CN113344909A - Method and device for identifying and displaying coking of flame-permeable high-temperature filter of thermal power boiler - Google Patents
Method and device for identifying and displaying coking of flame-permeable high-temperature filter of thermal power boiler Download PDFInfo
- Publication number
- CN113344909A CN113344909A CN202110747508.8A CN202110747508A CN113344909A CN 113344909 A CN113344909 A CN 113344909A CN 202110747508 A CN202110747508 A CN 202110747508A CN 113344909 A CN113344909 A CN 113344909A
- Authority
- CN
- China
- Prior art keywords
- coking
- image
- thermal power
- temperature filter
- 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.)
- Granted
Links
- 238000004939 coking Methods 0.000 title claims abstract description 287
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000004445 quantitative analysis Methods 0.000 claims abstract description 27
- 238000013528 artificial neural network Methods 0.000 claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 15
- 239000000463 material Substances 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 8
- 239000000571 coke Substances 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 239000002245 particle Substances 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 2
- 230000000149 penetrating effect Effects 0.000 claims 1
- 238000013135 deep learning Methods 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 4
- 238000005235 decoking Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000010224 classification analysis Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Radiation Pyrometers (AREA)
Abstract
The application discloses a method and a device for identifying and displaying coking of a flame-permeable high-temperature filter of a thermal power boiler, wherein the method comprises the steps of preprocessing an acquired coking image of the flame-permeable high-temperature filter of the thermal power boiler; carrying out coking identification based on a neural network prediction algorithm; carrying out quantitative analysis on the identified coking, and calculating the fraction of the coking; when the fraction of coking is larger than a first preset threshold value, early warning is carried out, and when the fraction of coking is larger than a second preset threshold value, intervention measures are taken; indicating the presence of said coking. The method can realize quantitative analysis of coking of the flame-penetrating high-temperature filter of the thermal power boiler, realize classification and display of coking by utilizing coking image recognition based on deep learning, and improve detection precision and efficiency. The device for identifying and displaying the coking of the flame-permeable high-temperature filter of the thermal power boiler has the same advantages as the method.
Description
Technical Field
The invention belongs to the technical field of thermal power plant boiler coking monitoring, and particularly relates to a method and a device for identifying and displaying coking of a flame-permeable high-temperature filter of a thermal power plant boiler.
Background
Coking of the boiler is a common problem in coal-fired thermal power plants, and can destroy normal combustion working conditions, reduce boiler efficiency, destroy normal water circulation, even cause pipe explosion accidents, and cause blockage of a hearth outlet to stop the boiler in serious conditions, thereby affecting the economical efficiency and safety of boiler operation. At present, when a boiler hearth of a thermal power plant is decoked, a professional technician needs to be sent to observe and pre-judge the coking state through a fire observation port, and decoking is carried out through experience.
The boiler coking early warning method based on the convolutional neural network is characterized in that temperature data of a plurality of measuring points in the same time period are collected, image characteristics of the temperature data of the measuring points are obtained through the neural network, whether the measuring points are coked or not is judged, the coking type cannot be judged, the coking state cannot be directly observed, the indirect measurement mode belongs to prediction of small sample data, the coking state and degree are not accurate enough, and visual display cannot be achieved.
Disclosure of Invention
In order to solve the problems, the invention provides a method and a device for identifying and displaying coking of a flame-permeable high-temperature filter of a thermal power boiler, which can realize quantitative analysis of coking and utilize coking image identification based on deep learning to realize classification and display of coking and improve detection precision and efficiency.
The invention provides a method for identifying and displaying coking of a flame-permeable high-temperature filter of a thermal power boiler, which comprises the following steps:
preprocessing the collected flame-penetrating high-temperature filter coking image of the thermal power boiler;
carrying out coking identification based on a neural network prediction algorithm;
carrying out quantitative analysis on the identified coking, and calculating the fraction of the coking;
when the fraction of coking is larger than a first preset threshold value, early warning is carried out, and when the fraction of coking is larger than a second preset threshold value, intervention measures are taken;
indicating the presence of said coking.
Preferably, in the method for identifying and displaying coking of the flame-permeable high-temperature filter of the thermal power boiler, the preprocessing of the acquired coking image includes:
reducing the data amount of the original image based on a weighted average method;
image noise generated by the influence of the environment in the furnace is inhibited based on a median filtering method;
delineating a coking target object based on wavelet transformation;
dividing the original image into a coking image and a background image based on an iterative method;
and carrying out corrosion-first and expansion-second operation on the coking image, eliminating small particle noise and smoothing a coking boundary.
Preferably, in the method for identifying and displaying coking of the fire-penetrating high-temperature filter of the thermal power boiler, the identifying coking based on the neural network prediction algorithm includes:
creating a labeled coking image database, the labels including coke breeches, high temperature coking, other and normal;
segmenting the coking image database, wherein 60% of training set is acquired, and 40% of testing set is acquired;
establishing an enhanced coking image database by setting an image size and turning immediately, loading the enhanced coking image database into an Alex network, and modifying the output classification number of the full-connection layer;
setting learning rate and cycle parameters, and starting training;
reading the coking images in the test set, and performing prediction classification to obtain accuracy information;
the neural network is optimized by optimizing the learning rate and enhancing the distribution of the data set.
Preferably, in the method for identifying and displaying the coking of the flame-permeable high-temperature filter of the thermal power boiler, the quantitatively analyzing the identified coking includes:
selecting a calibration object with a known actual size d;
measuring the pixel numbers D1 and D2 of a calibration material and a coking material in the image, and determining a calibration coefficient D/D1;
and carrying out quantitative calculation on the coking area in the target image.
Preferably, in the method for identifying and displaying coking of the flame-permeable high-temperature filter of the thermal power boiler, the displaying of coking includes:
and displaying a coking image, a coking classification result, a coking quantitative analysis result and a coking treatment suggestion.
The invention provides a thermal power boiler flame penetration high-temperature filter coking identification display device, which comprises:
the pretreatment component is used for pretreating the collected flame-penetrating high-temperature filter coking image of the thermal power boiler;
identification means for identifying coking based on a neural network prediction algorithm;
the analysis and calculation part is used for carrying out quantitative analysis on the identified coking and calculating the fraction of the coking;
the early warning component is used for carrying out early warning when the fraction of coking is greater than a first preset threshold value and taking intervention measures when the fraction of coking is greater than a second preset threshold value;
and the display component is used for displaying the condition of the coking.
Preferably, in the above coking identification and display device for a fire-penetrating high-temperature filter of a thermal power boiler, the preprocessing unit includes:
a data amount reduction unit for reducing an amount of original image data based on a weighted average method;
the noise suppression unit is used for suppressing image noise generated by the influence of the environment in the furnace based on a median filtering method;
the mapping unit is used for mapping out the coking target object based on wavelet transformation;
a background distinguishing unit for distinguishing the original image into a coke and a background based on an iterative method;
and the boundary smoothing unit is used for carrying out corrosion-first and expansion-second operation on the coking image, eliminating small particle noise and smoothing the coking boundary.
Preferably, in the device for identifying and displaying coking of a fire-through high-temperature filter of a thermal power boiler, the identifying means includes:
the database creating unit is used for creating a coking image database with labels, wherein the labels comprise a coke block, high-temperature coking, other and normal;
the segmentation unit is used for segmenting the coking image database, wherein the training set is 60 percent, and the testing set is 40 percent;
the enhancement database creating unit is used for creating an enhancement coking image database in a mode of setting the image size and turning immediately, loading the enhancement coking image database into an Alex network and modifying the output classification number of the full-connection layer;
the training unit is used for setting learning rate and cycle parameters and starting training;
the prediction classification unit is used for reading the coking images in the test set, performing prediction classification and obtaining accuracy information;
and the neural network optimization unit is used for optimizing the neural network in a mode of optimizing the learning rate and enhancing the data set distribution.
Preferably, in the above thermal power boiler flame-penetrating high-temperature filter coking identification display device, the analysis calculation unit includes:
the calibration object selecting unit is used for selecting a calibration object with a known actual size d;
the pixel number measuring unit is used for measuring the pixel numbers D1 and D2 of the calibration materials and the coking materials in the image and determining a calibration coefficient D/D1;
and the coking area calculating unit is used for quantitatively calculating the coking area in the target image.
Preferably, in the device for identifying and displaying the coking of the flame-permeable high-temperature filter of the thermal power boiler, the display part is specifically used for displaying a coking image, a coking classification result, a coking quantitative analysis result and a coking treatment suggestion.
According to the above description, the method for identifying and displaying coking of the flame-permeable high-temperature filter of the thermal power boiler provided by the invention comprises the steps of preprocessing the collected coking image of the flame-permeable high-temperature filter of the thermal power boiler; carrying out coking identification based on a neural network prediction algorithm; carrying out quantitative analysis on the identified coking, and calculating the fraction of the coking; when the fraction of coking is larger than a first preset threshold value, early warning is carried out, and when the fraction of coking is larger than a second preset threshold value, intervention measures are taken; the situation of the coking is displayed, so that quantitative analysis of the coking can be realized, the coking image recognition based on deep learning is utilized, the classification and display of the coking are realized, and the detection precision and efficiency are improved. The device for identifying and displaying the coking of the flame-permeable high-temperature filter of the thermal power boiler has the same advantages as the method.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in 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 embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic diagram of an embodiment of a flame-transparent high-temperature filter coking identification display method and device for a thermal power boiler, provided by the invention;
FIG. 2 is a schematic diagram of a visual software module adopted by the flame penetration high-temperature filter coking identification display method of the thermal power boiler;
fig. 3 is a schematic diagram of an embodiment of a flame-permeable high-temperature filter coking identification display device for a thermal power boiler provided by the invention.
Detailed Description
The core of the invention is to provide a method and a device for identifying and displaying coking of the flame-permeable high-temperature filter of the thermal power boiler, which can realize quantitative analysis of coking of the flame-permeable high-temperature filter of the thermal power boiler and utilize coking image identification based on deep learning to realize classification and display of coking and improve detection precision and efficiency.
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.
Fig. 1 shows an embodiment of a method for identifying and displaying coking of a flame-permeable high-temperature filter of a thermal power boiler, where fig. 1 is a schematic diagram of an embodiment of a method for identifying and displaying coking of a flame-permeable high-temperature filter of a thermal power boiler, according to the present invention, and the method includes the following steps:
s1: preprocessing the collected flame-penetrating high-temperature filter coking image of the thermal power boiler;
it is noted that after pretreatment, the coking part of the flame-permeable high-temperature filter of the thermal power boiler can be more obviously prominent and easily identified, and the identification efficiency is improved.
S2: carrying out coking identification based on a neural network prediction algorithm;
specifically, the neural network prediction algorithm can be trained based on the Alex network in MATLAB.
S3: carrying out quantitative analysis on the identified coking, and calculating the fraction of the coking;
specifically, the coking state can be classified according to the coking type and the coking area, and for example, the coking state can be classified into red, orange, yellow and green grades, wherein red represents danger and green represents safety.
S4: when the fraction of coking is larger than a first preset threshold value, early warning is carried out, and when the fraction of coking is larger than a second preset threshold value, intervention measures are taken;
specifically, whether an early warning is given or not can be judged according to the analyzed fraction of the coking, so that an operator can conveniently respond to the coking condition in time, and the situation is prevented from being more serious due to overlong time, and the situation can be avoided, wherein the situation can be set to be that manual intervention is required when the time is higher than 70 minutes, and intervention measures are required when the time is higher than 90 minutes, so that the severe conditions such as overlarge coking are avoided.
S5: indicating the presence of coking.
The real-time coking condition can be displayed by adopting an upper computer screen, and various parameters, images, analysis results and the like of coking can be displayed at the same time, so that an operator can better master the real-time coking condition.
According to the above description, in the embodiment of the method for identifying and displaying coking of the flame-permeable high-temperature filter of the thermal power boiler, the acquired coking image of the flame-permeable high-temperature filter of the thermal power boiler is preprocessed; carrying out coking identification based on a neural network prediction algorithm; carrying out quantitative analysis on the identified coking, and calculating the fraction of the coking; when the fraction of coking is larger than a first preset threshold value, early warning is carried out, and when the fraction of coking is larger than a second preset threshold value, intervention measures are taken; the situation of coking is displayed, so that quantitative analysis of coking and coking image recognition based on deep learning can be realized, the classification and display of coking are realized, and the detection precision and efficiency are improved.
In a specific embodiment of the above method for identifying and displaying coking of the flame-permeable high-temperature filter of the thermal power boiler, the preprocessing the collected coking image of the flame-permeable high-temperature filter of the thermal power boiler may include:
the data volume of the original image is reduced based on a weighted average method, namely a graying process, so that the processing speed can be increased;
image noise generated by the influence of the environment in the furnace is inhibited based on a median filtering method, namely a smooth denoising process, so that the image quality can be improved;
based on wavelet transformation, a coking target object is sketched out, so that the characteristic of the coking target object is more obvious, namely an edge detection process;
dividing an original image into coking and background objects based on an iterative method, namely a binarization process;
the coking image is subjected to corrosion operation and then expansion operation, so that small particle noise is eliminated, and a coking boundary is smoothed, namely an opening operation process.
In another specific embodiment of the above method for identifying and displaying coking of the fire-penetrating high-temperature filter of the thermal power boiler, the identifying coking based on the neural network prediction algorithm may include the following steps:
creating a labeled coking image database, the labels including coke blocks, high temperature coking, others and normal;
segmenting a coking image database, wherein 60% of a training set is acquired, and 40% of a testing set is acquired;
establishing an enhanced coking image database by setting an image size and turning immediately, loading the enhanced coking image database into an Alex network, and modifying the output classification number of the full-connection layer;
setting learning rate and cycle parameters, starting training, and storing the trained network;
reading the coking images in the test set, and performing prediction classification to obtain accuracy information;
the neural network is optimized by optimizing the learning rate and enhancing the data set distribution so as to continuously improve the accuracy.
In another specific embodiment of the above method for identifying and displaying the coking of the fire-penetrating high-temperature filter of the thermal power boiler, the quantitatively analyzing the identified coking may include:
selecting a calibration object with a known actual size d;
measuring the pixel numbers D1 and D2 of a calibration material and a coking material in the image, and determining a calibration coefficient D/D1;
and carrying out quantitative calculation on the coking area in the target image.
That is to say, with this kind of mode just can discern the specific size of coking, then send out the early warning after reaching certain threshold value, make timely processing, avoid the coking to cause bigger risk.
In a preferred embodiment of the above method for identifying and displaying coking of the flame-penetrating high-temperature filter of the thermal power boiler, the displaying of coking may include:
and displaying a coking image, a coking classification result, a coking quantitative analysis result and a coking treatment suggestion.
Specifically, two interfaces may be displayed in this step: the method comprises the following steps that firstly, an image processing interface comprises various image processing algorithms to be selected, the area of a focal block is calculated, and the contents of an original image, a processed image and the like are displayed; and the other is a fault diagnosis interface which comprises the display of the identification coking image, the display of the classification result of the coking image, the display of the diagnosis result, the display of a score, the display of an alarm indicator light, the display of a processing method suggestion and the like.
Referring to fig. 2, fig. 2 is a schematic diagram of a visualized software module adopted in a method for identifying and displaying the coking of a flame-permeable high-temperature filter of a thermal power boiler, which includes a coking image reading module, a coking image processing module, a coking image classification and identification module, a coking image display module, a coking image quantitative analysis module, an alarm module, a result display module and a suggestion prompt module, wherein after the coking image is analyzed and processed by the coking image reading module and the image processing module, the coking image display module respectively displays an original image and a processed image in real time and visually, and meanwhile, the coking image is subjected to classification and quantitative analysis by the coking image classification and identification module and the coking quantitative analysis module, the result is displayed by the classification result display module and the quantitative analysis result display module, and the alarm module performs threshold judgment according to the classification result and the quantitative analysis result, And scoring, if the score exceeds a set threshold value, a red light is turned on to give an alarm, another image window is started at the moment, the coking single-frame image at the moment is displayed in a home page in an amplifying mode and automatically stored in a coking image folder, if the score does not exceed the threshold value, the alarm module does not make subsequent response, and the suggestion module also makes corresponding operation suggestion according to the result of coking classification identification and the result of quantitative analysis.
In conclusion, by using the method for identifying and displaying the coking of the flame-permeable high-temperature filter of the thermal power boiler, the coking can be identified, classified and quantitatively analyzed, a basis is provided for formulating a decoking strategy, human factors are overcome, and the safe and economic operation of the boiler is ensured.
Fig. 3 shows an embodiment of a device for identifying and displaying coking of a flame-permeable high-temperature filter of a thermal power boiler, where fig. 3 is a schematic diagram of an embodiment of a device for identifying and displaying coking of a flame-permeable high-temperature filter of a thermal power boiler, which is provided by the present invention, and the device can be integrated in an upper computer, and includes:
the pretreatment component 301 is used for pretreating the collected flame-penetrating high-temperature filter coking image of the thermal power boiler, and it needs to be noted that after pretreatment, the coking part can be more obvious and easily identified, and the identification efficiency is improved;
an identification component 302, configured to perform coking identification based on a neural network prediction algorithm, specifically, the neural network prediction algorithm may be trained based on Alex networks in MATLAB;
the analysis and calculation part 303 is configured to perform quantitative analysis on the identified coking and calculate a fraction of the coking, specifically, the coking state may be scored according to the coking type and the coking area, for example, the coking state may be classified into red, orange, yellow, and green levels, where red indicates danger and green indicates safety;
the early warning component 304 is used for giving an early warning when the fraction of the coking is greater than a first preset threshold value and taking an intervention measure when the fraction of the coking is greater than a second preset threshold value, and specifically, whether the early warning is given out can be judged according to the fraction of the coking analyzed, so that an operator can timely react to the coking condition to avoid the situation from being more serious due to overlong time, and the situation can be avoided from being more serious, wherein the situation can be set to be, but not limited to, that manual intervention is required when the fraction is greater than 70 minutes, and the intervention measure is required when the fraction is greater than 90 minutes, so that the severe conditions such as overlarge coking are avoided;
the display part 305 is used for displaying the condition of the coking, and specifically, but not limited to, an upper computer screen is used for displaying the condition of the coking, and various parameters, images, analysis results and the like of the coking can be displayed at the same time, so that an operator can better master the real-time condition of the coking.
In a specific embodiment of the above fire-penetrating high-temperature filter coking identification display device for a thermal power boiler, the preprocessing component may include:
a data amount reducing unit for reducing the data amount of the original image based on a weighted average method, which is a graying process, so that the processing speed can be increased;
a noise suppression unit for suppressing the image noise generated by the environment influence in the furnace based on the median filtering method, namely a smooth denoising process, thereby improving the image quality
The mapping unit is used for mapping the coking target object based on wavelet transformation, namely an edge detection process;
the background distinguishing unit is used for dividing the original image into a coking object and a background object based on an iteration method, namely a binarization process;
and the boundary smoothing unit is used for carrying out corrosion-first and expansion-second operation on the coking image, eliminating small particle noise and smoothing the coking boundary, namely an opening operation process.
In another specific embodiment of the above fire-penetrating high-temperature filter coking identification display device for a thermal power boiler, the identification component may include:
the database creating unit is used for creating a coking image database with labels, and the labels comprise a coke block, high-temperature coking, other and normal;
the segmentation unit is used for segmenting the coking image database, the training set is 60 percent, and the testing set is 40 percent;
the enhancement database creating unit is used for creating an enhancement coking image database in a mode of setting the image size and turning immediately, loading the enhancement coking image database into an Alex network and modifying the output classification number of the full-connection layer;
the training unit is used for setting learning rate and cycle parameters and starting training;
the prediction classification unit is used for reading the coking images in the test set, performing prediction classification and obtaining accuracy information;
and the neural network optimization unit is used for optimizing the neural network in a mode of optimizing the learning rate and enhancing the data set distribution.
In another specific embodiment of the above fire-penetrating high-temperature filter coking identification display device for a thermal power boiler, the analyzing and calculating component may include:
the calibration object selecting unit is used for selecting a calibration object with a known actual size d;
the pixel number measuring unit is used for measuring the pixel numbers D1 and D2 of the calibration materials and the coking materials in the image and determining a calibration coefficient D/D1;
and the coking area calculating unit is used for quantitatively calculating the coking area in the target image.
That is to say, with this kind of mode just can discern the specific size of coking, then send out the early warning after reaching certain threshold value, make timely processing, avoid the coking to cause bigger risk.
In a preferred embodiment of the above thermal power boiler flame-penetrating high-temperature filter coking identification display device, the display unit may be specifically configured to display a coking image, a coking classification result, a coking quantitative analysis result, and a coking treatment suggestion.
Two interfaces can be shown: the method comprises the following steps that firstly, an image processing interface comprises various image processing algorithms to be selected, the area of a focal block is calculated, and the contents of an original image, a processed image and the like are displayed; and the other is a fault diagnosis interface which comprises the display of the identification coking image, the display of the classification result of the coking image, the display of the diagnosis result, the display of a score, the display of an alarm indicator light, the display of a processing method suggestion and the like.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for identifying and displaying coking of a flame-permeable high-temperature filter of a thermal power boiler is characterized by comprising the following steps:
preprocessing the collected flame-penetrating high-temperature filter coking image of the thermal power boiler;
carrying out coking identification based on a neural network prediction algorithm;
carrying out quantitative analysis on the identified coking, and calculating the fraction of the coking;
when the fraction of coking is larger than a first preset threshold value, early warning is carried out, and when the fraction of coking is larger than a second preset threshold value, intervention measures are taken;
indicating the presence of said coking.
2. The method for identifying and displaying the coking of the flame-permeable high-temperature filter of the thermal power boiler according to claim 1, wherein the preprocessing of the collected coking image of the flame-permeable high-temperature filter of the thermal power boiler comprises:
reducing the data amount of the original image based on a weighted average method;
image noise generated by the influence of the environment in the furnace is inhibited based on a median filtering method;
delineating a coking target object based on wavelet transformation;
dividing the original image into a coking image and a background image based on an iterative method;
and carrying out corrosion-first and expansion-second operation on the coking image, eliminating small particle noise and smoothing a coking boundary.
3. The method for identifying and displaying the coking of the fire-penetrating high-temperature filter of the thermal power boiler according to claim 2, wherein the identifying the coking based on the neural network prediction algorithm comprises:
creating a labeled coking image database, the labels including coke breeches, high temperature coking, other and normal;
segmenting the coking image database, wherein 60% of training set is acquired, and 40% of testing set is acquired;
establishing an enhanced coking image database by setting an image size and turning immediately, loading the enhanced coking image database into an Alex network, and modifying the output classification number of the full-connection layer;
setting learning rate and cycle parameters, and starting training;
reading the coking images in the test set, and performing prediction classification to obtain accuracy information;
the neural network is optimized by optimizing the learning rate and enhancing the distribution of the data set.
4. The method for identifying and displaying the coking of the through flame high-temperature filter of the thermal power boiler according to claim 3, wherein the quantitative analysis of the identified coking comprises the following steps:
selecting a calibration object with a known actual size d;
measuring the pixel numbers D1 and D2 of a calibration material and a coking material in the image, and determining a calibration coefficient D/D1;
and carrying out quantitative calculation on the coking area in the target image.
5. The method for identifying and displaying the coking of the flame-permeable high-temperature filter of the thermal power boiler according to claim 4, wherein the displaying the coking comprises:
and displaying a coking image, a coking classification result, a coking quantitative analysis result and a coking treatment suggestion.
6. The utility model provides a fire penetrating high temperature filter coking of thermal power boiler discerns display device which characterized in that includes:
the pretreatment component is used for pretreating the collected flame-penetrating high-temperature filter coking image of the thermal power boiler;
identification means for identifying coking based on a neural network prediction algorithm;
the analysis and calculation part is used for carrying out quantitative analysis on the identified coking and calculating the fraction of the coking;
the early warning component is used for carrying out early warning when the fraction of coking is greater than a first preset threshold value and taking intervention measures when the fraction of coking is greater than a second preset threshold value;
and the display component is used for displaying the condition of the coking.
7. The fire-penetrating high-temperature filter coking identification display device for thermal power boilers as claimed in claim 6, wherein the preprocessing part comprises:
a data amount reduction unit for reducing an amount of original image data based on a weighted average method;
the noise suppression unit is used for suppressing image noise generated by the influence of the environment in the furnace based on a median filtering method;
the mapping unit is used for mapping out the coking target object based on wavelet transformation;
a background distinguishing unit for distinguishing the original image into a coke and a background based on an iterative method;
and the boundary smoothing unit is used for carrying out corrosion-first and expansion-second operation on the coking image, eliminating small particle noise and smoothing the coking boundary.
8. The fire-penetrating high-temperature filter coking identification display device for thermal power boilers as claimed in claim 7, wherein the identification means comprises:
the database creating unit is used for creating a coking image database with labels, wherein the labels comprise a coke block, high-temperature coking, other and normal;
the segmentation unit is used for segmenting the coking image database, wherein the training set is 60 percent, and the testing set is 40 percent;
the enhancement database creating unit is used for creating an enhancement coking image database in a mode of setting the image size and turning immediately, loading the enhancement coking image database into an Alex network and modifying the output classification number of the full-connection layer;
the training unit is used for setting learning rate and cycle parameters and starting training;
the prediction classification unit is used for reading the coking images in the test set, performing prediction classification and obtaining accuracy information;
and the neural network optimization unit is used for optimizing the neural network in a mode of optimizing the learning rate and enhancing the data set distribution.
9. The fire-penetrating high-temperature filter coking identification display device for thermal power boilers according to claim 8, wherein the analysis calculation means includes:
the calibration object selecting unit is used for selecting a calibration object with a known actual size d;
the pixel number measuring unit is used for measuring the pixel numbers D1 and D2 of the calibration materials and the coking materials in the image and determining a calibration coefficient D/D1;
and the coking area calculating unit is used for quantitatively calculating the coking area in the target image.
10. The fire-penetrating flame high-temperature filter coking identification display device of the thermal power boiler according to claim 9, wherein the display unit is specifically used for displaying coking images, coking classification results, coking quantitative analysis results and coking treatment suggestions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110747508.8A CN113344909B (en) | 2021-07-01 | 2021-07-01 | Method and device for identifying and displaying flame penetration height Wen Lvjing coking of thermal power boiler |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110747508.8A CN113344909B (en) | 2021-07-01 | 2021-07-01 | Method and device for identifying and displaying flame penetration height Wen Lvjing coking of thermal power boiler |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113344909A true CN113344909A (en) | 2021-09-03 |
| CN113344909B CN113344909B (en) | 2023-12-08 |
Family
ID=77482194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110747508.8A Active CN113344909B (en) | 2021-07-01 | 2021-07-01 | Method and device for identifying and displaying flame penetration height Wen Lvjing coking of thermal power boiler |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113344909B (en) |
Citations (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000132080A (en) * | 1998-10-22 | 2000-05-12 | Kawasaki Heavy Ind Ltd | Fire simulation device for fire extinguishing training |
| JP2009236391A (en) * | 2008-03-27 | 2009-10-15 | Japan Atom Power Co Ltd:The | High temperature atmosphere furnace observation device |
| CN101655700A (en) * | 2009-09-17 | 2010-02-24 | 同济大学 | Topographic control system and method of waste pyrolysis |
| CN101688127A (en) * | 2007-06-04 | 2010-03-31 | 埃克森美孚化学专利公司 | A process for pyrolyzing a hydrocarbon feedstock pyrolysis reactor system |
| CN101799661A (en) * | 2007-01-10 | 2010-08-11 | 株式会社日立制作所 | The training operator device of the control device of boiler plant and boiler plant |
| US20100332474A1 (en) * | 2009-06-25 | 2010-12-30 | University Of Tennessee Research Foundation | Method and apparatus for predicting object properties and events using similarity-based information retrieval and model |
| CN102425807A (en) * | 2011-11-23 | 2012-04-25 | 华北电力大学（保定） | Feedforward-feedback composite optimization control method for pulverized coal fired boiler combustion |
| CN102707762A (en) * | 2012-06-04 | 2012-10-03 | 同济大学 | Heating power control method for waste high polymer material pyrolysis |
| CN202692120U (en) * | 2012-07-09 | 2013-01-23 | 大唐双鸭山热电有限公司 | Visual monitoring control module in boiler hearth |
| CN105046868A (en) * | 2015-06-16 | 2015-11-11 | 苏州华启智能科技股份有限公司 | Fire early warning method based on infrared thermal imager in narrow environment |
| CN105423273A (en) * | 2015-12-15 | 2016-03-23 | 天津鹰麟节能科技发展有限公司 | Spectroscopic boiler anti-coking system and control method |
| CN107559878A (en) * | 2017-09-25 | 2018-01-09 | 华能国际电力股份有限公司日照电厂 | The method and device of fire coal management |
| CN109063412A (en) * | 2018-08-27 | 2018-12-21 | 浙江大学 | Source Data Fusion System and method for the assessment of coal pyrolysis in plasma producing acetylene reactiveness |
| CN109145689A (en) * | 2017-06-28 | 2019-01-04 | 南京理工大学 | A kind of robot fire detection method |
| CN208421626U (en) * | 2018-07-23 | 2019-01-22 | 合肥金星机电科技发展有限公司 | Ethane cracking furnace burning process monitors system |
| CN109934417A (en) * | 2019-03-26 | 2019-06-25 | 国电民权发电有限公司 | Boiler coke method for early warning based on convolutional neural networks |
| CN109977838A (en) * | 2019-03-20 | 2019-07-05 | 西安理工大学 | A kind of flame combustion state detection method |
| CN110197199A (en) * | 2019-04-17 | 2019-09-03 | 广东石油化工学院 | Embedded DCNN and the weight tube temperature degree recognition methods of the pyrolysis furnace of edge calculations |
| CN110222814A (en) * | 2019-04-25 | 2019-09-10 | 广东石油化工学院 | The pipe recognition methods again of Ethylene Cracking Furnace Tubes based on embedded DCNN |
| CN110222633A (en) * | 2019-06-04 | 2019-09-10 | 北京工业大学 | City solid waste burning process combusts operating mode's switch method based on flame image color feature extracted |
| CN110419018A (en) * | 2016-12-29 | 2019-11-05 | 奇跃公司 | The automatic control of wearable display device based on external condition |
| CN110633675A (en) * | 2019-09-18 | 2019-12-31 | 东北大学 | System and method for identifying fire in video based on convolutional neural network |
| CN111062293A (en) * | 2019-12-10 | 2020-04-24 | 太原理工大学 | Unmanned aerial vehicle forest flame identification method based on deep learning |
| CN111095261A (en) * | 2017-04-27 | 2020-05-01 | 视网膜病答案有限公司 | Automatic analysis system and method for fundus images |
| CN111368771A (en) * | 2020-03-11 | 2020-07-03 | 四川路桥建设集团交通工程有限公司 | Tunnel fire early warning method and device based on image processing, computer equipment and computer readable storage medium |
| CN111473358A (en) * | 2020-05-09 | 2020-07-31 | 中国华能集团有限公司 | Hearth flame television decoking device and control method thereof |
| CN111882810A (en) * | 2020-07-31 | 2020-11-03 | 广州市微智联科技有限公司 | Fire identification and early warning method and system |
| CN112080745A (en) * | 2020-09-02 | 2020-12-15 | 新疆金泰非晶科技有限公司 | Composite coating containing amorphous alloy identification layer and preparation method and application thereof |
| CN112521955A (en) * | 2020-11-04 | 2021-03-19 | 中南大学 | Coke cake center temperature detection method and system |
| CN112784405A (en) * | 2021-01-06 | 2021-05-11 | 润电能源科学技术有限公司 | Boiler slagging prediction method based on numerical simulation and related device |
-
2021
- 2021-07-01 CN CN202110747508.8A patent/CN113344909B/en active Active
Patent Citations (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000132080A (en) * | 1998-10-22 | 2000-05-12 | Kawasaki Heavy Ind Ltd | Fire simulation device for fire extinguishing training |
| CN101799661A (en) * | 2007-01-10 | 2010-08-11 | 株式会社日立制作所 | The training operator device of the control device of boiler plant and boiler plant |
| CN101688127A (en) * | 2007-06-04 | 2010-03-31 | 埃克森美孚化学专利公司 | A process for pyrolyzing a hydrocarbon feedstock pyrolysis reactor system |
| JP2009236391A (en) * | 2008-03-27 | 2009-10-15 | Japan Atom Power Co Ltd:The | High temperature atmosphere furnace observation device |
| US20100332474A1 (en) * | 2009-06-25 | 2010-12-30 | University Of Tennessee Research Foundation | Method and apparatus for predicting object properties and events using similarity-based information retrieval and model |
| CN101655700A (en) * | 2009-09-17 | 2010-02-24 | 同济大学 | Topographic control system and method of waste pyrolysis |
| CN102425807A (en) * | 2011-11-23 | 2012-04-25 | 华北电力大学（保定） | Feedforward-feedback composite optimization control method for pulverized coal fired boiler combustion |
| CN102707762A (en) * | 2012-06-04 | 2012-10-03 | 同济大学 | Heating power control method for waste high polymer material pyrolysis |
| CN202692120U (en) * | 2012-07-09 | 2013-01-23 | 大唐双鸭山热电有限公司 | Visual monitoring control module in boiler hearth |
| CN105046868A (en) * | 2015-06-16 | 2015-11-11 | 苏州华启智能科技股份有限公司 | Fire early warning method based on infrared thermal imager in narrow environment |
| CN105423273A (en) * | 2015-12-15 | 2016-03-23 | 天津鹰麟节能科技发展有限公司 | Spectroscopic boiler anti-coking system and control method |
| CN110419018A (en) * | 2016-12-29 | 2019-11-05 | 奇跃公司 | The automatic control of wearable display device based on external condition |
| CN111095261A (en) * | 2017-04-27 | 2020-05-01 | 视网膜病答案有限公司 | Automatic analysis system and method for fundus images |
| CN109145689A (en) * | 2017-06-28 | 2019-01-04 | 南京理工大学 | A kind of robot fire detection method |
| CN107559878A (en) * | 2017-09-25 | 2018-01-09 | 华能国际电力股份有限公司日照电厂 | The method and device of fire coal management |
| CN208421626U (en) * | 2018-07-23 | 2019-01-22 | 合肥金星机电科技发展有限公司 | Ethane cracking furnace burning process monitors system |
| CN109063412A (en) * | 2018-08-27 | 2018-12-21 | 浙江大学 | Source Data Fusion System and method for the assessment of coal pyrolysis in plasma producing acetylene reactiveness |
| CN109977838A (en) * | 2019-03-20 | 2019-07-05 | 西安理工大学 | A kind of flame combustion state detection method |
| CN109934417A (en) * | 2019-03-26 | 2019-06-25 | 国电民权发电有限公司 | Boiler coke method for early warning based on convolutional neural networks |
| CN110197199A (en) * | 2019-04-17 | 2019-09-03 | 广东石油化工学院 | Embedded DCNN and the weight tube temperature degree recognition methods of the pyrolysis furnace of edge calculations |
| CN110222814A (en) * | 2019-04-25 | 2019-09-10 | 广东石油化工学院 | The pipe recognition methods again of Ethylene Cracking Furnace Tubes based on embedded DCNN |
| CN110222633A (en) * | 2019-06-04 | 2019-09-10 | 北京工业大学 | City solid waste burning process combusts operating mode's switch method based on flame image color feature extracted |
| CN110633675A (en) * | 2019-09-18 | 2019-12-31 | 东北大学 | System and method for identifying fire in video based on convolutional neural network |
| CN111062293A (en) * | 2019-12-10 | 2020-04-24 | 太原理工大学 | Unmanned aerial vehicle forest flame identification method based on deep learning |
| CN111368771A (en) * | 2020-03-11 | 2020-07-03 | 四川路桥建设集团交通工程有限公司 | Tunnel fire early warning method and device based on image processing, computer equipment and computer readable storage medium |
| CN111473358A (en) * | 2020-05-09 | 2020-07-31 | 中国华能集团有限公司 | Hearth flame television decoking device and control method thereof |
| CN111882810A (en) * | 2020-07-31 | 2020-11-03 | 广州市微智联科技有限公司 | Fire identification and early warning method and system |
| CN112080745A (en) * | 2020-09-02 | 2020-12-15 | 新疆金泰非晶科技有限公司 | Composite coating containing amorphous alloy identification layer and preparation method and application thereof |
| CN112521955A (en) * | 2020-11-04 | 2021-03-19 | 中南大学 | Coke cake center temperature detection method and system |
| CN112784405A (en) * | 2021-01-06 | 2021-05-11 | 润电能源科学技术有限公司 | Boiler slagging prediction method based on numerical simulation and related device |
Non-Patent Citations (5)
| Title |
|---|
| HE. K: "Guided Image Filtering", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS & MACHINE INTELLIGENCE》, pages 1397 - 1409 * |
| 常锐;裴海龙;: "基于形态学的快速图像搜索与识别算法", 计算机工程与设计, no. 07, pages 93 - 95 * |
| 王秀林,孔令君,姜仕涛,张竟思,付全方,张世荣,杨启璋: "锅炉性能优化系统的应用试验研究", 中国电力, no. 12, pages 49 - 52 * |
| 陈晓峰;王士同;曹苏群;崔运静;马培勇;仇性启;: "基于模糊聚类的稳健支撑向量回归机及火焰图像处理", 中国图象图形学报, no. 03, pages 92 - 99 * |
| 陈鑫;刘利;徐威;陈啸;: "大数据技术应用于火电机组深度调峰的研究", 科技创新与应用, no. 28, pages 156 - 157 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113344909B (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112581430B (en) | Deep learning-based aero-engine nondestructive testing method, device, equipment and storage medium | |
| CN106568783A (en) | Hardware part defect detecting system and method | |
| CN106874658A (en) | A kind of medical insurance fraud recognition methods based on Principal Component Analysis Algorithm | |
| US20220300809A1 (en) | Data generation system, learning apparatus, data generation apparatus, data generation method, and computer-readable storage medium storing a data generation program | |
| CN114581764B (en) | Underground structure crack disease discriminating method based on deep learning algorithm | |
| CN116542978B (en) | Quality detection method and device for FISH probe | |
| JPWO2020085327A1 (en) | Diagnostic device and diagnostic method | |
| CN107610119A (en) | The accurate detection method of steel strip surface defect decomposed based on histogram | |
| CN107576660B (en) | A kind of double yellow duck egg Automatic Visual Inspection method based on apart from contour | |
| CN112818806A (en) | Transformer substation inspection robot auxiliary navigation method based on deep learning | |
| CN117314826A (en) | Performance detection method of display screen | |
| CN113344909B (en) | Method and device for identifying and displaying flame penetration height Wen Lvjing coking of thermal power boiler | |
| CN113283276A (en) | Linkage thermal imaging self-learning fire point detection method and system | |
| CN113836813B (en) | Blast furnace tuyere water leakage detection method based on data analysis | |
| CN105718881A (en) | Zero-illuminance environment smoke monitoring method based on infrared video gray scale image | |
| CN116342932A (en) | Image processing-based garbage incinerator combustion state diagnosis method and system | |
| CN117455828A (en) | Combustion quality detection method based on MLP neural network | |
| CN113283322A (en) | Livestock trauma detection method, device, equipment and storage medium | |
| CN106872045A (en) | With infrared image temperature difference monitoring and evaluation crops early disease and its method for degree | |
| CN118090908B (en) | Automatic flaw detection system for annular forging | |
| CN118587829B (en) | Distributed photovoltaic fire disaster early warning method and system | |
| CN117853783B (en) | Single board defect identification method and system based on deep learning | |
| CN118409155B (en) | Automatic detection system for building electrical safety | |
| CN117605627B (en) | System and method for detecting oil leakage of core body of wind power gear box cooler | |
| CN117173141A (en) | Smelting observation system based on flame image characteristics |
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 |