CN116498892B - Mist-discharging and frosting-preventing method for LNG air-temperature type gasifier - Google Patents
Mist-discharging and frosting-preventing method for LNG air-temperature type gasifier Download PDFInfo
- Publication number
- CN116498892B CN116498892B CN202310786055.9A CN202310786055A CN116498892B CN 116498892 B CN116498892 B CN 116498892B CN 202310786055 A CN202310786055 A CN 202310786055A CN 116498892 B CN116498892 B CN 116498892B
- Authority
- CN
- China
- Prior art keywords
- image
- frosting
- gasifier
- probability
- points
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000007599 discharging Methods 0.000 title description 4
- 238000007405 data analysis Methods 0.000 claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims description 43
- 238000012545 processing Methods 0.000 claims description 39
- 238000004364 calculation method Methods 0.000 claims description 33
- 238000003062 neural network model Methods 0.000 claims description 21
- 239000006200 vaporizer Substances 0.000 claims description 17
- 238000010586 diagram Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 239000003595 mist Substances 0.000 claims description 9
- 230000008447 perception Effects 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000004387 environmental modeling Methods 0.000 claims description 3
- 230000002265 prevention Effects 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims 2
- 238000003379 elimination reaction Methods 0.000 claims 2
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 239000012080 ambient air Substances 0.000 abstract description 5
- 230000011664 signaling Effects 0.000 abstract description 2
- 239000007789 gas Substances 0.000 description 10
- 239000003570 air Substances 0.000 description 8
- 238000002309 gasification Methods 0.000 description 4
- 239000004568 cement Substances 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 230000000149 penetrating effect Effects 0.000 description 2
- 238000010298 pulverizing process Methods 0.000 description 2
- 230000008961 swelling Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000005457 ice water Substances 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C9/00—Methods or apparatus for discharging liquefied or solidified gases from vessels not under pressure
- F17C9/02—Methods or apparatus for discharging liquefied or solidified gases from vessels not under pressure with change of state, e.g. vaporisation
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C13/00—Details of vessels or of the filling or discharging of vessels
- F17C13/10—Arrangements for preventing freezing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C2221/00—Handled fluid, in particular type of fluid
- F17C2221/03—Mixtures
- F17C2221/032—Hydrocarbons
- F17C2221/033—Methane, e.g. natural gas, CNG, LNG, GNL, GNC, PLNG
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C2223/00—Handled fluid before transfer, i.e. state of fluid when stored in the vessel or before transfer from the vessel
- F17C2223/01—Handled fluid before transfer, i.e. state of fluid when stored in the vessel or before transfer from the vessel characterised by the phase
- F17C2223/0146—Two-phase
- F17C2223/0153—Liquefied gas, e.g. LPG, GPL
- F17C2223/0161—Liquefied gas, e.g. LPG, GPL cryogenic, e.g. LNG, GNL, PLNG
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C2250/00—Accessories; Control means; Indicating, measuring or monitoring of parameters
- F17C2250/03—Control means
- F17C2250/032—Control means using computers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C2250/00—Accessories; Control means; Indicating, measuring or monitoring of parameters
- F17C2250/03—Control means
- F17C2250/038—Control means using cameras
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C2260/00—Purposes of gas storage and gas handling
- F17C2260/03—Dealing with losses
- F17C2260/031—Dealing with losses due to heat transfer
- F17C2260/032—Avoiding freezing or defrosting
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C2265/00—Effects achieved by gas storage or gas handling
- F17C2265/06—Fluid distribution
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/30—Use of alternative fuels, e.g. biofuels
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Filling Or Discharging Of Gas Storage Vessels (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method for removing fog and preventing frosting of an LNG air-temperature type gasifier, which belongs to the technical field of gasifier instruction signaling and comprises the steps of scanning the surrounding space of a gasifier tank body and constructing a three-dimensional model of a scene around the gasifier tank body; carrying out space division on the three-dimensional model, and placing an image shooting device at a space connecting position to ensure that each space of the three-dimensional model can be covered by a monitoring range of the image shooting device; installing a plurality of image shooting devices around the gasifier tank body, transmitting the monitored data to a data analysis system, and analyzing videos shot by the image shooting devices; calculating the frosting trend of the gasifier through a data analysis system, and judging the frosting probability; the method can solve the problems that when the gasifier operates, the gasifier absorbs ambient heat and generates a large amount of white fog, so that the relative humidity of ambient air is increased, the ambient air is condensed into frost around the gasifier, and dangers are caused.
Description
Technical Field
The invention belongs to the technical field of gasifier instruction signaling, and particularly relates to a method for removing fog and preventing frosting of an LNG air-temperature gasifier.
Background
The LNG gasification station is a satellite station for receiving, storing and distributing LNG, is also an intermediate regulation place for town or gas enterprises to transfer LNG from a manufacturer to a user, is a main gas source or a transitional gas source which cannot be used for supplying gas through a pipeline at present, and is also a supplementary gas source or a peak regulation gas source which is used for supplying gas through a pipeline in a plurality of cities. The LNG gasification station is gradually built in a plurality of small and medium cities with developed economy and energy shortage in southeast coast of China by virtue of the advantages of short construction period and capability of rapidly meeting the gas market demand, and becomes a permanent gas supply facility or a transitional gas supply facility before the arrival of the pipeline natural gas.
In the early stage, the layout of the station is considered in the process of constructing the LNG gasification station, so that the safety distance required by design is achieved, the land space is utilized to the greatest extent, the gasifier is designed according to the minimum occupied area and the space arrangement, meanwhile, equipment manufacturers reduce the distance between heat absorption fins of the gasifier to meet the field layout and the safety distance, so that the air-temperature type gasifier frosts and freezes in the full-load gasification process, particularly in winter, the frost and expansion deformation of the gasifier are caused, the safe operation is influenced, and the potential safety hazard exists. In order to prevent the gasifier from icing and penetrating the ground concrete cement terrace to generate swelling pulverization, the periphery of the gasifier is tiled by an antifreezing stainless steel plate, so that the concrete cement pavement is prevented from being corroded by penetrating ice water, burst and swelling pulverization.
However, when the gasifier operates, the gasifier absorbs ambient heat and generates a large amount of mist, which causes an increase in the relative humidity of the ambient air, and if not treated in time, the ambient air further condenses into frost around the gasifier, which causes a hazard.
Disclosure of Invention
In view of the above, the invention provides a method for removing fog and preventing frosting of an LNG air-temperature type gasifier, which can solve the problems that when the gasifier operates, the gasifier absorbs ambient heat and generates a large amount of white fog, so that the relative humidity of ambient air is increased, and the surrounding air is frosted to cause danger.
The invention is realized in the following way:
the invention provides a method for removing fog and preventing frosting of an LNG air-temperature gasifier, which comprises the following specific operation steps:
s10: scanning the surrounding space of the gasifier tank body to construct a three-dimensional model of a scene around the gasifier tank body;
s20: carrying out space division on the three-dimensional model, and arranging an image shooting device at the space connection position to ensure that each space of the three-dimensional model can be covered by the monitoring range of the image shooting device;
s30: installing a plurality of image shooting devices around the gasifier tank body, shooting the surrounding environment of the gasifier tank body at regular time by the image shooting devices, transmitting shot video data to a data analysis system, and processing and analyzing videos shot by the images by the image shooting devices;
s40: calculating the frosting probability through the data analysis system, and sending a control signal to the explosion-proof fans around the gasifier;
s50: and the explosion-proof fan receives the control signal transmitted by the data analysis system, performs mechanical defogging, and enhances the air fluidity.
On the basis of the technical scheme, the mist-discharging and frost-preventing method of the LNG air-temperature type gasifier can be further improved as follows:
the data analysis system comprises an image frame extraction module, a mark point extraction module, an image contrast processing module, an image definition processing module and a probability calculation module;
the image frame extraction module is used for extracting the image video shot by the image shooting device in frames at different time intervals;
the marking point extraction module is used for marking the object points on the image extracted by the image frame extraction module;
the image comparison processing module is used for comparing the marked points on the image processed by the marked point extraction module with the object points of the original image to extract newly added object points;
the image definition processing module is used for performing definition processing on the newly added object points of the image;
the probability calculation module is used for analyzing the number and the positions of the newly added object points on the image to obtain the frosting probability of frosting of the gasifier.
Further, the specific step of calculating the frost probability by the data analysis system includes:
firstly, establishing a neural network model of the frosting temperature of a gasifier, determining time intervals for extracting frames at different temperatures, and extracting the frames of the images shot by the image shooting device according to the determined time intervals through the image frame extraction module;
the second step, the two-dimensional coordinates of the object points on the frame extraction image are marked by the marking point extraction module according to the image tone edge, and the image is converted into a marking point vector diagram;
thirdly, comparing the marked point vector image with a vector image of an unbummed original image shot by the image shooting device through the image comparison processing module to obtain a frosting point vector image;
fourth, overlapping the frosting point vector image with the corresponding frame extraction image to obtain a frosting point image;
fifthly, processing the frosting point image through the image definition processing module to obtain a probability calculation image;
and sixthly, establishing a frosting probability neural network model, and calculating the frosting probability of the gasifier through the probability calculation module by using the probability calculation image.
Further, the specific step of establishing the vaporizer frosting temperature neural network model and determining the time intervals of extracting frames at different temperatures comprises the following steps:
firstly, collecting frosting times at different temperatures within a temperature range of-20 DEG to 30 DEG;
secondly, dynamically analyzing the frosting times, estimating frosting probability through frosting frequency, and determining corresponding time intervals of the extracted frames through different frosting probabilities manually to form manual confirmation labels of the time intervals of the extracted frames;
thirdly, establishing a neural network model of the frosting temperature of the gasifier, taking the temperature as training input, and taking manual identification tags of time intervals of image extraction frames at different temperatures as output for training;
and fourthly, setting a temperature detector around the gasifier tank body, and inputting the temperature into the gasifier frosting temperature neural network model in real time to obtain the time interval for extracting the image frames.
Further, the specific step of converting the image into the marking point vector diagram includes the steps of:
the first step, carrying out linearization on the frame extraction image to obtain an edge contour map of the frame extraction image;
secondly, performing color level standardized adjustment on an edge profile of the frame extraction image to obtain a line enhanced profile;
thirdly, forming a graph from continuous contours in the contour map enhanced by the lines, marking the graph, and forming marking points on the graph;
and step four, acquiring two-dimensional coordinates of the marking points, and fitting the marking points through a Bezier curve drawing curve to obtain a marking point vector diagram.
Further, the specific step of comparing, by the image comparison processing module, the marker point vector image with a vector image of an unbumped original image captured by the image capturing device to obtain a frosting point vector image includes:
firstly, obtaining an original image which is not frosted at the position through the image shooting device;
the second step, vectorizing the original image without frosting to obtain an original vector image without frosting;
thirdly, comparing the proper quantity of the marked points with the non-frosted original vector image to obtain repeated points;
and step four, removing the repeated points on the marked point vector diagram to obtain a frosting point vector diagram.
Further, the specific step of establishing the frost probability neural network model and calculating the frost probability of the gasifier through the probability calculation module by using the probability calculation image includes:
the method comprises the steps that firstly, the number, the size and the diameter data of frosting points are obtained on a probability calculation image through scanning, and meanwhile, the frosting times under the corresponding probability calculation image are obtained through observation and statistics;
step two, dynamically analyzing the frosting times, and determining frosting probability through frosting frequency; the frosting frequency is the ratio of the frosting times under the data of the number, the size and the diameter of the corresponding frosting points to the total frosting times, and the frosting probability is the numerical value of the frosting frequency.
Thirdly, establishing a frosting probability neural network model, taking the data of the number, the size and the diameter of the frosting points as training input and taking the frosting probability as output for training;
and step four, inputting the obtained probability calculation image to obtain the real-time frosting probability.
Further, the specific step of calculating the frost forming probability by the data analysis system and sending a control signal to the explosion-proof fans around the gasifier comprises the following steps:
transmitting the image shot by the image shooting device in real time to the data analysis system, and judging the frosting probability of the gasifier; and when judging that the probability of frosting of the gasifier exceeds 50%, sending a control signal to the explosion-proof fans around the gasifier.
The specific operation steps of scanning the space around the gasifier tank body and constructing the three-dimensional model of the scene around the gasifier tank body comprise the following steps:
firstly, acquiring environmental perception data and pose estimation of the surrounding space of a gasifier tank body, and importing the environmental perception data and the pose estimation data into an existing three-dimensional environmental modeling system;
initializing an environment model according to the set resolution, wherein the model divides the ground into grids;
thirdly, when new perception data is obtained, transforming coordinates to obtain coordinate positions corresponding to a laser starting point and a midpoint, and estimating an interval to obtain a delimited interval estimation of a laser end point position;
fourthly, associating grids and creating corresponding empty voxels;
fifthly, applying constraint on the inserted empty element, and obtaining a three-dimensional environment modeling model;
and sixthly, repeating the steps, and completely constructing the three-dimensional model of the scene around the gasifier tank body.
The specific operation steps of the space division of the three-dimensional model comprise:
firstly, scanning a three-dimensional model of a scene around the gasifier tank body to form a point cloud picture;
secondly, voxelizing the initial point cloud to obtain a plurality of voxel cubes;
thirdly, selecting any voxel cube as a central cube, calculating a fitting plane normal vector in each adjacent cube adjacent to the central cube, calculating an included angle between each fitting plane normal vector and a central fitting plane normal vector of the central cube, and judging that the central cube and the adjacent cube can be fitted to form a cube fitting plane and determining a preliminary point cloud of the cube fitting plane when the included angle is smaller than a set included angle threshold;
the third step, the three-dimensional data of the cube fitting plane are projected to the cube fitting plane to form two-dimensional data, grid division is carried out on the two-dimensional data, the number of points in each grid is compared with a set point threshold value, so that grid numbers with the points larger than the point threshold value are formed into new data points, and the new data points are numbered and classified based on a clustering algorithm to obtain a fine segmentation plane of the cube fitting plane;
and sixthly, dividing the three-dimensional model of the scene around the gasifier tank.
Further, the specific step of processing the frosting point image by the image definition processing module to obtain a probability calculation image includes:
and sequentially carrying out gray scale, quantization, denoising, segmentation and edge processing on the image.
Compared with the prior art, the mist-discharging and frost-preventing method for the LNG air-temperature type gasifier has the beneficial effects that: by scanning the surrounding space of the gasifier tank body, a three-dimensional model of the surrounding scene of the gasifier tank body is constructed, so that the surrounding scene and the environment of the gasifier can be accurately grasped, and the surrounding environment of the gasifier can be conveniently divided; through space division of the three-dimensional model, an image shooting device is placed at the space connection position, each space of the three-dimensional model is ensured to be covered by a monitoring range of the image shooting device, and the periphery of the gasifier is monitored in an all-around mode; the plurality of image shooting devices are arranged around the gasifier tank body, the image shooting devices shoot the surrounding environment of the gasifier tank body at regular time, monitored data are transmitted to a data analysis system, videos shot by the image shooting devices are analyzed, monitoring of the environment of the gasifier tank body before frosting is achieved, whether frosting occurs or not is predicted in advance, so that the gasifier is frozen, swelled and deformed, and safe operation is affected; the data analysis system calculates the frosting trend of the gasifier, judges the frosting probability, sends a control signal to the explosion-proof fans around the gasifier when the frosting probability exceeds 50%, controls the explosion-proof fans to mechanically discharge fog, strengthens the air fluidity, reduces the influence of the relative humidity of the air on the frosting of the gasifier, and can solve the problems that the surrounding heat can be absorbed, a large amount of white fog is generated, the relative humidity of the surrounding air is increased, the surrounding air is condensed into frost around the gasifier, and dangers are caused when the gasifier operates.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a specific flow chart of a method for mist removal and frost prevention of an LNG air-temperature vaporizer.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
As shown in fig. 1, the invention provides an operation flow chart of a method for removing fog and preventing frosting of an LNG air-temperature gasifier, wherein the specific operation steps include:
s10: scanning the surrounding space of the gasifier tank body to construct a three-dimensional model of a scene around the gasifier tank body;
s20: carrying out space division on the three-dimensional model, and arranging an image shooting device at a space connection position to ensure that each space of the three-dimensional model can be covered by a monitoring range of the image shooting device;
s30: installing a plurality of image shooting devices around the gasifier tank body, shooting the surrounding environment of the gasifier tank body at regular time by the image shooting devices, transmitting shot video data to a data analysis system, and processing and analyzing videos shot by the images by the image shooting devices;
s40: calculating the frosting probability through a data analysis system, and sending a control signal to the explosion-proof fans around the gasifier;
s50: and the explosion-proof fan receives a control signal transmitted by the data analysis system, performs mechanical defogging, and enhances the air fluidity.
In the technical scheme, the data analysis system comprises an image frame extraction module, a mark point extraction module, an image contrast processing module, an image definition processing module and a probability calculation module;
the image frame extraction module is used for extracting image videos shot by the image shooting device from frames at different time intervals;
the marking point extraction module is used for marking the object points on the image extracted by the image frame extraction module;
the image contrast processing module is used for comparing the mark points on the image processed by the mark point extracting module with the object points of the original image to extract newly added object points;
the image definition processing module is used for performing definition processing on newly added object points of the image;
the probability calculation module is used for analyzing the number and the positions of the newly added object points on the image to obtain the frosting probability of the frosting of the gasifier.
Further, in the above technical solution, the specific step of calculating the frost probability by the data analysis system includes:
firstly, establishing a neural network model of the frosting temperature of a gasifier, determining time intervals for extracting frames at different temperatures, and extracting the frames of images shot by an image shooting device according to the determined time intervals through an image frame extraction module;
secondly, marking two-dimensional coordinates of object points on the frame extraction image according to the image tone edge by a marking point extraction module, and converting the image into a marking point vector diagram;
thirdly, comparing the marked point vector image with a vector image of an unbrosted original image shot by an image shooting device through an image comparison processing module to obtain a frosted point vector image;
fourth, overlapping the frosting point vector image with the corresponding frame extraction image to obtain a frosting point image;
fifthly, processing the frosted point image through an image definition processing module to obtain a probability calculation image;
and sixthly, establishing a frosting probability neural network model, and calculating the frosting probability of the gasifier through a probability calculation image by a probability calculation module.
Further, in the above technical solution, the specific steps of establishing the vaporizer frosting temperature neural network model and determining the time intervals of extracting frames at different temperatures include:
firstly, collecting frosting times at different temperatures within a temperature range of-20 DEG to 30 DEG;
secondly, dynamically analyzing the frosting times, estimating frosting probability through frosting frequency, and determining corresponding time intervals of the extracted frames through manual work on different frosting probabilities to form manual confirmation labels of the time intervals of the extracted frames;
thirdly, establishing a neural network model of the frosting temperature of the gasifier, taking the temperature as training input, and taking manual identification tags of time intervals of image extraction frames at different temperatures as output for training;
and fourthly, setting a temperature detector around the gasifier tank body, and inputting the temperature into the gasifier frosting temperature neural network model in real time to obtain the time interval for extracting the image frames.
Further, in the above technical solution, the specific step of extracting, by the marking point extracting module, two-dimensional coordinates of an object point on the image according to the image gray-scale edge frame to perform marking, and converting the image into the marking point vector diagram includes:
the method comprises the steps of firstly, carrying out linearization on a frame extraction image to obtain an edge contour map of the frame extraction image;
secondly, performing color level standardization adjustment on an edge contour map of the frame extraction image to obtain a contour map enhanced by lines;
thirdly, forming a graph from continuous contours in the contour map enhanced by the lines, marking the graph, and forming marking points on the graph;
and fourthly, acquiring two-dimensional coordinates of the marking points, and drawing curve fitting marking points through Bezier curves to obtain a marking point vector diagram.
Further, in the above technical solution, the specific step of comparing the marker point vector image with the vector image of the non-frosted original image captured by the image capturing device by the image comparison processing module to obtain the frosted point vector image includes:
firstly, obtaining an original image which is not frosted at the position through an image shooting device;
the second step, vectorizing the original image without frosting to obtain an original vector image without frosting;
thirdly, comparing a proper amount of marked points with the non-frosted original vector image to obtain repeated points;
and fourthly, removing repeated points on the marked point vector diagram to obtain a frosting point vector diagram.
Further, in the above technical solution, the specific steps of establishing the frost probability neural network model and calculating the frost probability of the gasifier through the probability calculation module by using the probability calculation image include:
the method comprises the steps that firstly, the number, the size and the diameter data of frosting points are obtained on a probability calculation image through scanning, and meanwhile, the frosting times under the corresponding probability calculation image are obtained through observation and statistics;
step two, dynamically analyzing the frosting times, and determining frosting probability through frosting frequency; the frosting frequency is the ratio of the frosting times under the data of the number, the size and the diameter of the corresponding frosting points to the total frosting times, and the frosting probability is the numerical value of the frosting frequency.
Thirdly, establishing a frosting probability neural network model, taking the data of the number, the size and the diameter of frosting points as training input and taking the frosting probability as output for training;
and step four, inputting the obtained probability calculation image to obtain the real-time frosting probability.
Further, in the above technical solution, the specific steps of "calculating the probability of frosting by the data analysis system, and sending a control signal by the explosion-proof fans around the gasifier" include:
transmitting the image shot by the image shooting device in real time to a data analysis system, and judging the frosting probability of the gasifier; when the probability of the vaporizer frosting is judged to be more than 50%, a control signal is sent to the explosion-proof fans around the vaporizer.
In the above technical solution, the specific operation steps of calculating the frost forming probability by the data analysis system and sending the control signal to the explosion-proof fans around the gasifier include:
firstly, acquiring environmental perception data and pose estimation of the surrounding space of a gasifier tank body, and importing the environmental perception data and the pose estimation data into an existing three-dimensional environmental modeling system;
initializing an environment model according to the set resolution, wherein the model divides the ground into grids;
thirdly, when new perception data is obtained, transforming coordinates to obtain coordinate positions corresponding to a laser starting point and a midpoint, and estimating an interval to obtain a delimited interval estimation of a laser end point position;
fourthly, associating grids and creating corresponding empty voxels;
fifthly, applying constraint on the inserted empty element, and obtaining a three-dimensional environment modeling model;
and sixthly, repeating the steps, and completely constructing the three-dimensional model of the scene around the gasifier tank.
The specific operation steps of the space division of the three-dimensional model comprise:
firstly, scanning a three-dimensional model of a scene around a gasifier tank body to form a point cloud picture;
secondly, voxelizing the initial point cloud to obtain a plurality of voxel cubes;
thirdly, selecting any solid cube as a central cube, calculating a fitting plane normal vector in each adjacent cube adjacent to the central cube, calculating an included angle between each fitting plane normal vector and a central fitting plane normal vector of the central cube, judging that the central cube and the adjacent cube can be fitted to form a cube fitting plane when the included angle is smaller than a set included angle threshold value, and determining a preliminary point cloud of the cube fitting plane;
the third step, the three-dimensional data of the fitting plane of the cube is projected to the fitting plane of the cube to form two-dimensional data, the two-dimensional data is subjected to grid division, the number of points in each grid is compared with a set point threshold value, so that grid numbers with the points larger than the point threshold value are formed into new data points, and the new data points are numbered and classified based on a clustering algorithm to obtain a precise segmentation plane of the fitting plane of the cube;
and sixthly, dividing on a three-dimensional model of a scene around the gasifier tank.
Further, in the above technical solution, the specific steps of processing the frosted point image by the image definition processing module to obtain the probability calculation image include:
and sequentially carrying out gray scale, quantization, denoising, segmentation and edge processing on the image.
Specifically, the principle of the invention is as follows: scanning the surrounding space of the gasifier tank body to construct a three-dimensional model of a scene around the gasifier tank body; carrying out space division on the three-dimensional model, and placing an image shooting device at a space connecting position to ensure that each space of the three-dimensional model can be covered by a monitoring range of the image shooting device; installing a plurality of image shooting devices around the gasifier tank body, shooting the surrounding environment of the gasifier tank body by the image shooting devices at regular time, transmitting monitored data to a data analysis system, and analyzing videos shot by the image shooting devices; calculating the frosting trend of the gasifier through a data analysis system, judging the frosting probability, and sending a control signal to the explosion-proof fans around the gasifier when the frosting probability exceeds 50%; and the explosion-proof fan receives a control signal transmitted by the data analysis system, performs mechanical defogging, and enhances the air fluidity.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (8)
1. The method for preventing fog and frost of the LNG air temperature type gasifier is characterized by comprising the following specific operation steps of:
s10: scanning the surrounding space of the gasifier tank body to construct a three-dimensional model of a scene around the gasifier tank body;
s20: carrying out space division on the three-dimensional model, and arranging an image shooting device at a space connecting position to ensure that each space of the three-dimensional model can be covered by a monitoring range of the image shooting device;
s30: installing a plurality of image shooting devices around the gasifier tank body, shooting the surrounding environment of the gasifier tank body at regular time by the image shooting devices, transmitting shot video data to a data analysis system, and processing and analyzing videos shot by the images by the image shooting devices;
s40: calculating the frosting probability through the data analysis system, and sending a control signal to the explosion-proof fans around the gasifier;
s50: the explosion-proof fan receives the control signal transmitted by the data analysis system, performs mechanical defogging, and enhances air fluidity;
the data analysis system comprises an image frame extraction module, a mark point extraction module, an image contrast processing module, an image definition processing module and a probability calculation module;
the image frame extraction module is used for extracting the image video shot by the image shooting device in frames at different time intervals;
the marking point extraction module is used for marking the object points on the image extracted by the image frame extraction module;
the image comparison processing module is used for comparing the marked points on the image processed by the marked point extraction module with the object points of the original image to extract newly added object points;
the image definition processing module is used for performing definition processing on the newly added object points of the image;
the probability calculation module is used for analyzing the number and the positions of newly added object points on the image to obtain the frosting probability of frosting of the gasifier;
the specific steps for calculating the frosting probability through the data analysis system comprise the following steps:
firstly, establishing a neural network model of the frosting temperature of a gasifier, determining time intervals for extracting frames at different temperatures, and extracting the frames of the images shot by the image shooting device according to the determined time intervals through the image frame extraction module;
the second step, the two-dimensional coordinates of the object points on the frame extraction image are marked by the marking point extraction module according to the image tone scale edges, and the image is converted into a marking point vector diagram;
thirdly, comparing the marked point vector image with a vector image of an unbummed original image shot by the image shooting device through the image comparison processing module to obtain a frosting point vector image;
fourth, overlapping the frosting point vector image with the corresponding frame extraction image to obtain a frosting point image;
fifthly, processing the frosting point image through the image definition processing module to obtain a probability calculation image;
and sixthly, establishing a frosting probability neural network model, and calculating the frosting probability of the gasifier through the probability calculation module by using the probability calculation image.
2. The method for mist and frost removal of an LNG air-temperature vaporizer according to claim 1, wherein the specific steps of establishing a vaporizer frost temperature neural network model and determining the time intervals for extracting frames at different temperatures comprise:
firstly, collecting frosting times at different temperatures within a temperature range of-20 DEG to 30 DEG;
secondly, dynamically analyzing the frosting times, estimating frosting probability through frosting frequency, and determining corresponding time intervals of the extracted frames through different frosting probabilities manually to form manual confirmation labels of the time intervals of the extracted frames;
thirdly, establishing a neural network model of the frosting temperature of the gasifier, taking the temperature as training input, and taking manual identification tags of time intervals of image extraction frames at different temperatures as output for training;
and fourthly, setting a temperature detector around the gasifier tank body, and inputting the temperature into the gasifier frosting temperature neural network model in real time to obtain the time interval for extracting the image frames.
3. The method for mist and frost removal of an LNG air-temperature vaporizer according to claim 2, wherein the specific step of converting the image into a vector map of mark points by the mark point extraction module according to two-dimensional coordinates of object points on the frame extraction image of the image gray-scale edge comprises:
the first step, carrying out linearization on the frame extraction image to obtain an edge contour map of the frame extraction image;
secondly, performing color level standardized adjustment on an edge profile of the frame extraction image to obtain a line enhanced profile;
thirdly, forming a graph from continuous contours in the contour map enhanced by the lines, marking the graph, and forming marking points on the graph;
and step four, acquiring two-dimensional coordinates of the marking points, and fitting the marking points through a Bezier curve drawing curve to obtain a marking point vector diagram.
4. The method for mist elimination and frost prevention of an LNG air-temperature vaporizer according to claim 3, wherein the specific step of comparing, by the image comparison processing module, the mark point vector image with a vector image of an unbumped original image captured by the image capturing device to obtain a frost point vector image comprises:
firstly, obtaining an original image which is not frosted at the position through the image shooting device;
the second step, vectorizing the original image without frosting to obtain an original vector image without frosting;
thirdly, comparing the proper quantity of the marked points with the non-frosted original vector image to obtain repeated points;
and step four, removing the repeated points on the marked point vector diagram to obtain a frosting point vector diagram.
5. The method for mist elimination and frost prevention of an LNG air temperature vaporizer according to claim 4, wherein the specific step of establishing a frost probability neural network model and calculating the vaporizer frost probability by the probability calculation module through the probability calculation image comprises:
the method comprises the steps that firstly, the number, the size and the diameter data of frosting points are obtained on a probability calculation image through scanning, and meanwhile, the frosting times under the corresponding probability calculation image are obtained through observation and statistics;
step two, dynamically analyzing the frosting times, and determining frosting probability through frosting frequency; the frosting frequency is the proportion of the frosting times under the data of the number, the size and the diameter of the corresponding frosting points to the total statistical frosting times, and the frosting probability is the numerical value of the frosting frequency;
thirdly, establishing a frosting probability neural network model, taking the data of the number, the size and the diameter of the frosting points as training input and taking the frosting probability as output for training;
and step four, inputting the obtained probability calculation image to obtain the real-time frosting probability.
6. The method for mist and frost removal of an LNG air-temperature vaporizer according to claim 5, wherein the specific step of calculating the probability of frost formation by the data analysis system and sending a control signal to the explosion-proof fans around the vaporizer comprises:
transmitting the image shot by the image shooting device in real time to the data analysis system, and judging the frosting probability of the gasifier; and when judging that the probability of frosting of the gasifier exceeds 50%, sending a control signal to the explosion-proof fans around the gasifier.
7. The method for mist and frost removal of an LNG cold air vaporizer of claim 6, wherein the specific operation steps of scanning the space around the vaporizer tank and constructing a three-dimensional model of the scene around the vaporizer tank comprise:
firstly, acquiring environmental perception data and pose estimation of the surrounding space of a gasifier tank body, and importing the environmental perception data and the pose estimation data into an existing three-dimensional environmental modeling system;
initializing an environment model according to the set resolution, wherein the model divides the ground into grids;
thirdly, when new perception data is obtained, transforming coordinates to obtain coordinate positions corresponding to a laser starting point and a midpoint, and estimating an interval to obtain a delimited interval estimation of a laser end point position;
fourthly, associating grids and creating corresponding empty voxels;
fifthly, applying constraint on the inserted empty element, and obtaining a three-dimensional environment modeling model;
and sixthly, repeating the steps, and completely constructing the three-dimensional model of the scene around the gasifier tank body.
8. The method for mist and frost removal of an LNG air-temperature vaporizer according to claim 7, wherein the specific step of processing the frost point image by the image sharpness processing module to obtain a probability calculation image comprises:
and sequentially carrying out gray scale, quantization, denoising, segmentation and edge processing on the image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310786055.9A CN116498892B (en) | 2023-06-30 | 2023-06-30 | Mist-discharging and frosting-preventing method for LNG air-temperature type gasifier |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310786055.9A CN116498892B (en) | 2023-06-30 | 2023-06-30 | Mist-discharging and frosting-preventing method for LNG air-temperature type gasifier |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116498892A CN116498892A (en) | 2023-07-28 |
CN116498892B true CN116498892B (en) | 2023-08-29 |
Family
ID=87327077
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310786055.9A Active CN116498892B (en) | 2023-06-30 | 2023-06-30 | Mist-discharging and frosting-preventing method for LNG air-temperature type gasifier |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116498892B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893751A (en) * | 2016-03-31 | 2016-08-24 | 北京长城华冠汽车科技股份有限公司 | Method and device for evaluating defrosting performance of automobile defrosting pipeline |
CN110094925A (en) * | 2019-05-08 | 2019-08-06 | 南京工程学院 | A kind of evaporimeter frosting detection method and the application that defrosts |
JP6652219B1 (en) * | 2018-11-29 | 2020-02-19 | ダイキン工業株式会社 | Refrigerant leak determination system and refrigeration cycle device |
CN112257340A (en) * | 2020-10-16 | 2021-01-22 | 石倩 | Control method and control system of photovoltaic cell panel defrosting robot |
CN113140043A (en) * | 2021-05-07 | 2021-07-20 | 江苏俱为科技有限公司 | Three-dimensional multilayer environment model construction method based on interval estimation |
CN113743428A (en) * | 2020-05-27 | 2021-12-03 | 广东芬尼克兹节能设备有限公司 | Method and device for performing accurate defrosting control by combining camera |
CN114998745A (en) * | 2022-07-19 | 2022-09-02 | 海门市腾飞橡塑厂 | Rubber product surface defrosting control method and system based on machine vision |
CN115307370A (en) * | 2022-06-23 | 2022-11-08 | 新奥数能科技有限公司 | Air cooler defrosting control method and device based on Yun Bian coordination |
-
2023
- 2023-06-30 CN CN202310786055.9A patent/CN116498892B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893751A (en) * | 2016-03-31 | 2016-08-24 | 北京长城华冠汽车科技股份有限公司 | Method and device for evaluating defrosting performance of automobile defrosting pipeline |
JP6652219B1 (en) * | 2018-11-29 | 2020-02-19 | ダイキン工業株式会社 | Refrigerant leak determination system and refrigeration cycle device |
CN110094925A (en) * | 2019-05-08 | 2019-08-06 | 南京工程学院 | A kind of evaporimeter frosting detection method and the application that defrosts |
CN113743428A (en) * | 2020-05-27 | 2021-12-03 | 广东芬尼克兹节能设备有限公司 | Method and device for performing accurate defrosting control by combining camera |
CN112257340A (en) * | 2020-10-16 | 2021-01-22 | 石倩 | Control method and control system of photovoltaic cell panel defrosting robot |
CN113140043A (en) * | 2021-05-07 | 2021-07-20 | 江苏俱为科技有限公司 | Three-dimensional multilayer environment model construction method based on interval estimation |
CN115307370A (en) * | 2022-06-23 | 2022-11-08 | 新奥数能科技有限公司 | Air cooler defrosting control method and device based on Yun Bian coordination |
CN114998745A (en) * | 2022-07-19 | 2022-09-02 | 海门市腾飞橡塑厂 | Rubber product surface defrosting control method and system based on machine vision |
Also Published As
Publication number | Publication date |
---|---|
CN116498892A (en) | 2023-07-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111369666A (en) | Dynamic target reconstruction method and device based on multiple RGBD cameras | |
Yang et al. | Semiautomated building facade footprint extraction from mobile LiDAR point clouds | |
CN106156752B (en) | A kind of model recognizing method based on inverse projection three-view diagram | |
CN103714541A (en) | Method for identifying and positioning building through mountain body contour area constraint | |
CN101957309A (en) | All-weather video measurement method for visibility | |
CN106127205A (en) | A kind of recognition methods of the digital instrument image being applicable to indoor track machine people | |
CN112307884A (en) | Forest fire spreading prediction method based on continuous time sequence remote sensing situation data and electronic equipment | |
CN108665468B (en) | Device and method for extracting tangent tower insulator string | |
CN109118457A (en) | Remote sensing image processing method and processing device | |
CN116498892B (en) | Mist-discharging and frosting-preventing method for LNG air-temperature type gasifier | |
CN104281857A (en) | Insulator detecting method based on orthogonal direction projection | |
CN114531700B (en) | Non-artificial base station antenna work parameter acquisition system and method | |
CN115620239A (en) | Point cloud and video combined power transmission line online monitoring method and system | |
CN111723656A (en) | Smoke detection method and device based on YOLO v3 and self-optimization | |
CN114384543A (en) | Road end three-dimensional target detection method and system based on background removal | |
CN110490061A (en) | A kind of uncertainties model and measure of characteristics of remote sensing image | |
CN113947724A (en) | Automatic line icing thickness measuring method based on binocular vision | |
CN107194954B (en) | Player tracking method and device of multi-view video | |
CN116051777B (en) | Super high-rise building extraction method, apparatus and readable storage medium | |
CN116363319B (en) | Modeling method, modeling device, equipment and medium for building roof | |
CN102750550A (en) | Multi-target tracking method and device based on video | |
CN114332006A (en) | Automatic quantitative assessment method for urban battlement loss | |
Guo et al. | Population estimation in Singapore based on remote sensing and open data | |
CN107392936A (en) | A kind of method for tracking target based on meanshift | |
CN114061476A (en) | Deflection detection method for insulator of power transmission line |
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 |