A method for identifying the production efficiency of a steam booster

Abstract

The present invention relates to the technical field of image processing, and particularly relates to a method for identifying the production efficiency of a steam booster; in the method, due to different radiation amounts, different temperature distributions are shown in the infrared thermal images taken at the same position on the surface of the Venturi tube of the steam booster, and connected regions appear. The degree of abnormality of each position is calculated based on the degree of chaos of the temperature distribution within the connected region and the degree of fluctuation of the area of the connected region, so as to judge the production efficiency of the steam booster. The solution of the present invention can more accurately find the abnormal position, enabling maintenance personnel to quickly repair or maintain the abnormal position.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a method for identifying the production efficiency of a steam generator. Background Art

[0002] In the field of traditional production efficiency detection of steam generators, evaluating whether the performance and efficiency of a steam generator are abnormal mainly relies on a variety of sensor technologies and infrared thermal imaging devices. These detection means achieve comprehensive monitoring of the working state of the steam generator by collecting key parameters during the operation of the steam generator, such as temperature distribution, pressure fluctuation, and flow rate. In particular, as a core component in the steam generator, the temperature distribution on the surface of the Venturi tube is regarded as an important indicator for judging the overall efficiency of the steam generator. By accurately analyzing the temperature distribution on the surface of the Venturi tube, it is possible to effectively identify whether there are problems with the production efficiency of the steam generator.

[0003] However, in actual operation, since the Venturi tube of the steam generator is usually designed with two conical structures, this special shape leads to significant differences in the radiation amount on the surface of the Venturi tube at different shooting angles. Specifically, even at the same position, the infrared thermal maps obtained at different shooting angles will show different temperature distribution characteristics. This temperature distribution difference caused by the angle change brings great troubles to subsequent image processing and data analysis.

[0004] In particular, in the image processing stage, different manifestations of temperature distribution often lead to an increase in the error of the connected component extraction algorithm. Connected component extraction is a key link in image processing, which is used to identify and distinguish different temperature regions or feature regions in an image. However, in the analysis of the infrared thermal map of the Venturi tube of the steam generator, due to the above-mentioned angle dependence problem, the accuracy of connected component extraction is greatly reduced, which may lead to misidentification of the production efficiency abnormality of the steam generator. This misidentification not only affects the accuracy of production efficiency detection, but also may mislead subsequent fault troubleshooting and maintenance strategies, bringing potential risks to the safe operation and energy efficiency management of the steam generator.

[0005] In view of the above problems, an innovative solution is urgently needed, aiming to improve the accuracy and reliability of identifying the production efficiency abnormality of the steam generator by improving image processing technology and overcoming the temperature distribution recognition error caused by the change of shooting angle. Summary of the Invention

[0006] The purpose of the present invention is to provide a method for identifying the production efficiency of a steam generator, so as to solve the problem of misidentification of the production efficiency abnormality of the steam generator caused by the extraction error of connected components due to different temperature distributions shown at the same position on the surface of the Venturi tube of the steam generator in infrared thermal maps taken at different angles through image processing technology. For this purpose, the present invention provides the following technical solutions.

[0007] In the present invention, a method for identifying the production efficiency of a steam booster is provided, including:

[0008] Obtaining infrared thermal maps at multiple angles at any position on the surface of the venturi tube of the steam booster at different times;

[0009] Calculating the probability that a pixel point in each infrared thermal map at each time belongs to the edge, where the probability is positively correlated with the gradient magnitude of any pixel point in any one of the R, G, and B channels in the corresponding infrared thermal map and the importance degree of the corresponding channel; the importance degree characterizes the change in the difference between the pixel values of the pixel points in the target area and the background area in any channel in the historical infrared thermal maps of each historical abnormal production;

[0010] If the probability is greater than a preset threshold, the corresponding pixel point belongs to an edge pixel point. Based on all the edge pixel points, a connected domain of the corresponding infrared thermal map is obtained, and the overlapping area of the connected domains at all angles at each time obtained is used as the target connected domain at the corresponding time;

[0011] Calculating the degree of abnormality at any position; the degree of abnormality is positively correlated with the degree of chaos in the temperature distribution of the target connected domain at each time and inversely correlated with the area of the corresponding target connected domain, and the degree of chaos in the temperature distribution characterizes the degree of fluctuation of the temperature gradient of each pixel point in the target connected domain;

[0012] If the degree of abnormality is greater than the threshold, the production efficiency of the steam booster is abnormal.

[0013] The above solution obtains infrared thermal maps at multiple angles at any position on the surface of the venturi tube of the steam booster at different times and calculates the probability that a pixel point in each infrared thermal map at each time belongs to the edge. The probability is positively correlated with the gradient magnitude of any pixel point in any one of the R, G, and B channels in the corresponding infrared thermal map and the importance degree of the corresponding channel. Among them, the importance degree characterizes the change in the difference between the pixel values of the pixel points in the target area and the background area in any channel in the historical infrared thermal maps of each historical abnormal production. If the probability is greater than the preset threshold, the corresponding pixel point belongs to an edge pixel point. Based on all the edge pixel points, a connected domain of the corresponding infrared thermal map is obtained, and the overlapping area of the connected domains at all angles at each time obtained is used as the target connected domain at the corresponding time. Calculate the degree of abnormality at any position. Among them, the degree of abnormality is positively correlated with the degree of chaos in the temperature distribution of the target connected domain at each time and inversely correlated with the area of the corresponding target connected domain. The degree of chaos in the temperature distribution characterizes the degree of fluctuation of the temperature gradient of each pixel point in the target connected domain. If the degree of abnormality is greater than the threshold, the production efficiency of the steam booster is abnormal. Therefore, the solution of the present invention can more accurately find the abnormal position, enabling the maintenance personnel to quickly repair or maintain the abnormal position.

[0014] Optionally, the degree of abnormality is specifically: ;

[0015] where Q c represents the degree of abnormality at the c-th position, M c represents the total number of moments of the infrared thermal map taken at the c-th position, S k,c represents the area of the target connected region at the c-th position at the k-th moment, represents the average value of the areas of the target connected regions at all moments at the c-th position, H k represents the degree of temperature distribution disorder of the target connected region at the k-th moment, and exp( ) is the exponential function with the natural constant e as the base.

[0016] The above solution provides an important reference basis for monitoring the production efficiency of the steam booster by calculating the degree of abnormality.

[0017] Optionally, the degree of importance specifically includes:

[0018] ;

[0019] where D i represents the degree of importance of channel i; m represents the number of historical infrared thermal maps of historical abnormal production collected, a i,j represents the average value of the pixel values of all pixel points in the target area of the j-th historical infrared thermal map of historical abnormal production on channel i, b i,j represents the average value of the pixel values of all pixel points in the background area of the j-th historical infrared thermal map of historical abnormal production on channel i; the target area is the abnormal temperature distribution area obtained by segmenting the j-th historical infrared thermal map, and the background area is the normal temperature distribution area obtained by segmenting the j-th historical infrared thermal map.

[0020] The above solution provides a method for accurately calculating the degree of importance of the RGB channels.

[0021] Optionally, the probability is specifically:

[0022] ;

[0023] where P is the probability that the pixel point belongs to the edge point, D i represents the degree of importance of channel i, F i is the gradient magnitude of the pixel point on channel i, max(F) is the maximum value of the gradient magnitude, and channel i is any one of the R, G, and B channels.

[0024] The above solution can extract the connected region by calculating the probability that the pixel point belongs to the edge pixel point, and can obtain an accurate connected region.

[0025] Optionally, the degree of temperature distribution disorder is specifically:

[0026] ;

[0027] where H k represents the degree of temperature distribution disorder of the target connected region at the k-th moment, N represents the set of different directions, represents the standard deviation of the temperature gradient of any pixel point in the target connected region in the l-th direction, and norm() is a normalization function.

[0028] The above solution calculates the degree of temperature disorder to obtain the temperature distribution on the surface of the steam-raising machine Venturi tube, providing an important reference basis for monitoring the production efficiency of the steam-raising machine.

[0029] Optionally, the degree of temperature distribution disorder is obtained by calculating the entropy of the temperature gradients of each pixel point in the target connected region.

[0030] Optionally, it further includes: the step of denoising each infrared thermal image using Gaussian filtering.

[0031] Optionally, after determining that the production efficiency of the steam-raising machine is abnormal, an abnormal report is generated, and the abnormal report includes the abnormal location, the degree of abnormality, and the recommended maintenance measures.

[0032] Optionally, after determining that the production efficiency of the steam-raising machine is abnormal, it further includes:

[0033] Establishing and maintaining a database for storing the infrared thermal images, the calculation results of the importance degrees of the RGB channels, the data for analyzing the degree of abnormality, and the maintenance records.

[0034] Optionally, the historical infrared thermal image of the historical abnormal production is the infrared thermal image collected when there is an abnormality in the amount of steam produced per unit time by the historical steam-raising machine.

[0035] The beneficial effects of the present invention are:

[0036] The solution of the present invention calculates the channel degrees on different channels of pixel points using the historical infrared thermal images of historical abnormal production, analyzes the current infrared thermal image based on the channel degrees to extract connected regions, and then synthesizes the connected regions from multiple angles to determine the final target connected region. By analyzing the target connected region, the abnormal location can be found more accurately, enabling maintenance personnel to quickly repair or maintain the abnormal location. Description of the Drawings

[0037] Figure 1The flowchart of the steps for a method of identifying the production efficiency of a steam booster in this embodiment is schematically shown. Detailed implementation manners

[0038] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, rather than all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0039] It should be understood that the sequence numbers of the steps in the following embodiments do not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0040] The present invention is directed to a detection scheme for the production efficiency of a steam booster. The detection scheme for the production efficiency of the steam booster needs to accurately identify the production efficiency of the steam booster by using image processing technology.

[0041] Therefore, based on the above content, the present invention provides a method and system for identifying the production efficiency of a steam booster to accurately detect the production efficiency of the steam booster.

[0042] Specifically, as Figure 1 shown, a method for identifying the production efficiency of a steam booster in this embodiment includes the following steps:

[0043] Step S1: Obtain infrared thermal maps at multiple angles at any position on the surface of the venturi tube of the steam booster at different times.

[0044] Specifically, the production efficiency of the steam booster is mainly measured by the temperature, pressure, and flow rate of the output steam. When the steam booster is blocked or leaks, it will cause a decrease in flow rate and abnormal production efficiency. This is because the steam booster is blocked or leaks, and the main manifestation of the blockage or leakage of the steam booster is the abnormal temperature distribution on the surface of the venturi tube of the steam booster. Therefore, infrared thermal imaging devices are placed at different angles on the surface of the venturi tube of the steam booster, and the infrared thermal imaging devices are used to continuously capture infrared thermal maps of multiple angles on the surface of the venturi tube of the steam booster. Gaussian filtering is used to denoise the infrared thermal maps, and then the infrared thermal maps of multiple angles on the surface of the venturi tube and the temperature values corresponding to the pixel points in the infrared thermal maps can be obtained.

[0045] Among them, the obtained infrared thermal map is the current thermal map, and a set of multi-angle infrared thermal maps corresponds to each moment. The multi-angle infrared thermal map of the surface of the venturi tube of the steam booster refers to the image representation of the temperature distribution measurement of the surface of the venturi tube in the steam booster from multiple angles by using infrared thermal imaging technology. Such a thermal map can intuitively display the temperature distribution of the venturi tube under different working conditions, thereby helping to analyze the heat exchange performance of the venturi tube and possible heat loss or hot spot areas. The denoising processing parameters of the Gaussian filter can be adjusted according to the noise level requirements of the infrared thermal map.

[0046] In this embodiment, by obtaining the multi-angle infrared thermal maps of multiple positions on the surface of the venturi tube of the steam booster at different moments, and preprocessing the infrared thermal maps of each position, so as to obtain multiple infrared thermal maps corresponding to each moment, and analyze the abnormal situation of the temperature distribution on the surface of the venturi tube of the steam booster.

[0047] Step S2: Calculate the probability that the pixel points in each infrared thermal map at each moment belong to the edge. If the probability is greater than the preset threshold, the corresponding pixel points belong to the edge pixel points. Based on all the edge pixel points, obtain the connected domain of the corresponding infrared thermal map, and use the overlapping area of the connected domains of all angles at each moment obtained as the target connected domain at the corresponding moment.

[0048] Specifically, due to the different radiation amounts of the venturi tube of the steam booster at different angles, the same position in the infrared thermal maps of the venturi tube of the steam booster taken at different angles shows different temperatures and temperature distributions, and the phenomenon that local temperature fluctuations are misidentified as gas flow blockage or steam booster leakage occurs.

[0049] Therefore, in this embodiment, by obtaining the historical infrared thermal maps of historical abnormal production, calculating the importance of the pixel points in the historical infrared thermal maps on different channels, and then using the gradient amplitude of each channel and the importance of each channel to obtain the edge pixel points in each current infrared thermal map, so as to obtain the connected domain of each image, and then using the overlapping part of the connected domains of each current infrared thermal map as the target connected domain.

[0050] It should be noted that the obtained historical infrared thermal map has the same position as the current infrared thermal map of any position to be detected.

[0051] In this embodiment, calculate the importance of the pixel points in the historical infrared thermal map in the three channels of R, G, and B, calculate the probability that each pixel point in the current infrared thermal map belongs to the edge pixel point according to each importance. If the probability is greater than the preset threshold, the corresponding pixel point belongs to the edge pixel point, and use the edge pixel points to obtain the connected domain of the corresponding current infrared thermal map.

[0052] Among them, the connected region helps to identify and analyze the temperature distribution on the surface of the steam booster. In the infrared thermal image, the connected region usually represents a set of pixel points with similar temperature values. These sets of pixel points are obtained by sequentially connecting continuous edge pixel points to form a complete region.

[0053] In the present invention, by analyzing the connected region in the infrared thermal image of the steam booster, the region with abnormal temperature can be identified. The gradient magnitude of the RGB channels refers to the rate or intensity difference of the pixel value change of the image on each of the three channels of red (R), green (G), and blue (B).

[0054] In this embodiment, since the infrared thermal image is an RGB image obtained by color mapping of temperature, the brightness difference of different colors may be small, resulting in the phenomenon that the extracted connected region of the traditional image is too large or too small when extracted based on the pixel value or pixel gradient of the pixel points. Therefore, the present invention calculates the importance degree of each channel according to the pixel points in the target region and the background region of the historical infrared thermal images of historical abnormal production, so as to obtain the importance degree of the three channels, and obtains the probability that the pixel point is an edge pixel point according to the importance degree and the gradient magnitude on each channel.

[0055] The calculation of the importance degree is as follows: ;

[0056] Among them, D i represents the importance degree of channel i; m represents the number of historical infrared thermal images of historical abnormal production collected, and a i,j represents the average value of the pixel values of all pixel points in the target region of the j-th historical infrared thermal image of historical abnormal production on channel i, and b i,j represents the average value of the pixel values of all pixel points in the background region of the j-th historical infrared thermal image of historical abnormal production on channel i.

[0057] Among them, the target region is the abnormal temperature distribution region obtained by segmenting the th historical infrared thermal image, and the background region is the normal temperature distribution region obtained by segmenting the th historical infrared thermal image. represents the difference between the connected region of the steam booster with abnormal production and the background region on channel i.

[0058] The above segmentation can use an image segmentation method to divide the historical infrared thermal image into regions.

[0059] Using the gradient magnitude of each channel and the importance degree of each channel to calculate the probability that each pixel point in the image belongs to an edge point, the specific calculation process of the probability is as follows: ;

[0060] where P is the probability that a pixel belongs to an edge point, D i represents the importance of channel i, and F i is the gradient magnitude of the pixel at channel i, max(F) is the maximum value of the gradient magnitude, and channel i is any one of the three channels R, G, and B.

[0061] After obtaining the probabilities of each pixel and the edge pixels, the pixels with the probability of each pixel and the edge pixels greater than the target threshold are used as edge pixels to extract the connected regions in the corresponding current infrared thermal image.

[0062] Step S3: Calculate the degree of abnormality at any position.

[0063] Specifically, since the abnormal temperature distribution when the steam booster is blocked or leaking usually shows irregular gradient changes from the center point of the blockage or leakage to the surrounding areas, therefore, the present invention calculates the degree of temperature distribution disorder in the connected region at each moment according to the gradients of the pixels in the target connected region at each position in different directions, and calculates the degree of abnormality at the corresponding position according to the degree of temperature distribution disorder and the area at each moment.

[0064] In this embodiment, the degree of temperature distribution disorder in the connected region at each moment is calculated by the gradients of the pixels in the target connected region in different directions, specifically: ;

[0065] where H k represents the degree of temperature distribution disorder of the target connected region at the k-th moment, N represents the set of different directions, represents the standard deviation of the temperature gradient of any pixel in the target connected region in the l-th direction, ( ) is the normalization function.

[0066] Among them, the directions in the set of directions can be multiple directions such as 0°, 45°, 90°, 135°, etc. The larger it is, the more irregular the temperature gradient change in the connected region in this direction is. Therefore, the probability of blockage or abnormality is greater.

[0067] Since there is a situation of uneven mixing of the motive steam and the inhaled exhausted steam in the steam booster, resulting in a short-term abnormal temperature distribution in some areas on the surface of the venturi tube of the steam booster, using the infrared thermal image at a certain moment will cause the normal production state to be recognized as abnormal. Therefore, the present invention calculates the degree of abnormality at each position according to the degree of temperature distribution disorder and the area of the target connected region at each position. The calculation of the degree of abnormality is: ;

[0068] Q c represents the degree of abnormality at the c-th position, and M cDenotes the total number of moments of the infrared thermal map taken at the c-th position, S k,c Denotes the area of the target connected region at the k-th moment at the c-th position, Denotes the average value of the areas of the target connected regions at all moments at the c-th position, H k Denotes the degree of disorder of the temperature distribution of the target connected region at the k-th moment. The greater the degree of disorder of the temperature distribution, the greater the degree of abnormality. Since H k There is a case where it is 0. Therefore, 0.001 is introduced, and exp( ) is the exponential function with the natural constant e as the base.

[0069] Denotes the degree of fluctuation of the area of the target connected region at the k-th moment at the c-th position. Since there are abnormal temperature distributions in the blocked or leaked areas at all moments, the change in the area of the target connected region is small, which means that the probability of abnormality at the c-th position is greater and the degree of abnormality is greater.

[0070] In this embodiment, by calculating the gradients of the pixel points in the target connected region in different directions, the degree of disorder of the temperature distribution in the target connected region is evaluated, and according to the degree of disorder of the temperature distribution and the degree of area fluctuation in the target connected region at each moment, the degree of abnormality of each position on the surface of the steam injector Venturi tube is calculated, so as to identify the abnormality of the production efficiency of the steam injector according to the degree of abnormality.

[0071] Step S4: If the degree of abnormality is greater than the threshold value, the production efficiency of the steam injector is abnormal.

[0072] Specifically, when the degree of abnormality of one position on the surface of the steam injector Venturi tube is greater than the preset threshold value, it indicates that there is a blockage or leakage at this position and the production efficiency of the steam injector is abnormal, and relevant personnel are arranged for inspection and maintenance. Otherwise, it indicates that the production efficiency of the steam injector is normal.

[0073] Optionally, after determining whether the production efficiency of the steam injector is abnormal, an abnormality report can be generated. Among them, the abnormality report includes the abnormal position, the degree of abnormality, and the recommended inspection and maintenance measures, so that the user can repair or perform regular maintenance on the abnormal position.

[0074] Optionally, after determining whether the production efficiency of the steam injector is abnormal, a database is established and maintained for storing historical infrared thermal maps, calculation results of channel importance, data of abnormality degree analysis, and inspection and maintenance records, so as to facilitate subsequent analysis and improvement.

[0075] In this embodiment, by obtaining the degree of abnormality of each position on the surface of the steam injector Venturi tube and comparing it with the preset threshold value, when the degree of abnormality of a position is greater than the preset threshold value, an abnormality warning is given, and thus it can be known whether the production efficiency of the steam injector is normal.

Claims

1. A method for identifying the production efficiency of a steam turbine, characterized in that: include: Obtain infrared thermal images of any position on the surface of the venturi tube of the steam booster at multiple angles at different times; The probability that a pixel point in each infrared thermogram belongs to an edge at each moment is calculated, and the probability is positively correlated with the gradient amplitude of any pixel point in the corresponding infrared thermogram in any of the three channels R, G, and B, and the importance of any channel; the importance represents the difference change between the pixel values ​​of the pixel points in the target area and the pixel points in the background area in any channel in the historical infrared thermogram of each historical abnormal production; If the probability is greater than a preset threshold, the corresponding pixel point belongs to an edge pixel point, and a connected domain of the corresponding infrared thermal map is obtained based on all edge pixels, and the overlapping area of ​​the connected domains at all angles at each moment is taken as the target connected domain at the corresponding moment; Calculate the degree of abnormality at any location, specifically: ; Among them, Q c Indicates the abnormality of the cth position; M c represents the total number of times the infrared thermal image is taken at the cth position; S k,c represents the area of ​​the target connected domain at the c-th position at the k-th time; represents the average area of ​​the target connected domain at the c-th position at all times; H k Indicates the degree of disorder of temperature distribution in the target connected domain at the kth moment, which characterizes the degree of fluctuation of temperature gradient of each pixel in the target connected domain in different directions; exp( ) is an exponential function with the natural constant e as the base; If the abnormality degree is greater than a threshold value, the production efficiency of the steam booster is abnormal.

2. A method for identifying the production efficiency of a steam booster according to claim 1, characterized in that: The degree of importance specifically includes: ; Among them, D i represents the importance of channel i; m represents the number of historical infrared thermal images of historical abnormal production collected, a i,j The average pixel value of all pixels in the target area on channel i in the jth historical infrared thermal map representing historical abnormal production, b i,j The target area is the abnormal temperature distribution area obtained by segmenting the j-th historical infrared thermogram, and the background area is the normal temperature distribution area obtained by segmenting the j-th historical infrared thermogram.

3. A method for identifying the production efficiency of a steam booster according to claim 1, characterized in that: The probability is specifically: ; Among them, P is the probability that the pixel belongs to the edge point, D i Indicates the importance of channel i, F i is the gradient amplitude of the pixel in channel i, max(F) is the maximum value of the gradient amplitude, and channel i is any of the three channels R, G, and B.

4. A method for identifying steam booster production efficiency according to claim 1, characterized in that: The degree of disorder of the temperature distribution is specifically: ; Among them, H k represents the degree of temperature distribution disorder of the target connected domain at the kth moment, N represents the collection of different directions, It represents the standard deviation of the temperature gradient in the lth direction of any pixel in the target connected domain, and norm() is the standardization function.

5. A method for identifying production efficiency of a steam booster according to claim 1, characterized in that: The degree of disorder of the temperature distribution is obtained by calculating the entropy of the temperature gradient of each pixel in the target connected domain.

6. A method for identifying the production efficiency of a steam booster according to claim 1, characterized in that: Also includes: The steps of using Gaussian filtering to denoise each infrared thermal image.

7. A method for identifying steam booster production efficiency according to claim 1, characterized in that: Also includes: After determining that the production efficiency of the steam booster is abnormal, an abnormality report is generated, wherein the abnormality report includes the abnormality location, the abnormality degree and the recommended repair and maintenance measures.

8. A method for identifying steam booster production efficiency according to claim 1, characterized in that: After judging that the production efficiency of the steam booster is abnormal, it also includes: Establish and maintain a database for storing the infrared thermal map, calculation results of the importance of the RGB channels, abnormality analysis data, and inspection and maintenance records.

9. A method for identifying steam booster production efficiency according to claim 1, characterized in that: The historical infrared thermogram of historical abnormal production is an infrared thermogram of the historical steam booster turbine produced when the steam volume per unit time was abnormal.

Images