of industrial wastewater automated detection system | |
| Tic et al. | Operation and accuracy of particle counters for on-line condition monitoring of hydraulic oils | |
| CN213456320U (en) | Portable waste gas sampling measurement system | |
| CN206161639U (en) | Water quality monitoring system | |
| CN113694714B (en) | Slurry system for desulfurization absorption tower and online slurry health state evaluation method | |
| CN112999835B (en) | Gypsum quality on-line monitoring method for limestone-gypsum wet desulphurization process | |
| CN103487352B (en) | A kind of intelligence of dope viscosity analyzer is cleaned inspection control system and detecting and control method thereof | |
| CN210347252U (en) | Smoke and dust flue gas atmosphere detection device | |
| CN209417046U (en) | A kind of portable oily Multi-parameter detection device | |
| CA2827876C (en) | Apparatus and method for estimation of ore quality using color correlations | |
| Hatonen et al. | Using image information and partial least squares method to estimate mineral concentrations in mineral flotation | |
| CN219016289U (en) | Water quality detection system | |
| CN1811425A (en) | Silicon microchannel array erythrocyte rheological analyzing method and apparatus | |
| TWM413120U (en) | Water quality measurement equipment for monitoring chemical oxygen demand (COD) and suspended solid (SS) |
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 |