CN116342965A - Water level measurement error analysis and control method and system - Google Patents
Water level measurement error analysis and control method and system Download PDFInfo
- Publication number
- CN116342965A CN116342965A CN202310603123.3A CN202310603123A CN116342965A CN 116342965 A CN116342965 A CN 116342965A CN 202310603123 A CN202310603123 A CN 202310603123A CN 116342965 A CN116342965 A CN 116342965A
- Authority
- CN
- China
- Prior art keywords
- water level
- image
- level image
- water
- gray
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 317
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000005259 measurement Methods 0.000 title claims abstract description 23
- 238000004458 analytical method Methods 0.000 title claims abstract description 21
- 239000011159 matrix material Substances 0.000 claims abstract description 42
- 238000006243 chemical reaction Methods 0.000 claims abstract description 12
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 229920006395 saturated elastomer Polymers 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 8
- 239000007788 liquid Substances 0.000 claims description 43
- 238000007781 pre-processing Methods 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 4
- 230000003213 activating effect Effects 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 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
- 238000013021 overheating Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
- G01F23/80—Arrangements for signal processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
- G06V10/84—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using probabilistic graphical models from image or video features, e.g. Markov models or Bayesian networks
Abstract
The invention discloses a water level measurement error analysis and control method and a system, which are applied to the technical field of image processing, wherein the method comprises the following steps: acquiring a drum water level image; determining a region containing a water level gauge and a region identified by errors through coarse positioning of the first water level image; positioning the water level of the steam-containing area and the water level of the saturated water area through fine positioning; establishing gray level co-occurrence matrix
The method comprises the steps of carrying out a first treatment on the surface of the Analyzing a local mode and an arrangement rule of a first water level image in the gray level co-occurrence matrix; mapping the features of the first water level image to a high-dimensional feature space through a nonlinear function, and constructing a classification hyperplane to classify the first water level image; acquiring a time stamp of the drum water level, outputting an analog signal, and converting the analog signal into corresponding digital information through A/D conversion; the effect on the detail aspect of the first water level image is enhanced, so that the control is more accurate.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method and a system for analyzing and controlling a water level measurement error.
Background
The steam drum is a device for steam-water separation, a large amount of steam-water mixture exists in the steam drum, and the steam drum water level system is a large-lag nonlinear system. The larger the evaporation amount, the smaller the water capacity, the smaller the water storage amount which allows fluctuation, and the higher the control requirement on the drum water level. When the water level is too high, the steam is brought with water and salt, so that the overall quality is seriously reduced, and the production and the safety are seriously influenced; too low a water level will destroy the water circulation of part of the water-cooled wall, causing the water-cooled wall to be damaged due to local overheating. Therefore, the drum water level is required to be measured and controlled in real time, and the following problems exist in the prior technical scheme:
(1) When the water supply quantity is controlled only according to the water level signal, the load change is large, namely when the step disturbance is large, the error is generated in the measurement of the water level of the steam drum due to the phenomenon of false water level;
(2) Analog control of drum water level is increasingly limited and it is difficult to implement multivariable control.
The patent application number CN202210670908.8 discloses a method for cooperatively identifying the drum water level of an FCB set based on various neural networks, which comprises the following specific contents: acquiring two-way videos from two steam drum bicolor water level gauges: analyzing a two-way video: training a first generation reactance network: respectively training a second neural network and a third neural network according to at least one of the calibrated video frame picture and the calibrated water level value, the electric signal AI of the drum water level in-situ liquid level transmitter at the corresponding moment and the electric signal DI of the drum water level electric contact water level gauge at the corresponding moment; and determining the drum water level in real time based on the trained first generation reactance network, the second neural network and the third neural network.
The prior art adopts different measuring modes to fuse and monitor the drum water level, so that the drum water level is monitored intelligently, but the drum bicolor water level gauge adopted aiming at the scheme can only be used for water level monitoring in a control room, cannot participate in automatic water level adjustment and protection, and has the condition of generating errors when the drum water level is measured, so that the application provides a water level measuring error analysis and control method and system, realizes self-adaptive control of the drum water level, and effectively analyzes the measuring result.
Disclosure of Invention
The purpose of the application is to provide a water level measurement error analysis and control method and system, which aim at solving the problems that the data for measuring the water level of a steam drum has errors and the water level of the steam drum cannot be effectively controlled.
In order to achieve the above purpose, the present application provides the following technical solutions:
the application provides a water level measurement error analysis and control method, which comprises the following steps:
s1: acquiring a drum water level image, and preprocessing to obtain a first water level image;
s2: determining a region containing a water level gauge and a region identified by errors through coarse positioning of the first water level image; positioning the water level of the steam-containing area and the water level of the saturated water area through fine positioning, and comprehensively obtaining the position of a steam drum water level demarcation point;
s3: establishing gray level co-occurrence matrix
The gray level co-occurrence matrix reflects comprehensive information of the direction, adjacent interval and variation amplitude of the first water level image;
analyzing a local mode and an arrangement rule of a first water level image in the gray level co-occurrence matrix, and extracting features of the first water level image from the gray level co-occurrence matrix, wherein the features of the first water level image comprise angular second moment, contrast, correlation degree and entropy;
s4: mapping the features of the first water level image to a high-dimensional feature space through a nonlinear function, and constructing a classification hyperplane to classify the first water level image;
s5: classifying to obtain low liquid level H1, high liquid level H2, extremely low liquid level H3 and extremely high liquid level H4, acquiring a timestamp of the drum water level, outputting an analog signal, converting the analog signal into corresponding digital information through A/D conversion, and sequentially comparing the digital information with the classified water level by a singlechip.
Further, the step S3 includes:
calculating the measurement of the gray level distribution uniformity of the first water level image, wherein the formula is as follows:
wherein the method comprises the steps of
For the probability of grey level occurrence in the first water level image, is>
For the pixel gray level satisfying the distance in the first water level image,/for the pixel gray level satisfying the distance in the first water level image>
For the pixel gray scale meeting the direction in the first water level image, L is in the gray scale co-occurrence matrixA number of rows;
the contrast of the first water level image is calculated, and the formula is as follows:
wherein the method comprises the steps of
Contrast is the definition of texture in the first water level image, when +.>
The larger the first water level image is, the clearer the first water level image is;
the correlation degree of the first water level image is calculated, and the formula is as follows:
wherein the method comprises the steps of
The method comprises the following steps of:
the correlation degree is the similarity degree of image points in the gray level co-occurrence matrix in the row or column direction;
calculating entropy of the first water level image, wherein the formula is as follows:
entropy is a measure of the amount of information that the first water level image has, if the first water level image has no amount of information
If->
Maximum value>
Middle->
Is equal.
Further, the area containing the water level gauge and the area with error identification are determined through coarse positioning of the first water level image; and positioning the water level of the steam-containing area and the water level of the saturated water area through fine positioning, wherein the step of comprehensively obtaining the position of the drum water level demarcation point comprises the following steps:
the rough positioning is to extract an interface by using a segmentation threshold value, and the specific process is as follows:
obtaining the maximum and minimum gray values of the first water level image
Let the threshold initial value be:
wherein->
The ratio of gray level average values of the water level meter area and the background area is obtained; according to threshold->
Dividing the image into two parts A and B, and finding the average gray value +.>
The method comprises the steps of carrying out a first treatment on the surface of the Updating the threshold value, ending iteration if the iteration times exceed a preset value, otherwise, re-solving the average gray value of the two parts; and dividing the first water level image by using a threshold value after iteration is finished, and determining a region containing the water level gauge and a region with error identification.
Further, the fine positioning is to position the first water level image by adopting a convolutional neural network, and the activation function is as follows:
wherein the method comprises the steps of
Is the total number of types>
Is a characteristic channel->
In pixel +.>
Activation function at ∈>
Is a characteristic channel->
Is at maximum activation function of->
Then for other characteristic channels +.>
，/>
The method comprises the steps of carrying out a first treatment on the surface of the For activating function->
The minimized error of (2) is:
wherein the method comprises the steps of
Is a weight.
Further, the step of mapping the features of the first water level image to the high-dimensional feature space through a nonlinear function and constructing a classification hyperplane to classify the first water level image includes:
the method for obtaining the classification hyperplane comprises the following steps:
wherein->
For relaxation variable, ++>
For the adjustment factor, N is the classifier and w is the plane parameter.
Further, the step of obtaining low liquid level H1, high liquid level H2, extremely low liquid level H3 and extremely high liquid level H4 by classification, obtaining a timestamp of the drum water level, outputting an analog signal, converting the analog signal into corresponding digital information by a/D conversion, performing data processing by a singlechip, and comparing the obtained digital information with the classified water level in sequence, comprises the following steps:
when the water level of the steam drum reaches a preset detection position, the output port of the steam drum outputs low level to the singlechip; the first position from top to bottom is a water level upper limit alarm line, namely when the water level is higher than the first position, the boiled water valve control system automatically alarms; the second position is to automatically stop the water adding line, namely when the water level is higher than the second position, the control system automatically closes the water adding valve to stop water adding; the third position is an automatic water adding line, namely when the water level is lower than the third position, the control system can automatically switch on a water adding valve to start water adding; the fourth position is a water level lower limit alarm line, namely, when the water level is lower than the position, the control system automatically alarms.
Further, the step of obtaining the drum water level image and preprocessing to obtain the first water level image includes:
and removing noise from the drum water level image by adopting a smoothing processing method, and carrying out edge sharpening on the drum water level image by utilizing a sharpening algorithm.
There is also provided a water level measurement error analysis and control system, characterized by comprising:
the acquisition module is used for: acquiring a drum water level image, and preprocessing to obtain a first water level image;
and a positioning module: determining a region containing a water level gauge and a region identified by errors through coarse positioning of the first water level image; positioning the water level of the steam-containing area and the water level of the saturated water area through fine positioning, and comprehensively obtaining the position of a steam drum water level demarcation point;
and an analysis module: establishing gray level co-occurrence matrix
The gray level co-occurrence matrix reflects comprehensive information of the direction, adjacent interval and variation amplitude of the first water level image;
analyzing a local mode and an arrangement rule of a first water level image in the gray level co-occurrence matrix, and extracting features of the first water level image from the gray level co-occurrence matrix, wherein the features of the first water level image comprise angular second moment, contrast, correlation degree and entropy;
and a classification module: classifying the first water level image by adopting a C-SVM classification method, mapping an input vector to a high-dimensional feature space through a nonlinear function, and constructing a classification hyperplane to classify nonlinear data;
and the control module is used for: classifying to obtain low liquid level H1, high liquid level H2, extremely low liquid level H3 and extremely high liquid level H4, acquiring a timestamp of the drum water level, outputting an analog signal, converting the analog signal into corresponding digital information through A/D conversion, and sequentially comparing the digital information with the classified water level by a singlechip.
The application provides a water level measurement error analysis and control method and system, which have the following beneficial effects:
(1) Acquiring a drum water level image, performing image preprocessing on the drum water level image to improve the display quality of the water level image, and determining a region containing a water level gauge and a region with error identification through coarse positioning and fine positioning; interference of the background on the first water level image can be eliminated to the greatest extent, the effect on the detail aspect of the first water level image is enhanced, and the control is more accurate;
(2) Establishing a gray level co-occurrence matrix, wherein the gray level co-occurrence matrix reflects comprehensive information of the direction, adjacent interval and variation amplitude of the first water level image, and extracting characteristic information of the image to enable a classification result to be more accurate and clear;
(3) The water level of the drum is controlled by adopting a singlechip, the CPU circularly detects the output state of a sensor, 3-bit seven-segment LEDs are used for displaying the liquid level height, detecting the liquid level data, implementing alarm safety prompt, when the liquid level of the water body is lower than a preset value, automatically opening a pump for water feeding, and when the water level reaches a set value, automatically closing the water pump or opening a drainage pump; the water level of the steam drum is controlled by sequentially comparing the water level obtained by the data processing with the water level obtained by classification through A/D conversion into corresponding digital information and carrying out data processing by a singlechip.
Drawings
FIG. 1 is a flow chart of a water level measurement error analysis and control method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a water level measurement error analysis and control system according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a liquid level control system according to an embodiment of the present application.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
Referring to fig. 1, a flow chart of a water level measurement error analysis and control method provided in the present application is shown;
the water level measurement error analysis and control method provided by the application comprises the following steps:
s1: acquiring a drum water level image, and preprocessing to obtain a first water level image; and removing noise from the drum water level image by adopting a smoothing processing method, and carrying out edge sharpening on the drum water level image by utilizing a sharpening algorithm.
In this step, because the acquired drum water level image contains various noises, the edges of the water level partial area are blurred, and the range is large during acquisition, the image contains not only the water level gauge itself but also a large amount of background information, and these factors all cause interference to the characteristics of the drum water level, so a series of pretreatment processes are required; firstly, a smoothing method is adopted, the main purpose of which is to eliminate noise, the smoothing method of the image depends on the characteristics of the noise, and generally, the noise can be reduced by using domain averaging in the spatial domain, wherein the domain averaging is divided into linearity and nonlinearity, and the cost of noise elimination is increased by large-size filtering of a template, and the loss of detail and the increase of calculation amount are caused. Since the edges of the drum water level image are very blurred, the details of the image are kept and the noise of the image is filtered;
the sharpening algorithm is utilized to enlarge the edge gradient value of the image, the condition that the red and green edges of the steam drum high-level water level gauge are blurred can be well improved, and the water level gauge can be clearly divided from the background, so that the image segmentation is more favorable for the next image segmentation, and the common sharpening algorithm comprises a first-order differential operator, a second-order differential operator and the like.
S2: determining a region containing a water level gauge and a region identified by errors through coarse positioning of the first water level image; positioning the water level of the steam-containing area and the water level of the saturated water area through fine positioning, and comprehensively obtaining the position of a steam drum water level demarcation point;
the rough positioning is to extract an interface by using a segmentation threshold value, and the specific process is as follows:
obtaining the maximum and minimum gray values of the first water level image
Let the threshold initial value be:
wherein->
The ratio of gray level average values of the water level meter area and the background area is obtained; according to threshold->
Dividing the image into two parts A and B, and finding the average gray value +.>
The method comprises the steps of carrying out a first treatment on the surface of the Updating the threshold value, ending iteration if the iteration times exceed a preset value, otherwise, re-solving the average gray value of the two parts; dividing the first water level image by using a threshold value after iteration is finished, and determining a region containing a water level gauge and a region with error identification;
the fine positioning is to position the first water level image by adopting a convolutional neural network, and the activation function is as follows:
wherein the method comprises the steps of
Is the total number of types>
Is a characteristic channel->
In pixel +.>
Activation function at ∈>
Is a characteristic channel->
Is at maximum activation function of->
Then for other characteristic channels +.>
，/>
The method comprises the steps of carrying out a first treatment on the surface of the For activating function->
The minimized error of (2) is:
wherein the method comprises the steps of
Is a weight.
In this step, the maximum and minimum gray values of the first water level image are obtained during coarse positioning
Let the threshold initial value be: />
Wherein->
The ratio of gray level average values of the water level meter area and the background area is obtained; according to threshold->
Dividing the image into two parts A and B, and finding the average gray value +.>
：
Wherein the method comprises the steps of
Is an image->
Gray value of dot +.>
Is an image->
The weight coefficient of the point;
a new threshold value is calculated:
if->
（/>
The allowable error) or the iteration times exceed a preset value, ending the iteration, otherwise, re-solving the average gray values of the two parts; dividing the first water level image by using a threshold value after iteration is finished, and determining a region containing a water level gauge and a region with error identification; interference of the background on the first water level image can be eliminated to the greatest extent, the effect on the detail aspect of the first water level image is enhanced, and the control is more accurate.
S3: establishing gray level co-occurrence matrix
The gray level co-occurrence matrix reflects comprehensive information of the direction, adjacent interval and variation amplitude of the first water level image;
and analyzing the local mode and the arrangement rule of the first water level image in the gray level co-occurrence matrix, and extracting the characteristics of the first water level image from the gray level co-occurrence matrix, wherein the characteristics of the first water level image comprise angular second moment, contrast, correlation degree and entropy.
In the step, the gray level co-occurrence matrix is an analysis method based on estimating a 2-order combined conditional probability density function, the gray level matrix of the image reflects visual information of the image, and the gray level co-occurrence matrix reflects comprehensive information of the first water level image about direction, adjacent interval and variation amplitude; analyzing the gray level co-occurrence matrix can analyze the local mode and the arrangement rule of the first water level image, and the characteristics of the first water level can be extracted from the gray level co-occurrence matrix, wherein the characteristics comprise the characteristics of angular second moment, contrast, correlation degree and entropy; the angular second moment is a measure of the uniformity of the gray scale distribution of an image when the distribution of elements in the gray scale co-occurrence matrix is more concentrated on the principal diagonal. Illustrating that the gray distribution of the first water level image is uniform when the local area is observed, and the angular second moment is the sum of squares of pixel values of the gray level co-occurrence matrix; the contrast of the first water level image can be understood as the definition of the image, wherein the larger the contrast is, the clearer the image is; the correlation degree is the similarity degree of the elements of the gray level co-occurrence matrix in the row direction or the column direction; entropy is a measure of the amount of information that the first water level image has, texture information also belongs to image information, and if the first water level image does not have any texture, the gray level co-occurrence matrix is a matrix of zero.
S4: mapping the features of the first water level image to a high-dimensional feature space through a nonlinear function, and constructing a classification hyperplane to classify the first water level image; the method for obtaining the classification hyperplane comprises the following steps:
wherein
For relaxation variable, ++>
For the adjustment factor, N is the classifier and w is the plane parameter.
In this step, the features of the first water level image are mapped as input vectors to a high-dimensional feature space by a nonlinear function, and a classification hyperplane is constructed in the space, so that the classification of nonlinear data can be performed, and the specific form of the nonlinear function is not required to be known in the mapping process, and only a kernel function is required to be used in the input space
Thus, the popularization capability can be improved.
S5: classifying to obtain a low liquid level H1, a high liquid level H2, an extremely low liquid level H3 and an extremely high liquid level H4, acquiring a timestamp of the drum water level, outputting an analog signal, converting the analog signal into corresponding digital information through A/D conversion, and sequentially comparing the digital information with the classified water level by a singlechip; when the water level of the steam drum reaches a preset detection position, the output port of the steam drum outputs low level to the singlechip; the first position from top to bottom is a water level upper limit alarm line, namely when the water level is higher than the first position, the boiled water valve control system automatically alarms; the second position is to automatically stop the water adding line, namely when the water level is higher than the second position, the control system automatically closes the water adding valve to stop water adding; the third position is an automatic water adding line, namely when the water level is lower than the third position, the control system can automatically switch on a water adding valve to start water adding; the fourth position is a water level lower limit alarm line, namely, when the water level is lower than the position, the control system automatically alarms.
In the step, four classified liquid levels are transmitted to a singlechip through an analog-to-digital converter, three states of the liquid levels and alarm safety prompts are displayed through a 3-bit seven-segment LED display, the LED display has the characteristics of clear display, high brightness, low use voltage, high photoelectric conversion efficiency and the like, whether a water pump is started or not is determined according to the current liquid level value and the water level set by a user, whether a motor for driving a valve is required to be started or stopped is determined according to the current liquid level value and the water level set by the user, wherein a structural schematic diagram of a liquid level control system is shown in a figure 3, a sensor can be observed to output an analog signal, the analog signal is converted into a digital signal through the analog-to-digital converter, the digital signal is controlled through operation of the singlechip, the LED display is performed through an alarm device, and the regulation control on the liquid level of a water body is realized through the starting of the valve after the alarm display.
Also provided is a water level measurement error analysis and control system, comprising:
the acquisition module is used for: acquiring a drum water level image, and preprocessing to obtain a first water level image;
and a positioning module: determining a region containing a water level gauge and a region identified by errors through coarse positioning of the first water level image; positioning the water level of the steam-containing area and the water level of the saturated water area through fine positioning, and comprehensively obtaining the position of a steam drum water level demarcation point;
and an analysis module: establishing gray level co-occurrence matrix
The gray level co-occurrence matrix reflects comprehensive information of the direction, adjacent interval and variation amplitude of the first water level image;
analyzing a local mode and an arrangement rule of a first water level image in the gray level co-occurrence matrix, and extracting features of the first water level image from the gray level co-occurrence matrix, wherein the features of the first water level image comprise angular second moment, contrast, correlation degree and entropy;
and a classification module: classifying the first water level image by adopting a C-SVM classification method, mapping an input vector to a high-dimensional feature space through a nonlinear function, and constructing a classification hyperplane to classify nonlinear data;
and the control module is used for: classifying to obtain low liquid level H1, high liquid level H2, extremely low liquid level H3 and extremely high liquid level H4, acquiring a timestamp of the drum water level, outputting an analog signal, converting the analog signal into corresponding digital information through A/D conversion, and sequentially comparing the digital information with the classified water level by a singlechip.
In summary, the first water level image is obtained by preprocessing the drum water level image, and the position of the drum water level demarcation point is comprehensively obtained by adopting two positioning of coarse positioning and fine positioning; and establishing a gray level co-occurrence matrix to extract characteristic information of the drum water level, classifying, converting the characteristic information into corresponding digital information through A/D conversion, performing data processing by a singlechip, and sequentially comparing the data processing with the classified water level to realize the control of the drum water level.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the application, the scope of which is defined in the appended claims and their equivalents.
Of course, the present invention can be implemented in various other embodiments, and based on this embodiment, those skilled in the art can obtain other embodiments without any inventive effort, which fall within the scope of the present invention.
Claims (8)
1. The water level measurement error analysis and control method is characterized by comprising the following steps:
s1: acquiring a drum water level image, and preprocessing to obtain a first water level image;
s2: determining a region containing a water level gauge and a region identified by errors through coarse positioning of the first water level image; positioning the water level of the steam-containing area and the water level of the saturated water area through fine positioning, and comprehensively obtaining the position of a steam drum water level demarcation point;
s3: establishing gray level co-occurrence matrix
The gray level co-occurrence matrix reflects comprehensive information of the direction, adjacent interval and variation amplitude of the first water level image;
analyzing a local mode and an arrangement rule of a first water level image in the gray level co-occurrence matrix, and extracting features of the first water level image from the gray level co-occurrence matrix, wherein the features of the first water level image comprise angular second moment, contrast, correlation degree and entropy;
s4: mapping the features of the first water level image to a high-dimensional feature space through a nonlinear function, and constructing a classification hyperplane to classify the first water level image;
s5: classifying to obtain low liquid level H1, high liquid level H2, extremely low liquid level H3 and extremely high liquid level H4, acquiring a timestamp of the drum water level, outputting an analog signal, converting the analog signal into corresponding digital information through A/D conversion, and sequentially comparing the digital information with the classified water level by a singlechip.
2. The water level measurement error analysis and control method according to claim 1, wherein the step S3 includes:
calculating the measurement of the gray level distribution uniformity of the first water level image, wherein the formula is as follows:
wherein the method comprises the steps of
For the probability of grey level occurrence in the first water level image, is>
For the pixel gray level satisfying the distance in the first water level image,/for the pixel gray level satisfying the distance in the first water level image>
The pixel gray scale meeting the direction in the first water level image is represented by L, which is the number of lines in the gray level co-occurrence matrix;
the contrast of the first water level image is calculated, and the formula is as follows:
wherein the method comprises the steps of
Contrast is the definition of texture in the first water level image, when +.>
The larger the first water level image is, the clearer the first water level image is;
the correlation degree of the first water level image is calculated, and the formula is as follows:
wherein the method comprises the steps of
The method comprises the following steps of:
the correlation degree is the similarity degree of image points in the gray level co-occurrence matrix in the row or column direction;
calculating entropy of the first water level image, wherein the formula is as follows:
entropy is a measure of the amount of information that the first water level image has, if the first water level image has no amount of information
If (if)
Maximum value>
Middle->
Is equal.
3. The method according to claim 1, wherein the area containing the water level gauge and the area of error recognition are determined by rough positioning of the first water level image; and positioning the water level of the steam-containing area and the water level of the saturated water area through fine positioning, wherein the step of comprehensively obtaining the position of the drum water level demarcation point comprises the following steps:
the rough positioning is to extract an interface by using a segmentation threshold value, and the specific process is as follows:
obtaining the maximum and minimum gray values of the first water level image
Let the threshold initial value be: />
Wherein->
The ratio of gray level average values of the water level meter area and the background area is obtained; according to threshold->
Dividing the image into two parts A and B, and finding the average gray value +.>
The method comprises the steps of carrying out a first treatment on the surface of the Updating the threshold value, ending iteration if the iteration times exceed a preset value, otherwise, re-solving the average gray value of the two parts; and dividing the first water level image by using a threshold value after iteration is finished, and determining a region containing the water level gauge and a region with error identification.
4. The method for analyzing and controlling water level measurement errors according to claim 3, wherein the fine positioning is to position the first water level image by using a convolutional neural network, and the activation function is as follows:
wherein the method comprises the steps of
Is the total number of types>
Is a characteristic channel->
In pixel +.>
Activation function at ∈>
Is a characteristic channel->
Is at maximum activation function of->
Then for other characteristic channels +.>
，/>
The method comprises the steps of carrying out a first treatment on the surface of the For activating function->
The minimized error of (2) is:
wherein the method comprises the steps of
Is a weight.
5. The water level measurement error analysis and control method according to claim 1, wherein the step of mapping the features of the first water level image to a high-dimensional feature space by a nonlinear function and constructing a classification hyperplane to classify the first water level image comprises:
the method for obtaining the classification hyperplane comprises the following steps:
wherein->
For relaxation variable, ++>
For the adjustment factor, N is the classifier and w is the plane parameter.
6. The method for analyzing and controlling water level measurement errors according to claim 1, wherein the step of classifying to obtain low liquid level H1, high liquid level H2, very low liquid level H3, very high liquid level H4, obtaining a time stamp of a drum water level, outputting an analog signal, converting the analog signal into corresponding digital information through a/D conversion, performing data processing by a singlechip, and sequentially comparing the obtained water level with the classified water level comprises the steps of:
when the water level of the steam drum reaches a preset detection position, the output port of the steam drum outputs low level to the singlechip; the first position from top to bottom is a water level upper limit alarm line, namely when the water level is higher than the first position, the boiled water valve control system automatically alarms; the second position is to automatically stop the water adding line, namely when the water level is higher than the second position, the control system automatically closes the water adding valve to stop water adding; the third position is an automatic water adding line, namely when the water level is lower than the third position, the control system can automatically switch on a water adding valve to start water adding; the fourth position is a water level lower limit alarm line, namely, when the water level is lower than the position, the control system automatically alarms.
7. The method for analyzing and controlling water level measurement errors according to claim 1, wherein the step of obtaining a drum water level image and performing preprocessing to obtain a first water level image comprises:
and removing noise from the drum water level image by adopting a smoothing processing method, and carrying out edge sharpening on the drum water level image by utilizing a sharpening algorithm.
8. The water level measurement error analysis and control system is characterized by comprising:
the acquisition module is used for: acquiring a drum water level image, and preprocessing to obtain a first water level image;
and a positioning module: determining a region containing a water level gauge and a region identified by errors through coarse positioning of the first water level image; positioning the water level of the steam-containing area and the water level of the saturated water area through fine positioning to obtain the position of a steam drum water level demarcation point;
and an analysis module: establishing gray level co-occurrence matrix
The gray level co-occurrence matrix reflects comprehensive information of the direction, adjacent interval and variation amplitude of the first water level image;
analyzing a local mode and an arrangement rule of a first water level image in the gray level co-occurrence matrix, and extracting features of the first water level image from the gray level co-occurrence matrix, wherein the features of the first water level image comprise angular second moment, contrast, correlation degree and entropy;
and a classification module: classifying the first water level image by adopting a C-SVM classification method, mapping an input vector to a high-dimensional feature space through a nonlinear function, and constructing a classification hyperplane to classify nonlinear data;
and the control module is used for: classifying to obtain low liquid level H1, high liquid level H2, extremely low liquid level H3 and extremely high liquid level H4, acquiring a timestamp of the drum water level, outputting an analog signal, converting the analog signal into corresponding digital information through A/D conversion, and sequentially comparing the digital information with the classified water level by a singlechip.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310603123.3A CN116342965B (en) | 2023-05-26 | 2023-05-26 | Water level measurement error analysis and control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310603123.3A CN116342965B (en) | 2023-05-26 | 2023-05-26 | Water level measurement error analysis and control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116342965A true CN116342965A (en) | 2023-06-27 |
| CN116342965B CN116342965B (en) | 2023-11-24 |
Family
ID=86886185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310603123.3A Active CN116342965B (en) | 2023-05-26 | 2023-05-26 | Water level measurement error analysis and control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116342965B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106920241A (en) * | 2017-03-13 | 2017-07-04 | 华北电力大学 | A kind of steam water-level monitoring method, apparatus and system |
| KR101873124B1 (en) * | 2016-12-30 | 2018-06-29 | 부산대학교 산학협력단 | Method and system for measuring watar level of liquid storage tanks |
| CN109522889A (en) * | 2018-09-03 | 2019-03-26 | 中国人民解放军国防科技大学 | Hydrological ruler water level identification and estimation method based on image analysis |
| US20210374466A1 (en) * | 2020-05-26 | 2021-12-02 | Zhejiang University | Water level monitoring method based on cluster partition and scale recognition |
| CN115393700A (en) * | 2022-07-26 | 2022-11-25 | 腾讯科技（深圳）有限公司 | Water level height identification method and device, electronic equipment and storage medium |
| WO2022253027A1 (en) * | 2021-05-31 | 2022-12-08 | 江苏科技大学 | Underwater sonar image matching method based on gaussian distribution clustering |
| CN115601713A (en) * | 2022-12-15 | 2023-01-13 | 中国电建集团江西省电力设计院有限公司（Cn） | Steam drum water level image recognition method and device |
-
2023
- 2023-05-26 CN CN202310603123.3A patent/CN116342965B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101873124B1 (en) * | 2016-12-30 | 2018-06-29 | 부산대학교 산학협력단 | Method and system for measuring watar level of liquid storage tanks |
| CN106920241A (en) * | 2017-03-13 | 2017-07-04 | 华北电力大学 | A kind of steam water-level monitoring method, apparatus and system |
| CN109522889A (en) * | 2018-09-03 | 2019-03-26 | 中国人民解放军国防科技大学 | Hydrological ruler water level identification and estimation method based on image analysis |
| US20210374466A1 (en) * | 2020-05-26 | 2021-12-02 | Zhejiang University | Water level monitoring method based on cluster partition and scale recognition |
| WO2022253027A1 (en) * | 2021-05-31 | 2022-12-08 | 江苏科技大学 | Underwater sonar image matching method based on gaussian distribution clustering |
| CN115393700A (en) * | 2022-07-26 | 2022-11-25 | 腾讯科技（深圳）有限公司 | Water level height identification method and device, electronic equipment and storage medium |
| CN115601713A (en) * | 2022-12-15 | 2023-01-13 | 中国电建集团江西省电力设计院有限公司（Cn） | Steam drum water level image recognition method and device |
Non-Patent Citations (4)
| Title |
|---|
| 仲志远;: "一种基于图像识别的水位测量算法", 国外电子测量技术, no. 06 * |
| 苏毅康;黄平;刘伟;夏飞;: "纹理分析在电厂锅炉汽包水位监视中的应用", 上海电力学院学报, no. 03, pages 1 - 5 * |
| 蔡皓, 于向军, 吕震中: "锅炉汽包水位数字图像处理算法研究", 锅炉技术, no. 01, pages 2 * |
| 赵安科;: "基于模式识别与灰度共生矩阵的神经元图像分类", 西安石油大学学报(自然科学版), no. 05 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116342965B (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110705376A (en) | Abnormal behavior detection method based on generative countermeasure network | |
| CN115018844B (en) | Plastic film quality evaluation method based on artificial intelligence | |
| CN109214470B (en) | Image visibility detection method based on coding network fine adjustment | |
| CN106443701A (en) | Flood pre-disaster early warning method based on sequential water scope remote sensing image | |
| CN111141653B (en) | Tunnel leakage rate prediction method based on neural network | |
| CN106056597A (en) | Object visual detection method and device | |
| CN117274722B (en) | Intelligent detection method for distribution box based on infrared image | |
| CN116758491A (en) | Printing monitoring image analysis method and system applied to 3D printing | |
| CN116205910B (en) | Injection molding temperature self-adaptive learning regulation and control system for power adapter | |
| CN110889843A (en) | SAR image ship target detection method based on maximum stable extremal region | |
| CN115994907B (en) | Intelligent processing system and method for comprehensive information of food detection mechanism | |
| Mamatov et al. | Methods for improving contrast of agricultural images | |
| CN116342965B (en) | Water level measurement error analysis and control method and system | |
| CN116883412B (en) | Graphene far infrared electric heating equipment fault detection method | |
| CN111753877A (en) | Product quality detection method based on deep neural network transfer learning | |
| CN115423807B (en) | Cloth defect detection method based on outlier detection | |
| CN115601713A (en) | Steam drum water level image recognition method and device | |
| Hu et al. | Quantum automated object detection algorithm | |
| CN111612734A (en) | Background clutter characterization method based on image structure complexity | |
| CN116309493A (en) | Method and system for detecting defects of textile products | |
| Jeffrey Kuo et al. | Self-organizing map network for automatically recognizing color texture fabric nature | |
| CN111325720B (en) | Multi-visual feature integrated reference-free super-resolution image quality evaluation method | |
| CN114611633A (en) | Health monitoring method of electromagnetic valve | |
| Yang et al. | Infrared image change detection of substation equipment in power system using Random Forest | |
| CN116754467B (en) | Evaluation method for ageing performance of natural rubber |
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 |