CN109754019B - Method for continuously monitoring combustion condition of boiler - Google Patents
Method for continuously monitoring combustion condition of boiler Download PDFInfo
- Publication number
- CN109754019B CN109754019B CN201910023176.1A CN201910023176A CN109754019B CN 109754019 B CN109754019 B CN 109754019B CN 201910023176 A CN201910023176 A CN 201910023176A CN 109754019 B CN109754019 B CN 109754019B
- Authority
- CN
- China
- Prior art keywords
- image
- combustion
- hearth
- identified
- flame
- 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
Images
Abstract
The invention discloses a method for continuously monitoring the combustion condition of a boiler, which comprises the following steps: collecting video signals of furnace flame in a preset time under the condition of full load in a combustion area to be monitored; obtaining a time sequence image of the flame center according to the video signal and determining an image scale reference image; acquiring a hearth combustion image to be identified in real time, and determining a scale image of the hearth combustion image to be identified according to the hearth combustion image to be identified and an image scale reference image; classifying the combustion images of the hearth to be identified by adopting a support vector machine model; and determining a flame recognition algorithm for the image to be recognized by adopting a support vector machine model, and calculating a two-dimensional coordinate of the flame center position of the combustion image of the hearth to be recognized. The invention classifies images and selects a flame center calculation algorithm by using a support vector machine model, can solve the influence of reflection, refraction and hearth dirt on the combustion condition of a hearth, and improves the accuracy of identifying the position of the flame center in the hearth in real time.
Description
Technical Field
The invention relates to the technical field of industrial boilers, in particular to a method for continuously monitoring the combustion condition of a boiler.
Background
At present, in China, methods for continuously monitoring the combustion condition in a hearth of a power plant boiler combustion system mainly comprise an eye measurement method, a characteristic parameter method and an image observation method. The visual inspection method is to directly observe the combustion condition in the furnace through a fire observation port during operation, and the method is simpler but is greatly influenced by human subjective factors; the characteristic parameter method is to measure various parameters such as pressure, charge, light intensity and the like in the flame by using experimental instrument equipment, has high precision and real and credible data, but has high requirements on the instrument equipment, and the measurement result is greatly influenced by external factors; the image observation method is to indirectly observe the change of the combustion condition by using an image and then mark the height and the central position of the flame to calculate the combustion parameter.
Disclosure of Invention
The invention aims to provide a method for continuously monitoring the combustion condition of a boiler, which has the advantages of high precision and short reaction time.
In order to achieve the purpose, the invention provides the following scheme:
the invention discloses a method for continuously monitoring the combustion condition of a boiler, which comprises the following steps:
collecting video signals of furnace flame in a preset time under the condition of full load in a combustion area to be monitored;
obtaining time series images of the flame center according to the video signal;
calculating the pixel number of each frame of image according to the time interval of each frame of image in the time sequence image, the focal length of each frame of image and the size of a hearth, and comparing the pixel numbers of all the time sequence images to determine an image scale reference image;
acquiring a hearth combustion image to be identified in real time, and determining a monitoring area of the hearth combustion image to be identified according to the hearth combustion image to be identified and the image scale reference image;
classifying the hearth combustion image to be identified by adopting a support vector machine model according to the image characteristics of the hearth combustion image to be identified;
determining a flame identification algorithm for the to-be-identified furnace combustion image by adopting a support vector machine model according to the image characteristics and the type of the to-be-identified furnace combustion image, and calculating two-dimensional coordinates of the flame center position in the monitoring area of the to-be-identified furnace combustion image;
and converting the two-dimensional coordinates into the position of the flame center corresponding to the combustion image of the hearth to be identified in the hearth.
Optionally, the obtaining of the time series image of the flame center according to the video signal specifically includes: and processing the video signal by adopting Adobe Premiere software to obtain a time series image of the flame center.
Optionally, the to-be-identified furnace combustion image is divided into 3 channels according to HSV (Hue, Saturation, Value) color space, an average brightness Value and a mean square error of each channel of the to-be-identified furnace combustion image are respectively calculated, and the average brightness Value and the mean square error of each channel of the to-be-identified furnace combustion image are used as the image features of the to-be-identified furnace combustion image.
Optionally, the classification of the combustion image of the furnace to be identified includes an image of normal combustion and an image of abnormal combustion, the image of normal combustion is an image of a range from a full-load combustion state to a lowest stable combustion heat load state in the furnace, and the image of abnormal combustion is an image exceeding the full-load combustion state or being lower than the lowest stable combustion heat load state.
Optionally, the determining, according to the to-be-identified furnace combustion image and the image scale reference image, a monitoring region of the to-be-identified furnace combustion image specifically includes:
step 1041: judging whether the combustion of the hearth to be identified is a normal combustion image, if so, turning to a step 1042, and if not, turning to a step 1043;
step 1042: taking the image scale reference image as a first picture, and taking the furnace combustion image to be identified as a second picture; performing gamma correction on the first picture and the second picture respectively; taking a picture of a brightness V channel obtained by the division of the second picture through the HSV color space as a third picture; according to the absolute value of the difference of the pixel matrixes of the first picture after gamma correction and the second picture after gamma correction, the third picture is subjected to local self-adaptive thresholding, morphological closing operation and expansion operation, and a monitoring area of the combustion image of the hearth to be identified is obtained through contour operation;
step 1043: calculating the average brightness of the illumination of the combustion image of the hearth to be identified, and if the average brightness is greater than 90, turning to the step 1042; otherwise, performing HSV color segmentation on the combustion image of the hearth to be identified, performing median blurring, histogram equalization, local adaptive thresholding, morphological closing operation and expansion operation on the image of the brightness V channel, and acquiring the monitoring region of the combustion image of the hearth to be identified through contour operation.
Optionally, before the comparing the number of pixels of all the time series images to determine the image scale reference image, the method specifically includes: and carrying out binarization processing on each frame of image in the time sequence image, and calculating the pixel number of each frame of image after binarization processing.
Optionally, the acquiring the video signal of the flame of the furnace chamber under the full load condition in the combustion area to be monitored specifically includes: and acquiring a video signal of the flame of the hearth by adopting a hearth flame monitoring system.
Optionally, the focal length is a focal length of a periscope tube in the furnace flame monitoring system.
According to the invention content provided by the invention, the invention discloses the following technical effects: the invention carries out software processing on the collected video signal, determines a scale reference image according to the image data and the size of the hearth after the software processing, classifies the image to be identified obtained in real time by utilizing a support vector machine model and selects a flame center identification algorithm.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for continuously monitoring the combustion condition of a boiler according to an embodiment of the present invention;
FIG. 2 is a block diagram of a video signal acquisition device according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the calibration of the coordinate scale of the flame position according to the embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method for continuously monitoring the combustion condition of a boiler, which realizes the real-time monitoring of the central position of flame in a hearth and has the advantages of high precision and short reaction time.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a schematic flow chart of a method for continuously monitoring a combustion condition of a boiler according to an embodiment of the present invention, and as shown in fig. 1, the method for continuously monitoring a combustion condition of a boiler according to the present invention includes:
step 101: collecting video signals of furnace flame in a preset time under the condition of full load in a combustion area to be monitored;
step 102: obtaining time series images of the flame center according to the video signal;
step 103: calculating the pixel number of each frame of image according to the time interval of each frame of image in the time sequence image, the focal length of each frame of image and the size of a hearth, comparing the pixel numbers of all the time sequence images, and determining the image with the fullest flame as an image scale reference image; and calibrating the key scale of the image scale reference image.
Step 104: acquiring a hearth combustion image to be identified in real time, determining a monitoring area of the hearth combustion image to be identified according to the hearth combustion image to be identified and the image scale reference image, and calculating full-scale values of an X axis and a Y axis of a two-dimensional coordinate corresponding to the monitoring area; the size of the monitoring area is consistent with that of the image scale reference image;
step 105: classifying the hearth combustion image to be identified by adopting a support vector machine model according to the image characteristics of the hearth combustion image to be identified;
step 106: determining a flame identification algorithm for the to-be-identified furnace combustion image by adopting a support vector machine model according to the image characteristics and the type of the to-be-identified furnace combustion image, and calculating two-dimensional coordinates of the flame center position in the monitoring area of the to-be-identified furnace combustion image; the flame center refers to the brightest point of flame in the image;
FIG. 3 is a schematic diagram of the calibration of the flame position coordinate scales of the present invention, as shown in FIG. 3: recording full-scale coordinate values of a monitoring area of a hearth combustion image to be identified as (M, N); the flame coordinates of the combustion image of the hearth to be identified at present are (m, n); coordinate points with coordinate values of 0, M/3, 2M/3 and 3M/3 on the X coordinate axis are respectively represented as M1, M2, M3 and M4, points with coordinate values of 0, N/3, 2N/3 and 3N/3 on the Y coordinate axis are respectively represented as points N1, N2, N3 and N4, and are respectively divided into three sections from left to right on the X axis and from bottom to top on the Y axis through the calibration of an image scale:
if the coordinate value m on the X axis of the furnace combustion image to be identified is located at the first section on the X axis, the coordinate value of the flame center on the X axis is as follows: u1 ═ M2-M (M/3)/(M2-M1) ═ M2-M;
if the coordinate value m on the X axis of the combustion image of the hearth to be identified is located at the second section on the X axis, the coordinate value of the flame center on the X axis is as follows: m/3+ (M3-M) (M/3)/(M3-M2) ═ M/3+ (M3-M) U2;
if the coordinate value m of the combustion image of the hearth to be identified is at the third section of the X axis, the coordinate value of the flame center on the X axis is as follows: u3 ═ 2M/3+ (M4-M) × (M/3)/(M4-M3) ═ 2M/3+ (M4-M);
if the coordinate value n on the Y axis of the furnace combustion image to be identified is located at the first section on the Y axis, the coordinate value of the flame center on the Y axis is as follows: v1 ═ N2-N (N/3)/(N2-N1) ═ N2-N;
if the coordinate value n on the Y axis of the combustion image of the hearth to be identified is located at the second section on the Y axis, the coordinate value of the flame center on the Y axis is as follows: v2 ═ N/3+ (N3-N) × (N/3)/(N3-N2) ═ N/3+ (N3-N);
if the coordinate value n on the Y axis of the combustion image of the hearth to be identified is located at the third section on the Y axis, the coordinate value of the flame center on the Y axis is as follows: v3 ═ 2N/3+ (N4-N) × (N/3)/(N4-N3) ═ 2N/3+ (N4-N);
step 107: and converting the two-dimensional coordinates into the position of the flame center corresponding to the combustion image of the hearth to be identified in the hearth.
Wherein, step 102 specifically further comprises: and processing the video signal by adopting Adobe Premiere software to obtain a time series image of the flame center. The time series images are images of a series of hearth flame combustion conditions changing along with time, and the change conditions of the flame height and the flame center along with time can be seen from the time series images.
the proportional relation, namely the image scale, is judged by calculating the pixel number corresponding to the flame section (longitudinal section) in the image. The judging method comprises the following steps: the server processes the video signal through Adobe Premiere software to obtain a time series image, and carries out image binarization:
when f (m, n) is more than or equal to T, f (m, n) is 255;
when f (m, n) < T, f (m, n) ═ 0;
where T is the selected luminance threshold, here set at 60; f (m, n) is the luminance value at the point (m, n) in the time-series image processing.
And knowing the time interval of each frame of image, the focal length of a periscope tube, the size of a hearth and the position of the periscope tube in the hearth, and using MATLAB to compile a corresponding image analysis program to calculate the pixel number of the image after binarization processing based on the parameters.
The step 104 specifically includes that the classification of the combustion image of the furnace to be identified includes an image of normal combustion and an image of abnormal combustion, the image of normal combustion is an image of a range from a full-load combustion state to a lowest stable combustion heat load state in the furnace, and the image of abnormal combustion is an image exceeding the full-load combustion state or being lower than the lowest stable combustion heat load state.
Wherein, step 104 specifically includes: dividing the hearth combustion image to be identified into 3 channels according to HSV color space, respectively calculating the average brightness value and the mean square error of each channel of the hearth combustion image to be identified, and taking the average brightness value and the mean square error of each channel of the hearth combustion image to be identified as the image characteristics of the hearth combustion image to be identified.
The determining the monitoring area of the furnace combustion image to be identified according to the furnace combustion image to be identified and the image scale reference image specifically includes:
step 1041: judging whether the combustion of the hearth to be identified is a normal combustion image, if so, turning to a step 1042, and if not, turning to a step 1043;
step 1042: taking the image scale reference image as a first picture, and taking the furnace combustion image to be identified as a second picture; performing gamma correction on the first picture and the second picture respectively; taking a picture of a brightness V channel obtained by the division of the second picture through the HSV color space as a third picture; according to the absolute value of the difference of the pixel matrixes of the first picture after gamma correction and the second picture after gamma correction, the third picture is subjected to local self-adaptive thresholding, morphological closing operation and expansion operation, and a monitoring area of the combustion image of the hearth to be identified is obtained through contour operation;
the gamma correction can detect dark and light parts in the image signal and increase the ratio of the dark and light parts, thereby improving the image contrast effect.
Step 1043: calculating the average brightness of the illumination of the combustion image of the hearth to be identified, and if the average brightness is greater than 90, turning to the step 1042; otherwise, performing HSV color segmentation on the combustion image of the hearth to be identified, performing median blurring, histogram equalization, local adaptive thresholding, morphological closing operation and expansion operation on the image of the brightness V channel, and acquiring the monitoring region of the combustion image of the hearth to be identified through contour operation.
The focal length is the focal length of a periscope tube in the hearth flame monitoring system.
Fig. 2 is a structural diagram of a video signal acquisition device of the present invention, as shown in fig. 2, an electric actuator 205 pushes a periscope tube 203 into a furnace chamber from an opening of a furnace wall 201 to record a combustion condition inside the furnace chamber, wherein a connecting plate 202 is used for fixing the electric actuator 205, a camera shield 206 is used for protecting the periscope tube 203, a power box 208 is used for providing power for the device, a server 209 is used for receiving video signals acquired by the periscope tube 203 and performing data processing of the video signals, an ash blowing tube 207 prevents fly ash inside the furnace chamber from attaching to the periscope tube 203, and a variable optical diaphragm group 204 has a focusing function to adapt to the combustion conditions under different loads.
According to the method, the acquired video signals are subjected to software processing, the scale reference image is determined according to the image data and the size of the hearth after the software processing, the images to be recognized obtained in real time are classified by using a support vector machine model, and a flame center recognition algorithm is selected, so that the influence of reflection, refraction and hearth dirt on the combustion condition of the hearth can be well solved by using the stability of the algorithm, and the accuracy of recognizing the position of the flame center in the hearth in real time is improved; according to the invention, a reference object with great influence on the recognition result by the accuracy of the reference object is not needed, and the height of the reference object, the angle of a flame break angle, the horizontal distance and the height of a camera are not needed to be predicted; the method can overcome the defects of artificial subjective factors, large calculation amount and the like, and has the advantages of high precision, timely response, intelligent control and stable monitoring work.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (6)
1. A method of continuously monitoring the combustion conditions of a boiler, the method comprising:
collecting video signals of furnace flame in a preset time under the condition of full load in a combustion area to be monitored;
obtaining time series images of the flame center according to the video signal;
calculating the pixel number of each frame of image according to the time interval of each frame of image in the time sequence image, the focal length of each frame of image and the size of a hearth, and comparing the pixel numbers of all the time sequence images to determine an image scale reference image;
acquiring a hearth combustion image to be identified in real time, and determining a monitoring area of the hearth combustion image to be identified according to the hearth combustion image to be identified and the image scale reference image;
classifying the hearth combustion image to be identified by adopting a support vector machine model according to the image characteristics of the hearth combustion image to be identified;
determining a flame identification algorithm for the to-be-identified furnace combustion image by adopting a support vector machine model according to the image characteristics and the type of the to-be-identified furnace combustion image, and calculating two-dimensional coordinates of the flame center position in the monitoring area of the to-be-identified furnace combustion image;
converting the two-dimensional coordinates into the position of the flame center corresponding to the combustion image of the hearth to be identified in the hearth;
dividing the hearth combustion image to be identified into 3 channels according to HSV color space, respectively calculating the average brightness value and the mean square error of each channel of the hearth combustion image to be identified, and taking the average brightness value and the mean square error of each channel of the hearth combustion image to be identified as the image characteristics of the hearth combustion image to be identified;
the determining the monitoring area of the furnace combustion image to be identified according to the furnace combustion image to be identified and the image scale reference image specifically includes:
step 1041: judging whether the combustion of the hearth to be identified is a normal combustion image, if so, turning to a step 1042, and if not, turning to a step 1043;
step 1042: taking the image scale reference image as a first picture, and taking the furnace combustion image to be identified as a second picture; performing gamma correction on the first picture and the second picture respectively; taking a picture of a brightness V channel obtained by the division of the second picture through the HSV color space as a third picture; according to the absolute value of the difference of the pixel matrixes of the first picture after gamma correction and the second picture after gamma correction, the third picture is subjected to local self-adaptive thresholding, morphological closing operation and expansion operation, and a monitoring area of the combustion image of the hearth to be identified is obtained through contour operation;
step 1043: calculating the average brightness of the illumination of the combustion image of the hearth to be identified, and if the average brightness is greater than 90, turning to the step 1042; otherwise, performing HSV color segmentation on the combustion image of the hearth to be identified, performing median blurring, histogram equalization, local adaptive thresholding, morphological closing operation and expansion operation on the image of the brightness V channel, and acquiring the monitoring region of the combustion image of the hearth to be identified through contour operation.
2. The method for continuously monitoring the combustion condition of a boiler as claimed in claim 1, wherein said obtaining time series images of the flame center from said video signal comprises in particular: and processing the video signal by adopting Adobe Premiere software to obtain a time series image of the flame center.
3. The method for continuously monitoring the combustion condition of the boiler as claimed in claim 1, wherein the classification of the combustion images of the furnace to be identified comprises images of normal combustion and images of abnormal combustion, the images of normal combustion are images of the interval from the full-load combustion state to the lowest steady-combustion heat load state in the furnace, and the images of abnormal combustion are images of the exceeding of the full-load combustion state or the falling of the lowest steady-combustion heat load state.
4. The method for continuously monitoring the combustion condition of the boiler as claimed in claim 1, wherein before the comparing the number of pixels of all the time series images to determine the image scale reference image, the method specifically comprises: and carrying out binarization processing on each frame of image in the time sequence image, and calculating the pixel number of each frame of image after binarization processing.
5. The method according to claim 1, wherein the collecting video signals of the furnace flame at full load in the combustion area to be monitored comprises: and acquiring a video signal of the flame of the hearth by adopting a hearth flame monitoring system.
6. The method of continuously monitoring boiler combustion conditions according to claim 5, wherein said focal length is the focal length of a periscope tube in said furnace flame monitoring system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910023176.1A CN109754019B (en) | 2019-01-10 | 2019-01-10 | Method for continuously monitoring combustion condition of boiler |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910023176.1A CN109754019B (en) | 2019-01-10 | 2019-01-10 | Method for continuously monitoring combustion condition of boiler |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109754019A CN109754019A (en) | 2019-05-14 |
| CN109754019B true CN109754019B (en) | 2020-11-06 |
Family
ID=66405441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910023176.1A Active CN109754019B (en) | 2019-01-10 | 2019-01-10 | Method for continuously monitoring combustion condition of boiler |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109754019B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163278B (en) * | 2019-05-16 | 2023-04-07 | 东南大学 | Flame stability monitoring method based on image recognition |
| CN110222633B (en) * | 2019-06-04 | 2021-04-27 | 北京工业大学 | Method for identifying combustion condition of urban solid waste incineration process based on flame image color feature extraction |
| CN110379000B (en) * | 2019-06-24 | 2023-06-30 | 达闼机器人股份有限公司 | Method and device for detecting aircraft air inlet, storage medium and electronic equipment |
| CN111126206B (en) * | 2019-12-12 | 2023-04-07 | 创新奇智(成都)科技有限公司 | Smelting state detection system and method based on deep learning |
| CN112924033A (en) * | 2021-01-26 | 2021-06-08 | 广州康达环保技术有限公司 | Method for monitoring combustion flame state of garbage incinerator |
| CN113222244A (en) * | 2021-05-10 | 2021-08-06 | 刘旸 | Online boiler combustion optimization method based on flame combustion image judgment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002025590A1 (en) * | 2000-09-21 | 2002-03-28 | L'air Liquide, Societe Anonyme A Directoire Et Conseil De Surveillance Pour L'etude Et L'exploitation Des Procedes Georges Claude | Method and device for characterising or controlling temporal fluctuation zones of a scene |
| CN103617635A (en) * | 2013-11-28 | 2014-03-05 | 南京理工大学 | Transient flame detection method based on image processing |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI421721B (en) * | 2010-12-09 | 2014-01-01 | Ind Tech Res Inst | A method for combustion flames diagnosis |
| CN102968644A (en) * | 2012-11-21 | 2013-03-13 | 长春工业大学 | Method for predicting smelting finishing point of argon-oxygen refined iron alloy |
| CN104392213B (en) * | 2014-11-19 | 2017-12-19 | 郑可尧 | A kind of image information state recognition system suitable for fusion process |
| CN105678295B (en) * | 2016-01-04 | 2019-03-19 | 武汉科技大学 | Gas heating flame method of real-time based on the analysis of ROI the average image |
| CN106846305B (en) * | 2017-01-11 | 2019-09-10 | 华北电力大学 | A kind of boiler combustion stability monitoring method based on the more characteristics of image of flame |
-
2019
- 2019-01-10 CN CN201910023176.1A patent/CN109754019B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002025590A1 (en) * | 2000-09-21 | 2002-03-28 | L'air Liquide, Societe Anonyme A Directoire Et Conseil De Surveillance Pour L'etude Et L'exploitation Des Procedes Georges Claude | Method and device for characterising or controlling temporal fluctuation zones of a scene |
| CN103617635A (en) * | 2013-11-28 | 2014-03-05 | 南京理工大学 | Transient flame detection method based on image processing |
Non-Patent Citations (2)
| Title |
|---|
| Monitoring and controlling the combustion quality in thermal power plant boiler using image processing and robotic arm;P. Hari Krishnan等;《2014 International Conference on Green Computing Communication and Electrical Engineering》;20141016;第1-4页 * |
| 锅炉火焰图像特征及燃烧状态智能监测综述;佘星星 等;《上海电力学院学报》;20100831;第26卷(第4期);第399-405页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109754019A (en) | 2019-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109754019B (en) | Method for continuously monitoring combustion condition of boiler | |
| CN105956618B (en) | Converter steelmaking blowing state identification system and method based on image dynamic and static characteristics | |
| CN109902633A (en) | Accident detection method and device based on the camera supervised video of fixed bit | |
| US7936377B2 (en) | Method and system for optimizing an image for improved analysis of material and illumination image features | |
| US20160260306A1 (en) | Method and device for automated early detection of forest fires by means of optical detection of smoke clouds | |
| CN205538740U (en) | Intelligence timber surface defect detection system | |
| TW201702586A (en) | Optical film defect detection method and system thereof | |
| CN102881106A (en) | Dual-detection forest fire identification system through thermal imaging video and identification method thereof | |
| CN106483143A (en) | A kind of solar energy photovoltaic panel dust stratification on-Line Monitor Device and its detection method | |
| JP2010210318A (en) | Measuring device of dust, and estimation method of generation source | |
| CN112730251B (en) | Device and method for detecting screen color defects | |
| CN111127810A (en) | Automatic alarming method and system for open fire of machine room | |
| CN109035225B (en) | Design quality evaluation method for automobile brake pad appearance quality inspection lighting system | |
| CN108198226B (en) | Ceramic color identification method, electronic equipment, storage medium and device | |
| CN104021576A (en) | Method and system for tracking moving objects in scene | |
| CN116054417B (en) | Monitoring system and method for transformer substation | |
| CN110045242B (en) | Method, system, medium and equipment for monitoring arc light in switch cabinet | |
| CN111626104A (en) | Cable hidden danger point detection method and device based on unmanned aerial vehicle infrared thermal imagery | |
| CN115082504A (en) | Light spot identification method for solar photovoltaic panel | |
| KR100615672B1 (en) | Fire observation system using xy axis projection graph and its fire observation method and computer-readable recording medium to realize fire observation method | |
| JP2009017158A (en) | Camera inspection device | |
| CN103630547B (en) | There is flaw detection method and the pick-up unit thereof of the optical thin film of periodic structure | |
| CN106646677A (en) | Rainfall detecting method and device | |
| CN105516716A (en) | Site test method of video image quality of a closed-loop security and protection system | |
| JPH11284982A (en) | Monitoring device and method |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230116 Address after: 150078 No. 2, Honghu Road, Yingbin Road, Harbin Development Zone, Harbin, Heilongjiang Province Patentee after: Harbin Hongqi Boiler Co.,Ltd. Address before: 510663 No. 59, Zhuji Road, Tianhe District, Guangzhou, Guangdong Patentee before: Guangzhou Yujing Technology Service Co.,Ltd. Effective date of registration: 20230116 Address after: 510663 No. 59, Zhuji Road, Tianhe District, Guangzhou, Guangdong Patentee after: Guangzhou Yujing Technology Service Co.,Ltd. Address before: 066000 No. 438, Hebei Avenue, Qinhuangdao, Hebei Patentee before: Yanshan University |
|
| TR01 | Transfer of patent right |