CN114937036A - Blast furnace equipment operation evaluation method and system based on artificial intelligence - Google Patents
Blast furnace equipment operation evaluation method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN114937036A CN114937036A CN202210844908.5A CN202210844908A CN114937036A CN 114937036 A CN114937036 A CN 114937036A CN 202210844908 A CN202210844908 A CN 202210844908A CN 114937036 A CN114937036 A CN 114937036A
- Authority
- CN
- China
- Prior art keywords
- combustion
- area
- blast furnace
- images
- combustion zone
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 70
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 25
- 238000002485 combustion reaction Methods 0.000 claims abstract description 234
- 230000008859 change Effects 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 24
- 230000006870 function Effects 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 15
- 239000000126 substance Substances 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000004422 calculation algorithm Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000012549 training Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000007621 cluster analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 210000000038 chest Anatomy 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the technical field of artificial intelligence, in particular to a blast furnace equipment operation evaluation method and a blast furnace equipment operation evaluation system based on artificial intelligence, which comprise the following steps: the method comprises the steps of obtaining N images of the blast furnace to be detected at different moments, obtaining a combustion area and an unburned area in the N images according to the gray value of each pixel point in the N images, and determining fluctuation index values, effective combustion area abundance index values, effective combustion area temperature evaluation index values and combustion change rate of the blast furnace to be detected of the combustion area in the N images according to the combustion area and the unburned area in the N images, so that the operation state of the blast furnace to be detected is obtained. The invention can obtain the running state index in the blast furnace in real time through the camera, so as to obtain the running state in the blast furnace at any time and improve the detection real-time performance of the running state of the blast furnace equipment.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a blast furnace equipment operation evaluation method and system based on artificial intelligence.
Background
In industrial production, blast furnace equipment has the advantages of good production economic index, simple process, large production capacity, high labor production efficiency, low energy consumption and the like, so the blast furnace equipment is applied to the field of producing various energy sources, for enterprises applying blast furnace production, the quality of blast furnace operation directly relates to the benefit of the enterprises, and whether the blast furnace can operate with high efficiency and long service life is more and more emphasized by the enterprises for blast furnace production in various countries.
At the enterprise of domestic and foreign applied blast furnace at the operation in-process, the industrial blast furnace has the condition such as air supply outlet is obstructed, factors such as buggy composition is not up to standard and operating personnel's improper operation, leads to local or flameout completely in the blast furnace thorax, if this moment still constantly transport the buggy toward the blast furnace in, will cause the inhomogeneous accident of flame burning in the blast furnace, simultaneously, if the inside flame of blast furnace is crossed the burning and can lead to high furnace inside temperature too high, will lead to blast furnace explosion scheduling problem. The traditional method for manually observing the combustion condition in the blast furnace has the disadvantages of great harm to human bodies, strong subjectivity of human eye observation, low accuracy of evaluation results, low detection efficiency and poor real-time performance.
Disclosure of Invention
The invention aims to provide a blast furnace equipment operation evaluation method and system based on artificial intelligence, which are used for solving the problem of poor real-time performance of the traditional method for manually observing the operation condition of a blast furnace.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
the invention provides a blast furnace equipment operation evaluation method based on artificial intelligence, which comprises the following steps:
acquiring N images of the blast furnace to be detected at different moments, and obtaining a combustion area and an unburned area in the N images according to the gray value of each pixel point in the N images;
determining the centroid coordinate of the unburned region and the area, centroid coordinate and edge length of the combustion region according to the combustion region and the unburned region in the N images, and further obtaining the fluctuation index value of the combustion region in the N images;
calculating the brightness value and the saturation of each pixel point of the combustion area in the N images so as to determine the temperature evaluation index of each pixel point of the combustion area, and further obtain the effective combustion area abundance index value and the effective combustion area temperature evaluation index value of the combustion area in the N images;
obtaining the combustion change rate of the blast furnace to be detected according to the brightness values of all pixel points in the combustion area of the N images;
and obtaining the running state in the blast furnace to be detected according to the fluctuation index value, the effective combustion area abundance index value, the effective combustion area temperature evaluation index value and the combustion change rate of the blast furnace to be detected in the N images.
Further, the step of obtaining the burned area and the unburned area in the N images includes:
respectively carrying out window area division on the N images to obtain each window area of the N images;
calculating the gray level change rate and the gray level mean value in each window region of the N images according to the gray level value of each pixel point in the N images, thereby obtaining each window feature vector of the N images;
and clustering the characteristic vectors of the windows of the N images respectively, and determining a combustion window area and an unburned window area in each window area according to a clustering result so as to obtain the combustion area and the unburned area in the N images.
Further, the calculation formula of the fluctuation index value of the combustion zone is as follows:
wherein the content of the first and second substances,
is a waveform index value of the combustion region,
is the length of the edge of the combustion zone,
is the first fluctuation weight of the combustion zone,
is the second fluctuation weight of the combustion zone,
is the area of the combustion zone and,
is the abscissa of the centroid point of the combustion zone,
is the ordinate of the centroid point of the combustion zone,
is the abscissa of the centroid point of the unburned region,
is the ordinate of the centroid point of the unburned region.
Further, the calculation formula of the brightness value and the saturation of each pixel point in the combustion area is as follows:
wherein the content of the first and second substances,
respectively in the combustion zone
Go to the first
The R, G, B values of the column pixel points,
is in the combustion zone
Go to the first
The luminance values of the column pixel points are,
is in the combustion zone
Go to the first
The saturation of the column pixel points is,
in order to take the function of the maximum value,
is a function of taking the minimum value.
Further, the calculation formula of the temperature evaluation index of each pixel point in the combustion area is as follows:
wherein the content of the first and second substances,
is in the combustion zone
Go to the first
The temperature evaluation index corresponding to the row pixel point,
is in the combustion zone
Go to the first
The luminance values of the column pixel points are,
is in the combustion zone
Go to the first
Saturation of column pixels.
Further, the calculation formula of the effective combustion area abundance index value is as follows:
wherein the content of the first and second substances,
is a combustion zone
The effective combustion zone abundance index value of (a),
is in the combustion zone
Go to the first
The temperature evaluation index corresponding to the row pixel point,
the area of the combustion zone is,
in order to evaluate the indicator threshold for temperature,
is in the combustion zone
Go to the first
The temperature evaluation index value of the column pixel point,
the number of pixel points of the combustion area in the horizontal direction and the vertical direction is respectively.
Further, the calculation formula of the effective combustion zone temperature estimation index value is as follows:
wherein, the first and the second end of the pipe are connected with each other,
the index value is evaluated for the effective combustion zone temperature,
is in the combustion zone
Go to the first
The temperature evaluation index corresponding to the row pixel point,
for evaluation of temperatureThe index threshold is estimated and the index threshold is estimated,
is in the combustion zone
Go to the first
The temperature evaluation index value of the column pixel point,
the number of pixel points of the combustion area in the horizontal direction and the vertical direction is respectively.
Further, the step of obtaining the combustion change rate of the blast furnace to be detected comprises the following steps:
and further obtaining a brightness fitting function of the combustion area according to the brightness value of each pixel point of the combustion area of the N images and the corresponding time of the N images, and obtaining the combustion change rate of the blast furnace to be detected according to the brightness fitting function of the combustion area.
The invention also provides an artificial intelligence based blast furnace equipment operation evaluation system which comprises a processor and a memory, wherein the processor is used for processing the instructions stored in the memory so as to realize the artificial intelligence based blast furnace equipment operation evaluation method.
The invention has the following beneficial effects:
the invention obtains N images of different moments in the blast furnace to be detected, obtains a combustion area and an unburnt area in the N images according to the gray value of each pixel point in the N images, divides the combustion area and the unburnt area in the images, is convenient for accurately analyzing the combustion state in the blast furnace, determines the centroid coordinate of the unburnt area and the area, the centroid coordinate and the edge length of the combustion area according to the combustion area and the unburnt area in the N images, further obtains the fluctuation index value of the combustion area in the N images, calculates the brightness value and the saturation of each pixel point in the combustion area in the N images, further determines the temperature evaluation index of each pixel point in the combustion area, further obtains the abundance index value and the temperature evaluation index value of the effective combustion area in the N images, and according to the brightness value of each pixel point in the combustion area of the N images, and obtaining the combustion change rate in the blast furnace to be detected, and obtaining the operation state in the blast furnace to be detected according to the fluctuation index value, the effective combustion area abundance index value, the effective combustion area temperature evaluation index value and the combustion change rate of the blast furnace to be detected in the N images. The invention acquires the image in the blast furnace in real time through the camera, and represents the running state in the blast furnace by utilizing the four index values of the combustion area, so that the management operator can conveniently and visually know the running condition in the blast furnace, thereby correspondingly adjusting the blast furnace and improving the real-time performance of running detection of blast furnace equipment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of the steps of the method for evaluating the operation of a blast furnace facility based on artificial intelligence according to the present invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, features and effects of the technical solutions according to the present invention will be given with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the blast furnace equipment operation evaluation method and system based on artificial intelligence in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating steps of a method for evaluating operation of a blast furnace facility based on artificial intelligence according to an embodiment of the present invention is shown, the method including the steps of:
step 1: and acquiring N images of the blast furnace to be detected at different moments, and acquiring a combustion area and an unburned area in the N images according to the gray values of all pixel points in the N images.
Set up industry CCD camera at the blast furnace fire door for gather N images of different moments in the blast furnace, because the temperature in the blast furnace is higher, the CCD camera of setting is high temperature resistant CCD camera, and in this embodiment, this CCD camera sets up directly over the blast furnace fire door, and guarantees that blast furnace fire door central point and the central point coincidence of camera collection image. It should be noted that the angle of view of the camera and the shooting range of the camera may be set according to actual conditions, and an implementer needs to adjust the camera according to actual conditions in an actual application process.
After the camera collects the image in the blast furnace, considering that the industrial environment is complex and severe, and a large amount of image noise is generated in the image collection process to influence the quality of the image collected in the blast furnace, therefore, in order to improve the detection and evaluation precision of the system, the invention carries out filtering and denoising on the image collected by the camera, carries out image enhancement processing and improves the image quality collected by the camera. In this embodiment, an adaptive median filtering algorithm is used to perform filtering and denoising on an image, and histogram equalization is used to perform image enhancement, where the specific process is the prior art and is not described in detail in this embodiment.
For images inside a blast furnace, it mainly consists of two areas: the more complete the combustion, the higher the grey value represented on the image, the combustion area in the image can directly and effectively reflect the combustion condition in the blast furnace, namely the running state of the blast furnace. In order to improve the system precision and ensure the accuracy of extracting the feature data of each subsequent region, the embodiment divides the image into regions to extract combustion regions, and specifically comprises the following steps:
and (1-1) respectively carrying out window area division on the N images to obtain each window area of the N images.
And converting the N images at different moments in the blast furnace to be detected into gray level images according to the processed N images at different moments in the blast furnace to be detected, thereby obtaining the N gray level images at different moments in the blast furnace to be detected. Since the graying process of the image is a well-known technology, it is not described in detail herein.
The sliding window is adopted to slide on the image, the window size and the sliding step length can be set by self, and in order to improve the calculation speed of the system and ensure the detection precision, the sliding window adopted by the embodiment is
And in order to avoid overlapping areas of the sliding windows, the sliding step length is set to be 9, and the sliding windows slide from top to bottom and from left to right from the top left corner of the image to obtain each window area of the N images.
And (1-2) calculating the gray level change rate and the gray level mean value in each window area of the N images according to the gray level value of each pixel point in the N images, thereby obtaining each window feature vector of the N images.
Adopting Peleg according to the gray value of each pixel point in N images
Calculating the gray level change rate of each window area of the N images by using a blanket algorithm, Peleg
The Blanket Algorithm can be used to identify smooth and rough conditions of the image surface texture, Peleg
The blanket algorithm is the prior art, and only Peleg is adopted in the embodiment
The blanket algorithm analyzes the image so as to extract image characteristic data, does not make relevant explanation on the specific process of the algorithm, and is based on Peleg
The blanket algorithm knows:
wherein the content of the first and second substances,
the thickness of the blanket, i.e. the dimension,
in the form of a fractal dimension,
is a constant value related to the image and is used for reflecting the change rate of the gray scale area of the image along with the change of the scale, when the curved surface of the gray scale is smooth or the gray scale changes slowly,
the value is small, and when the gray curved surface is rough or the gray change is severe,
the value is larger, and logarithms are respectively taken at two sides to obtain:
using Peleg
Blanket algorithm to obtain the gray scale change rate of each window area of the N images
。
In order to further improve the extraction precision of the combustion area, the gray level mean value of each window area is calculated by the following calculation formula:
wherein the content of the first and second substances,
for the second image in the blast furnace to be detected
Go to the first
The window area corresponding to the column pixel points is,
for the first image in the blast furnace to be detected
Go to the first
The gray values of the column pixels are set,
is the average value of the pixel gray scale of the window area in the image in the blast furnace to be detected.
Obtaining characteristic vectors of each window of the N images according to the gray scale change rate and the gray scale mean value in each window area of the N images
。
(1-3) clustering the window characteristic vectors of the N images respectively, and determining a combustion window area and an unburned window area in each window area according to a clustering result so as to obtain a combustion area and an unburned area in the N images.
After obtaining the window feature vectors of the N images, performing cluster analysis on the window feature vector sequences through a clustering algorithm, in this embodiment, performing cluster analysis on the window feature vector sequences by using a K-means clustering algorithm (K-means), and setting a clustering category to be 2 for identifying two regions in the images. And respectively calculating the gray level mean values of the images corresponding to the two regions for the two regions obtained after clustering, comparing the gray level mean values of the two regions, setting the region with the large gray level mean value as a combustion region and the region with the small gray level mean value as an unburned region, setting the pixel value of the pixel point of the combustion region in the image to be 1, and setting the pixel value of the pixel point of the unburned region to be 0.
And 2, step: and determining the centroid coordinate of the unburned region, the area of the combustion region, the centroid coordinate and the edge length according to the combustion region and the unburned region in the N images, and further obtaining the fluctuation index value of the combustion region in the N images.
Because the internal environment of the blast furnace is relatively complex, the position of a combustion area in the blast furnace is not positioned at the central position in the blast furnace, and the camera generates deviation along with the long-time use of the camera equipment, so that the central point of a furnace mouth of the blast furnace and the central point of an image cannot be completely coincided, and then the fluctuation analysis result of the combustion area in the blast furnace is influenced, and therefore, the combustion condition in the blast furnace is analyzed through the distribution condition of the mass centers of the combustion area and the unburned area. Calculating the coordinates of the centroid of the combustion area according to the combustion area and the unburned area
And unburned zone coordinates
. To be liftedAnd (3) analyzing the fluctuation of the high combustion area by combining the edge characteristics of the combustion area, and obtaining the area of the combustion area according to the number of pixel points in the combustion area. And obtaining the edge points of the combustion area by utilizing a four-neighborhood pixel point judgment method, and taking the sum of all the edge points as the edge length of the combustion area. Since the four-neighborhood pixel point determination method is the prior art, the details are not described herein.
Calculating the fluctuation index value of the combustion area according to the centroid coordinate of the unburned area and the area, the centroid coordinate and the edge length of the combustion area, wherein the calculation formula is as follows:
wherein the content of the first and second substances,
is an index value of the waveform of the combustion region,
is the length of the edge of the combustion zone,
is a first fluctuation weight of the combustion zone,
is the second fluctuation weight of the combustion zone,
is the area of the combustion zone and,
is the abscissa of the centroid point of the combustion zone,
is the ordinate of the centroid point of the combustion zone,
is the abscissa of the centroid point of the unburned region,
is the ordinate of the centroid point of the unburned region.
And 3, step 3: and calculating the brightness value and the saturation of each pixel point of the combustion area in the N images so as to determine the temperature evaluation index of each pixel point of the combustion area, and further obtain the effective combustion area abundance index value and the effective combustion area temperature evaluation index value of the combustion area in the N images.
The method comprises the following specific steps of obtaining the brightness value and the saturation of each pixel point in the combustion area:
according to R, G, B values of each pixel point of a combustion area in N images, HIS conversion is carried out on the combustion area, as the embodiment only needs to evaluate the temperature condition of the combustion area by using the brightness value and the saturation of the combustion area in the images, only the brightness value and the saturation of the combustion area in the images are extracted, and the calculation formula of the brightness value and the saturation of each pixel point of the combustion area is as follows:
wherein the content of the first and second substances,
respectively in the combustion zone
Go to the first
The R, G, B values of the column pixel points,
is in the combustion zone
Go to the first
The luminance values of the column pixel points are,
is in the combustion zone
Go to the first
The saturation of the column pixel points is,
in order to take the function of the maximum value,
is a function of taking the minimum value.
The method comprises the following specific steps of obtaining temperature evaluation indexes of all pixel points in a combustion area:
according to the brightness value and the saturation of each pixel point in the combustion area, calculating the temperature evaluation index of each pixel point in the combustion area, wherein the calculation formula is as follows:
wherein the content of the first and second substances,
is in the combustion zone
Go to the first
The temperature evaluation index corresponding to the row pixel point,
is in the combustion zone
Go to the first
The luminance values of the column pixel points are,
is in the combustion zone
Go to the first
Saturation of column pixels.
The specific steps for obtaining the effective combustion area abundance index value and the effective combustion area temperature evaluation index value of the combustion area are as follows:
according to the temperature evaluation index of each pixel point in the combustion area, acquiring the temperature distribution matrix of the combustion area, wherein the temperature condition of each pixel point in the combustion area corresponds to one pixel point in the matrix, and the temperature distribution matrix of the combustion area is as follows:
wherein the content of the first and second substances,
the number of pixel points of the combustion area in the horizontal direction and the vertical direction is respectively.
And setting an index threshold value for the temperature evaluation index of each pixel point in the combustion area, wherein if the temperature evaluation index of the pixel point in the combustion area is greater than or equal to the index threshold value, the area corresponding to the temperature evaluation index of the pixel point in the combustion area greater than the index threshold value is an effective combustion area.
Obtaining an effective combustion area abundance index value and an effective combustion area temperature evaluation index value of a combustion area according to the temperature evaluation index of each pixel point of the combustion area and a set index threshold, wherein the effective combustion area abundance index value has the following calculation formula:
wherein the content of the first and second substances,
is a combustion zone
The effective combustion zone abundance index value of (a),
in the combustion zone
Go to the first
The temperature evaluation index corresponding to the row pixel point,
is the area of the combustion zone and is,
in order to evaluate the indicator threshold for temperature,
in the combustion zone
Go to the first
The temperature evaluation index value of the column pixel point,
the number of pixel points of the combustion area in the horizontal direction and the vertical direction is respectively.
The calculation formula of the effective combustion area temperature evaluation index value is as follows:
wherein the content of the first and second substances,
the index value is evaluated for the effective combustion zone temperature,
is in the combustion zone
Go to the first
The temperature evaluation index corresponding to the row pixel point,
in order to evaluate the indicator threshold for temperature,
is in the combustion zone
Go to the first
The temperature evaluation index value of the row pixel point,
the number of pixel points of the combustion area in the horizontal direction and the vertical direction is respectively.
And 4, step 4: and obtaining the combustion change rate of the blast furnace to be detected according to the brightness value of each pixel point of the combustion area of the N images.
In order to analyze the combustion change condition of the combustion area in the blast furnace, a time variable is introduced, and the combustion change condition of the combustion area in the blast furnace is further analyzed by combining the time variable and the brightness values corresponding to all the pixel points, and the method specifically comprises the following steps:
and further obtaining a brightness fitting function of the combustion area according to the brightness value of each pixel point of the combustion area of the N images and the corresponding time of the N images, and obtaining the combustion change rate of the brightness fitting function of the combustion area according to the brightness fitting function of the combustion area.
Calculating the brightness mean value of the combustion area of the N images according to the brightness values of all pixel points of the combustion area of the N images, obtaining the brightness mean value corresponding to each moment according to the N moments corresponding to the N images, and performing least square fitting on the brightness mean value corresponding to each moment to obtain a brightness fitting function of the combustion area:
y is a luminance mean value calculated based on a function, x is each time corresponding to N images, k and b are initial parameters, and meanwhile, in order to ensure the fitting accuracy of the fitting function, the present embodiment will set a target loss function:
wherein, the first and the second end of the pipe are connected with each other,
respectively a fitting brightness mean value and a real brightness mean value corresponding to the time w,
is the objective loss function.
Objective loss function
When the minimum value is reached, the brightness fitting function is closest to the real brightness change curve, and the function at the moment is the best fitting function:
the brightness fitting slope is the combustion change rate of the blast furnace to be detected
. The rate of change of combustion
The rate of change of spark in the combustion zone can be characterized and thus can be used to detect the combustion condition of the spark in the blast furnace.
And 5: and obtaining the running state in the blast furnace to be detected according to the fluctuation index value, the effective combustion area abundance index value, the effective combustion area temperature evaluation index value and the combustion change rate of the blast furnace to be detected in the N images.
Obtaining the fluctuation index value of the combustion area in the N images according to the step (2), the step (3) and the step (4)
Effective combustion zone abundance index value
Effective combustion area temperature evaluation index value
And the combustion change rate of the blast furnace to be detected
Obtained for use in a watchCharacterizing one-dimensional characteristic vectors of a combustion area in the blast furnace to be detected:
。
the blast furnace operation state is evaluated and detected by adopting a neural network model, and the blast furnace operation state is evaluated by adopting a full-connection FC network in the embodiment. Before blast furnace operation state evaluation, a full-connection FC network is required to be constructed, a training data set of the full-connection FC network is acquired, and the constructed full-connection FC network is trained. The training data set includes a plurality of sets of training feature vectors, and in this embodiment, each set of training feature vectors includes fluctuation index values of a combustion zone of the blast furnace at each time of operation
Effective combustion zone abundance index value
Effective combustion area temperature evaluation index value
And the combustion change rate of the blast furnace to be detected
And taking five grades of the running state of the blast furnace as label data of the training data set, wherein the higher the grade of the running state of the blast furnace is, the better the running state of the blast furnace is. The embodiment determines the training data set and the label data of the fully connected FC network, and the details of the training process are prior art and will not be described in detail here.
Inputting the one-dimensional characteristic vector of the combustion area in the blast furnace to be detected into the constructed and trained full-connection FC network to obtain the grade of the running state of the blast furnace
In order to facilitate the visual understanding of the operation condition of the blast furnace by the blast furnace management operators, the blast furnace operation is setLine state level threshold
When blast furnace operation grade
And when the blast furnace is unstable in operation, the blast furnace operation evaluation system sends out early warning to prompt an operator to carry out detailed detection on the blast furnace operation evaluation system, and corresponding adjustment measures are taken to avoid safety production problems such as major accidents caused by poor operation of the blast furnace.
The present embodiment further provides an artificial intelligence based blast furnace equipment operation evaluation system, which includes a processor and a memory, where the processor is configured to process instructions stored in the memory to implement an artificial intelligence based blast furnace equipment operation evaluation method, and since the artificial intelligence based blast furnace equipment operation evaluation method has been described in detail above, details are not repeated here.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (9)
1. A blast furnace equipment operation evaluation method based on artificial intelligence is characterized by comprising the following steps:
acquiring N images of the blast furnace to be detected at different moments, and obtaining a combustion area and an unburned area in the N images according to the gray value of each pixel point in the N images;
determining the centroid coordinate of the unburned region and the area, centroid coordinate and edge length of the combustion region according to the combustion region and the unburned region in the N images, and further obtaining the fluctuation index value of the combustion region in the N images;
calculating the brightness value and the saturation of each pixel point of the combustion area in the N images so as to determine the temperature evaluation index of each pixel point of the combustion area, and further obtaining an effective combustion area abundance index value and an effective combustion area temperature evaluation index value of the combustion area in the N images;
obtaining the combustion change rate of the blast furnace to be detected according to the brightness values of all pixel points in the combustion area of the N images;
and obtaining the running state in the blast furnace to be detected according to the fluctuation index value, the effective combustion area abundance index value, the effective combustion area temperature evaluation index value and the combustion change rate of the blast furnace to be detected in the N images.
2. The artificial intelligence-based blast furnace equipment operation evaluation method according to claim 1, wherein the step of obtaining the combustion area and the unburned area in the N images comprises:
respectively carrying out window area division on the N images to obtain each window area of the N images;
calculating the gray level change rate and the gray level mean value in each window region of the N images according to the gray level value of each pixel point in the N images, thereby obtaining each window feature vector of the N images;
and clustering the characteristic vectors of each window of the N images respectively, and determining a combustion window area and an unburned window area in each window area according to a clustering result so as to obtain the combustion area and the unburned area in the N images.
3. The artificial intelligence-based blast furnace equipment operation evaluation method according to claim 1, wherein the fluctuation index value of the combustion zone is calculated by the formula:
wherein the content of the first and second substances,
is a waveform index value of the combustion region,
is the length of the edge of the combustion zone,
is the first fluctuation weight of the combustion zone,
is a second fluctuation weight of the combustion zone,
is the area of the combustion zone and,
is the abscissa of the centroid point of the combustion zone,
is the ordinate of the centroid point of the combustion zone,
is the abscissa of the centroid point of the unburned region,
is the ordinate of the centroid point of the unburned region.
4. The method for evaluating the operation of the blast furnace equipment based on the artificial intelligence as claimed in claim 1, wherein the calculation formula of the brightness value and the saturation of each pixel point in the combustion area is as follows:
wherein, the first and the second end of the pipe are connected with each other,
respectively in the combustion zone
Go to the first
The R, G, B values of the column pixel points,
is in the combustion zone
Go to the first
The luminance values of the column pixel points are,
is a combustion zoneIn the domain
Go to the first
The saturation of the column pixel points is,
in order to take the function of the maximum value,
is a function of taking the minimum value.
5. The method for evaluating the operation of the blast furnace equipment based on the artificial intelligence as claimed in claim 1, wherein the calculation formula of the temperature evaluation index of each pixel point in the combustion area is as follows:
wherein, the first and the second end of the pipe are connected with each other,
in the combustion zone
Go to the first
The temperature evaluation index corresponding to the row pixel point,
is in the combustion zone
Go to the first
The luminance values of the column pixel points are,
is in the combustion zone
Go to the first
Saturation of column pixels.
6. The method of claim 1, wherein the effective combustion zone abundance index value is calculated by the formula:
wherein, the first and the second end of the pipe are connected with each other,
is a combustion zone
The effective combustion zone abundance index value of (a),
is in the combustion zone
Go to the first
The temperature evaluation index corresponding to the row pixel point,
the area of the combustion zone is,
in order to evaluate the indicator threshold for temperature,
is in the combustion zone
Go to the first
The temperature evaluation index value of the row pixel point,
the number of pixel points of the combustion area in the horizontal direction and the vertical direction is respectively.
7. The artificial intelligence based blast furnace equipment operation evaluation method according to claim 1, wherein the calculation formula of the effective combustion zone temperature evaluation index value is:
wherein the content of the first and second substances,
for effective combustionThe zone temperature evaluation index value is set to be,
is in the combustion zone
Go to the first
The temperature evaluation index corresponding to the row pixel point,
in order to evaluate the indicator threshold for temperature,
is in the combustion zone
Go to the first
The temperature evaluation index value of the column pixel point,
the number of pixel points of the combustion area in the horizontal direction and the vertical direction is respectively.
8. The artificial intelligence based blast furnace equipment operation evaluation method according to claim 1, wherein the step of obtaining a combustion change rate of the blast furnace to be detected comprises:
and further obtaining a brightness fitting function of the combustion area according to the brightness value of each pixel point of the combustion area of the N images and the corresponding time of the N images, and obtaining the combustion change rate of the blast furnace to be detected according to the brightness fitting function of the combustion area.
9. An artificial intelligence based blast furnace equipment operation evaluation system, characterized by comprising a processor and a memory, wherein the processor is used for processing instructions stored in the memory to realize the artificial intelligence based blast furnace equipment operation evaluation method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210844908.5A CN114937036B (en) | 2022-07-19 | 2022-07-19 | Blast furnace equipment operation evaluation method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210844908.5A CN114937036B (en) | 2022-07-19 | 2022-07-19 | Blast furnace equipment operation evaluation method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114937036A true CN114937036A (en) | 2022-08-23 |
| CN114937036B CN114937036B (en) | 2022-09-20 |
Family
ID=82868364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210844908.5A Active CN114937036B (en) | 2022-07-19 | 2022-07-19 | Blast furnace equipment operation evaluation method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114937036B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115761604A (en) * | 2023-01-10 | 2023-03-07 | 矿冶科技集团有限公司 | Furnace mouth opening and closing state identification method and device |
| CN116612438A (en) * | 2023-07-20 | 2023-08-18 | 山东联兴能源集团有限公司 | Steam boiler combustion state real-time monitoring system based on thermal imaging |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001318002A (en) * | 2000-05-02 | 2001-11-16 | Nippon Steel Corp | Temperature distribution measuring instrument for race way in tuyere of blast furnace |
| CN103544273A (en) * | 2013-10-21 | 2014-01-29 | 武汉钢铁(集团)公司 | Method for assessing integral states of furnace conditions by aid of pattern recognition technology |
| CN113570602A (en) * | 2021-09-24 | 2021-10-29 | 江苏昌存铜业有限公司 | Hot-rolled steel coil curling evaluation method based on artificial intelligence |
-
2022
- 2022-07-19 CN CN202210844908.5A patent/CN114937036B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001318002A (en) * | 2000-05-02 | 2001-11-16 | Nippon Steel Corp | Temperature distribution measuring instrument for race way in tuyere of blast furnace |
| CN103544273A (en) * | 2013-10-21 | 2014-01-29 | 武汉钢铁(集团)公司 | Method for assessing integral states of furnace conditions by aid of pattern recognition technology |
| CN113570602A (en) * | 2021-09-24 | 2021-10-29 | 江苏昌存铜业有限公司 | Hot-rolled steel coil curling evaluation method based on artificial intelligence |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115761604A (en) * | 2023-01-10 | 2023-03-07 | 矿冶科技集团有限公司 | Furnace mouth opening and closing state identification method and device |
| CN116612438A (en) * | 2023-07-20 | 2023-08-18 | 山东联兴能源集团有限公司 | Steam boiler combustion state real-time monitoring system based on thermal imaging |
| CN116612438B (en) * | 2023-07-20 | 2023-09-19 | 山东联兴能源集团有限公司 | Steam boiler combustion state real-time monitoring system based on thermal imaging |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114937036B (en) | 2022-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114937036B (en) | Blast furnace equipment operation evaluation method and system based on artificial intelligence | |
| CN105067638B (en) | Tire fetal membrane face character defect inspection method based on machine vision | |
| CN103632158B (en) | Forest fire prevention monitor method and forest fire prevention monitor system | |
| CN110728223A (en) | Helmet wearing identification method based on deep learning | |
| CN113935666B (en) | Building decoration wall tile abnormity evaluation method based on image processing | |
| CN110427825A (en) | The video flame recognition methods merged based on key frame with quick support vector machines | |
| CN108960185A (en) | Vehicle target detection method and system based on YOLOv2 | |
| CN106886216A (en) | Robot automatic tracking method and system based on RGBD Face datections | |
| CN110334750A (en) | Iron tower of power transmission line bolt corrosion degree image classification recognition methods | |
| CN115564771B (en) | Concrete crack identification method based on building foundation column | |
| CN110057820B (en) | Method, system and storage medium for on-line detection of chlorine-hydrogen ratio of hydrogen chloride synthesis furnace | |
| CN111896541B (en) | Flue gas on-line monitoring system based on block chain | |
| CN109359604B (en) | Method for identifying instrument under shadow interference facing inspection robot | |
| Tian et al. | Corrosion identification of fittings based on computer vision | |
| CN113033704A (en) | Intelligent judging method for copper converter converting copper making period end point based on pattern recognition | |
| Wu et al. | Experimental analysis of image dehazing algorithms for pelletization process images | |
| CN106169079B (en) | A kind of pressure vessel quantity recognition methods based on computer vision | |
| CN107301653A (en) | Video image fire disaster flame detection method based on BP neural network | |
| CN111091586A (en) | Rapid smoke dynamic shielding area detection and positioning method and application thereof | |
| CN207319290U (en) | One kind interference far field beam test system | |
| CN112232307B (en) | Method for detecting wearing of safety helmet in night vision environment | |
| CN112396101A (en) | Intelligent image analysis and decision-making method based on firepower plant hearth flame television | |
| CN113033705B (en) | Intelligent judgment and verification method for copper converter blowing slagging period end point based on pattern recognition | |
| CN105787944B (en) | A kind of paving leaf platform stem-butts laying monitoring device and monitoring method based on industrial camera | |
| Rudz et al. | On the evaluation of segmentation methods for wildland fire |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231227 Address after: 226100 No. 888, Fengcheng Road, Yudong Town, Haimen City, Nantong City, Jiangsu Province Patentee after: Nantongshan Tongdao Bridge Machinery Equipment Co.,Ltd. Address before: No. 12, Chuangye Road, Yudong Town, Haimen City, Nantong City, Jiangsu Province, 226100 Patentee before: Nantong Boying Machinery Casting Co.,Ltd. |