A visualization method and system for steel structure construction based on BIM technology

By using image processing methods based on BIM technology, the features of steel structure construction components are extracted and quality assessment indices are generated. This solves the shortcomings of traditional BIM technology in real-time updates and welding assessments in steel structure construction, and enables the provision of accurate quality assessments and rectification plans.

CN118608615BActive Publication Date: 2024-11-12CCCC THIRD NAVIGATION (NANTONG) OFFSHORE ENG CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411088539.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-12
Estimated Expiration
2044-08-09

AI Technical Summary

Technical Problem

Traditional BIM technology struggles to update real-time site changes during steel structure construction, fails to effectively identify differences between temporary structures and the planning model at construction sites, and has limitations in welding effect evaluation methods due to insufficient timeliness, limited detection range, and high cost.

Method used

By acquiring measurement data and image information of the construction site, image scaling and grayscale processing are performed. Canny edge detection and grayscale co-occurrence matrix analysis are used to analyze weld texture, generate geometric deviation coefficient and welding coefficient, calculate quality assessment index, recommend rectification plan, and mark unqualified process points in BIM model.

Benefits of technology

It enables precise quality assessment of steel structure construction components, provides quantitative analysis and targeted rectification solutions, meets different construction needs and site conditions, and improves construction quality and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118608615B_ABST
    Figure CN118608615B_ABST
Patent Text Reader

Abstract

The present invention provides a steel structure construction visualization method and system based on BIM technology, and relates to the technical field of BIM. The present invention obtains measurement data and image information of a construction site and pre-processes the image, and uses the maximum inter-class variance method to segment the image background; extracts welding area texture features from the segmented image to obtain welding features, obtains a geometric deviation coefficient through measurement data, and obtains a welding coefficient through the welding features; generates a quality assessment index through the geometric deviation coefficient and the welding coefficient; determines whether a corresponding process point is qualified through the quality assessment index, analyzes the geometric deviation coefficient and the welding coefficient in historical plans, recommends rectification plans for unqualified process points, loads the plan into a BIM model, and marks the unqualified process points in the model, wherein the marking content includes the quality assessment index and the recommended plan.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of BIM technology, and in particular to a steel structure construction visualization method and system based on BIM technology. Background Art

[0002] In traditional steel structure construction management and monitoring, monitoring methods mainly rely on manual visual inspection and basic image processing technology, which limits the accuracy and objectivity of construction quality assessment. Although the application of building information modeling (BIM) technology in construction management is increasing, providing the ability to digitally represent and simulate the construction process in three dimensions, it still has significant deficiencies in processing real-time images of the construction site, accurately identifying construction sites, and making highly accurate quality assessments. Specifically, traditional BIM technology has difficulty in updating changes in the construction site in real time, resulting in the inability to effectively distinguish between temporary structures or errors in construction and the differences between the planning model. In addition, traditional methods are also unable to effectively identify and handle the complex environment of the construction site. These limitations have led to a slow response to potential problems in the construction process and an inability to promptly correct construction errors that may lead to serious consequences.

[0003] Welding is crucial in steel structure construction, and its quality directly affects the safety, stability and service life of the entire project. However, traditional means of welding effect evaluation, such as post-welding non-destructive testing, although they can provide relatively reliable judgments, have the disadvantages of insufficient timeliness, limited detection range and high cost. Image processing technology has the advantages of wide range, high precision and cost in welding effect evaluation, which make up for the shortcomings of traditional welding evaluation methods. Therefore, there is an urgent need for a method of evaluating welding effects based on image processing to detect the qualified status of steel structure construction processes.

[0004] In the prior art, the publication number BIM discloses a BIM-based construction visualization method and system thereof, which belongs to the field of BIM technology. The method includes: loading a BIM model, wherein the BIM model includes a three-dimensional model as a construction reference; setting defect feature information of building defects, wherein the defect feature information is used to characterize the distinguishing features from other types of building defects; setting rectification information corresponding to the defect feature information, wherein the rectification information is used to provide construction personnel with rectification plans for building defects; obtaining on-site construction images, wherein the on-site construction images are obtained by shooting; comparing the on-site construction images with images corresponding to the locations of the on-site construction images in the three-dimensional model, and when the defect feature information is identified, the rectification information can be obtained according to the defect feature information. The method has the advantages of realizing construction visualization and identifying construction defects and providing rectification plans. However, the prior art still has shortcomings. The distinguishing feature identification process of building defects in the prior art is particularly important for providing relevant rectification information and giving corresponding rectification plans, but the prior art does not have a specific discussion on the distinguishing features of building defects, and the plan lacks persuasiveness. Secondly, the prior art provides a set of rectification plans based on the distinguishing features of building defects and the corresponding rectification information, but depending on the actual situation, a single rectification plan may not necessarily meet complex actual needs.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a steel structure construction visualization method and system based on BIM technology to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A visualization method for steel structure construction based on BIM technology, the specific steps include:

[0009] Step 1: Obtain the measurement data and image information of the construction site, scale the original image, adjust the image size to 224*224, and then grayscale the image to obtain the construction image; build an ideal BIM model according to the design drawings, map the construction image to the corresponding position of the ideal BIM model, and the measurement data includes the weld width and welding inclination angle;

[0010] Step 2: Count the frequency of pixels at each level in the 256 gray levels to form a gray histogram, and calculate the inter-class variance of each threshold in the histogram. Select the best separation threshold through the inter-class variance, and use the best separation threshold to perform threshold segmentation on the construction site image, dividing the construction site image into the foreground part and the background part, and extract the foreground part as the construction site image;

[0011] Step 3: Use the Canny edge detection algorithm to extract the edge information of the construction components from the construction site image, and use the gray level co-occurrence matrix to perform texture analysis on the weld closed area; obtain the homogeneity, contrast and energy of the weld closed area texture; generate the welding coefficient through homogeneity, contrast and energy; generate the geometric deviation coefficient through the weld width and welding inclination angle;

[0012] Step 4: Generate a quality assessment index through the geometric deviation coefficient and the welding coefficient, compare the quality assessment index with the preset threshold, mark the process of the construction part with a quality assessment index less than the threshold as qualified, otherwise, mark the process of the construction part with a quality assessment index greater than or equal to the threshold as unqualified;

[0013] Step 5: Collect historical rectification plans for unqualified process locations, calculate the geometric deviation coefficient and welding coefficient of the historical rectification plans, generate the spatial deviation rate and welding deviation rate based on the historical geometric deviation coefficient, historical welding coefficient, actual geometric deviation coefficient and actual welding coefficient, and then generate the efficiency recommendation coefficient and quality recommendation coefficient based on the spatial deviation rate and welding deviation rate, and recommend rectification plans for unqualified process points based on the efficiency recommendation coefficient and quality recommendation coefficient;

[0014] Step 6: Load the BIM model and mark the unqualified process points in the BIM model. The marking content includes the quality assessment index and recommended rectification plan.

[0015] Furthermore, the specific logic for calculating the optimal separation threshold is:

[0016] Traverse all possible thresholds, divide the construction site image into background and foreground parts according to the value of each threshold, count the number of pixels in the background and foreground parts, calculate the mean of the grayscale values ​​of the pixels in the background and foreground parts, and calculate the inter-class variance of the corresponding threshold. The specific formula is:

[0017] σ(t) 2 =w B (t)*w F (t)*(μ B (t)-μ F (t)) 2

[0018] Among them, σ(t) 2represents the inter-class variance when the threshold is t, t∈[0, 255], and t∈N + , w B (t), w F (t) are the number of pixels in the background and foreground when the threshold is t, μ B (t), μ F (t) are the mean grayscale values ​​of the pixels in the background and foreground when the threshold is t;

[0019] Calculate the value of the threshold when the between-class variance reaches the maximum, and define this value as the optimal separation threshold.

[0020] Furthermore, the specific logic for extracting the edge information of each construction component using the Canny edge detection algorithm is: calculating the horizontal gradient and vertical gradient of the construction site image, and the specific formula is:

[0021]

[0022] Among them, I x is the horizontal gradient when the pixel coordinates are (x, y), I y is the vertical gradient when the pixel coordinates are (x, y), and I is the image grayscale value when the pixel coordinates are (x, y);

[0023] The image gradient amplitude is calculated by horizontal gradient and vertical gradient, and the specific formula is as follows:

[0024]

[0025] Among them, M x,y is the gradient amplitude when the pixel coordinates are (x, y),

[0026] The gradient amplitude M x,y The gradient amplitude is set to 1 when it is greater than the threshold; the gradient amplitude M x,y The gradient amplitude is set to 0 when it is less than or equal to the threshold.

[0027] Furthermore, the specific logic for generating the geometric deviation coefficient is as follows: the geometric deviation coefficient is generated according to the weld width and the welding inclination angle, and the specific formula is as follows:

[0028] SP=|A-A0|(W-W0) 2

[0029] Among them, SP is the geometric deviation coefficient, A is the weld width, A0 is the standard weld width, W is the welding inclination angle, and W0 is the standard welding inclination angle.

[0030] Furthermore, the specific logic for generating the welding coefficient is as follows: a welding evaluation model is constructed by mathematically analyzing the homogeneity, contrast and energy of the texture in the closed area of ​​the weld to generate the welding coefficient. The specific formula is as follows:

[0031]

[0032] Among them, H is the welding coefficient, Co is the texture contrast, Tz is the texture homogeneity, and AS is the texture energy.

[0033] Furthermore, the specific logic for generating the quality assessment index is: generating the quality assessment index through the geometric deviation coefficient and the welding coefficient; the specific formula for generating the quality assessment index is:

[0034]

[0035] Among them, Q is the quality assessment index, H is the welding coefficient, and SP is the geometric deviation coefficient.

[0036] Furthermore, the specific logic for recommending rectification plans is as follows: calculate the geometric deviation coefficient and welding coefficient of historical unqualified process points, divide the absolute value of the difference between the actual geometric deviation coefficient and the historical geometric deviation coefficient by the actual geometric deviation coefficient to obtain the spatial deviation rate, divide the absolute value of the difference between the actual welding coefficient and the historical welding coefficient by the welding coefficient to obtain the welding deviation rate, obtain the efficiency recommendation coefficient and the quality recommendation coefficient through the spatial deviation rate and the welding deviation rate, and take the historical plan with the maximum efficiency recommendation coefficient and the maximum quality recommendation coefficient as the recommended rectification plan; the specific formula for calculating the spatial deviation rate and the welding deviation rate is as follows:

[0037]

[0038] Among them, L SP is the spatial deviation rate, SP0 is the actual geometric deviation coefficient, SP is the geometric deviation coefficient of the historical rectification plan, L H is the welding deviation rate, H0 is the actual welding coefficient, and H is the welding coefficient of the historical rectification plan;

[0039] The specific formula for calculating the recommendation coefficient is:

[0040]

[0041] Among them, T1 is the recommended efficiency coefficient, T2 is the recommended quality coefficient, α, β, γ, δ are weight coefficients, α>2β>0, δ>2δ>0.

[0042] The present invention further provides a steel structure construction visualization system based on BIM technology, which is used to implement the steel structure construction visualization method based on BIM technology, specifically comprising:

[0043] The image acquisition module is used to obtain the measurement data and image information of the construction site, and to scale the original image, adjust the image size to 224*224, and then grayscale the image to obtain the construction image; build an ideal BIM model according to the design drawings, and map the construction image to the corresponding position of the ideal BIM model. The measurement data includes the weld width and the welding inclination angle;

[0044] Background segmentation module, used to count the frequency of pixel points in each level of 256 gray levels to form a gray histogram, and calculate the inter-class variance of each threshold in the histogram, select the best separation threshold through the inter-class variance, use the best separation threshold to perform threshold segmentation on the construction site image, divide the construction site image into foreground part and background part, and extract the foreground part as the construction site image;

[0045] The feature extraction module is used to extract the edge information of the construction components from the construction site image using the Canny edge detection algorithm, and to perform texture analysis on the weld closure area using the grayscale co-occurrence matrix; to obtain the homogeneity, contrast and energy of the weld closure area texture; to generate the welding coefficient through the homogeneity, contrast and energy; and to generate the geometric deviation coefficient through the weld width and welding inclination angle;

[0046] The quality judgment module is used to generate a quality evaluation index through the geometric deviation coefficient and the welding coefficient, compare the quality evaluation index with a preset threshold, mark the process of the construction part with a quality evaluation index less than the threshold as qualified, and conversely, mark the process of the construction part with a quality evaluation index greater than or equal to the threshold as unqualified;

[0047] The scheme recommendation module is used to collect historical rectification schemes for unqualified process locations, calculate the geometric deviation coefficient and welding coefficient of the historical rectification schemes, generate the spatial deviation rate and welding deviation rate based on the historical geometric deviation coefficient, historical welding coefficient, actual geometric deviation coefficient and actual welding coefficient, and then generate the efficiency recommendation coefficient and quality recommendation coefficient based on the spatial deviation rate and welding deviation rate, and recommend rectification schemes for unqualified process points based on the efficiency recommendation coefficient and quality recommendation coefficient;

[0048] The model loading module is used to load the BIM model and mark the unqualified process points in the BIM model. The marking content includes the quality assessment index and the recommended rectification plan.

[0049] Compared with the prior art, the invention has the following beneficial effects: the invention extracts features of the geometric position and welding condition of steel structure construction components and generates a spatial deviation index that can reflect the deviation of the steel material construction position and a welding index that can reflect the welding quality by extracting features, and generates a quality evaluation index based on this, and judges the qualified condition of the corresponding position process by quantitatively analyzing the quality evaluation index, which provides important conditions for determining the rectification plan; and provides an important basis for the visualization of steel material construction;

[0050] The present invention analyzes the historical rectification plans of unqualified process points, fully considers the actual needs of the construction site, and specifically recommends two sets of rectification plans that can solve the problem and have their own characteristics. The two sets of plans have different rectification directions to meet different construction needs and site conditions, and also provide more options for the construction team. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the overall method flow of the present invention.

[0052] Figure 2 It is a schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0053] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0054] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0055] Example:

[0056] See also Figure 1 , the present invention provides a technical solution:

[0057] A visualization method for steel structure construction based on BIM technology, the specific steps include:

[0058] Step 1: Obtain the measurement data and image information of the construction site, scale the original image, adjust the image size to 224*224, and then grayscale the image to obtain the construction image; build an ideal BIM model according to the design drawings, map the construction image to the corresponding position of the ideal BIM model, and the measurement data includes the weld width and welding inclination angle;

[0059] Resizing the image to 224*224 means adjusting the width and height of the image to the same fixed size, i.e., 224 pixels. Resizing the images to the same size can ensure that each image has the same size when using this method for inference recognition, which simplifies the inference process. Image resizing may introduce certain distortion or information loss. Resizing the image to the common 224*224 size can avoid excessive distortion and retain important features in the image.

[0060] Grayscale processing is the process of converting a color image into a grayscale image, making the values ​​of the three components R (red), G (green), and B (blue) equal. The specific formula is:

[0061] Y=0.298*R+0.587*G+0.114*B

[0062] Wherein, Y is the gray value of the pixel in the first recognition image, and R, G, and B are the red component value, green component value, and blue component value of the pixel of the leaf image after image scaling, respectively.

[0063] The welding inclination angle is the acute angle formed by the welding positions of the two parts.

[0064] Step 2: Count the frequency of pixels at each level in the 256 gray levels to form a gray histogram, and calculate the inter-class variance of each threshold in the histogram. Select the best separation threshold through the inter-class variance, and use the best separation threshold to perform threshold segmentation on the construction site image, dividing the construction site image into the foreground part and the background part, and extract the foreground part as the construction site image;

[0065] The specific logic for calculating the optimal separation threshold is:

[0066] Traverse all possible thresholds, divide the construction site image into background and foreground parts according to the value of each threshold, count the number of pixels in the background and foreground parts, calculate the mean of the grayscale values ​​of the pixels in the background and foreground parts, and calculate the inter-class variance of the corresponding threshold. The specific formula is:

[0067] σ(t) 2 =w B (t)*w F (t)*(μB (t)-μ F (t)) 2

[0068] Among them, σ(t) 2 represents the inter-class variance when the threshold is t, t∈[0, 255], and t∈N + , w B (t), w F (t) are the number of pixels in the background and foreground when the threshold is t, μ B (t), μ F (t) are the mean grayscale values ​​of the pixels in the background and foreground when the threshold is t;

[0069] Calculate the threshold value when the inter-class variance reaches the maximum, and define this value as the optimal separation threshold. Threshold segmentation can separate the background part, and focus on the quality assessment of the foreground part more clearly and accurately without being disturbed by irrelevant background factors.

[0070] Step 3: Use the Canny edge detection algorithm to extract the edge information of the construction components from the construction site image, and use the gray level co-occurrence matrix to perform texture analysis on the weld closed area; obtain the homogeneity, contrast and energy of the weld closed area texture; generate the welding coefficient through homogeneity, contrast and energy; generate the geometric deviation coefficient through the weld width and welding inclination angle;

[0071] The specific logic for extracting the edge information of each construction component using the Canny edge detection algorithm is: calculating the horizontal gradient and vertical gradient of the construction site image, and the specific formula is:

[0072]

[0073] Among them, I x is the horizontal gradient when the pixel coordinates are (x, y), I y is the vertical gradient when the pixel coordinates are (x, y), and I is the image grayscale value when the pixel coordinates are (x, y);

[0074] The image gradient amplitude is calculated by horizontal gradient and vertical gradient, and the specific formula is as follows:

[0075]

[0076] Among them, M x,y is the gradient amplitude when the pixel coordinates are (x, y),

[0077] The gradient amplitude M x,y The gradient amplitude is set to 1 when it is greater than the threshold; the gradient amplitude M x,yThe gradient amplitude when it is less than or equal to the threshold is set to 0. The position of each construction component and welding area can be determined through edge recognition and threshold segmentation, creating conditions for subsequent feature extraction.

[0078] Some structures on the steel structure components may also constitute closed areas. The closed areas constituted by these structures are quite different from the weld closed areas in shape and size. Therefore, the closed area corresponding to the weld can be directly marked as the weld closed area according to the shape and size of the closed area in the image.

[0079] The specific logic for generating the geometric deviation coefficient is: the geometric deviation coefficient is generated according to the weld width and the welding inclination angle, and the specific formula is:

[0080] SP=|A-A0|(W-W0) 2

[0081] Among them, the geometric deviation coefficient of SP, A is the weld width, A0 is the standard weld width, W is the welding inclination angle, and W0 is the standard welding inclination angle. The geometric deviation coefficient SP reflects the geometric deviation of the component relative to the ideal welding situation. The larger its value, the greater the geometric deviation of the component relative to the ideal welding situation, and the greater the probability of problems in the corresponding process; A-A0 reflects the deviation of the welding width from the ideal welding width. The larger its value, the greater the deviation; W-W0 reflects the deviation of the component welding angle from the ideal component welding angle. The larger its value, the greater the deviation. By analyzing the geometric deviation coefficient SP, the geometric deviation of the component welding situation relative to the ideal welding situation can be judged. The standard weld width and welding inclination angle are the specified parameters in the design plan.

[0082] The texture analysis of the closed area of ​​the weld is performed using the grayscale co-occurrence matrix. First, the grayscale co-occurrence matrix is ​​created. The specific logic is as follows: simplify the grayscale set of 256 levels to eight levels, take any point (x, y) in the foreground image and name it as the reference point, and any point (x+a, y+b) that deviates from this point, a and b are positive integers greater than zero, and this point is named as the deviation point; the probability of the grayscale value of the point pair appearing is p(g1, g2), and when the point (x, y) moves across the entire screen, various p(g1, g2) values ​​will be obtained, and there are 64 combinations of p(g1, g2). For the entire screen, count the number of occurrences of each p(g1, g2) value, and then arrange them into a square matrix, which is called a grayscale co-occurrence matrix. The specific expression of the grayscale co-occurrence matrix is:

[0083]

[0084] P is the gray-level co-occurrence matrix, p ijIt represents the probability of the occurrence of the i-th reference point and the j-th deviation point, i is the gray level of the reference point, and j is the gray level of the deviation point.

[0085] The specific formulas used to calculate homogeneity, contrast, and energy are:

[0086]

[0087] AS is the grayscale co-occurrence matrix energy, Co is the grayscale co-occurrence matrix contrast, and Tz is the grayscale co-occurrence matrix homogeneity; the grayscale co-occurrence matrix energy AS reflects the repeatability of the texture pattern in the welding area. The larger its value, the higher the frequency of repeated texture patterns; the grayscale co-occurrence matrix contrast Co reflects the uniformity of the texture in the welding area. The larger its value, the more uniform the texture distribution in the welding area. The grayscale co-occurrence matrix homogeneity Tz reflects the similarity of adjacent pixels in the welding area. The larger its value, the smoother the texture change. They can all reflect the texture characteristics of the welding area, and these characteristics can be used to evaluate the welding effect.

[0088] The specific logic for generating the welding coefficient is: a welding evaluation model is constructed by mathematically analyzing the homogeneity, contrast and energy of the texture in the closed area of ​​the weld to generate the welding coefficient. The specific formula is:

[0089]

[0090] Among them, H is the welding coefficient, Co is the texture contrast, Tz is the texture homogeneity, and AS is the texture energy. The welding coefficient H reflects the welding effect. The larger its value, the better the welding effect; the grayscale co-occurrence matrix AS reflects the repeatability of the texture pattern in the welding area. The larger its value, the higher the frequency of repeated texture patterns, and the better the welding effect; the grayscale co-occurrence matrix contrast Co reflects the uniformity of the texture in the welding area. The larger its value, the more uniform the texture distribution in the welding area, and the better the welding effect; the grayscale co-occurrence matrix homogeneity Tz reflects the similarity of adjacent pixels in the welding area. The larger its value, the smoother the texture change, and the better the welding effect. This formula generates a welding coefficient that can evaluate the welding effect by analyzing the texture characteristics of the welding area, providing an important basis for subsequent analysis.

[0091] Step 4: Generate a quality assessment index through the geometric deviation coefficient and the welding coefficient, compare the quality assessment index with the preset threshold, mark the process of the construction site with a quality assessment index less than the threshold as qualified, otherwise, mark the process of the construction site with a quality assessment index greater than or equal to the threshold as unqualified.

[0092] The specific logic for generating the quality assessment index is: the quality assessment index is generated by the geometric deviation coefficient and the welding coefficient; the specific formula for generating the quality assessment index is:

[0093]

[0094] Among them, Q is the quality assessment index, H is the welding coefficient, and SP is the geometric deviation coefficient. The quality assessment index Q reflects the overall completion effect of the process. The larger its value, the better the process completion effect; the welding coefficient H reflects the welding effect. The larger its value, the better the welding effect; the geometric deviation coefficient SP reflects the geometric deviation of the component relative to the ideal welding situation. The larger its value, the greater the geometric deviation of the component relative to the ideal welding situation, and the greater the probability of problems in the corresponding process; this generates a quality assessment index Q that can reflect the overall completion effect of the process by analyzing the geometric deviation coefficient SP and the welding coefficient H, which provides an important basis for the process qualification judgment.

[0095] Step 5: Collect historical rectification plans for unqualified process locations, calculate the geometric deviation coefficient and welding coefficient of the historical rectification plans, generate the spatial deviation rate and welding deviation rate based on the historical geometric deviation coefficient, historical welding coefficient, actual geometric deviation coefficient and actual welding coefficient, and then generate the efficiency recommendation coefficient and quality recommendation coefficient based on the spatial deviation rate and welding deviation rate, and recommend rectification plans for unqualified process points based on the efficiency recommendation coefficient and quality recommendation coefficient.

[0096] The specific logic for recommending rectification plans is as follows: calculate the geometric deviation coefficient and welding coefficient of historical unqualified process points, divide the absolute value of the difference between the actual geometric deviation coefficient and the historical geometric deviation coefficient by the actual geometric deviation coefficient to obtain the spatial deviation rate, divide the absolute value of the difference between the actual welding coefficient and the historical welding coefficient by the welding coefficient to obtain the welding deviation rate, obtain the efficiency recommendation coefficient and quality recommendation coefficient through the spatial deviation rate and welding deviation rate, and take the historical plan with the maximum efficiency recommendation coefficient and quality recommendation coefficient as the recommended rectification plan; the specific formula for calculating the spatial deviation rate and welding deviation rate is as follows:

[0097]

[0098] Among them, L SP is the spatial deviation rate, SP0 is the actual geometric deviation coefficient, SP is the geometric deviation coefficient of the historical rectification plan, L H is the welding deviation rate, H0 is the actual welding coefficient, H is the welding coefficient of the historical rectification plan; the spatial deviation rate L SP Reflects the relative difference between the current process space deviation and the historical plan. The larger the value, the greater the relative difference. The welding deviation rate L H It reflects the relative difference between the welding deviation of the current process and the historical plan. The larger the value, the greater the relative difference.

[0099] The specific formula for calculating the recommendation coefficient is:

[0100]

[0101] Among them, T1 is the efficiency recommendation coefficient, T2 is the quality recommendation coefficient, α, β, γ, δ are weight coefficients, α>2β>0, δ>2δ>0. T1 is the efficiency recommendation coefficient, which reflects the degree of recommendation for the historical rectification plan in terms of completion efficiency. The larger its value, the higher the degree of recommendation for the historical plan. On the basis of qualified procedures, the faster the completion time of the historical rectification plan is, and the rectification of the geometric position is relatively time-saving. Therefore, the weight coefficient corresponding to the inverse of the geometric deviation rate is set larger. T2 is the quality recommendation coefficient, which reflects the degree of recommendation for the historical rectification plan in terms of completion effect. The larger its value, the higher the degree of recommendation for the historical plan. On the basis of qualified procedures, the final quality of the historical rectification plan is higher. The smaller the deviation of the welding coefficient representing the welding quality is, the better the welding quality of the rectification plan will be. Therefore, the weight coefficient of the inverse of the welding deviation rate is set larger. This embodiment specifically recommends two sets of rectification plans that can solve the problem and have their own characteristics. These two sets of plans have different rectification directions to meet different construction needs and site conditions, and also provide more choices for the construction team.

[0102] Step 6: Load the BIM model and mark the unqualified process points in the model. The marking content includes the quality assessment index and recommended rectification plan.

[0103] The recommended rectification plans are the two sets of rectification plans with the highest efficiency recommendation coefficients and quality recommendation coefficients mentioned above.

[0104] See also Figure 2 The present invention further provides a steel structure construction visualization system based on BIM technology, which is used to implement the steel structure construction visualization method based on BIM technology, specifically including:

[0105] The image acquisition module is used to obtain the measurement data and image information of the construction site, and to scale the original image, adjust the image size to 224*224, and then grayscale the image to obtain the construction image; build an ideal BIM model according to the design drawings, and map the construction image to the corresponding position of the ideal BIM model. The measurement data includes the weld width and the welding inclination angle;

[0106] Background segmentation module, used to count the frequency of pixel points in each level of 256 gray levels to form a gray histogram, and calculate the inter-class variance of each threshold in the histogram, select the best separation threshold through the inter-class variance, use the best separation threshold to perform threshold segmentation on the construction site image, divide the construction site image into foreground part and background part, and extract the foreground part as the construction site image;

[0107] The feature extraction module is used to extract the edge information of the construction components from the construction site image using the Canny edge detection algorithm, and to perform texture analysis on the weld closure area using the grayscale co-occurrence matrix; to obtain the homogeneity, contrast and energy of the weld closure area texture; to generate the welding coefficient through the homogeneity, contrast and energy; and to generate the geometric deviation coefficient through the weld width and welding inclination angle;

[0108] The quality judgment module is used to generate a quality evaluation index through the geometric deviation coefficient and the welding coefficient, compare the quality evaluation index with a preset threshold, mark the process of the construction part with a quality evaluation index less than the threshold as qualified, and conversely, mark the process of the construction part with a quality evaluation index greater than or equal to the threshold as unqualified;

[0109] The scheme recommendation module is used to collect historical rectification schemes for unqualified process locations, calculate the geometric deviation coefficient and welding coefficient of the historical rectification schemes, generate the spatial deviation rate and welding deviation rate based on the historical geometric deviation coefficient, historical welding coefficient, actual geometric deviation coefficient and actual welding coefficient, and then generate the efficiency recommendation coefficient and quality recommendation coefficient based on the spatial deviation rate and welding deviation rate, and recommend rectification schemes for unqualified process points based on the efficiency recommendation coefficient and quality recommendation coefficient;

[0110] The model loading module is used to load the BIM model and mark the unqualified process points in the BIM model, including the quality assessment index and recommended rectification plan. The two sets of plans have different rectification directions to meet different construction needs and site conditions, and also provide more options for the construction team.

[0111] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0112] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A visualization method for steel structure construction based on BIM technology, characterized in that: The specific steps include: Step 1: Obtain the measurement data and image information of the construction site, scale the original image, adjust the image size to 224*224, and then grayscale the image to obtain the construction image; build an ideal BIM model according to the design drawings, map the construction image to the corresponding position of the ideal BIM model, and the measurement data includes the weld width and welding inclination angle; Step 2: Count the frequency of pixels at each level in the 256 gray levels to form a gray histogram, and calculate the inter-class variance of each threshold in the histogram. Select the best separation threshold through the inter-class variance, and use the best separation threshold to perform threshold segmentation on the construction site image, dividing the construction site image into the foreground part and the background part, and extract the foreground part as the construction site image; Step 3: Use the Canny edge detection algorithm to extract the edge information of the construction components from the construction site image, and use the gray level co-occurrence matrix to perform texture analysis on the weld closed area; obtain the homogeneity, contrast and energy of the weld closed area texture; generate the welding coefficient through homogeneity, contrast and energy; generate the geometric deviation coefficient through the weld width and welding inclination angle; Step 4: Generate a quality assessment index through the geometric deviation coefficient and the welding coefficient, compare the quality assessment index with the preset threshold, mark the process of the construction part with a quality assessment index less than the threshold as qualified, otherwise, mark the process of the construction part with a quality assessment index greater than or equal to the threshold as unqualified; Step 5: Collect historical rectification plans for unqualified process locations, calculate the geometric deviation coefficient and welding coefficient of the historical rectification plans, generate the spatial deviation rate and welding deviation rate based on the historical geometric deviation coefficient, historical welding coefficient, actual geometric deviation coefficient and actual welding coefficient, and then generate the efficiency recommendation coefficient and quality recommendation coefficient based on the spatial deviation rate and welding deviation rate, and recommend rectification plans for unqualified process points based on the efficiency recommendation coefficient and quality recommendation coefficient; Step 6: Load the BIM model and mark the unqualified process points in the BIM model. The marking content includes the quality assessment index and recommended rectification plan.

2. A method for visualizing steel structure construction based on BIM technology according to claim 1, characterized in that: The specific logic for calculating the optimal separation threshold is: Traverse all possible thresholds, divide the construction site image into background and foreground parts according to the value of each threshold, count the number of pixels in the background and foreground parts, calculate the mean of the grayscale values ​​of the pixels in the background and foreground parts, and calculate the inter-class variance of the corresponding threshold. The specific formula is: σ(t) 2 =w B (t)*w F (t)*(μ B (t)-m F (t)) 2 Among them, σ(t) 2 represents the inter-class variance when the threshold is t, t∈[0, 255], and t∈N + ,w B (t), w F (t) are the number of pixels in the background and foreground when the threshold is t, μ B (t), μ F (t) are the mean grayscale values ​​of the pixels in the background and foreground when the threshold is t; Calculate the value of the threshold when the between-class variance reaches the maximum, and define this value as the optimal separation threshold.

3. The method for visualizing steel structure construction based on BIM technology according to claim 1, characterized in that: The specific logic for extracting the edge information of each construction component using the Canny edge detection algorithm is: calculating the horizontal gradient and vertical gradient of the construction site image, and the specific formula is: Among them, I x is the horizontal gradient when the pixel coordinates are (x, y), I y is the vertical gradient when the pixel coordinates are (x, y), and I is the image grayscale value when the pixel coordinates are (x, y); The image gradient amplitude is calculated by horizontal gradient and vertical gradient, and the specific formula is as follows: Among them, M x,y is the gradient amplitude when the pixel coordinates are (x, y), The gradient amplitude M x,y The gradient amplitude is set to 1 when it is greater than the threshold; the gradient amplitude M x,y The gradient amplitude is set to 0 when it is less than or equal to the threshold.

4. The method for visualizing steel structure construction based on BIM technology according to claim 1, characterized in that: The specific logic for generating the geometric deviation coefficient is: the geometric deviation coefficient is generated according to the weld width and the welding inclination angle, and the specific formula is: SP=|A-A0|(W-W0) 2 Among them, SP is the geometric deviation coefficient, A is the weld width, A0 is the standard weld width, W is the welding inclination angle, and W0 is the standard welding inclination angle.

5. The method for visualizing steel structure construction based on BIM technology according to claim 1, characterized in that: The specific logic for generating the welding coefficient is: a welding evaluation model is constructed by mathematically analyzing the homogeneity, contrast and energy of the texture in the closed area of ​​the weld to generate the welding coefficient. The specific formula is: Among them, H is the welding coefficient, Co is the texture contrast, Tz is the texture homogeneity, and AS is the texture energy.

6. The method for visualizing steel structure construction based on BIM technology according to claim 1, characterized in that: The specific logic for generating the quality assessment index is: the quality assessment index is generated by the geometric deviation coefficient and the welding coefficient; the specific formula for generating the quality assessment index is: Among them, Q is the quality assessment index, H is the welding coefficient, and SP is the geometric deviation coefficient.

7. The method for visualizing steel structure construction based on BIM technology according to claim 1, characterized in that: The specific logic for recommending rectification plans is as follows: calculate the geometric deviation coefficient and welding coefficient of historical unqualified process points, divide the absolute value of the difference between the actual geometric deviation coefficient and the historical geometric deviation coefficient by the actual geometric deviation coefficient to obtain the spatial deviation rate, divide the absolute value of the difference between the actual welding coefficient and the historical welding coefficient by the welding coefficient to obtain the welding deviation rate, obtain the efficiency recommendation coefficient and quality recommendation coefficient through the spatial deviation rate and welding deviation rate, and take the historical plan with the maximum efficiency recommendation coefficient and quality recommendation coefficient as the recommended rectification plan; the specific formula for calculating the spatial deviation rate and welding deviation rate is as follows: Among them, L SP is the spatial deviation rate, SP0 is the actual geometric deviation coefficient, SP is the geometric deviation coefficient of the historical rectification plan, L H is the welding deviation rate, H0 is the actual welding coefficient, and H is the welding coefficient of the historical rectification plan; The specific formula for calculating the recommendation coefficient is: Among them, T1 is the recommended efficiency coefficient, T2 is the recommended quality coefficient, α, β, γ, δ are weight coefficients, α>2β>0, δ>2δ>0.

8. A steel structure construction visualization system based on BIM technology, characterized by: The system is used to implement the steel structure construction visualization method based on BIM technology as described in any one of claims 1 to 7, specifically comprising: The image acquisition module is used to obtain the measurement data and image information of the construction site, and to scale the original image, adjust the image size to 224*224, and then grayscale the image to obtain the construction image; build an ideal BIM model according to the design drawings, and map the construction image to the corresponding position of the ideal BIM model. The measurement data includes the weld width and the welding inclination angle; Background segmentation module, used to count the frequency of pixel points in each level of 256 gray levels to form a gray histogram, and calculate the inter-class variance of each threshold in the histogram, select the best separation threshold through the inter-class variance, use the best separation threshold to perform threshold segmentation on the construction site image, divide the construction site image into foreground part and background part, and extract the foreground part as the construction site image; The feature extraction module is used to extract the edge information of the construction components from the construction site image using the Canny edge detection algorithm, and to perform texture analysis on the weld closure area using the grayscale co-occurrence matrix; to obtain the homogeneity, contrast and energy of the weld closure area texture; to generate the welding coefficient through the homogeneity, contrast and energy; and to generate the geometric deviation coefficient through the weld width and welding inclination angle; The quality judgment module is used to generate a quality evaluation index through the geometric deviation coefficient and the welding coefficient, compare the quality evaluation index with a preset threshold, mark the process of the construction part with a quality evaluation index less than the threshold as qualified, and conversely, mark the process of the construction part with a quality evaluation index greater than or equal to the threshold as unqualified; The scheme recommendation module is used to collect historical rectification schemes for unqualified process locations, calculate the geometric deviation coefficient and welding coefficient of the historical rectification schemes, generate the spatial deviation rate and welding deviation rate based on the historical geometric deviation coefficient, historical welding coefficient, actual geometric deviation coefficient and actual welding coefficient, and then generate the efficiency recommendation coefficient and quality recommendation coefficient based on the spatial deviation rate and welding deviation rate, and recommend rectification schemes for unqualified process points based on the efficiency recommendation coefficient and quality recommendation coefficient; The model loading module is used to load the BIM model and mark the unqualified process points in the BIM model. The marking content includes the quality assessment index and the recommended rectification plan.