CN113674280A - Method for measuring temperature of hearth of power station boiler - Google Patents
Method for measuring temperature of hearth of power station boiler Download PDFInfo
- Publication number
- CN113674280A CN113674280A CN202111239303.5A CN202111239303A CN113674280A CN 113674280 A CN113674280 A CN 113674280A CN 202111239303 A CN202111239303 A CN 202111239303A CN 113674280 A CN113674280 A CN 113674280A
- Authority
- CN
- China
- Prior art keywords
- flame
- degree
- fuzzy
- standard
- fluctuation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000011218 segmentation Effects 0.000 claims abstract description 29
- 230000000875 corresponding effect Effects 0.000 claims description 38
- 230000008859 change Effects 0.000 claims description 10
- 238000003708 edge detection Methods 0.000 claims description 6
- 230000002596 correlated effect Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 239000007789 gas Substances 0.000 description 4
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003546 flue gas Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005422 blasting Methods 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004939 coking Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
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
- G01J5/0003—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiant heat transfer of samples, e.g. emittance meter
-
- 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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to a method for measuring the temperature of a hearth of a power station boiler. The method comprises the steps of collecting internal images of a multi-frame boiler to obtain flame segmentation images of each frame; calculating the fuzzy degree of each frame of boiler internal image based on the flame contour edge in the flame segmentation image to obtain a fuzzy degree set; obtaining the flame fluctuation degree from the flame contour edge; and acquiring a standard fuzzy degree by combining the flame fluctuation degree and the fuzzy degree set, and obtaining the hearth temperature according to the standard fuzzy degree. Based on image blurring and flame fluctuation caused by hot gas flow fluctuation, the temperature of the hearth can be accurately measured by combining the blurring degree of the image and the flame fluctuation, so that a large error of a measurement result is avoided, and accurate boiler operation conditions can be obtained in real time.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method for measuring the temperature of a hearth of a power station boiler.
Background
The hearth temperature is an important parameter in the combustion process of the reaction boiler, and the combustion flame distribution in the hearth must be reasonable and stable to ensure the good operation of the power station boiler. The problems of boiler efficiency, hearth coking, furnace tube blasting, NOx generation and the like are all related to the temperature field in the hearth, so that the accurate measurement of the temperature field in the hearth has important significance for diagnosing the operating condition of the boiler.
At present, most of boiler furnace temperature abnormity detection methods utilize a sensor to monitor the temperature inside a boiler or measure the temperature of the boiler according to the characteristics of the furnace outlet flue gas of the boiler.
In the prior art, the problems exist that: the hearth temperature is measured through the sensor and the hearth outlet flue gas, and the problems of inaccurate measured temperature or low sensor sensitivity and the like caused by hearth local defects and hearth aging are easily caused.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a method for measuring the temperature of a hearth of a power station boiler, which adopts the following technical scheme:
one embodiment of the invention provides a method for measuring the temperature of a hearth of a power station boiler, which comprises the following steps:
collecting multi-frame boiler internal images, and performing semantic segmentation on each frame of boiler internal image to obtain a flame segmentation image;
performing edge detection on the flame segmentation image to obtain a flame contour edge, and obtaining a first fuzzy index of the boiler internal image according to pixel points on the flame contour edge and gray values of pixel points around the flame contour edge; generating a gradient histogram from the flame segmentation image to obtain a gradient histogram curve, and obtaining a second fuzzy index of the boiler internal image by comparing the gradient change of the gradient histogram curve with that of a standard gradient histogram curve, wherein the standard gradient histogram curve is corresponding to the boiler internal image when no image blur exists; acquiring the fuzzy degree of each frame of the boiler internal image by combining the first fuzzy index and the second fuzzy index to obtain a fuzzy degree set;
acquiring a center of mass point of the flame connected domain, and acquiring the flame fluctuation degree by the position change of a plurality of frames of internal images of the boiler corresponding to the center of mass point;
and obtaining a standard fuzzy degree according to the fuzzy degree set and the flame fluctuation degree, constructing a proportional relation between the standard fuzzy degree and the flame fluctuation degree, obtaining the corresponding standard fuzzy degrees under different flame fluctuation degrees according to the proportional relation, and obtaining the hearth temperature according to the standard fuzzy degree.
Preferably, the method for acquiring the first fuzzy index includes:
calculating the gray average value of corresponding pixels in 8 fields of the initial pixels by taking any pixel on the edge of the flame contour as the initial pixels, and combining the gray average value and the gray value of the initial pixels to obtain the gray difference corresponding to the initial pixels;
calculating a gray difference mean value according to the gray differences of all pixel points on the flame contour edge, and taking the gray difference mean value as the first fuzzy index.
Preferably, the method for acquiring the second fuzzy index includes:
setting a gradient threshold value based on the heavy tail distribution, calculating a derivative of each point in the gradient histogram curve, taking the derivative as a gradient value, and acquiring a corresponding tail curve when the gradient value is smaller than the gradient threshold value;
and respectively calculating the gradient difference value of the corresponding point in the tail curve and the standard gradient histogram curve, and obtaining the second fuzzy index according to the gradient difference value.
Preferably, the method for obtaining the fluctuation degree of the flame from the position change of the multiple frames of internal images of the boiler corresponding to the centroid point comprises the following steps:
calculating Euclidean distances between the centroid points corresponding to the adjacent frames, and constructing a rectangular coordinate system by taking the Euclidean distances as a longitudinal axis and the number of the adjacent frames as a transverse axis to obtain a fluctuation curve;
and connecting the starting point of the fluctuation curve to form a horizontal line parallel to the horizontal axis, calculating the area of a region formed by the horizontal line and the fluctuation curve, and taking the area as the flame fluctuation degree.
Preferably, the method for obtaining the standard fuzzy degree from the fuzzy degree set and the flame fluctuation degree comprises:
and forming binary data points by using each fuzzy degree in the fuzzy degree set and the flame fluctuation degree, carrying out density clustering on the binary data points to obtain a data point dense area, and obtaining the standard fuzzy degree according to the fuzzy degree in the data point dense area.
Preferably, the method of deriving the standard blur degree from the blur degree in the data point-dense region includes:
acquiring a region central point of the data point dense region, and taking the fuzzy degree of the binary data point as the standard fuzzy degree if the region central point corresponds to the binary data point; and if the area central point does not correspond to the binary data point, taking the average value of the fuzziness of the two groups of binary data points adjacent to the area central point as the standard fuzziness.
Preferably, the furnace temperature is positively correlated with the standard degree of ambiguity.
The embodiment of the invention at least has the following beneficial effects: based on image blurring and flame fluctuation caused by hot gas flow fluctuation, the temperature of the hearth can be accurately measured by combining the blurring degree of the image and the flame fluctuation, so that a large error of a measurement result is avoided, and accurate boiler operation conditions can be obtained in real time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flowchart illustrating steps of a method for measuring a furnace temperature of a utility boiler according to an embodiment of the present invention.
Detailed Description
In order to further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the method for measuring the furnace temperature of the utility boiler according to the present invention, the specific implementation, structure, features and effects thereof will be provided in conjunction with the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
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 describes a specific scheme of the method for measuring the temperature of the furnace chamber of the utility boiler in detail with reference to the accompanying drawings.
The embodiment of the invention aims at the following specific scenes: set up high temperature resistant camera through setting up to one side at the boiler, survey mouthful from the boiler and gather the inside image of boiler, include: flame, slag, and camera acquisition frequency is: and (5) blowing oxygen in the boiler at intervals, and acquiring an internal image of the boiler.
The principle of the temperature estimation measurement is: because the airflow above the boiler is unstable due to high temperature in the boiler, the fluctuation of hot airflow can be caused, and further, the fluctuation of the airflow can cause the blurring of the shot image and the fluctuation of flame, so that the temperature in the boiler can be estimated by utilizing the blurring of the image and the fluctuation characteristic of the flame.
Referring to fig. 1, a flow chart of steps of a method for measuring a furnace temperature of a utility boiler according to an embodiment of the present invention is shown, the method includes the following steps:
and S001, collecting multi-frame boiler internal images, and performing semantic segmentation on each frame of boiler internal image to obtain a flame segmentation image.
Specifically, continuous multiframe boiler internal images are collected through a camera, and each frame of boiler internal image is subjected to region segmentation to obtain a flame segmentation image, wherein the region segmentation method comprises the following steps:
(1) marking the collected boiler internal image, wherein the boiler internal image comprises: and marking the pixel points of the flame area as 1 and the pixel points of other areas as 0 in the flame area and other areas.
(2) And inputting the marked internal image of the boiler into a semantic segmentation network of a coder-full connection structure, training a semantic segmentation coder, extracting an image feature vector, and outputting the category of pixel points of the image feature vector through the full connection network to obtain a flame segmentation image.
(3) The loss function is a cross-entropy loss function.
S002, performing edge detection on the flame segmentation image to obtain a flame contour edge, and obtaining a first fuzzy index of the boiler internal image according to pixel points on the flame contour edge and gray values of pixel points around the flame contour edge; generating a gradient histogram from the flame segmentation image to obtain a gradient histogram curve, and obtaining a second fuzzy index of the boiler internal image by comparing the gradient change of the gradient histogram curve with that of a standard gradient histogram curve, wherein the standard gradient histogram curve is corresponding to the boiler internal image when the boiler internal image is not blurred; and combining the first fuzzy index and the second fuzzy index to obtain the fuzzy degree of each frame of the boiler internal image so as to obtain a fuzzy degree set.
Specifically, a single frame flame segmentation image is extracted, and Canny edge detection is carried out on the flame segmentation image to obtain a flame contour edge, wherein a Canny edge detection algorithm is a known algorithm.
When the image is fuzzy, the fuzzy characteristic reflects the most sensitive high-frequency components such as the edge, the texture and the like of the image, and the clearer the image is, the larger the gray difference between the edge pixel point and the surrounding 8 neighborhood pixel points is, so that the edge upper image is utilizedMean value of gray difference of 8 neighborhoods of pixel pointsThe degree of image blur is evaluated.
Taking any pixel point on the edge of the flame outline as an initial pixel point, and calculating the gray average value of the corresponding pixel point in 8 fields of the initial pixel pointCombined with mean of gray levelAnd the gray value of the initial pixel pointObtaining the gray difference corresponding to the initial pixel point(ii) a Calculating the gray difference of each pixel point on the flame contour edge, and calculating the average value of the gray differences according to the gray differences of all the pixel pointsWhereinIs the flame profile edge firstThe difference in the gray levels of the individual pixel points,averaging the gray scale differences for the number of pixels at the edge of the flame profileAs a first blur indicator.
Further, the clearer the image is, the more the curve corresponding to the gradient histogram of the image satisfies the heavy tail distribution, and when the image is overall blurred, the thinner the tail of the curve corresponding to the gradient histogram is, that is, the larger the gradient change between adjacent points on the curve is, therefore, the image blur degree is evaluated according to the gradient histogram of the flame segmentation image, the evaluation method is as follows: setting a gradient threshold value based on the heavy tail distribution, calculating a derivative of each point in a gradient histogram curve, taking the derivative as a gradient value, and acquiring a corresponding tail curve when the gradient value is smaller than the gradient threshold value; and respectively calculating the gradient difference value of corresponding points in the tail curve and the standard gradient histogram curve, and obtaining a second fuzzy index according to the gradient difference value.
As an example, firstly, a standard gradient histogram curve needs to be obtained, and since a standard flame segmentation image cannot be obtained, that is, a flame segmentation image without image blur is obtained, the standard gradient histogram curve is approximately replaced by a standard function curve, and then the expression of the standard function curve is:(ii) a Then obtaining a gradient histogram of the flame segmentation image, calculating a derivative of each point on a gradient histogram curve in the gradient histogram, regarding the derivative as a gradient value at the point, and setting a gradient threshold valueObtaining the point with gradient value less than gradient threshold value, cutting off the corresponding curve formed on the gradient histogram curve, and using the curve as tail curve(ii) a Calculating the gradient difference value of corresponding points in the tail curve and the standard gradient histogram curve to obtain the mean value of the difference valueWherein, in the step (A),is the first on the tail curveGradient of pointsThe value of the one or more of the one,is the gradient value of the corresponding point on the standard gradient histogram curve,the number of points on the tail curve is the average of the difference valuesAs a second blur indicator.
Calculating the fuzzy degree of the boiler internal image by combining the first fuzzy index and the second fuzzy indexFurther, the blur degree of each frame of the boiler internal image is obtained to constitute a blur degree set by step S002.
And S003, obtaining a flame connected domain in the flame segmentation image based on the flame contour edge, obtaining a centroid point of the flame connected domain, and obtaining the flame fluctuation degree according to the position change of the centroid point corresponding to the internal image of the multi-frame boiler.
Specifically, because the fluctuation of the hot gas flow can generate the fluctuation of the flame, the fluctuation characteristic of the flame is analyzed through the internal image of the continuous multi-frame boiler to obtain the fluctuation degree of the flame, and the method for obtaining the fluctuation degree of the flame comprises the following steps:
(1) respectively obtaining flame contour edges in continuous multi-frame boiler internal images through the Canny edge detection, and based on an edge curve corresponding to the flame contour edges in the single-frame boiler internal images, aiming at pixel points on the edge curveCalculating pixel pointsAnd its left adjacent pixel pointFirst slope and pixel in betweenDotAnd its right adjacent pixel pointAnd obtaining a slope difference value according to the first slope and the second slope, and further obtaining a slope difference value corresponding to each pixel point on the edge curve, and obtaining a corresponding first pixel point when the slope difference value is maximum.
(2) And (2) acquiring all first pixel points in the single-frame boiler internal image by using the step (1), and connecting the first pixel points contained in the upper half part of the boiler internal image to obtain a flame connected domain, thereby acquiring the centroid point of the flame connected domain.
It should be noted that the reason for utilizing the first pixel point included in the upper half of the internal image of the boiler is that when hot gas flows, the swing of the high position of the flame is most obvious, and further, the region change corresponding to the high position can represent the volatility of the flame most.
(3) And (3) obtaining the centroid points of the flame connected domain in the continuous multi-frame boiler internal images by using the steps (1) and (2). Calculating Euclidean distance between corresponding centroid points of adjacent framesWherein, in the step (A),is as followsThe mass center point corresponding to the internal image of the frame boiler,is as followsFraming a centroid point corresponding to the internal image of the boiler; constructing a rectangular coordinate system by taking the Euclidean distance as a longitudinal axis and the number of adjacent frames as a transverse axis to obtain a waveA curve; connecting the starting point of the fluctuation curve to make a horizontal line parallel to the horizontal axis, and calculating the area of the region formed by the horizontal line and the fluctuation curveArea of willAs a degree of flame fluctuation.
And step S004, obtaining a standard fuzzy degree from the fuzzy degree set and the flame fluctuation degree, constructing a proportional relation between the standard fuzzy degree and the flame fluctuation degree, obtaining corresponding standard fuzzy degrees under different flame fluctuation degrees by using the proportional relation, and obtaining the hearth temperature according to the standard fuzzy degrees.
Specifically, each fuzzy degree in the fuzzy degree set and the flame fluctuation degree form a binary data point, density clustering is performed on a plurality of binary data points to obtain a data point dense region, a standard fuzzy degree is obtained from the fuzzy degree in the data point dense region, and the method for obtaining the standard fuzzy degree comprises the following steps: obtaining the area central point of the dense area of the data points, if the area central point corresponds to the binary data point, the fuzzy degree of the binary data point is determinedAs a standard degree of blurring(ii) a Otherwise, if the center point of the region does not correspond to the binary data point, the average value of the two sets of binary data points adjacent to the center point of the region is used as the standard fuzzy degree。
Constructing a proportional relation between the standard fuzzy degree and the flame fluctuation degreeObtaining corresponding standard fuzzy ranges under different flame fluctuation degrees by utilizing proportional relationAnd (4) degree.
Due to the temperature of the hearthWhen the size of the furnace hearth is changed, hot air flows with different degrees can be generated, and further, the acquired image is blurred, so that the blurring degree of the image is related to the temperature of the furnace hearth. Therefore, the boiler is utilized to be at different hearth temperaturesNext, the standard fuzzy degree of the internal image of the boiler is constructedTemperature of furnace chamberNon-linear function relation model ofAnd the hearth temperature is positively correlated with the standard fuzzy degree, and then the hearth temperature can be obtained in real time through the nonlinear function relation model.
In summary, the embodiment of the invention provides a method for measuring the temperature of a furnace chamber of a power station boiler, which collects multiple frames of internal images of the boiler to obtain flame segmentation images of each frame; calculating the fuzzy degree of each frame of boiler internal image based on the flame contour edge in the flame segmentation image to obtain a fuzzy degree set; obtaining the flame fluctuation degree from the flame contour edge; and acquiring a standard fuzzy degree by combining the flame fluctuation degree and the fuzzy degree set, and obtaining the hearth temperature according to the standard fuzzy degree. Based on image blurring and flame fluctuation caused by hot gas flow fluctuation, the temperature of the hearth can be accurately measured by combining the blurring degree of the image and the flame fluctuation, so that a large error of a measurement result is avoided, and accurate boiler operation conditions can be obtained in real time.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. A method for measuring the temperature of a hearth of a power station boiler is characterized by comprising the following steps:
collecting multi-frame boiler internal images, and performing semantic segmentation on each frame of boiler internal image to obtain a flame segmentation image;
performing edge detection on the flame segmentation image to obtain a flame contour edge, and obtaining a first fuzzy index of the boiler internal image according to pixel points on the flame contour edge and gray values of pixel points around the flame contour edge; generating a gradient histogram from the flame segmentation image to obtain a gradient histogram curve, and obtaining a second fuzzy index of the boiler internal image by comparing the gradient change of the gradient histogram curve with that of a standard gradient histogram curve, wherein the standard gradient histogram curve is corresponding to the boiler internal image when no image blur exists; acquiring the fuzzy degree of each frame of the boiler internal image by combining the first fuzzy index and the second fuzzy index to obtain a fuzzy degree set;
acquiring a center of mass point of the flame connected domain, and acquiring the flame fluctuation degree by the position change of a plurality of frames of internal images of the boiler corresponding to the center of mass point;
and obtaining a standard fuzzy degree according to the fuzzy degree set and the flame fluctuation degree, constructing a proportional relation between the standard fuzzy degree and the flame fluctuation degree, obtaining the corresponding standard fuzzy degrees under different flame fluctuation degrees according to the proportional relation, and obtaining the hearth temperature according to the standard fuzzy degree.
2. The method according to claim 1, wherein the method for obtaining the first fuzzy index comprises:
calculating the gray average value of corresponding pixels in 8 fields of the initial pixels by taking any pixel on the edge of the flame contour as the initial pixels, and combining the gray average value and the gray value of the initial pixels to obtain the gray difference corresponding to the initial pixels;
calculating a gray difference mean value according to the gray differences of all pixel points on the flame contour edge, and taking the gray difference mean value as the first fuzzy index.
3. The method according to claim 1, wherein the second fuzzy index obtaining method comprises:
setting a gradient threshold value based on the heavy tail distribution, calculating a derivative of each point in the gradient histogram curve, taking the derivative as a gradient value, and acquiring a corresponding tail curve when the gradient value is smaller than the gradient threshold value;
and respectively calculating the gradient difference value of the corresponding point in the tail curve and the standard gradient histogram curve, and obtaining the second fuzzy index according to the gradient difference value.
4. The method of claim 1, wherein the step of deriving the degree of flame fluctuation from the plurality of frames of the internal images of the boiler corresponding to the change in the position of the centroid point comprises:
calculating Euclidean distances between the centroid points corresponding to the adjacent frames, and constructing a rectangular coordinate system by taking the Euclidean distances as a longitudinal axis and the number of the adjacent frames as a transverse axis to obtain a fluctuation curve;
and connecting the starting point of the fluctuation curve to form a horizontal line parallel to the horizontal axis, calculating the area of a region formed by the horizontal line and the fluctuation curve, and taking the area as the flame fluctuation degree.
5. The method of claim 1, wherein said method of deriving a standard degree of ambiguity from said set of degrees of ambiguity and said degree of flame fluctuation comprises:
and forming binary data points by using each fuzzy degree in the fuzzy degree set and the flame fluctuation degree, carrying out density clustering on the binary data points to obtain a data point dense area, and obtaining the standard fuzzy degree according to the fuzzy degree in the data point dense area.
6. The method of claim 5, wherein said deriving said standard degree of blur from said degree of blur in said data point-dense region comprises:
acquiring a region central point of the data point dense region, and taking the fuzzy degree of the binary data point as the standard fuzzy degree if the region central point corresponds to the binary data point; and if the area central point does not correspond to the binary data point, taking the average value of the fuzziness of the two groups of binary data points adjacent to the area central point as the standard fuzziness.
7. The method of claim 1, wherein the furnace temperature is positively correlated with the standard degree of ambiguity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111239303.5A CN113674280A (en) | 2021-10-25 | 2021-10-25 | Method for measuring temperature of hearth of power station boiler |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111239303.5A CN113674280A (en) | 2021-10-25 | 2021-10-25 | Method for measuring temperature of hearth of power station boiler |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113674280A true CN113674280A (en) | 2021-11-19 |
Family
ID=78551030
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111239303.5A Pending CN113674280A (en) | 2021-10-25 | 2021-10-25 | Method for measuring temperature of hearth of power station boiler |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113674280A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115283125A (en) * | 2022-10-09 | 2022-11-04 | 如皋市中如新材料科技有限公司 | Running abnormity monitoring method based on stone crushing equipment |
CN116228548A (en) * | 2023-05-10 | 2023-06-06 | 江苏太湖锅炉股份有限公司 | Intelligent measurement method for boiler furnace temperature |
CN116674134A (en) * | 2023-08-03 | 2023-09-01 | 绵阳华远同创科技有限公司 | Automatic casting processing method and system for resin words |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5225883A (en) * | 1991-06-05 | 1993-07-06 | The Babcock & Wilcox Company | Video temperature monitor |
CN101281063A (en) * | 2008-05-16 | 2008-10-08 | 天津市电视技术研究所 | High temperature furnace inner video image temperature measuring system |
CN104008385A (en) * | 2014-03-19 | 2014-08-27 | 合肥工业大学 | Coal-fired power plant furnace chamber flame judging method based on double images |
CN106778816A (en) * | 2016-11-23 | 2017-05-31 | 华北电力大学 | Combustion stability method of discrimination based on burning mixed coefficint and fuzzy diagnosis |
-
2021
- 2021-10-25 CN CN202111239303.5A patent/CN113674280A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5225883A (en) * | 1991-06-05 | 1993-07-06 | The Babcock & Wilcox Company | Video temperature monitor |
CN101281063A (en) * | 2008-05-16 | 2008-10-08 | 天津市电视技术研究所 | High temperature furnace inner video image temperature measuring system |
CN104008385A (en) * | 2014-03-19 | 2014-08-27 | 合肥工业大学 | Coal-fired power plant furnace chamber flame judging method based on double images |
CN106778816A (en) * | 2016-11-23 | 2017-05-31 | 华北电力大学 | Combustion stability method of discrimination based on burning mixed coefficint and fuzzy diagnosis |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115283125A (en) * | 2022-10-09 | 2022-11-04 | 如皋市中如新材料科技有限公司 | Running abnormity monitoring method based on stone crushing equipment |
CN116228548A (en) * | 2023-05-10 | 2023-06-06 | 江苏太湖锅炉股份有限公司 | Intelligent measurement method for boiler furnace temperature |
CN116674134A (en) * | 2023-08-03 | 2023-09-01 | 绵阳华远同创科技有限公司 | Automatic casting processing method and system for resin words |
CN116674134B (en) * | 2023-08-03 | 2023-10-20 | 绵阳华远同创科技有限公司 | Automatic casting processing method and system for resin words |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113674280A (en) | Method for measuring temperature of hearth of power station boiler | |
CN107657619B (en) | A kind of low-light (level) Forest fire image dividing method | |
CN108563975B (en) | High-density crowd number estimation method based on deep learning | |
CN110766058A (en) | Battlefield target detection method based on optimized RPN (resilient packet network) | |
CN115841624B (en) | Blast furnace gas flow distribution identification method based on infrared image | |
CN108492313A (en) | A kind of dimension self-adaption visual target tracking method based on middle intelligence similarity measure | |
CN113688830B (en) | Deep learning target detection method based on center point regression | |
CN110221312A (en) | A method of quickly detecting ground point cloud based on laser radar | |
CN109711389A (en) | A kind of milking sow posture conversion identification method based on Faster R-CNN and HMM | |
CN108667684A (en) | A kind of data flow anomaly detection method based on partial vector dot product density | |
CN112699824B (en) | Method and device for detecting constant of electric energy meter and storage medium | |
CN116843682B (en) | Boiler thermal efficiency on-line detection and analysis system using thermal infrared imager | |
CN103942786B (en) | The self adaptation block objects detection method of unmanned plane visible ray and infrared image | |
CN109325510A (en) | A kind of image characteristic point matching method based on lattice statistical | |
CN113392846A (en) | Water gauge water level monitoring method and system based on deep learning | |
CN107238442B (en) | Without the detector thermometric method for regulating temperature of temperature stabilizer | |
CN106815851B (en) | A kind of grid circle oil level indicator automatic reading method of view-based access control model measurement | |
CN116843725B (en) | River surface flow velocity measurement method and system based on deep learning optical flow method | |
CN117910073A (en) | Artwork package design optimization system and method based on 3D printing technology | |
CN112528566A (en) | Real-time air quality data calibration method and system based on AdaBoost training model | |
CN115147349A (en) | Method and device for determining smelting end point of converter, electronic equipment and storage medium | |
CN114494819B (en) | Anti-interference infrared target identification method based on dynamic Bayesian network | |
CN115311266A (en) | Printing and dyeing identification method in textile printing and dyeing process | |
CN114742849A (en) | Leveling instrument distance measuring method based on image enhancement | |
CN108986175B (en) | Temperature interpretation method for temperature indicating paint area |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211119 |
|
RJ01 | Rejection of invention patent application after publication |