CN117147631A - Regional environment analysis-based intelligent gas detection and early warning method and system - Google Patents
Regional environment analysis-based intelligent gas detection and early warning method and system Download PDFInfo
- Publication number
- CN117147631A CN117147631A CN202311414782.9A CN202311414782A CN117147631A CN 117147631 A CN117147631 A CN 117147631A CN 202311414782 A CN202311414782 A CN 202311414782A CN 117147631 A CN117147631 A CN 117147631A
- Authority
- CN
- China
- Prior art keywords
- gas
- information
- regional
- early warning
- gas concentration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004458 analytical method Methods 0.000 title claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 238000003702 image correction Methods 0.000 claims abstract description 20
- 238000010586 diagram Methods 0.000 claims description 24
- 238000000605 extraction Methods 0.000 claims description 21
- 238000001914 filtration Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 15
- 230000004927 fusion Effects 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 10
- 238000003891 environmental analysis Methods 0.000 claims description 10
- 239000004065 semiconductor Substances 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 8
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 6
- 239000007789 gas Substances 0.000 description 231
- 238000005516 engineering process Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 3
- 239000010931 gold Substances 0.000 description 3
- 229910052737 gold Inorganic materials 0.000 description 3
- 238000003331 infrared imaging Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 231100000331 toxic Toxicity 0.000 description 2
- 230000002588 toxic effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- HPTJABJPZMULFH-UHFFFAOYSA-N 12-[(Cyclohexylcarbamoyl)amino]dodecanoic acid Chemical compound OC(=O)CCCCCCCCCCCNC(=O)NC1CCCCC1 HPTJABJPZMULFH-UHFFFAOYSA-N 0.000 description 1
- 238000000862 absorption spectrum Methods 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000012855 volatile organic compound Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
- G08B21/14—Toxic gas alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/20—Status alarms responsive to moisture
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Abstract
The invention relates to the technical field of gas detection, in particular to a gas intelligent detection early warning method and system based on regional environment analysis, wherein the method comprises the following steps: collecting regional environment information, wherein the regional environment information comprises temperature information, humidity information, pressure information, gas concentration information and a regional infrared image; preprocessing the acquired infrared image of the region, wherein the preprocessing comprises image correction, image denoising and data enhancement; constructing a gas detection network to obtain positioning information of a gas release source; constructing a gas concentration calibration network, and calibrating the gas concentration information by integrating temperature information and pressure information in the regional environment to obtain regional gas concentration information; comprehensively analyzing the positioning information of the gas release source and the regional gas concentration information, and outputting early warning information. According to the invention, by constructing the gas detection network and the gas concentration calibration network, the gas concentration is detected and early warning information is timely and efficiently output while the positioning of the gas leakage source is realized.
Description
Technical Field
The invention relates to the technical field of gas detection, in particular to a gas intelligent detection early warning method and system based on regional environment analysis.
Background
With the rapid development of modern industry, various toxic and harmful gases are widely used in the production process. Once toxic and harmful gas leaks, accidents such as explosion and the like are extremely easy to cause, and serious consequences are brought. How to quickly and accurately find out the gas leakage accident, and determine the position of the leakage source and the gas concentration of the leakage area, so that the leakage accident can be effectively controlled, is the urgent need of the current research.
The conventional gas detection technology uses a contact type gas sensor, and has the defects of long response time, low operability and safety, inability to rapidly locate a leakage source and the like. With the development of gas infrared imaging technology, a technical support is provided for imaging and rapid positioning of leaked gas, so that the gas leakage can be monitored in a large range and with high efficiency. However, the existing gas detection method based on the infrared imaging technology is only suitable for positioning a gas leakage source, and does not comprehensively analyze temperature information, humidity information and pressure information in the regional environment to accurately detect the gas concentration.
For example, in Chinese patent with the publication number of CN113688801B, a chemical gas leakage detection method and a system based on spectrum video are disclosed, which relate to the technical field of gas detection, and the method carries out image-level preprocessing on the collected spectrum video of the chemical gas; dividing the spectrum video into a plurality of fragments in time sequence, sampling a video frame in each fragment, and respectively extracting the characteristics of each video frame; the method comprises the steps of obtaining short-time sequence enhancement characteristics of each video frame by fusing local motion information of a plurality of adjacent video frames in the characteristics of each video frame; the method comprises the steps of merging time sequence information in short time sequence enhancement features of each video frame through a shifting and weighting channel-by-channel integration method to obtain global time sequence merging features of each video frame; and merging the short-time sequence enhancement feature and the global time sequence fusion feature into a main network through residual connection, and calculating to obtain a detection result of the chemical gas leakage.
In China patent with the publication number CN112781791B, a VOCs gas leakage detection method and system based on optical gas imaging are disclosed, and the method comprises the following modules: the image acquisition module is used for acquiring a frame of infrared image of the region to be detected, and taking the frame of infrared image as a background image if the frame of infrared image is a first frame of infrared image; the background subtraction module is used for extracting a dynamic change area of the infrared image of the current frame; the parameter calculation module is used for calculating parameters of the dynamic change area meeting the detection conditions of the dynamic area; the gas leakage judging module is used for judging whether gas leakage occurs or not when the calculated parameters of the infrared image meet detection conditions; and the alarm module is used for outputting alarm signals when gas leakage occurs and marking the extracted dynamic change area. The problems proposed in the background art exist in the above patents: the existing gas detection method based on the infrared imaging technology is only suitable for positioning a gas leakage source, and does not comprehensively analyze temperature information, humidity information and pressure information in the regional environment to accurately detect the gas concentration.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides an intelligent gas detection early warning method and system based on regional environment analysis.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the invention provides a gas intelligent detection early warning method based on regional environment analysis, which comprises the following steps:
collecting regional environment information, wherein the regional environment information comprises temperature information, humidity information, pressure information, gas concentration information and a regional infrared image;
preprocessing the acquired infrared image of the region, wherein the preprocessing comprises image correction, image denoising and data enhancement;
constructing a gas detection network to obtain positioning information of a gas release source;
constructing a gas concentration calibration network, and calibrating the gas concentration information by integrating temperature information and pressure information in the regional environment to obtain regional gas concentration information;
comprehensively analyzing the positioning information of the gas release source and the regional gas concentration information, and outputting early warning information.
As a preferable technical scheme, the gas concentration information is collected by a semiconductor gas sensor and an infrared gas sensor together, and the specific steps include:
acquiring first gas concentration information through a semiconductor type gas sensor, and acquiring second gas concentration information through an infrared type gas sensor;
if the humidity information in the regional environment is greater than or equal to a preset humidity threshold, the gas concentration information is first gas concentration information, and if the humidity information in the regional environment is less than the preset humidity threshold, the gas concentration information is second gas concentration information.
As a preferable technical solution, the image correction specific steps include:
let the size of the regional infrared image be，/>Column number of infrared image representing area, +.>Representing the number of lines of the regional infrared image, by the regional infrared image +.>The column pixel point is used as the center to construct a pixel with the size of +.>Is (are) sliding window->Column number of sliding window->Representing the number of rows of the sliding window->And->Are all odd numbers;
calculating pixel points in an infrared imageA gradient in the horizontal direction of the sliding window being the center：
；
In the middle of，/>，/>Representing the +.o in an IR image of a region>Line->Gray values of column pixel points;
calculating pixel points in an infrared imageAverage gradient in horizontal direction of sliding window as center：
；
Along-area infrared image firstColumn pixel vertical sliding window, calculating the +.>Cumulative histogram of window with minimum average gradient among all sliding windows of column pixel points +.>：
；
In the middle ofRepresenting the number of lines of the regional infrared image, i.e. the number of pixels per column, +.>Representing cumulative histogram->Gray level of +.>Representing the pixel point->Is +.>；
Computing region infrared image NoMedian histogram +.f. of window with minimum average gradient among all sliding windows of column pixel points>：
；
；
In the middle ofRepresents standard deviation +.4 times>Rounding up to minus infinity, < >>Representing standard deviation +.>Is used for the high-order weight of (1),representing a threshold value;
acquisition of regional infrared imageCorrection gray value of column pixel>：
；
And executing the steps, and sequentially acquiring the correction gray value of each column of pixel points of the infrared image of the region to finish image correction.
As a preferable technical scheme, the image denoising is represented by the following formula:
；
in the middle ofRepresenting the +.o in the area infrared image>The pixel gray values in the filtering template with the pixel as the center,representing the +.o in the area infrared image>Weighting coefficient of each pixel point in the filtering template taking each pixel point as center, +.>Representing the size of the filtering template +.>Representing the width of the filtering template, +.>Representing the height of the filtering template, +.>Representing the infrared image of the region +.>And (5) denoising the gray value of each pixel point.
As a preferred technical solution, the data enhancement is used for expanding the regional infrared image, and the specific steps include:
image transformation is performed on the regional infrared image, the image transformation including at least one of horizontal flip, vertical flip, random angular rotation, and mosaics random enhancement.
As a preferred technical solution, the specific steps of the random enhancement of the mosaics include:
generating a sheetBackground map of size, ">The size background picture can accommodate 4 pieces of size +.>Is a region infrared image of (2);
the size of the center point of the background picture is as followsRandomly selecting a splicing center for dividing the background picture into four areas of upper left, upper right, lower right and lower left;
randomly selecting 4 infrared images of different areas, sequentially arranging the infrared images in the upper left, the upper right, the lower left and the lower right of the background image, and cutting off the images and the marking frames exceeding the background boundary area to obtain the background image with the size ofIs a region infrared image of (2);
the spliced size isThe area infrared image is scaled to a size +.>Finishing the random enhancement of the Mosaic;
as an preferable technical scheme, the gas detection network comprises a gas infrared feature extraction unit, a gas motion feature extraction unit, a feature fusion unit and a gas release source positioning unit, wherein the gas release source positioning unit comprises 21×1 convolution layers and 43×3 convolution layers, and the output of the gas release source positioning unit is gas release source positioning information.
As a preferred embodiment, the gas concentration calibration network may be represented by the following formula:
；
in the middle ofIndicating calibrated zone gas concentration information, +.>Representing the output layer node transfer function,/->The category number of the regional environment information representing input, < +.>Indicating the connection weights of the intermediate layer to the output layer, < ->Representing intermediate layer node transfer function, ">Indicating the number of intermediate layer nodes, ">Information representing the environment of the inputted area, including temperature information, pressure information and gas concentration information, < >>Representing the connection weights of the input layer to the intermediate layer, < ->Represents an intermediate layer threshold value->Representing the output layer threshold.
As an optimized technical scheme, the early warning information comprises a first early warning information and a second early warning information, and the specific steps of outputting the early warning information comprise:
calculating the distance from the current detection position to the gas release source through the gas release source positioning information;
if the distance is smaller than or equal to a preset safety distance threshold value or the regional gas concentration information is larger than a preset gas concentration threshold value, outputting first early warning information;
if the distance is greater than a preset safety distance threshold value or the regional gas concentration information is less than or equal to a preset gas concentration threshold value, outputting second early warning information;
the first early warning information is sound early warning and light early warning, the second early warning information is light early warning, the preset safety distance threshold is determined by gas types, leakage rate and regional environment information, the value range is 30-430 m, the preset gas concentration threshold is determined by gas types and operation place standards, and the value range is 500-12500 ppm.
As a preferred technical solution, the gas infrared feature extraction unit is configured to extract a gas infrared feature map, and the specific steps include:
performing boundary filling on the input regional infrared image, wherein the filling width is 1, and obtaining a first gas infrared characteristic diagram;
the characteristic extraction is carried out on the first gas infrared characteristic map through the 3X 3 convolution layer, the ReLU activation function and the 3X 3 convolution layer in sequence, so as to obtain a second gas infrared characteristic map;
and adding the first gas infrared characteristic diagram and the second gas infrared characteristic diagram, and inputting the sum into a ReLU activation function to obtain a final gas infrared characteristic diagram.
As a preferable technical solution, the gas motion feature extraction unit is configured to extract a gas motion feature map, and the gas motion feature extraction unit includes 17×7 convolution layers, 25×5 convolution layers, and 6 3×3 convolution layers.
As an preferable technical scheme, the feature fusion unit is used for carrying out feature fusion on the gas infrared feature map and the gas motion feature map, and is represented by the following formula:
；
in the middle ofRepresenting a gas movement profile, < >>Representing the infrared signature of a gas,>a set of feature maps representing infrared images of the same area,/->Representing pixel-by-pixel addition, +.>Representing pixel-by-pixel multiplication +.>And representing the fused characteristic diagram.
The invention also provides a gas intelligent detection early warning system based on regional environment analysis, which comprises:
the information acquisition module is used for acquiring regional environment information, wherein the regional environment information comprises temperature information, humidity information, pressure information, gas concentration information and regional infrared images;
the image preprocessing module is used for preprocessing the acquired infrared image of the region, wherein the preprocessing comprises image correction, image denoising and data enhancement;
the gas detection network construction module is used for constructing a gas detection network to obtain positioning information of a gas release source;
the gas concentration calibration network construction module is used for constructing a gas concentration calibration network, and integrating temperature information and pressure information in the regional environment to calibrate the gas concentration information so as to obtain regional gas concentration information;
and the early warning information output module is used for comprehensively analyzing the positioning information of the gas release source and the regional gas concentration information and outputting early warning information.
The invention relates to a computer readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program realizes an intelligent gas detection early warning method based on regional environment analysis.
The controller comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor is used for realizing an intelligent gas detection early warning method based on regional environment analysis when executing the computer program.
Compared with the prior art, the invention has the following advantages and beneficial effects:
(1) According to the invention, the accuracy of positioning the gas leakage source is improved by carrying out image correction, image denoising and data enhancement on the acquired infrared image of the region. By constructing the gas detection network and the gas concentration calibration network, the temperature information, the humidity information and the pressure information in the regional environment are comprehensively analyzed, the gas concentration in the regional environment is detected and early warning information is timely and efficiently output while the positioning of the gas leakage source is realized.
(2) According to the invention, by collecting temperature information and pressure information in the regional environment and constructing a gas concentration calibration network, gas concentration measurement errors caused by absorption spectrum line distortion caused by temperature and pressure fluctuation are reduced, and dynamic detection and automatic calibration of gas concentration are realized.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the following drawings in which:
FIG. 1 is a schematic diagram of the whole flow of an intelligent gas detection and early warning method based on regional environmental analysis;
FIG. 2 is a schematic diagram of the gas detection network in the gas intelligent detection early warning method based on regional environmental analysis;
fig. 3 is a schematic structural diagram of an intelligent gas detection and early warning system based on regional environmental analysis.
Detailed Description
The following detailed description of the present invention is made with reference to the accompanying drawings and specific embodiments, and it is to be understood that the specific features of the embodiments and the embodiments of the present invention are detailed description of the technical solutions of the present invention, and not limited to the technical solutions of the present invention, and that the embodiments and the technical features of the embodiments of the present invention may be combined with each other without conflict.
Example 1
As shown in fig. 1, the embodiment provides a gas intelligent detection and early warning method based on regional environment analysis, which specifically includes the following steps:
s1: collecting regional environment information, wherein the regional environment information comprises temperature information, humidity information, pressure information, gas concentration information and a regional infrared image;
the gas concentration information is collected by a semiconductor gas sensor and an infrared gas sensor together, and the method specifically comprises the following steps:
acquiring first gas concentration information through a semiconductor type gas sensor, and acquiring second gas concentration information through an infrared type gas sensor;
if the humidity information in the regional environment is greater than or equal to a preset humidity threshold, the gas concentration information is first gas concentration information, and if the humidity information in the regional environment is less than the preset humidity threshold, the gas concentration information is second gas concentration information.
S2: preprocessing the acquired infrared image of the region, wherein the preprocessing comprises image correction, image denoising and data enhancement;
s21: the specific steps of image correction include:
let the size of the regional infrared image be，/>Representation of regional infrared mapColumn number of images->Representing the number of lines of the regional infrared image, by the regional infrared image +.>The column pixel point is used as the center to construct a pixel with the size of +.>Is (are) sliding window->Column number of sliding window->Representing the number of rows of the sliding window->And->Are all odd numbers;
calculating pixel points in an infrared imageGradient in the horizontal direction of the sliding window as center +.>：
；
In the middle of，/>，/>Representing the +.o in an IR image of a region>Line->Gray values of column pixel points;
calculating pixel points in an infrared imageAverage gradient in horizontal direction of sliding window as center：
；
Along-area infrared image firstColumn pixel vertical sliding window, calculating the +.>Cumulative histogram of window with minimum average gradient among all sliding windows of column pixel points +.>：
；
In the middle ofRepresenting the number of lines of the regional infrared image, i.e. the number of pixels per column, +.>Representing cumulative histogram->Gray level of +.>Representing the pixel point->Is +.>；
Computing region infrared image NoMedian histogram +.f. of window with minimum average gradient among all sliding windows of column pixel points>：
；
；
In the middle ofRepresents standard deviation +.4 times>Rounding up to minus infinity, < >>Representing standard deviation +.>Gaussian weight of ∈ ->Representing a threshold value;
acquisition of regional infrared imageCorrection gray value of column pixel>：
；
The steps are executed, the correction gray value of each column of pixel points of the infrared image of the area is sequentially obtained, and image correction is completed;
s22: image denoising is represented by the following formula:
；
in the middle ofRepresenting the +.o in the area infrared image>The pixel gray values in the filtering template with the pixel as the center,representing the +.o in the area infrared image>Weighting coefficient of each pixel point in the filtering template taking each pixel point as center, +.>Representing the size of the filtering template +.>Representing the width of the filtering template, +.>Representing the height of the filtering template, +.>Representing the infrared image of the region +.>Gray values after denoising of the pixel points;
s23: the data enhancement is used for expanding the regional infrared image so as to improve the generalization performance of the network, and the specific implementation process is as follows:
according to the characteristic that the regional infrared image has no fixed direction, when the image is input into a network for training, the image is subjected to image transformation such as horizontal overturning, vertical overturning, random angle rotation, mosaic random enhancement and the like with a certain probability, so that the purpose of expanding the regional infrared image is achieved;
the specific steps of the Mosaic random enhancement include:
generating a sheetBackground map of size, ">The size background picture can accommodate 4 pieces of size +.>Is a region infrared image of (2);
the size of the center point of the background picture is as followsRandomly selecting a splicing center for dividing the background picture into four areas of upper left, upper right, lower right and lower left;
randomly selecting 4 infrared images of different areas, sequentially arranging the infrared images in the upper left, the upper right, the lower left and the lower right of the background image, and cutting off the images and the marking frames exceeding the background boundary area to obtain the background image with the size ofIs a region infrared image of (2);
the spliced size isThe area infrared image is scaled to a size +.>And finishing the Mosaic random enhancement.
S3: constructing a gas detection network to obtain positioning information of a gas release source;
as shown in fig. 2, the gas detection network includes a gas infrared feature extraction unit, a gas motion feature extraction unit, a feature fusion unit and a gas release source positioning unit, wherein the gas release source positioning unit includes 21×1 convolution layers and 43×3 convolution layers, and the output of the gas release source positioning unit is gas release source positioning information;
the gas infrared characteristic extraction unit is used for extracting a gas infrared characteristic diagram, and specifically comprises the following steps:
performing boundary filling on the input regional infrared image, wherein the filling width is 1, and obtaining a first gas infrared characteristic diagram;
the characteristic extraction is carried out on the first gas infrared characteristic map through the 3X 3 convolution layer, the ReLU activation function and the 3X 3 convolution layer in sequence, so as to obtain a second gas infrared characteristic map;
adding the first gas infrared characteristic diagram and the second gas infrared characteristic diagram, and inputting a ReLU activation function to obtain a final gas infrared characteristic diagram;
the gas motion feature extraction unit is used for extracting a gas motion feature graph and comprises 17×7 convolution layers, 25×5 convolution layers and 6 3×3 convolution layers;
the feature fusion unit is used for carrying out feature fusion on the gas infrared feature map and the gas motion feature map, and is expressed by the following formula:
；
in the middle ofRepresenting a gas movement profile, < >>Representing the infrared signature of a gas,>a set of feature maps representing infrared images of the same area,/->Representing pixel-by-pixel addition, +.>Representing pixel-by-pixel multiplication +.>And representing the fused characteristic diagram.
S4: constructing a gas concentration calibration network, and calibrating the gas concentration information by integrating temperature information and pressure information in the regional environment to obtain regional gas concentration information;
the gas concentration calibration network may be represented by the following formula:
；
in the middle ofIndicating calibrated zone gas concentration information, +.>Representing the output layer node transfer function,/->The category number of the regional environment information representing input, < +.>Indicating the connection weights of the intermediate layer to the output layer, < ->Representing intermediate layer node transfer function, ">Indicating the number of intermediate layer nodes, ">Information representing the environment of the inputted area, including temperature information, pressure information and gas concentration information, < >>Representing the connection weights of the input layer to the intermediate layer, < ->Represents an intermediate layer threshold value->Representing the output layer threshold.
S5: comprehensively analyzing the positioning information of the gas release source and the regional gas concentration information, and outputting early warning information;
the early warning information comprises a first early warning information and a second early warning information, and the specific steps of outputting the early warning information comprise:
calculating the distance from the current detection position to the gas release source through the gas release source positioning information;
if the distance is smaller than or equal to a preset safety distance threshold value or the regional gas concentration information is larger than a preset gas concentration threshold value, outputting first early warning information;
if the distance is greater than a preset safety distance threshold value or the regional gas concentration information is less than or equal to a preset gas concentration threshold value, outputting second early warning information;
the first early warning information is sound early warning and light early warning, the second early warning information is light early warning, the preset safety distance threshold is determined by gas types, leakage rate and regional environment information, the value range is 30-430 m, the preset gas concentration threshold is determined by gas types and operation place standards, and the value range is 500-12500 ppm.
Example 2
As shown in fig. 3, the present embodiment provides a gas intelligent detection and early warning system 20 based on regional environmental analysis, which includes:
the information acquisition module 21 is used for acquiring regional environment information, wherein the regional environment information comprises temperature information, humidity information, pressure information, gas concentration information and regional infrared images;
the image preprocessing module 22 is used for preprocessing the acquired infrared image of the region, wherein the preprocessing comprises image correction, image denoising and data enhancement;
the gas detection network construction module 23 is used for constructing a gas detection network to obtain gas release source positioning information;
the gas concentration calibration network construction module 24 is configured to construct a gas concentration calibration network, calibrate the gas concentration information by integrating temperature information and pressure information in the regional environment, and obtain regional gas concentration information;
the early warning information output module 25 is used for comprehensively analyzing the positioning information of the gas release source and the regional gas concentration information and outputting early warning information;
in this embodiment, the gas concentration information is collected by the semiconductor gas sensor and the infrared gas sensor together, and the specific steps include:
acquiring first gas concentration information through a semiconductor type gas sensor, and acquiring second gas concentration information through an infrared type gas sensor;
if the humidity information in the regional environment is greater than or equal to a preset humidity threshold, the gas concentration information is first gas concentration information, and if the humidity information in the regional environment is less than the preset humidity threshold, the gas concentration information is second gas concentration information;
in this embodiment, the image preprocessing module 22 performs preprocessing on the collected infrared image of the region, where the preprocessing includes image correction, image denoising and data enhancement;
the specific steps of image correction include:
let the size of the regional infrared image be，/>Column number of infrared image representing area, +.>Representing the number of lines of the regional infrared image, by the regional infrared image +.>The column pixel point is used as the center to construct a pixel with the size of +.>Is (are) sliding window->Column number of sliding window->Representing the number of rows of the sliding window->And->Are all odd numbers;
calculating pixel points in an infrared imageGradient in the horizontal direction of the sliding window as center +.>：
；
In the middle of，/>，/>Representing the +.o in an IR image of a region>Line->Gray values of column pixel points;
calculating pixel points in an infrared imageAverage gradient in horizontal direction of sliding window as center：
；
Along-area infrared image firstColumn pixel vertical sliding window, calculating the +.>Cumulative histogram of window with minimum average gradient among all sliding windows of column pixel points +.>：
；
In the middle ofRepresenting the number of lines of the regional infrared image, i.e. the number of pixels per column, +.>Representing cumulative histogram->Gray level of +.>Representing a command pixelPoint->Is +.>；
Computing region infrared image NoMedian histogram +.f. of window with minimum average gradient among all sliding windows of column pixel points>：
；
；
In the middle ofRepresents standard deviation +.4 times>Rounding up to minus infinity, < >>Representing standard deviation +.>Gaussian weight of ∈ ->Representing a threshold value;
acquisition of regional infrared imageCorrection gray value of column pixel>：
；
The steps are executed, the correction gray value of each column of pixel points of the infrared image of the area is sequentially obtained, and image correction is completed;
image denoising is represented by the following formula:
；
in the middle ofRepresenting the +.o in the area infrared image>The pixel gray values in the filtering template with the pixel as the center,representing the +.o in the area infrared image>Weighting coefficient of each pixel point in the filtering template taking each pixel point as center, +.>Representing the size of the filtering template +.>Representing the width of the filtering template, +.>Representing the height of the filtering template, +.>Representing the infrared image of the region +.>Gray values after denoising of the pixel points;
the data enhancement is used for expanding the regional infrared image so as to improve the generalization performance of the network, and the specific implementation process is as follows:
according to the characteristic that the regional infrared image has no fixed direction, when the image is input into a network for training, the image is subjected to image transformation such as horizontal overturning, vertical overturning, random angle rotation, mosaic random enhancement and the like with a certain probability, so that the purpose of expanding the regional infrared image is achieved;
the specific steps of the Mosaic random enhancement include:
generating a sheetBackground map of size, ">The size background picture can accommodate 4 pieces of size +.>Is a region infrared image of (2);
the size of the center point of the background picture is as followsRandomly selecting a splicing center for dividing the background picture into four areas of upper left, upper right, lower right and lower left;
randomly selecting 4 infrared images of different areas, sequentially arranging the infrared images in the upper left, the upper right, the lower left and the lower right of the background image, and cutting off the images and the marking frames exceeding the background boundary area to obtain the background image with the size ofIs a region infrared image of (2);
the spliced size isThe area infrared image is scaled to a size +.>Finishing the random enhancement of the Mosaic;
in this embodiment, the gas detection network construction module 23 constructs a gas detection network to obtain gas release source positioning information;
the gas detection network comprises a gas infrared feature extraction unit, a gas motion feature extraction unit, a feature fusion unit and a gas release source positioning unit, wherein the gas release source positioning unit comprises 21×1 convolution layers and 43×3 convolution layers, and the output of the gas release source positioning unit is gas release source positioning information;
the gas infrared characteristic extraction unit is used for extracting a gas infrared characteristic diagram, and specifically comprises the following steps:
performing boundary filling on the input regional infrared image, wherein the filling width is 1, and obtaining a first gas infrared characteristic diagram;
the characteristic extraction is carried out on the first gas infrared characteristic map through the 3X 3 convolution layer, the ReLU activation function and the 3X 3 convolution layer in sequence, so as to obtain a second gas infrared characteristic map;
adding the first gas infrared characteristic diagram and the second gas infrared characteristic diagram, and inputting a ReLU activation function to obtain a final gas infrared characteristic diagram;
the gas motion feature extraction unit is used for extracting a gas motion feature graph and comprises 17×7 convolution layers, 25×5 convolution layers and 6 3×3 convolution layers;
the feature fusion unit is used for carrying out feature fusion on the gas infrared feature map and the gas motion feature map, and is expressed by the following formula:
；
in the middle ofRepresenting a gas movement profile, < >>Representing the infrared signature of a gas,>representing the same areaA set of feature maps of an infrared image, +.>Representing pixel-by-pixel addition, +.>Representing pixel-by-pixel multiplication +.>Representing the fused feature map;
in this embodiment, the gas concentration calibration network construction module 24 constructs a gas concentration calibration network, and calibrates the gas concentration information by integrating the temperature information and the pressure information in the regional environment to obtain regional gas concentration information;
the gas concentration calibration network may be represented by the following formula:
；
in the middle ofIndicating calibrated zone gas concentration information, +.>Representing the output layer node transfer function,/->The category number of the regional environment information representing input, < +.>Indicating the connection weights of the intermediate layer to the output layer, < ->Representing intermediate layer node transfer function, ">Indicating the number of intermediate layer nodes, ">Information representing the environment of the inputted area, including temperature information, pressure information and gas concentration information, < >>Representing the connection weights of the input layer to the intermediate layer, < ->Represents an intermediate layer threshold value->Representing the output layer threshold.
In this embodiment, the early warning information output module 25 comprehensively analyzes the gas release source positioning information and the regional gas concentration information, and outputs early warning information;
the early warning information comprises a first early warning information and a second early warning information, and the specific steps of outputting the early warning information comprise:
calculating the distance from the current detection position to the gas release source through the gas release source positioning information;
if the distance is smaller than or equal to a preset safety distance threshold value or the regional gas concentration information is larger than a preset gas concentration threshold value, outputting first early warning information;
if the distance is greater than a preset safety distance threshold value or the regional gas concentration information is less than or equal to a preset gas concentration threshold value, outputting second early warning information;
the first early warning information is sound early warning and light early warning, the second early warning information is light early warning, the preset safety distance threshold is determined by gas types, leakage rate and regional environment information, the value range is 30-430 m, the preset gas concentration threshold is determined by gas types and operation place standards, and the value range is 500-12500 ppm.
The steps for implementing the corresponding functions of each parameter and each unit module in the gas intelligent detection and early warning system based on regional environment analysis according to the present invention may refer to each parameter and step in the embodiment of the gas intelligent detection and early warning method based on regional environment analysis, which are not described herein.
Example 3
The embodiment of the invention provides a computer readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for intelligently detecting and pre-warning gas based on regional environment analysis is realized. It should be noted that: all computer programs of the intelligent gas detection and early warning method based on regional environment analysis are realized by using Python language, wherein an image preprocessing module, a gas detection network construction module, a gas concentration calibration network construction module and an early warning information output module are controlled by a remote server; the CPU of the remote server is Intel Xeon Gold 5118, the GPU is NVIDIA GTX 2080Ti 11GB, the operating system is Ubuntu 18.04.2, the deep learning framework is PyTorch1.7.0, CUDA version 10.2, and the cuDNN 7.6.5 is used for acceleration reasoning; intel Xeon Gold 5118 contains a memory and a processor, wherein the memory is used to store a computer program; the processor is used for executing a computer program to enable the Intel Xeon Gold 5118 to execute and realize an intelligent gas detection and early warning method based on regional environment analysis.
Those skilled in the art will appreciate that the present invention may be implemented as a system, method, or computer program product.
Accordingly, the present disclosure may be embodied in the following forms, namely: either entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or entirely software, or a combination of hardware and software, referred to herein generally as a "circuit," module "or" system. Furthermore, in some embodiments, the invention may also be embodied in the form of a computer program product in one or more computer-readable media, which contain computer-readable program code.
Any combination of one or more computer readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (14)
1. The intelligent gas detection and early warning method based on regional environment analysis is characterized by comprising the following steps of:
collecting regional environment information, wherein the regional environment information comprises temperature information, humidity information, pressure information, gas concentration information and a regional infrared image;
preprocessing the acquired infrared image of the region, wherein the preprocessing comprises image correction, image denoising and data enhancement;
constructing a gas detection network to obtain positioning information of a gas release source;
constructing a gas concentration calibration network, and calibrating the gas concentration information by integrating temperature information and pressure information in the regional environment to obtain regional gas concentration information;
comprehensively analyzing the positioning information of the gas release source and the regional gas concentration information, and outputting early warning information.
2. The method for intelligent detection and early warning of gas based on regional environmental analysis according to claim 1, wherein the gas concentration information is collected by a semiconductor gas sensor and an infrared gas sensor together, and the specific steps comprise:
acquiring first gas concentration information through a semiconductor type gas sensor, and acquiring second gas concentration information through an infrared type gas sensor;
if the humidity information in the regional environment is greater than or equal to a preset humidity threshold, the gas concentration information is first gas concentration information, and if the humidity information in the regional environment is less than the preset humidity threshold, the gas concentration information is second gas concentration information.
3. The method for intelligent detection and early warning of gas based on regional environmental analysis according to claim 1, wherein the specific image correction step comprises the following steps:
with regional infrared imageThe size of the column pixel point is +.>Is (are) sliding window->Column number of sliding window->A number of rows representing a sliding window;
calculating pixel points in an infrared imageAn average gradient in the horizontal direction of the sliding window being the center, +.>Column pixel vertical sliding window, calculating the +.>Cumulative histograms and median histograms of windows with minimum average gradient in all sliding windows of the column pixel points;
acquisition of regional infrared image by cumulative and median histogramsAnd correcting gray values of the column pixel points, sequentially obtaining the corrected gray values of each column pixel point of the infrared image of the region, and finishing image correction.
4. The intelligent gas detection and early warning method based on regional environment analysis according to claim 1, wherein the image denoising is represented by the following formula:
；
in the middle ofRepresenting the +.o in the area infrared image>Gray values of pixel points in filtering template with centers of the pixel points, < +.>Representing the +.o in the area infrared image>Weighting coefficient of each pixel point in the filtering template taking each pixel point as center, +.>Representing the size of the filtering template +.>Representing the width of the filtering template，/>Representing the height of the filtering template, +.>Representing the infrared image of the region +.>And (5) denoising the gray value of each pixel point.
5. The method for intelligent detection and early warning of gas based on regional environmental analysis according to claim 1, wherein the data enhancement is used for expanding regional infrared images, and the specific steps include:
image transformation is performed on the regional infrared image, the image transformation including at least one of horizontal flip, vertical flip, random angular rotation, and mosaics random enhancement.
6. The intelligent gas detection and early warning method based on regional environment analysis according to claim 1, wherein the gas detection network comprises a gas infrared feature extraction unit, a gas motion feature extraction unit, a feature fusion unit and a gas release source positioning unit, wherein the gas release source positioning unit comprises 21×1 convolution layers and 43×3 convolution layers, and the output of the gas release source positioning unit is gas release source positioning information.
7. The method for intelligent detection and early warning of gas based on regional environmental analysis according to claim 1, wherein the gas concentration calibration network can be represented by the following formula:
；
in the middle ofIndicating calibrated zone gas concentration information, +.>Representing the output layer node transfer function,/->The category number of the regional environment information representing input, < +.>Indicating the connection weights of the intermediate layer to the output layer, < ->Representing the transfer function of the intermediate layer node,indicating the number of intermediate layer nodes, ">Information representing the environment of the inputted area, including temperature information, pressure information and gas concentration information, < >>Representing the connection weights of the input layer to the intermediate layer, < ->Represents an intermediate layer threshold value->Representing the output layer threshold.
8. The method for intelligent gas detection and early warning based on regional environmental analysis according to claim 1, wherein the early warning information comprises two early warning levels of first early warning information and second early warning information, and the specific step of outputting the early warning information comprises the following steps:
calculating the distance from the current detection position to the gas release source through the gas release source positioning information;
if the distance is smaller than or equal to a preset safety distance threshold value or the regional gas concentration information is larger than a preset gas concentration threshold value, outputting first early warning information;
and if the distance is greater than a preset safety distance threshold or the regional gas concentration information is less than or equal to the preset gas concentration threshold, outputting second early warning information.
9. The method for intelligent gas detection and early warning based on regional environmental analysis according to claim 6, wherein the gas infrared feature extraction unit is used for extracting a gas infrared feature map, and the specific steps include:
performing boundary filling on the input regional infrared image, wherein the filling width is 1, and obtaining a first gas infrared characteristic diagram;
the characteristic extraction is carried out on the first gas infrared characteristic map through the 3X 3 convolution layer, the ReLU activation function and the 3X 3 convolution layer in sequence, so as to obtain a second gas infrared characteristic map;
and adding the first gas infrared characteristic diagram and the second gas infrared characteristic diagram, and inputting the sum into a ReLU activation function to obtain a final gas infrared characteristic diagram.
10. The gas intelligent detection and early warning method based on regional environment analysis according to claim 6, wherein the gas motion feature extraction unit is used for extracting a gas motion feature map, and comprises 17×7 convolution layers, 25×5 convolution layers and 6 3×3 convolution layers.
11. The intelligent gas detection and early warning method based on regional environment analysis according to claim 6, wherein the feature fusion unit is used for carrying out feature fusion on a gas infrared feature map and a gas motion feature map, and the feature fusion unit is represented by the following formula:
；
in the middle ofRepresenting a gas movement profile, < >>Representing the infrared signature of a gas,>a set of feature maps representing infrared images of the same area,/->Representing pixel-by-pixel addition, +.>Representing pixel-by-pixel multiplication +.>And representing the fused characteristic diagram.
12. A gas intelligent detection and early warning system based on regional environment analysis, which is realized based on the gas intelligent detection and early warning method based on regional environment analysis according to any one of claims 1 to 11, and is characterized in that the system comprises:
the information acquisition module is used for acquiring regional environment information, wherein the regional environment information comprises temperature information, humidity information, pressure information, gas concentration information and regional infrared images;
the image preprocessing module is used for preprocessing the acquired infrared image of the region, wherein the preprocessing comprises image correction, image denoising and data enhancement;
the gas detection network construction module is used for constructing a gas detection network to obtain positioning information of a gas release source;
the gas concentration calibration network construction module is used for constructing a gas concentration calibration network, and integrating temperature information and pressure information in the regional environment to calibrate the gas concentration information so as to obtain regional gas concentration information;
and the early warning information output module is used for comprehensively analyzing the positioning information of the gas release source and the regional gas concentration information and outputting early warning information.
13. A computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements a regional environment analysis based intelligent gas detection pre-warning method according to any one of claims 1 to 11.
14. A controller comprising a memory and a processor, the memory being configured to store a computer program, wherein the processor is configured to implement a regional environment analysis-based intelligent gas detection and early warning method according to any one of claims 1 to 11 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311414782.9A CN117147631A (en) | 2023-10-30 | 2023-10-30 | Regional environment analysis-based intelligent gas detection and early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311414782.9A CN117147631A (en) | 2023-10-30 | 2023-10-30 | Regional environment analysis-based intelligent gas detection and early warning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117147631A true CN117147631A (en) | 2023-12-01 |
Family
ID=88906459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311414782.9A Pending CN117147631A (en) | 2023-10-30 | 2023-10-30 | Regional environment analysis-based intelligent gas detection and early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117147631A (en) |
Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201188050Y (en) * | 2008-01-04 | 2009-01-28 | 福建师范大学 | On-line monitoring device for SF6 gas leakage base on multi-sensor |
| CN102609906A (en) * | 2012-01-12 | 2012-07-25 | 北京理工大学 | Gas infrared image enhancing method based on anisotropic diffusion |
| CN103217397A (en) * | 2013-01-23 | 2013-07-24 | 山西省电力公司晋城供电分公司 | SF6 gas detection method based on infrared image processing |
| CN104101571A (en) * | 2014-07-27 | 2014-10-15 | 北京航星网讯技术股份有限公司 | Methane gas detecting method and device with laser distance-measuring function |
| CN104123810A (en) * | 2013-04-25 | 2014-10-29 | 北京格宝应用技术有限公司 | Gas leakage alarm device and method thereof |
| CN105447471A (en) * | 2015-12-04 | 2016-03-30 | 国网技术学院 | Infrared detection based device gas leakage identification method and apparatus |
| CN106874949A (en) * | 2017-02-10 | 2017-06-20 | 华中科技大学 | A kind of moving platform moving target detecting method and system based on infrared image |
| CN107065027A (en) * | 2017-05-11 | 2017-08-18 | 清华大学 | Detection system, method, device and the equipment of source of leaks |
| CN107451590A (en) * | 2017-07-19 | 2017-12-08 | 哈尔滨工程大学 | Gas detection identification and concentration method for expressing based on EO-1 hyperion infrared image |
| CN108535188A (en) * | 2018-05-23 | 2018-09-14 | 广东容祺智能科技有限公司 | A kind of the unmanned plane gas detecting system and its detection method of single line laser |
| CN109727202A (en) * | 2017-10-27 | 2019-05-07 | 清华大学 | Gas infrared video Enhancement Method, device and storage medium |
| CN110211056A (en) * | 2019-05-06 | 2019-09-06 | 南京理工大学 | Adaptive infrared image based on value histogram in part removes striped algorithm |
| CN110231308A (en) * | 2019-08-05 | 2019-09-13 | 南京南智芯光科技有限公司 | A kind of active illumination gas imaging detection method and system |
| CN110992301A (en) * | 2019-10-14 | 2020-04-10 | 数量级(上海)信息技术有限公司 | Gas contour identification method |
| CN112504997A (en) * | 2020-12-10 | 2021-03-16 | 中国科学院深圳先进技术研究院 | Gas leakage detection method and system |
| CN112595767A (en) * | 2020-12-14 | 2021-04-02 | 深圳市豪恩安全科技有限公司 | Calibration method, system and equipment of semiconductor type gas sensor |
| CN112781791A (en) * | 2020-12-30 | 2021-05-11 | 大连海事大学 | VOCs gas leakage detection method and system based on optical gas imaging |
| CN113203772A (en) * | 2021-03-18 | 2021-08-03 | 中国外运股份有限公司 | Industrial intelligent composite gas detector and detection method |
| CN114062615A (en) * | 2021-12-14 | 2022-02-18 | 合肥航谱时代科技有限公司 | Gas leakage monitoring method based on image |
| CN114088890A (en) * | 2022-01-24 | 2022-02-25 | 中国农业科学院农业信息研究所 | Self-adaptive temperature and humidity compensation method and system based on deep BP neural network |
| CN114283552A (en) * | 2021-12-27 | 2022-04-05 | 河南驰诚电气股份有限公司 | Combustible gas alarm system and method for driving wireless electromagnetic valve |
| CN115938077A (en) * | 2022-09-27 | 2023-04-07 | 安徽砺剑防务科技有限公司 | Chemical industry park gas remote measuring alarm integration method and system |
| CN115966063A (en) * | 2022-12-06 | 2023-04-14 | 成都盈盛源电气科技有限公司 | Gas leakage infrared imaging automatic alarm method |
| US20230177726A1 (en) * | 2021-12-03 | 2023-06-08 | Sixgill, LLC | System and method of detecting gas leaks |
| CN116309473A (en) * | 2023-03-20 | 2023-06-23 | 中国科学技术大学先进技术研究院 | Training method of gas leakage detection model and gas leakage detection method |
| CN116642810A (en) * | 2023-04-14 | 2023-08-25 | 苏州百工环保科技有限公司 | Dust monitoring method and system based on Internet of things |
| CN116878748A (en) * | 2023-06-06 | 2023-10-13 | 浙江省计量科学研究院 | Laser and image fusion intelligent gas leakage positioning method and device |
-
2023
- 2023-10-30 CN CN202311414782.9A patent/CN117147631A/en active Pending
Patent Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201188050Y (en) * | 2008-01-04 | 2009-01-28 | 福建师范大学 | On-line monitoring device for SF6 gas leakage base on multi-sensor |
| CN102609906A (en) * | 2012-01-12 | 2012-07-25 | 北京理工大学 | Gas infrared image enhancing method based on anisotropic diffusion |
| CN103217397A (en) * | 2013-01-23 | 2013-07-24 | 山西省电力公司晋城供电分公司 | SF6 gas detection method based on infrared image processing |
| CN104123810A (en) * | 2013-04-25 | 2014-10-29 | 北京格宝应用技术有限公司 | Gas leakage alarm device and method thereof |
| CN104101571A (en) * | 2014-07-27 | 2014-10-15 | 北京航星网讯技术股份有限公司 | Methane gas detecting method and device with laser distance-measuring function |
| CN105447471A (en) * | 2015-12-04 | 2016-03-30 | 国网技术学院 | Infrared detection based device gas leakage identification method and apparatus |
| CN106874949A (en) * | 2017-02-10 | 2017-06-20 | 华中科技大学 | A kind of moving platform moving target detecting method and system based on infrared image |
| CN107065027A (en) * | 2017-05-11 | 2017-08-18 | 清华大学 | Detection system, method, device and the equipment of source of leaks |
| CN107451590A (en) * | 2017-07-19 | 2017-12-08 | 哈尔滨工程大学 | Gas detection identification and concentration method for expressing based on EO-1 hyperion infrared image |
| CN109727202A (en) * | 2017-10-27 | 2019-05-07 | 清华大学 | Gas infrared video Enhancement Method, device and storage medium |
| CN108535188A (en) * | 2018-05-23 | 2018-09-14 | 广东容祺智能科技有限公司 | A kind of the unmanned plane gas detecting system and its detection method of single line laser |
| CN110211056A (en) * | 2019-05-06 | 2019-09-06 | 南京理工大学 | Adaptive infrared image based on value histogram in part removes striped algorithm |
| CN110231308A (en) * | 2019-08-05 | 2019-09-13 | 南京南智芯光科技有限公司 | A kind of active illumination gas imaging detection method and system |
| CN110992301A (en) * | 2019-10-14 | 2020-04-10 | 数量级(上海)信息技术有限公司 | Gas contour identification method |
| CN112504997A (en) * | 2020-12-10 | 2021-03-16 | 中国科学院深圳先进技术研究院 | Gas leakage detection method and system |
| CN112595767A (en) * | 2020-12-14 | 2021-04-02 | 深圳市豪恩安全科技有限公司 | Calibration method, system and equipment of semiconductor type gas sensor |
| CN112781791A (en) * | 2020-12-30 | 2021-05-11 | 大连海事大学 | VOCs gas leakage detection method and system based on optical gas imaging |
| CN113203772A (en) * | 2021-03-18 | 2021-08-03 | 中国外运股份有限公司 | Industrial intelligent composite gas detector and detection method |
| US20230177726A1 (en) * | 2021-12-03 | 2023-06-08 | Sixgill, LLC | System and method of detecting gas leaks |
| CN114062615A (en) * | 2021-12-14 | 2022-02-18 | 合肥航谱时代科技有限公司 | Gas leakage monitoring method based on image |
| CN114283552A (en) * | 2021-12-27 | 2022-04-05 | 河南驰诚电气股份有限公司 | Combustible gas alarm system and method for driving wireless electromagnetic valve |
| CN114088890A (en) * | 2022-01-24 | 2022-02-25 | 中国农业科学院农业信息研究所 | Self-adaptive temperature and humidity compensation method and system based on deep BP neural network |
| CN115938077A (en) * | 2022-09-27 | 2023-04-07 | 安徽砺剑防务科技有限公司 | Chemical industry park gas remote measuring alarm integration method and system |
| CN115966063A (en) * | 2022-12-06 | 2023-04-14 | 成都盈盛源电气科技有限公司 | Gas leakage infrared imaging automatic alarm method |
| CN116309473A (en) * | 2023-03-20 | 2023-06-23 | 中国科学技术大学先进技术研究院 | Training method of gas leakage detection model and gas leakage detection method |
| CN116642810A (en) * | 2023-04-14 | 2023-08-25 | 苏州百工环保科技有限公司 | Dust monitoring method and system based on Internet of things |
| CN116878748A (en) * | 2023-06-06 | 2023-10-13 | 浙江省计量科学研究院 | Laser and image fusion intelligent gas leakage positioning method and device |
Non-Patent Citations (9)
| Title |
|---|
| 刘亚欣等: "机器人感知技术", 机械工业出版社, pages: 197 * |
| 徐守坤: "基于多特征与DCNN的红外SF6泄漏检测方法研究", 计算机应用与软件, vol. 38, no. 6 * |
| 徐守坤等: "基于多特征与DCNN 的红外SF6泄漏检测方法研究", 计算机应用与软件, vol. 38, no. 6, pages 134 * |
| 曾延安;张超;元秀华;张南洋生;朱兵;张力;: "便携式SF_6气体红外光谱成像检漏仪", 仪表技术与传感器, no. 10 * |
| 杜京义;殷聪;王伟峰;蔡驰;王立春;: "基于TDLAS的痕量CO浓度检测系统及温压补偿", 光学技术, no. 01 * |
| 杜京义等, 光学技术, vol. 44, no. 1 * |
| 王建, 方德广, 尹明德: "基于Lonworks技术的气体监控系统研究", 机电工程技术, no. 04 * |
| 贾鹏;李江勇;: "子块重叠局部直方图均衡算法的优化研究", 激光与红外, no. 12, 20 December 2012 (2012-12-20), pages 197 * |
| 郭威彤;宋海声;杨鸿武;裴东;: "一种便携式室内空气质量快速检测仪设计", 传感器与微系统, no. 04 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102166458B1 (en) | Defect inspection method and apparatus using image segmentation based on artificial neural network | |
| CN111797890A (en) | Method and system for detecting defects of power transmission line equipment | |
| CN110717481B (en) | Method for realizing face detection by using cascaded convolutional neural network | |
| US20210174149A1 (en) | Feature fusion and dense connection-based method for infrared plane object detection | |
| CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
| KR102141302B1 (en) | Object detection method based 0n deep learning regression model and image processing apparatus | |
| CN104599292A (en) | Noise-resistant moving target detection algorithm based on low rank matrix | |
| CN111815576B (en) | Method, device, equipment and storage medium for detecting corrosion condition of metal part | |
| CN113936004B (en) | Lithium battery welding quality detection method, device and system | |
| CN115457428A (en) | Improved YOLOv5 fire detection method and device integrating adjustable coordinate residual attention | |
| CN116046692B (en) | Soil heavy metal pollution monitoring method and device based on hyperspectrum | |
| CN111008576A (en) | Pedestrian detection and model training and updating method, device and readable storage medium thereof | |
| CN111563896A (en) | Image processing method for catenary anomaly detection | |
| CN115310555A (en) | Image anomaly detection method based on local perception knowledge distillation network | |
| CN115829995A (en) | Cloth flaw detection method and system based on pixel-level multi-scale feature fusion | |
| CN116843999A (en) | Gas cylinder detection method in fire operation based on deep learning | |
| CN117147631A (en) | Regional environment analysis-based intelligent gas detection and early warning method and system | |
| CN110503631A (en) | A kind of method for detecting change of remote sensing image | |
| CN116434230A (en) | Ship water gauge reading method under complex environment | |
| CN111191575B (en) | Naked flame detection method and system based on flame jumping modeling | |
| CN115239733A (en) | Crack detection method, crack detection device, terminal equipment and storage medium | |
| CN114757941A (en) | Transformer substation equipment defect identification method and device, electronic equipment and storage medium | |
| CN113034432A (en) | Product defect detection method, system, device and storage medium | |
| CN112967241A (en) | Hyperspectral image anomaly detection method based on local gradient guidance | |
| CN110956130A (en) | Method and system for four-level face detection and key point regression |
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 |