CN116843682B - Boiler thermal efficiency on-line detection and analysis system using thermal infrared imager - Google Patents
Boiler thermal efficiency on-line detection and analysis system using thermal infrared imager Download PDFInfo
- Publication number
- CN116843682B CN116843682B CN202311099656.9A CN202311099656A CN116843682B CN 116843682 B CN116843682 B CN 116843682B CN 202311099656 A CN202311099656 A CN 202311099656A CN 116843682 B CN116843682 B CN 116843682B
- Authority
- CN
- China
- Prior art keywords
- point
- growth
- grown
- area
- boiler
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 19
- 238000001514 detection method Methods 0.000 title claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 26
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 11
- 230000011218 segmentation Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 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
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0044—Furnaces, ovens, kilns
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/002—Thermal testing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/008—Subject matter not provided for in other groups of this subclass by doing functionality tests
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/20—Investigating or analyzing materials by the use of thermal means by investigating the development of heat, i.e. calorimetry, e.g. by measuring specific heat, by measuring thermal conductivity
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a boiler thermal efficiency on-line detection and analysis system utilizing a thermal infrared imager, which comprises the following components: acquiring a boiler region in a boiler gray level image; obtaining a variable range and a threshold range of the point to be grown according to the gray value of the initial seed point and the gray difference between the point to be grown and the growing point, and obtaining an initial growing area according to the threshold range of the point to be grown; calculating the overall gray value level and the overall gray value level threshold of the growth area after the growth point to be grown is added into the growth area; obtaining all growth areas; processing the residual pixel points in the boiler region to obtain a final growth region; and screening the final growth area to obtain a segmented normal boiler area, and calculating the heat efficiency of the boiler by obtaining the whole temperature through the local temperature according to the segmented normal boiler area. The invention avoids the false growth of abnormal areas, thereby achieving the purposes of more accurate growth results and obtaining accurate boiler temperature and boiler thermal efficiency.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a boiler thermal efficiency on-line detection and analysis system utilizing a thermal infrared imager.
Background
In the working process of the industrial boiler, the thermal efficiency is usually detected and analyzed by forming an infrared image through an infrared thermal imager, and the thermal efficiency is calculated according to the temperature of the boiler surface obtained by the thermal imager. In actual production and life, because factors such as furnace dust appear on the surface of the boiler, the shape of the boiler is uneven, and the like, color development deviation of the infrared image can greatly influence judgment of the thermal efficiency of the boiler, the infrared image is required to be segmented through region growth, and the infrared image which can normally display the temperature region on the surface of the boiler is selected to acquire the temperature of the boiler.
The traditional region growing algorithm judges whether to grow according to a single gray threshold value in the growing process, and as the whole brightness of the infrared image is higher and the contrast is lower, the segmentation region is incomplete easily caused by too high gray threshold value selection, the defect region with gentle change is easily classified into a normal region due to too low threshold value selection, namely, a good segmentation effect is difficult to achieve by the single determination threshold value.
Disclosure of Invention
In order to solve the above problems, the present invention provides a boiler thermal efficiency on-line detection and analysis system using a thermal infrared imager, the system comprising:
the image acquisition module acquires a boiler region in the boiler gray level image;
the growth area acquisition module is used for acquiring initial seed points according to the boiler area; obtaining a growing area according to the initial seed points, and obtaining points to be grown according to the growing points in the growing area; obtaining a variable range of the point to be grown according to the gray value of the initial seed point and the gray difference between the point to be grown and the growing point, obtaining a threshold range of the point to be grown according to the variable range of the point to be grown, and obtaining an initial growing area according to the threshold range of the point to be grown; calculating the overall gray value level and the overall gray value level threshold of the growth area after the growth point to be grown is added into the growth area; obtaining all growth areas according to the overall gray value level and the overall gray value level threshold value of the growth areas after the points to be grown are added into the growth areas; processing the residual pixel points in the boiler region to obtain a final growth region;
the boiler thermal efficiency analysis module is used for screening the final growth area to obtain a segmented normal boiler area, and acquiring the overall temperature through the local temperature according to the segmented normal boiler area to calculate the boiler thermal efficiency;
the variable range of the point to be grown is obtained according to the gray value of the initial seed point and the gray difference between the point to be grown and the growing point, and the method comprises the following specific steps:
wherein R represents the variable range of the point to be grown,gray value representing initial seed point, +.>Representing the absolute value of the difference between the gray values of the points to be grown and the growing point,/and the gray value of the growing point>Representing an arctangent function.
Further, the initial seed point obtaining comprises the following specific steps:
and arbitrarily selecting a pixel point with the maximum gray value from the boiler area as an initial seed point.
Further, the growing area is obtained according to the initial seed point, the point to be grown is obtained according to the growing point in the growing area, and the method comprises the following specific steps:
in the initial process, the region formed by the initial seed points is recorded as a growth region, and the pixel points in the growth region are recorded as growth points; and regarding any growth point in the growth area, taking any pixel point which is positioned in 8 adjacent to the growth point and does not belong to the growth area as a point to be grown.
Further, the method for obtaining the threshold range of the point to be grown according to the variable range of the point to be grown and obtaining the initial growth area according to the threshold range of the point to be grown comprises the following specific steps:
obtaining the threshold range of the point to be grown according to the variable range of the point to be grown as，/>The gray value of the initial seed point is represented, and R represents the variable range of the point to be grown;
judging whether the point to be grown is added into the growing area as a growing point according to the gray value of the point to be grown and the threshold range of the point to be grown: if the gray value of the point to be grown is within the threshold range of the point to be grown, the point to be grown is added into the growing area as the growing point, otherwise, the point to be grown cannot be added into the growing area as the growing point; and similarly, judging whether the next point to be grown is added into the growth area as a growth point according to the gray value of the next point to be grown and the changeable range of the point to be grown until all the points to be grown in the growth area cannot be added into the growth area as growth points, and taking the growth area obtained at the moment as an initial growth area.
Further, the calculating the overall gray value level of the growth area after the growth point is added into the growth area comprises the following specific steps:
in the method, in the process of the invention,the overall gray value level of the growth area after adding the growth area to the point to be grown,/for the growth area>The whole gray value level of the growth area before the growth area is added to the point to be grown, h represents the gray value of the point to be grown,/->Indicating the number of growth points in the growth area before the point to be grown is added to the growth area.
Further, the method for obtaining the overall gray value level threshold specifically includes the following steps:
taking the average value of the gray values of all the pixel points of the initial growth area as the whole gray value level of the initial growth area, and taking the whole gray value level of the initial growth area as the whole gray value level threshold.
Further, the method for obtaining all the growth areas comprises the following specific steps:
selecting a pixel point with the maximum gray value as a seed point in other areas except the initial growth area in the boiler area; in the initial stage, only one seed point exists, the region formed by the seed points is recorded as a growth region, and the pixel points in the growth region are recorded as growth points;
for any growth point in the growth area, taking any pixel point which is positioned in 8 adjacent to the growth point and does not belong to the growth area as a point to be grown; obtaining a variable range of the point to be grown according to the gray difference between the point to be grown and the growth point, and obtaining a threshold range of the point to be grown according to the variable range of the point to be grown; calculating the integral gray value level of the growth area after the point to be grown is added into the growth area;
judging whether the point to be grown is added into the growing area as the growing point according to the integral gray value level, the integral gray value level threshold value, the gray value of the point to be grown and the threshold range of the point to be grown of the growing area after the point to be grown is added into the growing area: if the gray value of the point to be grown is within the threshold range of the point to be grown, and the overall gray value level of the growth area after the point to be grown is added into the growth area is greater than or equal to the overall gray value level threshold, the point to be grown is added into the growth area as the growth point, otherwise, the point to be grown cannot be added into the growth area as the growth point; similarly, judging whether the next point to be grown is added into the growth area as a growth point according to the gray value of the next point to be grown and the changeable range of the point to be grown until all the points to be grown in the growth area cannot be added into the growth area as growth points, and taking the growth area obtained at the moment as a new growth area;
and so on, all growth areas in the boiler area are obtained.
Further, the processing of the remaining pixel points in the boiler region to obtain a final growth region includes the following specific steps:
and marking any pixel point which does not belong to any growth area and is surrounded by the growth area in the boiler area as a target pixel point, and processing the target pixel point: calculating standard deviation of gray values of all pixels in 8 neighborhoods of the target pixel and the target pixel, and marking the standard deviation as a neighborhood difference level of the target pixel; if the neighborhood difference level of the target pixel point is larger than a preset threshold K, the target pixel point is a noise point, the gray value of the noise point is corrected to be the average value of the gray values of all the pixel points in the 8 neighborhood of the noise point, and the corrected noise point is used as a growth point to be added into a growth area;
and similarly, all pixel points which do not belong to any growth area in the boiler area and are surrounded by the growth area are processed, and the growth area obtained after the processing is taken as a final growth area.
Further, the screening of the final growth area to obtain the segmented normal boiler area comprises the following specific steps:
and screening the obtained final growth area, and taking the final growth area with the number of the pixel points being larger than a preset number threshold S as a segmented normal boiler area.
The technical scheme of the invention has the beneficial effects that: aiming at the problems that when the boiler infrared image is segmented through region growth and a region capable of normally displaying the surface temperature of the boiler is selected, the whole brightness of the boiler infrared image is higher and the contrast is lower, and a single determined threshold value is difficult to obtain a good segmentation effect; in order to ensure that the overall gray level in a growth area is higher, a pixel point corresponding to the maximum gray value is used as a seed point for area growth, the gray difference between a point to be grown and the growth point is analyzed to obtain the variable range of the point to be grown, the gray value of an initial seed point is combined to adaptively obtain the threshold range of the point to be grown, and then whether the point to be grown is used as the growth point to be added into the growth area is judged, so that the initial growth area is obtained; in addition to considering whether the gray value of the point to be grown is within the threshold range of the point to be grown, the whole gray value level of the growth area after the point to be grown is added as the growth point is compared with the whole gray value level of the growth area before the point to be grown is added as the growth point to be grown.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a system for on-line detection and analysis of thermal efficiency of a boiler using a thermal infrared imager in accordance with the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of the specific implementation, structure, characteristics and effects of the boiler thermal efficiency on-line detection and analysis system using the thermal infrared imager according to the invention with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the boiler thermal efficiency on-line detection and analysis system using a thermal infrared imager provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a system for on-line detection and analysis of thermal efficiency of a boiler using a thermal infrared imager according to an embodiment of the present invention is shown, the system includes the following modules:
an image acquisition module 101 is used for acquiring a boiler gray image and a boiler region.
It should be noted that, in this embodiment, the processing is performed based on image processing, and since the infrared image reflects the temperature condition mainly through brightness, the infrared image can be converted into a gray scale image, so that the storage space is saved, and meanwhile, the difficulty in operating the image is reduced. The semantic segmentation only keeps the boiler part, so that the interference of the environment area on the subsequent image segmentation process can be eliminated.
Specifically, an infrared camera arranged in a boiler room is used for collecting an infrared image of a boiler, and the infrared image of the boiler is subjected to gray-scale treatment to obtain a gray-scale image of the boiler; and carrying out semantic segmentation on the boiler gray level image to obtain a boiler region and a background region.
Thus, a boiler gray scale image and a boiler region are obtained.
A growth region acquisition module 102, configured to obtain an initial seed point according to the gray level image of the boiler region; obtaining a variable range of the point to be grown according to the gray value of the initial seed point and the gray difference between the point to be grown and the growing point, obtaining a threshold range of the point to be grown according to the variable range of the point to be grown, and obtaining an initial growing area according to the threshold range of the point to be grown; obtaining all growth areas according to the overall gray value level and the overall gray value level threshold value of the growth areas after the growth points to be grown are added into the growth areas; and processing the residual pixel points in the boiler region to obtain a final growth region.
It should be noted that, selecting a single gray threshold to perform region growth on the boiler image may affect the segmentation result due to different features of different regions of the boiler image: too small threshold selection can make the image belonging to the normal region unable to be segmented, while too large selection can lead to dividing the defect region into normal regions in some excessively gentle regions, so that the gray threshold needs to be adaptively set for different regions, thereby achieving better segmentation effect. Selecting the maximum gray value as a seed point according to the gray image of the boiler region; quantifying a floatable range of gray values according to the gray difference of the points to be grown, and acquiring a gray minimum threshold of the points to be grown based on the floatable range of the gray values of the seed points in the region; and comparing whether the point to be grown grows according to the gray threshold value, and growing accordingly until no point can continue growing.
1. And obtaining initial seed points according to the gray level image of the boiler region.
In the existing boiler gray level image, there is a region partly covered by the boiler ash or the boiler wall is thick, and the blocked region causes the influence of the color development of the thermal imager to lower the gray level value of the boiler gray level image, and the outer side of the thick boiler wall causes lower temperature due to heat dissipation. According to the imaging principle of the thermal infrared imager, the brightness of the pixel point is in direct proportion to the temperature, the brightness of the corresponding position of the position with higher temperature in the infrared image of the boiler is higher, and the gray value of the gray image of the boiler is also higher. The pixel points corresponding to the high-temperature points in the boiler gray level image are used as seed points, so that the seed points can be ensured to be in a normal color development area which is not affected on the surface of the boiler. If the gray value of the noise point located in the affected larger area is the largest and is selected as the seed point, a larger area cannot be grown due to the overlarge difference between the gray value and the surrounding gray values in the subsequent growth process, and the area is deleted in the screening process, so that the existence of the noise point cannot influence the area growth result in the embodiment.
It should be further noted that, the seed point is selected as the pixel point corresponding to the maximum gray value, so as to ensure that the overall gray level in the growth area is higher, the gray level of the point to be grown and the seed point should be relatively close, and the condition can be satisfied by performing area growth according to the pixel point corresponding to the maximum gray value in the boiler gray image as the seed point.
Specifically, arbitrarily selecting a pixel point with the maximum gray value in a boiler area as an initial seed point; at the beginning, only one initial seed point exists, at this time, the region composed of the initial seed points is recorded as a growth region, and the pixel points in the growth region are recorded as growth points.
2. Obtaining a variable range of the point to be grown according to the gray value of the initial seed point and the gray difference between the point to be grown and the growing point, obtaining a threshold range of the point to be grown according to the variable range of the point to be grown, and obtaining an initial growing area according to the threshold range of the point to be grown.
It should be noted that, the basic region growth performs the region growth only according to the similarity of the gray values and the single determination of the gray threshold value, and the single threshold value selection directly determines the final effect of the region growth. Therefore, the selection of the threshold becomes particularly important, and when the threshold is too large, some pixels which do not belong to the normal region in the gray image of the boiler are erroneously segmented, and when the threshold is too small, the segmentation result is smaller than that of the actual normal region, and the segmentation is incomplete. In addition, because the characteristics of different areas in the boiler gray image are different, a single threshold value may produce different results in different areas of the boiler gray image, and some areas are higher to divide the wrong area, while other areas are not completely divided.
It should be further noted that, in general region growing, only the gray scale difference between the pixels around the region and the adjacent pixels in the region is considered, and the gray scale value between the normal region and the abnormal region in the boiler gray scale image is excessive and tends to be relatively gentle, so that the false growth of the pixels may occur. In order to prevent the false growth, the difference between the point to be grown and the highest gray value in the region is considered, and when the gray difference between the point to be grown and the growth point in the growth region is small but the gray difference between the point to be grown and the seed point is large, the point to be grown is not grown. The gray scale variation of the normal region should be smooth, and the gray scale difference between the points to be grown and the growing points should be small. The gray level difference consideration is integrated, the point to be grown with small gray level difference has higher target degree, and the pixel point has higher changeable rate.
Specifically, for any one growth point in the growth area, taking any pixel point which is positioned in the 8 adjacent to the growth point and does not belong to the growth area as a point to be grown; the variable range of the point to be grown is obtained according to the gray level difference between the point to be grown and the growth point, and the specific calculation formula is as follows:
wherein R represents the variable range of the point to be grown,gray value representing initial seed point, +.>Representing the absolute value of the difference between the gray values of the points to be grown and the growing point,/and the gray value of the growing point>Representing an arctangent function.
And the variable range R of the point to be grown is obtained by multiplying the gray value of the seed point by the variable rate, and the variable range R is used for calculating whether the gray value of the point to be grown meets the growth condition. The larger the gray difference between the growing point and the growing point is, the smaller the changeable rate of the gray of the growing point and the seed point is, and when the gray difference reaches a specific value, the changeable rate tends to 0. The functional relationship is expressed as an arctangent function, and the result is divided by +.>A variable rate of 0-1 can be obtained; multiplying the variable rate by the gray value of the seed point to obtain the variable range of the point to be grown.
Advancing oneObtaining a threshold range of the point to be grown according to the variable range of the point to be grown, wherein the threshold range is，The gray value of the initial seed point is represented, and R represents the variable range of the point to be grown; judging whether the point to be grown is added into the growing area as a growing point according to the gray value of the point to be grown and the threshold range of the point to be grown: if the gray value of the point to be grown is within the threshold range of the point to be grown, the point to be grown is added into the growing area as the growing point, otherwise, the point to be grown cannot be added into the growing area as the growing point; and similarly, judging whether the next point to be grown is added into the growth area as a growth point according to the gray value of the next point to be grown and the changeable range of the point to be grown until all the points to be grown in the growth area cannot be added into the growth area as growth points, and taking the growth area obtained at the moment as an initial growth area.
3. And obtaining all the growing areas according to the integral gray value level and integral gray value level threshold of the growing areas after the growing points are added into the growing areas.
It should be noted that, in the region growing process, there may be a pixel point in which erroneous judgment may exist in the growing region due to insufficient gray values of the existing seed points, so it is determined whether a point to be grown is added to the growing region as a growing point, and in addition to considering whether the gray value of the point to be grown is within the threshold range of the point to be grown, it is also necessary to compare and determine the overall gray value level of the growing region after the point to be grown is added to the growing region as the growing point with the overall gray value level of the growing region before the point to be grown is added to the growing region as the growing point.
It should be further noted that, taking the average value of the gray values of all the growing points in the growing area as the overall gray value level of the growing area, and judging whether the growing point is added into the growing area as the growing point according to the influence of the growing point to be added into the growing area as the growing point. The first obtained growth area, namely the initial growth area, is obtained by taking the pixel point with the highest gray value in the boiler gray image as a seed point, and compared with other growth areas obtained later, the reliability of the initial growth area is highest, so that the whole gray value level of the initial growth area is taken as a threshold value of the whole gray value level, and when the threshold value of the whole gray value level is used for judging other growth areas obtained later, the effect on the whole gray value level of the growth area after the point to be grown is taken as the growth point to be added into the growth area is determined.
Specifically, the average value of the gray values of all the pixel points in the initial growth region is used as the overall gray value level of the initial growth region, and the overall gray value level of the initial growth region is used as the overall gray value level threshold.
Further, arbitrarily selecting a pixel point with the maximum gray value from other areas except the initial growth area in the boiler area as a seed point; at the beginning, only one seed point exists, at the moment, the region formed by the seed points is recorded as a growth region, and the pixel points in the growth region are recorded as growth points; for any growth point in the growth area, taking any pixel point which is positioned in 8 adjacent to the growth point and does not belong to the growth area as a point to be grown; obtaining a variable range of the point to be grown according to the gray difference between the point to be grown and the growth point, and obtaining a threshold range of the point to be grown according to the variable range of the point to be grown; the integral gray value level of the growth area after the growth point to be grown is added into the growth area is calculated, and a specific calculation formula is as follows:
in the method, in the process of the invention,the overall gray value level of the growth area after adding the growth area to the point to be grown,/for the growth area>Integral gray value of growth area before adding growth area for point to be grownThe level, i.e. the average value of the gray values of all pixel points in the growth area before the point to be grown is added into the growth area, h represents the gray value of the point to be grown, +.>Indicating the number of growth points in the growth area before the point to be grown is added to the growth area.
The method of recalculating the overall gray value level of the growth area after the growth point is added into the growth area, that is, the gray average value of the growth area, for each point to be grown has a great amount of calculation redundancy, so that the embodiment records the overall gray value level of the growth area after the last point to be grown is added into the growth area, takes the overall gray value level of the growth area after the last point to be grown is added into the growth area as the overall gray value level of the growth area before the point to be grown is added into the growth area, and calculates the overall gray value level of the growth area after the point to be grown is added into the growth area according to the overall gray value level of the growth area before the point to be grown and the gray value of the point to be grown, thereby reducing the calculation amount.
Further, judging whether the point to be grown is added into the growing area as the growing point according to the whole gray value level of the growing area after the point to be grown is added into the growing area, the whole gray value level threshold, the gray value of the point to be grown and the threshold range of the point to be grown: if the gray value of the point to be grown is within the threshold range of the point to be grown, and the overall gray value level of the growth area after the point to be grown is added into the growth area is greater than or equal to the overall gray value level threshold, the point to be grown is added into the growth area as the growth point, otherwise, the point to be grown cannot be added into the growth area as the growth point; and similarly, judging whether the next point to be grown is added into the growth area as a growth point according to the gray value of the next point to be grown and the changeable range of the point to be grown until all the points to be grown in the growth area cannot be added into the growth area as growth points, and taking the growth area obtained at the moment as a new growth area.
And so on, all growth areas in the boiler area are obtained.
4. And processing the residual pixel points in the boiler region to obtain a final growth region.
In the process of obtaining the region growth, if a noise pixel point is encountered, the gray scale difference between the noise pixel point and surrounding pixel points is large, so that the noise pixel point cannot be added into the growth region as a growth point, and at this time, the residual noise in the residual boiler region needs to be further determined.
A threshold value K is preset, where the embodiment k=80 is described as an example, and the embodiment is not specifically limited, where K depends on the specific implementation.
Specifically, any one pixel point which does not belong to any one growth area and is surrounded by the growth area in the boiler area is recorded as a target pixel point, and the target pixel point is processed: calculating standard deviation of gray values of all pixels in 8 neighborhoods of the target pixel and the target pixel, and marking the standard deviation as a neighborhood difference level of the target pixel; if the neighborhood difference level of the target pixel point is larger than a preset threshold K, the target pixel point is a noise point, the gray value of the noise point is corrected to be the average value of the gray values of all the pixel points in the 8 neighborhood of the noise point, and the corrected noise point is used as a growth point to be added into a growth area; and similarly, all pixel points which do not belong to any growth area in the boiler area and are surrounded by the growth area are processed, and the growth area obtained after the processing is taken as a final growth area.
The boiler thermal efficiency analysis module 103 is configured to obtain the overall temperature from the local temperature according to the divided normal boiler region, and calculate the boiler thermal efficiency.
The normal area brightness separated by the area growth can be combined with the thermal infrared imager to directly obtain the temperature condition of the area, and the factors such as the temperature change condition, the highest temperature and the like can be calculated according to the surface temperature of the boiler in a period of time, so that the thermal efficiency of the boiler can be calculated.
A number threshold S is preset, where the embodiment s=30 is described as an example, and the embodiment is not specifically limited, where S depends on the specific implementation.
Specifically, the obtained final growth area is screened, and the final growth area with the number of the pixel points being larger than a preset number threshold S is used as a segmented normal boiler area.
Further, inputting the segmented normal boiler region and the boiler infrared image into FLIR tools software to generate temperature value files of all pixel points of the boiler gray level image for measuring the surface temperature condition of the boiler; and (3) carrying out thermal effect calculation by taking the local temperature average value as the overall temperature average value, deducing the temperature of the segmented affected area in a linear interpolation mode, and carrying out final thermal effect calculation, wherein the thermal effect calculation is a known technology and is not repeated here.
The system comprises an image acquisition module, a growth area acquisition module and a boiler thermal efficiency analysis module, and aims at the problems that when an area capable of normally displaying the surface temperature of a boiler is selected by dividing the infrared image of the boiler through area growth, the whole brightness of the infrared image of the boiler is higher and the contrast is lower, and a single determined threshold value is difficult to obtain a good division effect; in order to ensure that the overall gray level in a growth area is higher, a pixel point corresponding to the maximum gray value is used as a seed point for area growth, the gray difference between a point to be grown and the growth point is analyzed to obtain the variable range of the point to be grown, the gray value of an initial seed point is combined to adaptively obtain the threshold range of the point to be grown, and then whether the point to be grown is used as the growth point to be added into the growth area is judged, so that the initial growth area is obtained; in addition to considering whether the gray value of the point to be grown is within the threshold range of the point to be grown, the whole gray value level of the growth area after the point to be grown is added as the growth point is compared with the whole gray value level of the growth area before the point to be grown is added as the growth point to be grown.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. A system for on-line detection and analysis of thermal efficiency of a boiler using a thermal infrared imager, the system comprising:
the image acquisition module acquires a boiler region in the boiler gray level image;
the growth area acquisition module is used for acquiring initial seed points according to the boiler area; obtaining a growing area according to the initial seed points, and obtaining points to be grown according to the growing points in the growing area; obtaining a variable range of the point to be grown according to the gray value of the initial seed point and the gray difference between the point to be grown and the growing point, obtaining a threshold range of the point to be grown according to the variable range of the point to be grown, and obtaining an initial growing area according to the threshold range of the point to be grown; calculating the overall gray value level and the overall gray value level threshold of the growth area after the growth point to be grown is added into the growth area; obtaining all growth areas according to the overall gray value level and the overall gray value level threshold value of the growth areas after the points to be grown are added into the growth areas; processing the residual pixel points in the boiler region to obtain a final growth region;
the boiler thermal efficiency analysis module is used for screening the final growth area to obtain a segmented normal boiler area, and acquiring the overall temperature through the local temperature according to the segmented normal boiler area to calculate the boiler thermal efficiency;
the variable range of the point to be grown is obtained according to the gray value of the initial seed point and the gray difference between the point to be grown and the growing point, and the method comprises the following specific steps:
wherein R represents the variable range of the point to be grown,gray value representing initial seed point, +.>Representing the absolute value of the difference between the gray values of the points to be grown and the growing point,/and the gray value of the growing point>Representing an arctangent function;
the method for calculating the integral gray value level of the growth area after the point to be grown is added into the growth area comprises the following specific steps:
in the method, in the process of the invention,the overall gray value level of the growth area after adding the growth area to the point to be grown,/for the growth area>The whole gray value level of the growth area before the growth area is added to the point to be grown, h represents the gray value of the point to be grown,/->Representing the number of growing points in the growing area before the growing points to be grown are added into the growing area;
the method for acquiring the integral gray value level threshold comprises the following steps:
taking the average value of the gray values of all the pixel points of the initial growth area as the whole gray value level of the initial growth area, and taking the whole gray value level of the initial growth area as the whole gray value level threshold;
the method for obtaining all the growth areas comprises the following specific steps:
selecting a pixel point with the maximum gray value as a seed point in other areas except the initial growth area in the boiler area; in the initial stage, only one seed point exists, the region formed by the seed points is recorded as a growth region, and the pixel points in the growth region are recorded as growth points;
for any growth point in the growth area, taking any pixel point which is positioned in 8 adjacent to the growth point and does not belong to the growth area as a point to be grown; obtaining a variable range of the point to be grown according to the gray difference between the point to be grown and the growth point, and obtaining a threshold range of the point to be grown according to the variable range of the point to be grown; calculating the integral gray value level of the growth area after the point to be grown is added into the growth area;
judging whether the point to be grown is added into the growing area as the growing point according to the integral gray value level, the integral gray value level threshold value, the gray value of the point to be grown and the threshold range of the point to be grown of the growing area after the point to be grown is added into the growing area: if the gray value of the point to be grown is within the threshold range of the point to be grown, and the overall gray value level of the growth area after the point to be grown is added into the growth area is greater than or equal to the overall gray value level threshold, the point to be grown is added into the growth area as the growth point, otherwise, the point to be grown cannot be added into the growth area as the growth point; similarly, judging whether the next point to be grown is added into the growth area as a growth point according to the gray value of the next point to be grown and the changeable range of the point to be grown until all the points to be grown in the growth area cannot be added into the growth area as growth points, and taking the growth area obtained at the moment as a new growth area;
and so on, all growth areas in the boiler area are obtained.
2. The system for on-line detection and analysis of thermal efficiency of a boiler using a thermal infrared imager according to claim 1, wherein the obtaining of the initial seed point comprises the following specific steps:
and arbitrarily selecting a pixel point with the maximum gray value from the boiler area as an initial seed point.
3. The system for on-line detection and analysis of thermal efficiency of a boiler using a thermal infrared imager according to claim 1, wherein the step of obtaining a growth area from an initial seed point and obtaining a point to be grown from a growth point in the growth area comprises the following specific steps:
in the initial process, the region formed by the initial seed points is recorded as a growth region, and the pixel points in the growth region are recorded as growth points; and regarding any growth point in the growth area, taking any pixel point which is positioned in 8 adjacent to the growth point and does not belong to the growth area as a point to be grown.
4. The system for on-line detection and analysis of thermal efficiency of a boiler using a thermal infrared imager according to claim 1, wherein the method for obtaining the threshold range of the point to be grown according to the variable range of the point to be grown and obtaining the initial growth area according to the threshold range of the point to be grown comprises the following specific steps:
obtaining the threshold range of the point to be grown according to the variable range of the point to be grown as，/>The gray value of the initial seed point is represented, and R represents the variable range of the point to be grown;
judging whether the point to be grown is added into the growing area as a growing point according to the gray value of the point to be grown and the threshold range of the point to be grown: if the gray value of the point to be grown is within the threshold range of the point to be grown, the point to be grown is added into the growing area as the growing point, otherwise, the point to be grown cannot be added into the growing area as the growing point; and similarly, judging whether the next point to be grown is added into the growth area as a growth point according to the gray value of the next point to be grown and the changeable range of the point to be grown until all the points to be grown in the growth area cannot be added into the growth area as growth points, and taking the growth area obtained at the moment as an initial growth area.
5. The system for on-line detection and analysis of thermal efficiency of a boiler using a thermal infrared imager according to claim 1, wherein the processing of the remaining pixels in the boiler region to obtain the final growth region comprises the following specific steps:
and marking any pixel point which does not belong to any growth area and is surrounded by the growth area in the boiler area as a target pixel point, and processing the target pixel point: calculating standard deviation of gray values of all pixels in 8 neighborhoods of the target pixel and the target pixel, and marking the standard deviation as a neighborhood difference level of the target pixel; if the neighborhood difference level of the target pixel point is larger than a preset threshold K, the target pixel point is a noise point, the gray value of the noise point is corrected to be the average value of the gray values of all the pixel points in the 8 neighborhood of the noise point, and the corrected noise point is used as a growth point to be added into a growth area;
and similarly, all pixel points which do not belong to any growth area in the boiler area and are surrounded by the growth area are processed, and the growth area obtained after the processing is taken as a final growth area.
6. The system for on-line detection and analysis of thermal efficiency of a boiler using a thermal infrared imager according to claim 1, wherein the step of screening the final growth region to obtain the segmented normal boiler region comprises the following specific steps:
and screening the obtained final growth area, and taking the final growth area with the number of the pixel points being larger than a preset number threshold S as a segmented normal boiler area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311099656.9A CN116843682B (en) | 2023-08-30 | 2023-08-30 | Boiler thermal efficiency on-line detection and analysis system using thermal infrared imager |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311099656.9A CN116843682B (en) | 2023-08-30 | 2023-08-30 | Boiler thermal efficiency on-line detection and analysis system using thermal infrared imager |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116843682A CN116843682A (en) | 2023-10-03 |
| CN116843682B true CN116843682B (en) | 2023-11-03 |
Family
ID=88172795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311099656.9A Active CN116843682B (en) | 2023-08-30 | 2023-08-30 | Boiler thermal efficiency on-line detection and analysis system using thermal infrared imager |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116843682B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117168630B (en) * | 2023-11-01 | 2023-12-29 | 江苏皓越真空设备有限公司 | Fault detection method and system for air pressure sintering furnace |
| CN117392130B (en) * | 2023-12-12 | 2024-02-23 | 山东海纳智能装备科技股份有限公司 | On-line fault diagnosis system based on infrared image |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170061265A1 (en) * | 2015-08-24 | 2017-03-02 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method and storage medium |
| CN114757949A (en) * | 2022-06-15 | 2022-07-15 | 济宁市海富电子科技有限公司 | Wire and cable defect detection method and system based on computer vision |
| CN115131387A (en) * | 2022-08-25 | 2022-09-30 | 山东鼎泰新能源有限公司 | Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing |
-
2023
- 2023-08-30 CN CN202311099656.9A patent/CN116843682B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170061265A1 (en) * | 2015-08-24 | 2017-03-02 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method and storage medium |
| CN114757949A (en) * | 2022-06-15 | 2022-07-15 | 济宁市海富电子科技有限公司 | Wire and cable defect detection method and system based on computer vision |
| CN115131387A (en) * | 2022-08-25 | 2022-09-30 | 山东鼎泰新能源有限公司 | Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116843682A (en) | 2023-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116843682B (en) | Boiler thermal efficiency on-line detection and analysis system using thermal infrared imager | |
| CN113689428A (en) | Mechanical part stress corrosion detection method and system based on image processing | |
| CN115829883A (en) | Surface image denoising method for dissimilar metal structural member | |
| CN116703251B (en) | Rubber ring production quality detection method based on artificial intelligence | |
| CN113902641B (en) | Data center hot zone judging method and system based on infrared image | |
| CN116188468B (en) | HDMI cable transmission letter sorting intelligent control system | |
| CN116245880A (en) | Electric vehicle charging pile fire risk detection method based on infrared identification | |
| CN111612773B (en) | Thermal infrared imager and real-time automatic blind pixel detection processing method | |
| CN116385434B (en) | Intelligent detection method for precast beam cracks | |
| CN110998654A (en) | Model learning device, learning completion model generation method, program, learning completion model, monitoring device, and monitoring method | |
| CN113674280A (en) | Method for measuring temperature of hearth of power station boiler | |
| CN116863253A (en) | Operation and maintenance risk early warning method based on big data analysis | |
| CN117911408B (en) | Road pavement construction quality detection method and system | |
| CN117291843B (en) | Efficient management method for image database | |
| CN116563283B (en) | Steam boiler gas leakage detection method and detection device based on image processing | |
| CN117541582A (en) | IGBT insulation quality detection method for high-frequency converter | |
| CN115880683B (en) | Urban waterlogging ponding intelligent water level detection method based on deep learning | |
| CN114881978A (en) | Target detection method, electronic device and intelligent control system | |
| CN110033466B (en) | Coronary artery straightening image segmentation boundary determination method based on multiple gray levels | |
| TW201118317A (en) | Vision-based method for combustion process monitoring, diagnosis, and computer-readable medium using the same | |
| CN110852228B (en) | Method and system for extracting dynamic background and detecting foreground object in monitoring video | |
| CN106605235A (en) | Method and system for determining whether a target object was present during a scanning operation | |
| CN116128877B (en) | Intelligent exhaust steam recovery monitoring system based on temperature detection | |
| CN116188510B (en) | Enterprise emission data acquisition system based on multiple sensors | |
| CN111091569B (en) | Industrial CT image segmentation method with self-adaptive local parameters |
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 |