CN111754455B - Water leakage detection method and system for thermal power plant - Google Patents
Water leakage detection method and system for thermal power plant Download PDFInfo
- Publication number
- CN111754455B CN111754455B CN202010410743.1A CN202010410743A CN111754455B CN 111754455 B CN111754455 B CN 111754455B CN 202010410743 A CN202010410743 A CN 202010410743A CN 111754455 B CN111754455 B CN 111754455B
- Authority
- CN
- China
- Prior art keywords
- feature
- water leakage
- area
- water
- infrared
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 182
- 238000001514 detection method Methods 0.000 title claims abstract description 106
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 238000012216 screening Methods 0.000 claims abstract description 21
- 238000009825 accumulation Methods 0.000 claims description 69
- 238000000605 extraction Methods 0.000 claims description 26
- 230000026676 system process Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 6
- 238000007689 inspection Methods 0.000 abstract description 4
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 17
- 230000001502 supplementing effect Effects 0.000 description 6
- 238000005286 illumination Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005498 polishing Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Abstract
The invention provides a water leakage detection method and system for a thermal power plant, which adopt unmanned water leakage inspection to replace manual water leakage inspection, detect water leakage faults of a machine of the thermal power plant, classify water leakage characteristics according to results and feed back alarm information. The invention solves the problems of overcoming the complex and dark factory environment of the thermal power plant, and completely exposing the water leakage reflection characteristic through a special auxiliary light source; further processing two detection data collected by the high-definition camera and the infrared camera, and improving the recognition and analysis capability of the water leakage characteristics; and finally, screening and classifying the water leakage characteristics according to the detection result and the detection experience. According to the invention, infrared and visible light data are simultaneously analyzed, the data analysis result is synthesized, the efficiency and reliability of water leakage detection are fully improved, and the effect of accurately screening the ponding characteristic is achieved.
Description
Technical Field
The invention relates to the field of water leakage detection of thermal power plants, in particular to a water leakage detection method and system of a thermal power plant.
Background
The thermal power plant is an important energy generation department, and continuous and stable operation power supply needs to be ensured. The equipment types that thermal power plant contained are more, and the detection mode that current thermal power plant leaked is that the workman shines the machine base station with the torch repeatedly and evaluates whether to leak according to the construction experience, and this kind of operational mode duty cycle is longer, and workman is difficult to long-time operation under high noise, high thermal operational environment. Because the factory environment is complex, the temperature, the illumination and other interference factors are more, the existing unmanned water leakage identification and diagnosis still have a plurality of problems and influence factors, and the method is difficult to be well applied to the factory environment. Firstly, the light in a factory is darker, the machine structure is complex, the complete leakage water is difficult to observe by a direct observation, monitoring or flashlight lighting method, the manual detection difficulty is high, and the omission rate is high; secondly, most of the existing water leakage detection technologies of the thermal power plant machines focus on methods of judging water leakage by reading readings of a pressure gauge and a flowmeter, paving test paper at a water leakage point to detect whether the test paper changes color or not, and the methods all need to add or modify devices on site, have unstable effects and are easy to produce misjudgment.
Patent CN 110529186A provides a tunnel structure leakage water accurate recognition device based on infrared thermal imaging, the method is applied to a patrol robot, and the robot comprises a detection device and a movement control device; the detection device comprises an infrared thermal imager, an industrial camera and a light supplementing device, and the mobile control device comprises a synchronous control card, a laser range finder, a range wheel device, an industrial personal computer and a power supply system; the laser range finder, the industrial camera, the infrared thermal imager and the light supplementing device are adjacently arranged on the base and are arranged on the equipment support of the equipment carrying platform. The position ranging is carried out through the ranging wheel, the detection signal is converted into the displacement mileage and is transmitted to the data acquisition and processing system, the light supplementing device (LED white light lamp) is positioned and moved, the image acquisition is carried out after the light supplementing range is adjusted through the rotating equipment support, the image is transmitted to the data acquisition and processing system for analysis, and finally the analysis result is output and fed back. However, in the method described in this patent, the light supplementing link still needs to be modified to a certain extent, the method has not strong adaptability to the environment, if the water is seeped into the ground surface in a scene with obvious water mark characteristics, the water is not fully supplemented by the method of the rotating LED white light lamp described in the patent, the water leaking area is difficult to be marked out in the image obtained by the high-definition camera, meanwhile, the suspicious area of the infrared image is extracted by filtering and gray value, the extracted characteristics are not further screened, if the weather condition is humid weather or the environment is complex, if the water is likely to be present in the infrared image in a low-temperature area similar to the temperature of the water leaking area, the direct extraction method after subtracting the preset gray value by the patent may cause the excessive infrared extraction result, reduce the effect of the important area division for the high-definition image, in the reality, because the plant area of the power plant is complex in environment, the equipment is wide in area, the water leaking scene is very complex, in the situation, the water is not permeated into the ground surface in real time, and obvious water is not seeped into the ground surface, if the water is likely to be present in the water is not easy, and the water is difficult to be exposed to the water is only in a smooth and smooth ground surface, if the water is difficult to be exposed by the white light is easy to be present on the ground surface. Therefore, more effective light supplementing equipment needs to be designed for the complex environment of the power plant area, colorless and transparent effusion on the smooth ground is fully exposed, and then feature screening and analysis are carried out.
Patent CN 109459191A provides a transformer substation indoor water leakage detection robot, makes the robot remove on the guide rail through the base through control push rod motor, and when the brush mounting panel fell to the minimum after the appointed point, the metal brush contacted with ground, was equipped with the voltage detection head on the brush mounting panel, whether detected ground through the voltage value change condition and leaked the water pocket. However, the method described in the patent is implemented on the premise that the guide rail is paved on site and then fixed-point detection is performed on the guide rail, only water leakage at a designated position near the track can be detected, initial water clusters generated by water leakage in equipment cannot be detected, meanwhile, the plant area environment of a power plant is complex, the equipment is numerous, the area is wide, part of the ground is uneven, the track is difficult to directly paved, the track scheme cannot penetrate into observation points of part of the equipment, and the method belongs to a high-cost detection scheme; on the other hand, the leakage detected by the method described in the patent does not mention a method for judging the size of the leakage area of the water mass, if the leakage point of the water mass is far away from the observation point of the track, the effect of micro leakage early warning is difficult to achieve, the observation mode depends on the fixed point of the electric brush to descend, the electric brush contacts the ground to observe the voltage change of the electric brush to observe whether the water mass leaks or not, but the movement range of the electric brush is limited by the practical condition of the machine, only the leakage water mass near the track can be detected, and for the water mass exceeding the track range, the water mass cannot be detected, and only the excessive migration of the water mass effusion can be achieved, and the detection can be carried out after the effusion is formed at the detection point; the method can not directly observe the effusion which is externally displayed by the non-rail edge machine, and has the defects of lack of flexibility relative to visual detection, difficulty in realizing functions such as micro-leakage early warning and the like.
Disclosure of Invention
The invention aims at providing a water leakage detection method for a thermal power plant, which aims at detecting various characteristics of water leakage and fully ensures detection accuracy.
A further object of the present invention is a detection system employing the water leakage detection method of a thermal power plant
In order to solve the technical problems, the technical scheme of the invention is as follows:
a water leakage detection method of a thermal power plant comprises the following steps:
s1: performing water leakage detection task planning according to the field environment and the historical detection data of the thermal power plant, wherein the water leakage detection task planning comprises the planning of an observation area, stations, points and a walking path;
s2: the mobile detection equipment is planned according to the water leakage detection task and goes to a station point corresponding to the area to be detected;
s3: the mobile detection equipment acquires image data of an area to be detected and transmits the image data to a background data processing system;
s4: the data processing system processes the image data, judges whether the area to be detected leaks or not, and if the area to be detected leaks, the step S5 is carried out, and if the area to be detected leaks, the step S6 is carried out;
s5: calculating the water leakage area, comparing the water leakage area with a preset water leakage alarm value, judging the state of equipment, storing an analysis result and outputting the result;
s6: and (3) moving the detection equipment to the next station, if the current working position is not the end point, repeatedly executing the steps S2 to S5 after the movement detection equipment runs to the next station until the detection task of the last working position is completed.
In the scheme, detection task planning and detection program design are carried out according to the distribution condition of the field devices and the previous detection experience of manual inspection, and the framework of a front-end acquisition system, an information transmission system and a data processing system is adopted, so that the mobile detection equipment can realize mobile fixed-point detection of most of working sites within a certain error range under the condition of not changing the field devices. Compared with contact and indirect observation, the direct visual observation has better convenience and freedom, is convenient for observing the water leakage characteristics inside the machine display and can simultaneously judge the water leakage conditions of a plurality of working sites in real time.
Preferably, in step S1, repeated simulation drip is performed on the water leakage point positions on the site according to the historical detection data of the site environment and the detection personnel of the thermal power plant, and the water leakage point and the water accumulation point are determined according to the water flow condition, so that water leakage detection task planning is performed.
Preferably, the image data in step S3 is transmitted to the background data processing system through the wireless access point.
Preferably, the image data acquisition in step S3 is specifically:
the industrial personal computer on the mobile detection equipment opens an infrared camera on the mobile detection equipment, the infrared camera collects infrared images of an area to be detected, the infrared camera is closed, an auxiliary light source is opened at the same time, and after time delay, the industrial high-definition camera is opened to shoot high-definition images.
Preferably, the infrared camera and industrial high definition camera should be as uniform in resolution as possible and the field of view is the same.
Preferably, the water cluster is gradually cooled in a normal temperature environment and shows a low temperature characteristic in the equipment environment of the power plant, so that the preliminary water cluster characteristic screening can be effectively completed through the infrared camera, on the other hand, the water cluster has a certain reflection characteristic for the light source, the water cluster is particularly characterized in that the water accumulation edge facing to the bright light can show bright light reflection, the other edge is darkened due to the water cluster backlight, and whether the area to be detected leaks or not is judged through the special auxiliary light source group in the step S4, which is particularly that:
s4.1: after carrying out Gaussian filtering treatment on the infrared image, decomposing the infrared image into an R channel image, a G channel image and a B channel image, carrying out ponding feature extraction on the R channel image by using a first threshold value, carrying out shape screening if the ponding feature extraction is successful, carrying out ponding feature extraction on the R channel image and the G channel image according to a second threshold value if the ponding feature extraction is unsuccessful, taking intersection of extraction results obtained after carrying out ponding feature extraction on the R channel image and the G channel image according to the second threshold value, carrying out shape screening on the intersection results, wherein the screening results are infrared ponding features, if the infrared ponding feature is obtained, carrying out expansion treatment on a feature region, carrying out maximum external ellipse, calculating the ellipse center of the ellipse, comparing the long and short axis parameters with the ellipse major axis with the horizontal line according to the resolution ratio of the infrared image, carrying out transformation on the long and short axis parameters according to the same coordinates as the ellipse center of an infrared output region, and carrying out subsequent feature extraction and drawing in a subsequent region of the ellipse region; if the infrared water accumulation characteristics have no extraction result, setting an analysis area of the high-definition image as a whole high-definition image, wherein the first threshold value is smaller than the second threshold value;
the infrared image is a color infrared image, the palette tone is color, for example, in an image temperature interval, a lower temperature area is colored blue and a higher temperature area is colored red;
s4.2: setting an analysis area according to an infrared analysis result, performing top hat processing on high-definition image data in the analysis area, performing top hat processing on corrected high-definition image data, respectively extracting white edges generated by water accumulation of an auxiliary light source and dark edges opposite to the auxiliary light source, according to a preset line segment splicing threshold, if the interval between the endpoints with the nearest interval of two line segments is lower than the splicing threshold, splicing the two line segments to form a closed ring by splicing adjacent line segments, and finally screening the water accumulation by high-definition water accumulation shape, if the contour closure degree of the extracted features is larger than a preset value of the contour closure degree, determining the water accumulation feature as water leakage, otherwise, removing residual environmental interference caused by polishing and complex environment, and finally obtaining an accurate water accumulation contour.
The main idea of data processing is to use an infrared image to perform preliminary detection, convert the water leakage and accumulation characteristic region result detected by the infrared image into a region of interest of a high-definition image, so that the high-definition image only performs characteristic extraction and analysis in the region of interest, thereby avoiding environmental interference and improving the success rate of high-definition image detection.
Preferably, the shape screening is an infrared image shape feature comparison, because the low-temperature feature of the humid environment shows a scattered feature or a cluster feature with very many internal holes in the infrared image, and the water leakage and accumulation feature shows a cluster feature with no or very few internal holes, so the shape screening in step S4.1 is specifically:
presetting a hole threshold value, processing the water accumulation feature one by one, expanding the original water accumulation feature, filling the holes in the feature, differentiating the water accumulation feature after the expansion processing with the original water accumulation feature, obtaining the internal hole feature of the original feature, converting the number of the circular or elliptical features in the water accumulation feature into the number of the holes in the water accumulation feature according to one conversion, comparing the number of the holes in the water accumulation feature with the preset hole threshold value, discarding the water accumulation feature if the number of the holes in the water accumulation feature is larger than the hole threshold value, and considering the water accumulation feature as a water leakage water accumulation water mass feature if the number of the holes in the water accumulation feature is not larger than the hole threshold value.
Preferably, the adjacent line segment stitching is a complete and closed water mass outline stitched by adjacent white edges and dark edges for water mass characteristics, and the rest of the interference line segment characteristics are discrete in distribution and difficult to form a closed loop, so that the outline closing degree in step S4.2 is specifically as follows:
presetting a parameter of the profile closure degree, wherein the parameter describes the closed-loop degree of the feature, the ratio of the distance between two endpoints of a line segment to the length of the line segment is compared, the range is [0,1], namely if the line segment is a closed ring, the distance between the two endpoints of the line segment is equal to 0, the ratio of the distance between the two endpoints of the line segment and the length of the line segment is equal to 0, the feature is completely closed, and the profile closure degree is 1; if the line segment is not a closed loop, the ratio of the distance between the two end points and the length of the line segment is not equal to 0, and the larger the end point distance is, the larger the ratio is, and the closer the contour closure degree is to 0; if the line segment is a straight line, the ratio of the distance between the two end points to the length of the line segment is 1, and the contour closure degree of the line segment is 0.
The detection system for water leakage of the thermal power plant, which is applied to the detection method, specifically comprises mobile detection equipment and a data processing system, wherein:
the mobile detection equipment is used for planning to go to a working site corresponding to the region to be detected according to the water leakage detection task, collecting image data of the region to be detected, and transmitting the image data to the data processing system;
the data processing system processes the image data, judges whether the area to be detected leaks, calculates the area of the leaking water, compares the area with a preset leaking water alarm value, judges the state of equipment, and simultaneously stores the analysis result and outputs the result.
Preferably, the mobile detection device comprises a data acquisition module and a mobile power supply module, wherein:
the data acquisition module comprises an infrared camera, a high-definition industrial camera and an auxiliary light source, wherein the infrared camera is used for acquiring an infrared image of a region to be detected, the high-definition industrial camera is used for acquiring a high-definition image of the region to be detected, the auxiliary light source is used for exposing water accumulation characteristics of water leakage, a group of white LED area light sources which are identical, symmetrically arranged and inclined with a water accumulation plane are adopted as the auxiliary light source, and the area light source is selected from the group of light sources so as to ensure the illumination intensity and the sufficient illumination range; the light sources are symmetrically distributed in a group, so that the target water mass can be fully irradiated, and bright and dark edge profile break points cannot occur due to insufficient irradiation; the downward inclination of the light source relative to the water accumulation plane can enable the water mass to achieve the effect of full illumination more easily, and the contour characteristics of the bright and dark edges are enhanced;
the mobile power supply module comprises an AGV trolley and a matched charging facility thereof, the AGV trolley is provided with a cradle head capable of controlling rotation, the cradle head works according to received signals, the AGV trolley can move at fixed points and control the data acquisition module through the control cradle head, and data transmitted by the received data acquisition module are packed and fed back to the data processing system.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the invention adopts binocular vision detection technology, does not need contact detection, is simpler and more convenient than contact detection, has wider detection range, and because the invention adopts a method of transmitting data to a data processing system to process the data to replace the complicated detection step of contact detection, the time consumption of single inspection is relatively less; the method is designed for the detection of the water accumulation clusters, the special reflection characteristics and the low-temperature characteristics of the water accumulation clusters are fully exposed, the multi-mode data combined analysis technology is adopted, the infrared analysis result is used as a reference for high-definition data analysis, the efficiency and the reliability of the high-definition data analysis are fully improved, and the effect of accurately screening the water accumulation characteristics is achieved.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
Fig. 2 is a schematic diagram of a system structure according to the present invention.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
for the purpose of better illustrating the embodiments, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the actual product dimensions;
it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples.
Example 1
The embodiment provides a water leakage detection method of a thermal power plant, as shown in fig. 1, comprising the following steps:
s1: performing water leakage detection task planning according to the field environment and the historical detection data of the thermal power plant, wherein the water leakage detection task planning comprises the planning of an observation area, stations, points and a walking path;
s2: the mobile detection equipment is planned according to the water leakage detection task and goes to a station point corresponding to the area to be detected;
s3: the mobile detection equipment acquires image data of an area to be detected and transmits the image data to a background data processing system;
s4: the data processing system processes the image data, judges whether the area to be detected leaks or not, and if the area to be detected leaks, the step S5 is carried out, and if the area to be detected leaks, the step S6 is carried out;
s5: calculating the water leakage area, comparing the water leakage area with a preset water leakage alarm value, judging the state of equipment, storing an analysis result and outputting the result;
s6: and (3) moving the detection equipment to the next station, if the current working position is not the end point, repeatedly executing the steps S2 to S5 after the movement detection equipment runs to the next station until the detection task of the last working position is completed.
In the step S1, repeated simulation drip is carried out on water leakage points on the scene according to historical detection data of the scene environment and detection personnel of the thermal power plant, and the water leakage points and the water accumulation points are determined according to water flow conditions, so that water leakage detection task planning is carried out.
In step S3, the image data is transmitted to the background data processing system through the wireless access point.
The image data acquisition in step S3 specifically includes:
the industrial personal computer on the mobile detection equipment opens an infrared camera on the mobile detection equipment, the infrared camera collects infrared images of an area to be detected, the infrared camera is closed, an auxiliary light source is opened at the same time, and after time delay, the industrial high-definition camera is opened to shoot high-definition images.
The infrared camera and the industrial high-definition camera are consistent in lens center position when collecting images.
Step S4, judging whether the area to be detected leaks or not, specifically:
s4.1: after carrying out Gaussian filtering treatment on the infrared image, decomposing the infrared image into an R channel image, a G channel image and a B channel image, carrying out ponding feature extraction on the R channel image by using a first threshold value, carrying out shape screening if the ponding feature extraction is successful, carrying out ponding feature extraction on the R channel image and the G channel image according to a second threshold value if the ponding feature extraction is unsuccessful, taking intersection of extraction results obtained after carrying out ponding feature extraction on the R channel image and the G channel image according to the second threshold value, carrying out shape screening on the intersection results, wherein the screening results are infrared ponding features, if the infrared ponding feature is obtained, carrying out expansion treatment on a feature region, carrying out maximum external ellipse, calculating the ellipse center of the ellipse, comparing the long and short axis parameters with the ellipse major axis with the horizontal line according to the resolution ratio of the infrared image, carrying out transformation on the long and short axis parameters according to the same coordinates as the ellipse center of an infrared output region, and carrying out subsequent feature extraction and drawing in a subsequent region of the ellipse region; if the infrared water accumulation characteristics have no extraction result, setting an analysis area of the high-definition image as a whole high-definition image, wherein the first threshold value is smaller than the second threshold value;
s4.2: setting an analysis area according to an infrared analysis result, carrying out top hat processing on high-definition image data in the analysis area, respectively extracting a white edge generated by water accumulation of an auxiliary light source and a dark edge opposite to the auxiliary light source, carrying out line segment splicing on two line segments according to a preset line segment splicing threshold value if the interval between the end points with the nearest interval between the two line segments is lower than the splicing threshold value, splicing the adjacent line segments into one line segment, enabling the water accumulation to form a closed ring, and finally screening by the high-definition water accumulation shape, wherein if the contour closure degree of the extracted characteristic is larger than a preset value of the contour closure degree, the extracted characteristic is the water accumulation characteristic, otherwise, removing residual environmental interference caused by polishing and complex environment, and finally obtaining an accurate water accumulation contour.
The shape screening in step S4.1 is specifically:
presetting a hole threshold value, processing the water accumulation feature one by one, expanding the original water accumulation feature, filling the holes in the feature, differentiating the water accumulation feature after the expansion processing with the original water accumulation feature, obtaining the internal hole feature of the original feature, converting the number of the circular or elliptical features in the water accumulation feature into the number of the holes in the water accumulation feature according to one conversion, comparing the number of the holes in the water accumulation feature with the preset hole threshold value, discarding the water accumulation feature if the number of the holes in the water accumulation feature is larger than the hole threshold value, and considering the water accumulation feature as a water leakage water accumulation water mass feature if the number of the holes in the water accumulation feature is not larger than the hole threshold value.
The profile closure degree in step S4.2 is specifically:
presetting a parameter of the profile closure degree, wherein the parameter describes the closed-loop degree of the feature, the ratio of the distance between two endpoints of a line segment to the length of the line segment is compared, the range is [0,1], namely if the line segment is a closed ring, the distance between the two endpoints of the line segment is equal to 0, the ratio of the distance between the two endpoints of the line segment and the length of the line segment is equal to 0, the feature is completely closed, and the profile closure degree is 1; if the line segment is not a closed loop, the ratio of the distance between the two end points and the length of the line segment is not equal to 0, and the larger the end point distance is, the larger the ratio is, and the closer the contour closure degree is to 0; if the line segment is a straight line, the ratio of the distance between the two end points to the length of the line segment is 1, and the contour closure degree of the line segment is 0.
Example 2
The embodiment provides a water leakage detection system of a thermal power plant, as shown in fig. 2, where the detection system applies the detection method described in embodiment 1, and specifically includes a mobile detection device and a data processing system, where:
the mobile detection equipment is used for planning to go to a working site corresponding to the region to be detected according to the water leakage detection task, collecting image data of the region to be detected, and transmitting the image data to the data processing system;
the data processing system processes the image data, judges whether the area to be detected leaks, calculates the area of the leaking water, compares the area with a preset leaking water alarm value, judges the state of equipment, and simultaneously stores the analysis result and outputs the result.
The mobile detection equipment comprises a data acquisition module and a mobile power supply module, wherein:
the data acquisition module comprises an infrared camera, a high-definition industrial camera and an auxiliary light source, wherein the infrared camera is used for acquiring an infrared image of a region to be detected, the high-definition industrial camera is used for acquiring a high-definition image of the region to be detected, the auxiliary light source is used for exposing water accumulation characteristics of water leakage, and the auxiliary light source is a group of white LED area light sources which are identical and symmetrically arranged and inclined with the water accumulation plane;
the mobile power supply module comprises an AGV trolley and a matched charging facility thereof, the AGV trolley is provided with a cradle head capable of controlling rotation, the cradle head works according to received signals, the AGV trolley can move at fixed points and control the data acquisition module through the control cradle head, and data transmitted by the received data acquisition module are packed and fed back to the data processing system.
The same or similar reference numerals correspond to the same or similar components;
the terms describing the positional relationship in the drawings are merely illustrative, and are not to be construed as limiting the present patent;
it is to be understood that the above examples of the present invention are provided by way of illustration only and not by way of limitation of the embodiments of the present invention. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (7)
1. The water leakage detection method of the thermal power plant is characterized by comprising the following steps of:
s1: performing water leakage detection task planning according to the field environment and the historical detection data of the thermal power plant, wherein the water leakage detection task planning comprises the planning of an observation area, stations, points and a walking path;
s2: the mobile detection equipment is planned according to the water leakage detection task and goes to a station point corresponding to the area to be detected;
s3: the mobile detection equipment acquires image data of an area to be detected and transmits the image data to a background data processing system;
s4: the data processing system processes the image data, judges whether the area to be detected leaks or not, and if the area to be detected leaks, the step S5 is carried out, and if the area to be detected leaks, the step S6 is carried out;
s5: calculating the area of water leakage, comparing the area with a preset alarm threshold value, judging the state of equipment, storing an analysis result and outputting the analysis result;
s6: moving the detection equipment to a next station, if the current working site is not the end point, repeatedly executing the steps S2 to S5 after the movement detection equipment runs to the next station until the detection task of the last working site is completed;
step S4, judging whether the area to be detected leaks or not, specifically:
s4.1: after Gaussian filtering processing is carried out on an infrared image, the infrared image is decomposed into an R channel image, a G channel image and a B channel image, ponding feature extraction is carried out on the R channel image by a first threshold value, if the ponding feature extraction is successful, shape screening is carried out, if the ponding feature extraction is unsuccessful, ponding feature extraction is carried out on the R channel image and the G channel image according to a second threshold value, the extraction results obtained after ponding feature extraction is carried out on the R channel image and the G channel image according to the second threshold value are intersected, shape screening is carried out on the intersection results, the screening results are the infrared ponding feature, if the infrared ponding feature is obtained, expansion processing is carried out on the area where the infrared ponding feature is located, the area after expansion processing is taken as the largest external ellipse, the ellipse center of the ellipse is calculated, the long and short axis parameters and the included angle between the ellipse long axis and the horizontal line are transformed according to the resolution ratio of the infrared image and the high definition image, the same coordinates as the ellipse center of the infrared output area are obtained, the long and the short axis corresponding to the high definition image size of the ellipse is the high definition image is the parameters, and the subsequent analysis is carried out on the ellipse area; if the infrared water accumulation characteristics have no extraction result, setting an analysis area of the high-definition image as a whole high-definition image, wherein the first threshold value is smaller than the second threshold value;
s4.2: firstly, carrying out Gaussian filtering on a high-definition image, setting an analysis area according to an infrared analysis result, carrying out top hat processing on high-definition image data in the analysis area, respectively extracting a white edge generated by a water accumulation cluster facing an auxiliary light source and a dark edge facing away from the auxiliary light source, carrying out line segment splicing on two line segments according to a preset line segment splicing threshold value if the interval between the end points with the nearest interval between the two line segments is lower than the splicing threshold value, splicing the two line segments to form a closed circular ring by the adjacent line segments, finally, screening the water accumulation cluster by the shape of the high-definition water accumulation, and otherwise, regarding the water accumulation cluster as the water accumulation cluster leakage characteristic due to the fact that the contour closure degree of the extracted characteristic is larger than the preset value of the contour closure degree, otherwise, removing residual environmental interference caused by lighting and complex environment, and finally obtaining the accurate water cluster contour.
2. The water leakage detection method of a thermal power plant according to claim 1, wherein the image data in step S3 is transmitted to a background data processing system through a wireless access point.
3. The water leakage detection method of a thermal power plant according to claim 1, wherein the image data acquisition in step S3 specifically includes:
the industrial personal computer on the mobile detection equipment opens an infrared camera on the mobile detection equipment, the infrared camera collects infrared images of an area to be detected, the infrared camera is closed, an auxiliary light source is opened at the same time, and after time delay, the industrial high-definition camera is opened to shoot high-definition images.
4. The water leakage detection method of a thermal power plant according to claim 1, wherein the shape screening in step S4.1 specifically comprises:
presetting a hole threshold value, processing the water accumulation feature one by one, expanding the original water accumulation feature, filling the holes in the feature, differentiating the water accumulation feature after the expansion processing with the original water accumulation feature, obtaining the internal hole feature of the original feature, converting the number of the circular or elliptical features in the water accumulation feature into the number of the holes in the water accumulation feature according to one conversion, comparing the number of the holes in the water accumulation feature with the preset hole threshold value, discarding the water accumulation feature if the number of the holes in the water accumulation feature is larger than the hole threshold value, and considering the water accumulation feature as a water leakage water accumulation feature if the number of the holes in the water accumulation feature is not larger than the hole threshold value.
5. The water leakage detection method of a thermal power plant according to claim 4, wherein the profile closure degree in step S4.2 is specifically:
presetting a parameter of the profile closure degree, wherein the parameter describes the closed-loop degree of the feature, the ratio of the distance between two endpoints of a line segment to the length of the line segment is compared, the range is [0,1], namely if the line segment is a closed ring, the distance between the two endpoints of the line segment is equal to 0, the ratio of the distance between the two endpoints of the line segment and the length of the line segment is equal to 0, the feature is completely closed, and the profile closure degree is 1; if the line segment is not a closed loop, the ratio of the distance between the two end points and the length of the line segment is not equal to 0, and the larger the end point distance is, the larger the ratio is, and the closer the contour closure degree is to 0; if the line segment is a straight line, the ratio of the distance between the two end points to the length of the line segment is 1, and the contour closure degree of the line segment is 0.
6. A water leakage detection system of a thermal power plant, characterized in that the detection system employs the detection method of any one of claims 1 to 5, specifically comprising a mobile detection device and a data processing system, wherein:
the mobile detection equipment is used for planning to go to a working site corresponding to the region to be detected according to the water leakage detection task, collecting image data of the region to be detected, and transmitting the image data to the data processing system;
the data processing system processes the image data, judges whether the area to be detected leaks, calculates the area of the leaking water, compares the area with a preset leaking water alarm value, judges the state of equipment, and outputs the result while storing the analysis result.
7. The water leakage detection system of a thermal power plant of claim 6, wherein the mobile detection device comprises a data acquisition module and a mobile power supply module, wherein:
the data acquisition module comprises an infrared camera, a high-definition industrial camera and an auxiliary light source, wherein the infrared camera is used for acquiring an infrared image of a region to be detected, the high-definition industrial camera is used for acquiring a high-definition image of the region to be detected, the auxiliary light source is used for exposing water accumulation characteristics of water leakage, and the auxiliary light source comprises a group of white LED area light sources which are identical and symmetrically arranged and inclined with the water accumulation plane;
the mobile power supply module comprises an AGV trolley and a matched charging facility thereof, the AGV trolley is provided with a cradle head capable of controlling rotation, the cradle head works according to received signals, the AGV trolley can move at fixed points and control the data acquisition module through the control cradle head, and data transmitted by the received data acquisition module are packed and fed back to the data processing system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010410743.1A CN111754455B (en) | 2020-05-15 | 2020-05-15 | Water leakage detection method and system for thermal power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010410743.1A CN111754455B (en) | 2020-05-15 | 2020-05-15 | Water leakage detection method and system for thermal power plant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111754455A CN111754455A (en) | 2020-10-09 |
| CN111754455B true CN111754455B (en) | 2024-03-19 |
Family
ID=72673986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010410743.1A Active CN111754455B (en) | 2020-05-15 | 2020-05-15 | Water leakage detection method and system for thermal power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111754455B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113341993A (en) * | 2021-06-21 | 2021-09-03 | 杭州越歌科技有限公司 | Automatic navigation method and system of pipeline detection robot, storage medium and robot |
| CN114274143A (en) * | 2021-12-28 | 2022-04-05 | 华能汕头海门发电有限责任公司 | Intelligent identification method for centralized control operation defect image of intelligent robot group in thermal power plant |
| CN114842629A (en) * | 2022-05-18 | 2022-08-02 | 国家电投集团东方新能源股份有限公司热力分公司 | Water immersion alarm method, device and system for heating station |
| CN116071656B (en) * | 2023-03-06 | 2023-06-06 | 河北工业大学 | Intelligent alarm method and system for infrared image ponding detection of underground transformer substation |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101673345A (en) * | 2009-07-01 | 2010-03-17 | 北京交通大学 | Method for extracting target closed contour based on shape prior |
| GB201711412D0 (en) * | 2016-12-30 | 2017-08-30 | Maxu Tech Inc | Early entry |
| CN107730539A (en) * | 2017-11-09 | 2018-02-23 | 江苏科技大学 | Autonomous underwater robot control system and sonar target tracking |
| CN110490847A (en) * | 2019-07-31 | 2019-11-22 | 浙江大学山东工业技术研究院 | The LED chip quality determining method of view-based access control model |
| CN110908370A (en) * | 2019-10-31 | 2020-03-24 | 华能国际电力股份有限公司海门电厂 | Unmanned inspection task planning method and system for thermal power plant |
-
2020
- 2020-05-15 CN CN202010410743.1A patent/CN111754455B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101673345A (en) * | 2009-07-01 | 2010-03-17 | 北京交通大学 | Method for extracting target closed contour based on shape prior |
| GB201711412D0 (en) * | 2016-12-30 | 2017-08-30 | Maxu Tech Inc | Early entry |
| CN107730539A (en) * | 2017-11-09 | 2018-02-23 | 江苏科技大学 | Autonomous underwater robot control system and sonar target tracking |
| CN110490847A (en) * | 2019-07-31 | 2019-11-22 | 浙江大学山东工业技术研究院 | The LED chip quality determining method of view-based access control model |
| CN110908370A (en) * | 2019-10-31 | 2020-03-24 | 华能国际电力股份有限公司海门电厂 | Unmanned inspection task planning method and system for thermal power plant |
Non-Patent Citations (1)
| Title |
|---|
| 武华.《基于视频图像分析的风电机组故障自动识别技术研究》.《中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑）》.2017,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111754455A (en) | 2020-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111754455B (en) | Water leakage detection method and system for thermal power plant | |
| CN110850723B (en) | Fault diagnosis and positioning method based on transformer substation inspection robot system | |
| KR20170025781A (en) | Apparatus and method for diagnosing electric power equipment using infrared thermal imaging camera | |
| CN103411530B (en) | Large free forging part size on-line measurement device and method | |
| CN110930415B (en) | Method for detecting spatial position of track contact net | |
| CN104749187A (en) | Tunnel lining disease detection device based on infrared temperature field and gray level image | |
| CN108593654A (en) | Tunnel image capturing system and method | |
| CN105158257A (en) | Sliding plate measurement method and device | |
| CN108225798B (en) | Tire slippage testing system and method based on edge enhancement identification | |
| CN204924983U (en) | Lens defect automatic checkout device of grating modulation | |
| CN206057201U (en) | A kind of rail clip spring crack detecting device of view-based access control model sensing | |
| US11494888B2 (en) | Work terminal, oil leakage detection apparatus, and oil leakage detection method | |
| CN209542486U (en) | Circuit board solder joint Defect Detection system based on coded structured light vision | |
| CN108566538A (en) | Based on the circular coal yard personnel safety guard of Infrared-Visible fusion tracking and the monitoring system and method for spontaneous combustion | |
| CN114113118B (en) | Rapid detection device and detection method for subway tunnel lining crack leakage water disease | |
| CN111561967A (en) | Real-time online detection method and system for pantograph-catenary operation state | |
| CN109115434A (en) | A kind of tunnel health monitoring systems and method | |
| CN108956613A (en) | Glass tin defects vision identification system | |
| CN108418550A (en) | The defects detection and localization method of cluster solar panels | |
| CN111208146A (en) | Tunnel cable detection system and detection method | |
| CN110030988A (en) | A kind of multi-beacon high-speed synchronous recognition methods for high dynamic pose measurement | |
| CN103091332B (en) | Detection method and detection system of U-shaped powder pipe based on machine vision | |
| CN208568616U (en) | Glass tin defects vision identification system | |
| CN106767497A (en) | A kind of white light interference contourgraph spacescan scope Adaptive Planning method | |
| CN115083209B (en) | Vehicle-road cooperation method and system based on visual positioning |
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 |