A computer-aided-based power construction project construction quality monitoring method

Abstract

The application relates to the technical field of quality monitoring, in particular to a computer-aided power construction engineering construction quality monitoring method, which comprises the following steps: acquiring an image of a region to be monitored; dividing the image into multiple regions; acquiring edges and highlighted edges in each region; acquiring a welding seam existence factor of each region according to the distance between highlighted edges, the distance between edge center points and the shape difference of the edges in the images of the region at previous and subsequent time points; acquiring a welding seam determination coefficient of each region at the current time point in combination with the difference between the number of edges, the difference between the average gray values of the edges and the difference between the average levels of the edge lengths of the region at the previous and subsequent time points; and further acquiring a welding seam region at the current time point; and judging whether welding quality problems exist in each welding seam region. The welding quality monitoring precision in the power construction process is improved by accurately acquiring the welding seam region.

Description

Technical Field

[0001] This application relates to the field of quality monitoring technology, specifically to a computer-aided method for monitoring the construction quality of power construction projects. Background Technology

[0002] Inspecting the installation quality of equipment in power construction projects is a crucial step in ensuring the safe operation of the power system. Therefore, computer vision-assisted methods are typically used for quality monitoring, based on relevant equipment quality control requirements. The installation of large gas turbine equipment is a critical component of power construction projects. For large gas turbines, the main installation process involves welding the various modules together. Therefore, the quality of welding directly determines the overall quality of the power construction project, making weld monitoring a vital aspect of power construction quality control.

[0003] Construction sites present complex and variable environments with diverse equipment, materials, and personnel. Furthermore, factors such as obstruction, excessively bright or dim lighting often interfere with the process, resulting in indistinct weld features in acquired images and compromising the accuracy of installation quality monitoring. Traditional solutions involve histogram enhancement of the acquired gas turbine images, followed by image recognition and segmentation to identify weld areas. However, due to variations in the location of the gas turbine and its welds, and the varying degrees of interference from obstruction and lighting (which can change with environmental factors like light intensity and angle), histogram enhancement can distort images, leading to the loss of weld features and inaccurate monitoring of weld quality. Therefore, a construction quality monitoring method adaptable to environmental changes is urgently needed. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a computer-aided method for monitoring the construction quality of power engineering projects, thereby resolving the existing issues.

[0005] The computer-aided construction quality monitoring method for power construction projects proposed in this application adopts the following technical solution:

[0006] One embodiment of this application provides a computer-aided method for monitoring the construction quality of power engineering projects, the method comprising the following steps:

[0007] Acquire images of the monitored area of ​​target equipment during the construction of power engineering projects;

[0008] The image is uniformly divided into multiple regions; the edges in each region are obtained, and the highlighted edges in each region are identified; the highlighted edges in each region are numbered; the edge movement factor of each region at the current moment is obtained based on the distance between the center points of all highlighted edges with the same number in the current moment image and the previous moment image, and the weld presence factor of each region at the current moment is obtained by combining the difference between the dispersion of the distance between the center points of all edges in each region at the current moment and the dispersion of the distance between the center points of all edges in each region at the previous moment, as well as the shape difference between all edges in each region at the current moment and all edges in each region at the previous moment.

[0009] Based on the differences in the number of edges, the average gray value of the edges, and the average level of edge length between different time periods, the reflectivity of each region at the current time is obtained. Combined with the weld presence factor of each region, the weld determination coefficient of each region at the current time is obtained, thereby obtaining the weld region at the current time; and determining whether there are welding quality problems in each weld region.

[0010] Preferably, the specific process for highlighting the edges in each region is as follows: the edges in each region whose average gray value is greater than or equal to a preset segmentation threshold are taken as the highlighting edges of each region.

[0011] Preferably, the specific process of numbering the highlighted edges in each region is as follows: all highlighted edges in each region are numbered in ascending order of the horizontal coordinate of the center point of the highlighted edge; when two or more highlighted edges have the same horizontal coordinate, the center points with the same horizontal coordinate are numbered in ascending order of the vertical coordinate.

[0012] Preferably, the edge movement factor of each region at the current time is the sum of the Euclidean distances between the center points of all highlighted edges with the same number in each region at the current time and at the previous time.

[0013] Preferably, the formula for calculating the weld presence factor in each region at the current moment is: In the formula, Let the weld existence factor be the weld seam presence factor of the i-th region at the current time. Let be the edge movement factor of the i-th region at the current time. Let be the absolute difference between the variance of the Euclidean distance between any two edge center points of the i-th region at the current time and the variance of the Euclidean distance between any two edge center points at the previous time. It is the absolute difference between the variance of the slope of pixels in all edges of the i-th region at the current time and the variance of the slope of pixels in all edges at the previous time.

[0014] Preferably, the slope of the pixels in the edge is obtained by performing curve fitting on each edge and obtaining the slope of each pixel in each edge according to the differential equation of the fitted curve of each edge.

[0015] Preferably, the formula for calculating the reflectivity of each region at the current moment is: In the formula, Let i be the reflectivity of the i-th region at the current time. and Let be the total number of edges of the i-th region at the current time and the previous time, respectively. and Let be the average gray values ​​of all edges of the i-th region at the current time and the previous time, respectively. and These are the average lengths of all edges in the i-th region at the current time and the previous time, respectively.

[0016] Preferably, the formula for calculating the weld determination coefficient of each region at the current moment is: In the formula, Determine the coefficients for the weld seam in the i-th region at the current time. Let the weld existence factor be the weld seam presence factor of the i-th region at the current time. Let i be the reflectivity of the i-th region at the current time. This is a preset constant.

[0017] Preferably, the weld region at the current moment is the region where the weld determination coefficient at the current moment is greater than or equal to the preset weld threshold.

[0018] Preferably, the specific process for determining whether there is a welding quality problem in each weld area is as follows: acquire a weld image database; use the standard weld images in the weld image database as template images for the template matching algorithm, use each weld area at the current moment as the target image for the template matching algorithm, and output the matching score of each weld area; when the matching score of a single weld area is greater than or equal to a preset matching threshold, it is determined that there is no welding quality problem in the weld area; otherwise, it is determined that there is a welding quality problem in the weld area.

[0019] This application has at least the following beneficial effects:

[0020] This application addresses the problem that when using traditional methods to process images of the monitored area of ​​target equipment affected by reflection, environmental interference factors may change over time, making it impossible to accurately identify the area where the weld is located. By analyzing the differences between the weld features in each area and the reflective features produced by the surface of the target equipment when the monitored area is affected by environmental changes, the location of the weld in the image can be accurately determined. This allows for computer-aided evaluation of the welding quality of the equipment, improving the accuracy of equipment welding quality monitoring during power construction projects. Attached Figure Description

[0021] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating the steps of a computer-aided method for monitoring the construction quality of power engineering projects, provided in this application;

[0023] Figure 2 A flowchart for obtaining the weld determination coefficients for each region at the current moment, as provided in this application. Detailed Implementation

[0024] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a computer-aided method for monitoring the construction quality of power construction projects proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0025] Unless otherwise defined, 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 application pertains.

[0026] The following description, in conjunction with the accompanying drawings, details a specific scheme for a computer-aided method for monitoring the construction quality of power engineering projects provided in this application.

[0027] This application provides a computer-aided method for monitoring the construction quality of power construction projects, specifically, the following method is provided. Please refer to [link to relevant documentation]. Figure 1 The method includes the following steps:

[0028] Step 1: Obtain images of the target equipment's monitoring area during the construction of the power project.

[0029] This embodiment uses a gas turbine unit at a power construction site as the target equipment. A CMOS high-definition camera is installed in the monitoring area of ​​the target equipment, and image data is acquired every time interval T. The acquired images are color RGB images. In this embodiment, T=2min. The implementer can adjust the time interval according to changes in interference factors in the actual construction environment.

[0030] A weld image database was constructed using historically collected weld image data. The weld image database contains standard weld images without welding quality problems.

[0031] Step 2: Divide the image evenly into multiple regions; obtain the edges in each region and identify the highlighted edges in each region; number the highlighted edges in each region; obtain the edge movement factor of each region at the current moment based on the distance between the center points of all highlighted edges with the same number in the current image and the previous image, and combine the difference between the dispersion of the distance between the center points of all edges in each region at the current moment and the dispersion of the distance between the center points of all edges in each region at the previous moment, as well as the shape difference between all edges in each region at the current moment and all edges in the previous moment, to obtain the weld presence factor of each region at the current moment.

[0032] Because the gas turbine equipment is entirely made of metal, it exhibits significant reflection under both ambient and artificial light, resulting in bright areas in the image. This interference can prevent the proper identification of quality control points. Furthermore, due to its metallic nature, the gas turbine surface has numerous reflective areas; not all reflective areas are areas requiring monitoring, necessitating careful differentiation.

[0033] Specifically, for sealed welding locations, the weld seam typically exhibits numerous regularly arranged, similarly shaped parallel stripes. Under strong light, the weld seam may reflect light, displaying a stepped brightness variation between its edges. The brightness increase between the edges is relatively uniform, and the position of the bright edges within the weld seam will change slightly with changes in the angle of the light source or the location of any obstruction, but the edge shape and spacing remain similar. Conversely, if the reflection occurs on the metal surface of the equipment outside the weld seam, it will appear as a large area of ​​high brightness with a lower degree of regularity, and the stripes will be unevenly distributed. The size of the bright area will change with changes in the position of the light source or any obstruction.

[0034] To analyze different locations in the image, this embodiment uniformly divides each acquired image into z×z regions of equal size (in this embodiment, z=8; the implementer can adjust this according to actual accuracy requirements; higher accuracy requires more regions, and vice versa). The acquired image is converted into a grayscale image. Each region in the grayscale image is used as input, and the Canny edge detection algorithm and dilation erosion algorithm are used to output all edges of each region in the image. The Canny edge detection algorithm and dilation erosion algorithm are well-known technologies, and their processes will not be described in detail here. The average grayscale value of each edge in each region is used as input, and the Otsu thresholding method is used to output a segmentation threshold. The obtained segmentation threshold is recorded as the preset segmentation threshold. Edges with an average grayscale value greater than or equal to the preset segmentation threshold are considered as bright edges of that region. For the detected bright edges in each region, they are sorted according to the abscissa of the center point of the bright edges in ascending order, and all bright edges in each region are numbered. For example, the bright edge with the smallest abscissa of the center point is the first bright edge, and so on. It should be noted that when two or more highlight edge center points have the same x-coordinate, the center points with the same x-coordinate are numbered in ascending order of their y-coordinates.

[0035] The sum of the Euclidean distances between the center points of all highlighted edges with the same number in the i-th region at the current time and at the previous time is denoted as the edge movement factor of the i-th region at the current time. It should be noted that if the total number of highlighted edges detected at two different times is different, the one with the smaller total number of highlighted edges shall be used, and the excess highlighted edges shall not be calculated.

[0036] Curve fitting is performed on all edges in the i-th region, and the slope of each pixel in each edge is obtained based on the differential equation of the fitted curve of each edge. The curve fitting algorithm can be least squares, polynomial fitting, or nonparametric fitting; this embodiment does not impose any specific limitations.

[0037] As a preferred embodiment, the weld presence factor of each region at the current moment is obtained based on the edge movement factor of each region at the current moment, the difference between the dispersion of the distance between all edge center points of each region at the current moment and the dispersion of the distance between all edge center points of each region at the previous moment, and the shape difference between all edges of each region at the current moment and all edges of each region at the previous moment. This factor is used to measure the probability that a single region at the current moment is where the weld is located.

[0038] In this embodiment, the weld presence factor of the i-th region at the current time is denoted as... Its specific expression is: In the formula, Let the weld existence factor be the weld seam presence factor of the i-th region at the current time. Let be the edge movement factor of the i-th region at the current time. Let be the absolute difference between the variance of the Euclidean distance between any two edge center points of the i-th region at the current time and the variance of the Euclidean distance between any two edge center points at the previous time. It is the absolute difference between the variance of the slope of pixels in all edges of the i-th region at the current time and the variance of the slope of pixels in all edges at the previous time.

[0039] The meaning of this expression is: the smaller the difference between the position of the highlighted edge in a single region at the current moment and the previous moment, the more similar the distance between the edges, and the more similar the shape between the edges, the more likely there is a weld in the region, and the more likely it is the area where the quality control point for construction quality monitoring is located.

[0040] Step 3: Based on the differences in the number of edges, the average gray value of the edges, and the average level of edge length between different times in each region, obtain the reflectivity of each region at the current time. Combine this with the weld presence factor of each region to obtain the weld determination coefficient of each region at the current time, and then obtain the weld region at the current time; determine whether there are welding quality problems in each weld region.

[0041] Furthermore, due to the differences in the location, intensity, and angle of light source illumination of equipment within the power plant, the presence of numerous moving objects and people, and the high smoothness of the metal surfaces of the gas turbine equipment, the reflections generated on the gas turbine equipment surface may include not only bright areas but also areas reflecting the scenery inside the plant. Since the gas turbine equipment surface is curved, the reflected light onto objects or people inside the plant also appears as parallel, similarly shaped stripes. Therefore, using only the above methods for calculation may not accurately distinguish the actual location of the weld, thus missing the inspection of that area. Further analysis is therefore required.

[0042] For the reflection of the curved metal surface of the gas turbine equipment, the main reflections are of people and objects in the factory. Since the objects and people in the factory will move in position, and the external light sources (i.e., light sources shining in from windows and factory doors) will change their angle of illumination over time, the objects or people in the factory reflected on the surface of the gas turbine equipment will change over time. Specifically, the number of edges in a single area will change over time, and the length and brightness of the edges will also change over time.

[0043] As a preferred implementation, the reflectivity of each region at the current moment is obtained based on the differences in the number of edges before and after each region, the differences in the average gray value of the edges, and the differences in the average level of edge length. This is used to characterize the possibility that the edge stripes in each region at the current moment are edge stripes produced by objects in a reflective scene.

[0044] In this embodiment, the reflectivity of the i-th region at the current time is denoted as... Its specific expression is: In the formula, Let i be the reflectivity of the i-th region at the current time. and Let be the total number of edges of the i-th region at the current time and the previous time, respectively. and Let be the average gray values ​​of all edges of the i-th region at the current time and the previous time, respectively. and These are the average lengths of all edges in the i-th region at the current time and the previous time, respectively.

[0045] The meaning of this expression is: the greater the difference between the total number of edges in the current moment and the previous moment in the i-th region, and the greater the change in edge brightness and edge length over time, the more likely the edge stripes in this region are edge stripes produced by the reflection of objects in the scene on the surface of the gas turbine equipment.

[0046] Furthermore, as a preferred embodiment, based on the weld presence factor and reflectivity factor of each region at the current moment, a weld determination coefficient for each region is obtained, characterizing the probability that each region in the current image is a weld location. The process for obtaining the weld determination coefficient for each region at the current moment is as follows: Figure 2 As shown.

[0047] In this embodiment, the weld determination coefficient of the i-th region at the current time is denoted as... Its specific expression is: In the formula, Determine the coefficients for the weld seam in the i-th region at the current time. Let the weld existence factor be the weld seam presence factor of the i-th region at the current time. Let i be the reflectivity of the i-th region at the current time. This is a preset constant used to prevent the denominator from being 0; in this embodiment, it is set to 0.1.

[0048] The meaning of this expression is: the higher the probability of a weld seam existing in the i-th region of the currently acquired image, and the lower the probability of edge stripes caused by reflection of light on the surface of the gas turbine equipment in that region, the more likely that region is the location of the weld seam, and the more necessary it is to carry out quality monitoring work in that region.

[0049] Using the above method, the weld determination coefficients for all regions in the image acquired at each time moment can be calculated. These weld determination coefficients are then used as input, and cross-validation is employed to output a segmentation threshold for the weld determination coefficients. This segmentation threshold is recorded as the preset weld threshold. When the weld determination coefficient of a single region is greater than or equal to the preset weld threshold, a weld is considered to exist in that region, and that region is designated as a weld region. The cross-validation method is a well-known technique and will not be elaborated upon in this application.

[0050] Furthermore, standard gas turbine weld seam image data from the weld seam image database is used as the template image for the template matching algorithm. Each acquired weld seam region is used as the target image for the template matching algorithm, and both are inputs to the algorithm, outputting a matching score for each weld seam region. The template matching algorithm is a well-known technique, and its specific process will not be detailed here. When the matching score of a single weld seam region is greater than or equal to a preset matching threshold, it is determined that the weld seam region does not have a welding quality problem; otherwise, it is determined that the weld seam region has a welding quality problem. In this case, the computer sends the weld seam location information in the current image to the mobile device of the relevant technician and guides the technician to conduct on-site inspection. In this embodiment, the preset matching threshold is 0.98, which can be adjusted by the implementer according to actual accuracy requirements.

[0051] Thus, a computer-aided method for monitoring the construction quality of power engineering projects has been completed.

[0052] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0053] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0054] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some of the technical features, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A computer-aided method for monitoring the construction quality of power engineering projects, characterized in that, The method includes the following steps: Acquire images of the monitored area of ​​target equipment during the construction of power engineering projects; The image is uniformly divided into multiple regions; the edges in each region are obtained, and the highlighted edges in each region are identified; the highlighted edges in each region are numbered; the edge movement factor of each region at the current moment is obtained based on the distance between the center points of all highlighted edges with the same number in the current moment image and the previous moment image, and the weld presence factor of each region at the current moment is obtained by combining the difference between the dispersion of the distance between the center points of all edges in each region at the current moment and the dispersion of the distance between the center points of all edges in each region at the previous moment, as well as the shape difference between all edges in each region at the current moment and all edges in each region at the previous moment. Based on the differences in the number of edges, the average gray value of the edges, and the average level of edge length between different regions, the reflectivity of each region at the current time is obtained. Combined with the weld presence factor of each region, the weld determination coefficient of each region at the current time is obtained, thereby obtaining the weld region at the current time; and determining whether there are welding quality problems in each weld region. The expression for the weld presence factor is: In the formula, Let the weld existence factor be the weld seam presence factor of the i-th region at the current time. Let be the edge movement factor of the i-th region at the current time. Let be the absolute difference between the variance of the Euclidean distance between any two edge center points of the i-th region at the current time and the variance of the Euclidean distance between any two edge center points at the previous time. It is the absolute difference between the variance of the slope of all pixels in the i-th region at the current time and the variance of the slope of all pixels in the previous time. The reflective factor is expressed as follows: In the formula, Let i be the reflectivity of the i-th region at the current time. and Let be the total number of edges of the i-th region at the current time and the previous time, respectively. and Let be the average gray values ​​of all edges of the i-th region at the current time and the previous time, respectively. and These are the average lengths of all edges in the i-th region at the current time and the previous time, respectively. The expression for the weld determination coefficient is: In the formula, Determine the coefficients for the weld seam in the i-th region at the current time. Let the weld existence factor be the weld seam presence factor of the i-th region at the current time. Let i be the reflectivity of the i-th region at the current time. This is a preset constant.

2. The computer-aided construction quality monitoring method for power construction projects as described in claim 1, characterized in that, The process for determining the highlighted edges in each region is as follows: edges in each region whose average gray value is greater than or equal to a preset segmentation threshold are taken as the highlighted edges of each region.

3. The computer-aided construction quality monitoring method for power construction projects as described in claim 1, characterized in that, The specific process of numbering the highlighted edges in each region is as follows: all highlighted edges in each region are numbered in ascending order of the horizontal coordinate of the center point of the highlighted edge; when two or more highlighted edges have the same horizontal coordinate, the center points with the same horizontal coordinate are numbered in ascending order of the vertical coordinate.

4. The computer-aided construction quality monitoring method for power construction projects as described in claim 1, characterized in that, The edge movement factor of each region at the current time is the sum of the Euclidean distances between the center points of all highlighted edges with the same number in each region at the current time and at the previous time.

5. The computer-aided construction quality monitoring method for power construction projects as described in claim 1, characterized in that, The slope of the pixels in the edge is obtained by performing curve fitting on each edge and obtaining the slope of each pixel in each edge according to the differential equation of the fitted curve of each edge.

6. The computer-aided construction quality monitoring method for power construction projects as described in claim 1, characterized in that, The weld region at the current moment is the region where the weld determination coefficient at the current moment is greater than or equal to the preset weld threshold.

7. The computer-aided construction quality monitoring method for power construction projects as described in claim 1, characterized in that, The specific process for determining whether there are welding quality problems in each weld area is as follows: obtain the weld image database; use the standard weld images in the weld image database as template images for the template matching algorithm, use each weld area at the current moment as the target image for the template matching algorithm, and output the matching score of each weld area; If the matching score of a single weld area is greater than or equal to the preset matching threshold, it is determined that there is no welding quality problem in that weld area; otherwise, it is determined that there is a welding quality problem in that weld area.

Images