Intelligent positioning method for tower crane type selection and site visual arrangement

Abstract

According to the intelligent positioning method for tower crane type selection and site visual arrangement, the working efficiency of tower crane scheme compiling personnel is greatly improved through visual hoisting requirements and tower crane hoisting capacity, the visual arrangement process of the tower crane is intelligently optimized based on a genetic algorithm improved by engineering priori knowledge, and the working efficiency of the tower crane scheme compiling personnel is greatly improved. The scheme with the lowest price is found while the lifting capacity requirement is met and space collision is avoided.

Description

Technical Field

[0001] The invention relates to the technical field of heavy lifting equipment selection and arrangement, and in particular to an intelligent positioning method for tower crane selection and site visualization arrangement. Background Art

[0002] As a key vertical transport tool, tower cranes play an irreplaceable role in many engineering construction activities, and their importance is self-evident. In the preparation stage of engineering construction, choosing the right tower crane and its positioning is a crucial link, which directly affects the construction fluency and progress of the entire project. Although the selection and positioning of tower cranes seem to be two separate steps, they are actually closely linked. The location of the tower crane determines which specific tower crane model needs to be selected.

[0003] In the traditional method, plan preparers roughly estimate the tower crane position through CAD drawings, which is highly dependent on engineering experience and inefficient. It is difficult to find a low-cost selection and layout solution that meets engineering needs. Summary of the invention

[0004] The present invention aims to solve the deficiencies of the prior art and provides an intelligent positioning method for tower crane selection and site visualization layout. By visualizing the lifting requirements and the lifting capacity of the tower crane, the work efficiency of the personnel who prepare the tower crane plan is greatly improved. The genetic algorithm improved based on engineering prior knowledge intelligently optimizes the tower crane visualization layout process and finds the lowest price solution while meeting the lifting weight requirements and avoiding space collisions.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] An intelligent positioning method for tower crane selection and site visualization layout uses a programming language to develop a visualization program, interactively creates visualization graphics through mouse clicks, intelligently moves the lifting capacity diagram of the tower crane, and solves the optimal selection and layout plan.

[0007] The following steps are involved:

[0008] S1. Conduct on-site survey of the construction site, process the site CAD drawings according to the layout of the above-ground buildings, underground pipelines, and temporary construction facilities, divide the areas according to the lifting requirements, calculate the lifting weight requirements of each area, obtain the lifting weight distribution map, divide the site area according to the above-ground and underground environmental boundaries, and obtain the regional restriction distribution map;

[0009] S2. Convert the pre-processed CAD drawing into image data, grayscale, Gaussian blur, and threshold the image, perform contour detection, and segment the connected areas of the site; map the lifting weight requirements and area restrictions of the segmented areas to the color domain through a normalized mapping function to form a lifting weight field of the site on the map. , space field ;

[0010] S3. Investigate the tower crane models available in the construction area, and draw a coverage image based on the model data of the tower crane products, the lifting arm length and the maximum lifting weight of the tower crane. Use the normalized mapping function to map the lifting capacity field of the tower crane. At the same time, the size of the foundation, the attachment method, the size of the attachment structure, and the spatial field of the tower crane are preliminarily designed. ;

[0011] S4. Visual positioning is carried out according to the principle of non-collision of the space field and the crane's lifting capacity field covering the site's lifting capacity field, and the overall lifting demand. Select a tower crane with corresponding capacity and Lifting capacity of mobile tower crane , calculate the pixels of the image in real time, calculate whether the lifting capacity meets the requirements and whether the space field collides through the discriminant function, and display it visually on the image, and gradually calculate the remaining lifting requirements And add tower cranes until it fully meets the construction needs;

[0012] S5. Adopt the genetic algorithm improved based on engineering prior knowledge to intelligently optimize the visual layout process of tower cranes and find the lowest price solution while meeting the lifting capacity requirements and avoiding space collisions.

[0013] S1 includes the following steps:

[0014] S11. Conduct on-site survey of the construction site to determine the spatial restricted areas of building height and traffic lines in the above-ground environment, the restricted areas of the on-site working surface of the on-site material warehouse, material yard, and mixing station, and the restricted areas of the tower crane foundation of the underground pipelines;

[0015] S12, standardize the CAD drawing, remove the dimension marks and text, and draw the restricted area boundary in step S11 on the CAD drawing to obtain a regional restriction distribution map;

[0016] S13. Calculate the lifting capacity requirements of each area according to the construction drawing, redivide the area according to the lifting capacity and environmental boundaries, draw it on the CAD drawing, and obtain a lifting capacity distribution map for computer vision processing.

[0017] S2 includes the following steps:

[0018] S21, converting the standardized drawing into image data, performing grayscale processing, Gaussian blurring, thresholding processing, and contour detection on the image, obtaining contour data of the lifting weight distribution and contour data of the spatial restricted area, and saving these contour data as a tree structure for subsequent calculations;

[0019] S22, using the depth-first search-based contour tree retrieval method to retrieve the contour line of the weight distribution map, in the standardized drawing image, click a point in the area ,calculate The area where the point is located is calculated as follows:

[0020] ;

[0021] In the formula,

[0022] Indicates The number of pixels clicked;

[0023] express The outer boundary contour of the area where the point is located;

[0024] express The coordinates of the pixel point;

[0025] Indicates the number of the retrieved contour line;

[0026] The value range is from 1 to , Indicates the number of key pixels on the contour line;

[0027] express The coordinates of the point;

[0028] calculate The Euclidean distance from each connected region boundary is determined The outer boundary of the region to which the point belongs;

[0029] S23, further searched All sub-contours of , ,,,, , further solving for The formula for the area is as follows:

[0030] ;

[0031] Segment the connected domains of all different lifting weights in the lifting weight distribution graph;

[0032] S24, will Lifting capacity of the area , after normalization, we get , further mapped to the color domain using the interpolation function, and assigned to Area, visualize the lifting weight, the color interpolation function is as follows:

[0033] ;

[0034] In the formula,

[0035] Indicates the color after mapping;

[0036] and Indicates the colors corresponding to the low and high bits of the lifting weight, and takes values ​​in RGB or HSV space;

[0037] S25, repeat steps S22-S24 to convert the weight distribution diagram into a visual lifting weight field ;

[0038] S26, using the method of steps S22-S25 to convert the regional restriction distribution map into a visualized spatial field , the color interpolation function uniformly takes the same color .

[0039] S3 includes the following steps:

[0040] S31. Investigate the tower crane models available in the construction area, and compile statistics on the types, parameters, and rental prices of tower cranes, crawler cranes, and truck cranes;

[0041] S32. For a type of tower crane, a coverage image is drawn based on the data of the tower crane's boom length and maximum lifting weight. Calculate the color at the center point:

[0042] ;

[0043] The calculation formula for pixels in the crane coverage area is as follows:

[0044] ;

[0045] In the formula,

[0046] Indicates the distance from the farthest end to the center of the tower crane coverage area;

[0047] Indicates the Euclidean distance between points in the region and the center point;

[0048] Forming the lifting capacity field of the tower crane ;

[0049] S33. Preliminarily design the foundation size, attachment method, and attachment structure size of the tower crane according to the specifications, and use the method of steps S22-S25 to construct a visual spatial field of the tower crane. , the color interpolation function uniformly takes the same color .

[0050] S4 includes the following steps:

[0051] S41. According to the specifications and on-site construction requirements, the lifting capacity of different types of mobile tower cranes is visualized. , at the site's lifting weight field Explore reasonable solutions by moving up and down, perform real-time lifting capacity judgment, spatial collision judgment, and cost calculation, select tower cranes in batches, give priority to selecting larger tower cranes according to lifting capacity requirements, gradually comply with the judgment principles, and calculate the overall lifting requirements of the site lifting capacity distribution diagram :

[0052] ;

[0053] In the formula,

[0054] , , Represents the pixel value of a point in the site lifting weight distribution map;

[0055] Calculate the overall lifting capacity of each type of tower crane :

[0056] ;

[0057] In the formula,

[0058] , , Indicates The pixel value of the point in the lifting capacity map of the tower crane;

[0059] S42, real-time lifting capacity determination, the determination principle is based on the lifting capacity of the tower crane Lifting capacity of the site The coverage capability of Next, select the closest of Corresponding to a tower crane , the lifting capacity field , superimposed on the lifting weight field of the site ,move The center coordinates of the circle are used to determine the lifting weight of the superimposed state in real time. The determination formula is as follows:

[0060] ;

[0061] In the formula,

[0062] Indicates The color value of the pixel after the superposition;

[0063] Indicates the color value of each pixel after the last overlay;

[0064] Tower crane The color value of each pixel;

[0065] , Indicates the offset distance of the center point of the tower crane relative to the center point of the site;

[0066] The calculation result uses the RGB value (0~255) to truncate, and visual color judgment is used to determine whether the tower crane can cover the lifting demand in the area. RGB (0,0,0) is black, which means it can cover;

[0067] Further calculation of After the stacking, the remaining lifting requirements ;

[0068] ;

[0069] In the formula,

[0070] , , Indicates The pixel value of the point in the site lifting weight distribution map after the superposition;

[0071] S43, perform spatial identification in real time. The identification principle is that the tower crane and its lower foundation do not conflict with existing structures or structures to be built on the ground or underground. Space field The space field with the venue Superposition, in step S42, the coordinate position is spatially determined, the determination formula is as follows:

[0072] ;

[0073] There is no space conflict.

[0074] S44, according to the tower crane model from large to small, then crawler crane, truck crane, The next choice is closest to of For the corresponding tower crane, step S41-S43 is repeated step by step until the judgment requirements are fully met:

[0075] ;

[0076] The remaining areas are equipped with mobile lifting equipment to meet lifting needs.

[0077] S5 contains the following steps:

[0078] S51. Coding scheme for tower crane and its location [ K , x k , y k ] , combined with prior knowledge to initialize the population, prioritize the placement of heavy tower cranes near the heavy lifting area, and convert the engineering prior information of tower cranes attached to existing building structures into probability distribution , when the population is randomly initialized, the solution population is formed by probability sampling;

[0079] S52, calculate the fitness, the fitness function is as follows:

[0080] ;

[0081] In the formula,

[0082] Indicates the total price of renting a tower crane;

[0083] Indicates constraint processing. Set constraints according to the space judgment and lifting weight judgment methods. When the judgment passes Take 1, if not passed Take 0;

[0084] S53. Select a solution with large fitness for crossover and mutation operations, and set the probability parameter to the product of fixed probability and prior probability:

[0085] Position Crossover: ;

[0086] Position variation: ;

[0087] S54, generate a new population, recalculate the fitness, and update the probability distribution according to the fitness gradient ;

[0088] S55, repeat steps S52-S54 until the maximum number of evolutions is reached End of time;

[0089] S56. Select the plan with the lowest total price as the final tower crane selection and layout plan.

[0090] The beneficial effects of the present invention are as follows: the present invention effectively visualizes the tower crane selection and arrangement process, and through the visual display of lifting weight requirements by region, it greatly improves the efficiency of program preparation personnel, facilitates construction personnel to intuitively understand the program, improves computability, optimizes efficiency, and creates economic effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] Figure 1 is a flow chart of the present invention;

[0092] Figure 2 It is a site visualization process diagram of the present invention;

[0093] Figure 3 It is a schematic diagram of the genetic algorithm flow chart improved based on engineering prior knowledge of the present invention;

[0094] The following is a detailed description of the embodiments of the present invention with reference to the accompanying drawings. DETAILED DESCRIPTION

[0095] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The embodiments are only used to explain the present invention and are not used to limit the scope of the present invention. The present invention is described in more detail by way of example with reference to the accompanying drawings in the following paragraphs. The advantages and features of the present invention will become clearer according to the following description. It should be noted that the accompanying drawings are all in a very simplified form and are not in precise proportions, and are only used to facilitate and clearly assist in explaining the purpose of the embodiments of the present invention.

[0096] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0097] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0098] In order to improve the efficiency of tower crane selection and layout, reduce the cost of renting tower cranes, and thus create economic benefits, the present invention focuses on the research of tower crane selection and site visualization layout and intelligent positioning.

[0099] With the development of high-tech technologies such as robots and artificial intelligence, intelligent construction and smart civil engineering are new productivity to improve the development momentum of civil engineering. Intelligent algorithms based on machine learning and computer vision have been widely used in civil engineering construction, structural monitoring and other fields, creating huge value. However, in the field of tower crane selection and layout, there is a lack of corresponding intelligent methods to optimize the scheme. Therefore, the tower crane selection and site visualization layout intelligent positioning method based on genetic algorithms improved by engineering prior knowledge came into being. By visualizing the lifting requirements and tower crane lifting capacity, the work efficiency of tower crane planners can be improved, and reasonable and economically efficient schemes can be quickly found.

[0100] An intelligent positioning method for tower crane selection and site visualization layout uses a programming language to develop a visualization program, interactively creates visualization graphics through mouse clicks, intelligently moves the lifting capacity diagram of the tower crane, and solves the optimal selection and layout plan.

[0101] like Figure 1-Figure 3 As shown, the following steps are included:

[0102] S1. Conduct on-site survey of the construction site, process the site CAD drawings according to the plane layout of the above-ground buildings, underground pipelines, and temporary construction facilities, and divide the areas according to the lifting requirements, calculate the lifting weight requirements of each area, and obtain the lifting weight distribution map. Divide the site area according to the above-ground and underground environmental boundaries to obtain the regional restriction distribution map;

[0103] Specifically:

[0104] S11. Conduct on-site survey of the construction site to determine the space restriction areas such as building height and traffic lines in the ground environment, the restricted areas of the on-site working surface such as on-site material warehouses, material yards, mixing stations, and the areas that restrict the tower crane foundation such as underground pipelines;

[0105] S12, standardize the CAD drawing, remove the dimension marks and text, and draw the restricted area boundary in step S11 on the CAD drawing to obtain a regional restriction distribution map;

[0106] S13. Calculate the lifting capacity requirements of each area according to the construction drawing, redivide the area according to the lifting capacity, environmental boundaries, etc., draw it on the CAD drawing, and obtain a lifting capacity distribution map for computer vision processing.

[0107] S2. Convert the pre-processed CAD drawing into image data, grayscale, Gaussian blur, and threshold the image, perform contour detection, and segment the connected areas of the site; map the lifting weight requirements and area restrictions of the segmented areas to the color domain through a normalized mapping function to form a lifting weight field of the site on the map. , space field ;

[0108] Specifically:

[0109] S21, converting the standardized drawing into image data, performing grayscale processing, Gaussian blurring, thresholding processing, and contour detection on the image, obtaining contour data of the lifting weight distribution and contour data of the spatial restricted area, and saving these contour data as a tree structure for subsequent calculations;

[0110] S22. Use the depth-first search (DFS)-based contour tree retrieval method to retrieve the contour line of the weight distribution map. In the standardized drawing image, click a point in the area. ,calculate The area where the point is located is calculated as follows:

[0111] ;

[0112] In the formula,

[0113] Indicates The number of pixels clicked;

[0114] express The outer boundary contour of the area where the point is located;

[0115] express The coordinates of the pixel point;

[0116] Indicates the number of the retrieved contour line;

[0117] The value range is from 1 to , Indicates the number of key pixels on the contour line;

[0118] express The coordinates of the point;

[0119] calculate The Euclidean distance from each connected region boundary is determined The outer boundary of the region to which the point belongs;

[0120] S23, further searched All sub-contours of , ,,,, , further solving for The formula for the area is as follows:

[0121] ;

[0122] That is, all connected domains of different lifting weights in the lifting weight distribution graph can be segmented;

[0123] S24, will Lifting capacity of the area , after normalization, we get , further mapped to the color domain using the interpolation function, and assigned to Area, visualize the lifting weight, the color interpolation function is as follows:

[0124] ;

[0125] In the formula,

[0126] Indicates the color after mapping;

[0127] and Indicates the colors corresponding to the low and high bits of the lifting weight, and takes values ​​in RGB or HSV space;

[0128] S25, repeat steps S22-S24 to convert the weight distribution diagram into a visual lifting weight field ;

[0129] S26, using the method of steps S22-S25 to convert the regional restriction distribution map into a visualized spatial field , the color interpolation function uniformly takes the same color .

[0130] S3. Investigate the tower crane models available in the construction area, and draw a coverage image based on the model data of the tower crane products, the lifting arm length, maximum lifting weight and other data of the tower crane. Use the normalized mapping function to map the lifting capacity field of the tower crane. At the same time, the size of the foundation, the attachment method, the size of the attachment structure, etc. are preliminarily designed to construct the space field of the tower crane. ;

[0131] Specifically:

[0132] S31. Investigate the tower crane models available in the construction area, and compile statistics on the types, parameters, rental prices, etc. of tower cranes, crawler cranes, and truck cranes;

[0133] S32. For a type of tower crane, draw a coverage image based on the crane's boom length, maximum lifting weight and other data. Calculate the color at the center point:

[0134] ;

[0135] The calculation formula for pixels in the crane coverage area is as follows:

[0136] ;

[0137] In the formula,

[0138] Indicates the distance from the farthest end to the center of the tower crane coverage area;

[0139] Indicates the Euclidean distance between points in the region and the center point;

[0140] Thus forming the lifting capacity field of the tower crane ;

[0141] S33. Preliminarily design the foundation size, attachment method, attachment structure size, etc. of the tower crane according to the specifications, and use the method of steps S22-S25 to construct a visual spatial field of the tower crane. , the color interpolation function uniformly takes the same color .

[0142] S4. Visual positioning is carried out according to the principle of non-collision of the space field and the crane's lifting capacity field covering the site's lifting capacity field, and the overall lifting demand. Select a tower crane with corresponding capacity and Lifting capacity of mobile tower crane , calculate the pixels of the image in real time, calculate whether the lifting capacity meets the requirements and whether the space field collides through the discriminant function, and display it visually on the image, and gradually calculate the remaining lifting requirements And add tower cranes until it fully meets the construction needs;

[0143] Specifically:

[0144] S41. According to the specifications and on-site construction requirements, the lifting capacity of different types of mobile tower cranes is visualized. , at the site's lifting weight field Explore reasonable solutions by moving up and down, perform real-time lifting capacity judgment, spatial collision judgment, and cost calculation, select tower cranes in batches, give priority to selecting larger tower cranes according to lifting capacity requirements, gradually comply with the judgment principles, and calculate the overall lifting requirements of the site lifting capacity distribution diagram :

[0145] ;

[0146] In the formula,

[0147] , , Represents the pixel value of a point in the site lifting weight distribution map;

[0148] Calculate the overall lifting capacity of each type of tower crane :

[0149] ;

[0150] In the formula,

[0151] , , Indicates The pixel value of the point in the lifting capacity map of the tower crane;

[0152] S42, real-time lifting capacity determination, the determination principle is based on the lifting capacity of the tower crane Lifting capacity of the site The coverage capability of Next, select the closest of Corresponding to a tower crane , the lifting capacity field , superimposed on the lifting weight field of the site ,move The center coordinates of the circle are used to determine the lifting weight of the superimposed state in real time. The determination formula is as follows:

[0153] ;

[0154] In the formula,

[0155] Indicates The color value of the pixel after the superposition;

[0156] Indicates the color value of each pixel after the last overlay;

[0157] Tower crane The color value of each pixel;

[0158] , Indicates the offset distance of the center point of the tower crane relative to the center point of the site;

[0159] The calculation result uses the RGB value (0~255) to truncate, and visual color judgment is used to determine whether the tower crane can cover the lifting demand in the area. RGB (0,0,0) is black, which means it can cover;

[0160] Further calculation of After the stacking, the remaining lifting requirements ;

[0161] ;

[0162] In the formula,

[0163] , , Indicates The pixel value of the point in the site lifting weight distribution map after the superposition;

[0164] S43, perform spatial identification in real time. The identification principle is that the tower crane and its lower foundation do not conflict with existing structures or structures to be built on the ground or underground. Space field The space field with the venue Superposition, in step S42, the coordinate position is spatially determined, the determination formula is as follows:

[0165] ;

[0166] There is no space conflict.

[0167] S44, according to the tower crane model from large to small, then crawler crane, truck crane, The next choice is closest to of For the corresponding tower crane, step S41-S43 is repeated step by step until the judgment requirements are fully met:

[0168] ;

[0169] The remaining areas are equipped with mobile lifting equipment to meet lifting needs.

[0170] S5. Adopt genetic algorithms based on engineering prior knowledge to intelligently optimize the visual layout process of tower cranes, and find the lowest price solution while meeting the lifting capacity requirements and avoiding space collisions;

[0171] Specifically:

[0172] S51. Coding scheme for tower crane and its location [ K , x k , y k ] , combined with prior knowledge to initialize the population, prioritize the placement of heavy tower cranes near the heavy lifting area, and convert the engineering prior information of tower cranes attached to existing building structures into probability distribution , when the population is randomly initialized, the solution population is formed by probability sampling;

[0173] S52, calculate the fitness, the fitness function is as follows:

[0174] ;

[0175] In the formula,

[0176] Indicates the total price of renting a tower crane;

[0177] Indicates constraint processing. Set constraints according to the space judgment and lifting weight judgment methods. When the judgment passes Take 1, if not passed Take 0;

[0178] S53. Select a solution with large fitness for crossover and mutation operations, and set the probability parameter to the product of fixed probability and prior probability:

[0179] Position Crossover: ;

[0180] Position variation: ;

[0181] S54, generate a new population, recalculate the fitness, and update the probability distribution according to the fitness gradient ;

[0182] S55, repeat steps S52-S54 until the maximum number of evolutions is reached End of time;

[0183] S56. Select the plan with the lowest total price as the final tower crane selection and layout plan. Specific embodiment 1:

[0185] Combination Figure 2 , Figure 3 , a tower crane selection and site visualization layout intelligent positioning method in the present invention is used to formulate a plan for the site tower crane selection and layout of a super high-rise building project.

[0186] Conduct on-site survey of the construction site and calculate the lifting tonnage of each area during the entire construction process. The super-high-rise core tube in the central area is equipped with steel structures such as steel beams and steel stairs. The lifting capacity is between 0.1-4.5t. The lifting capacity distribution and regional restrictions are drawn on the CAD drawing respectively.

[0187] The lifting weight distribution map and the area restriction distribution map are converted into image data in png format. The program is written in Python language to process the image and perform contour detection to obtain the contour of the lifting weight distribution map. The connected domain of each area is segmented by mouse clicks, and the color interpolation function is used to assign values, and the values ​​are mapped from the lifting weight space to the RGB space. Take (0, 0, 255), Take (255, 0, 0).

[0188] The local tower crane rental prices are shown in Table 1. The rental price of a truck crane is between 500 and 2,000 yuan per day. The foundation dimensions and attachment method are preliminarily designed, and the area occupied by the tower crane foundation is drawn, and a visualization diagram of the lifting capacity field within the coverage area is drawn.

[0189]

[0190] Move the center point of the tower crane on the site map to determine in real time whether there is a space conflict and whether the lifting weight can be covered. When calculating, the RGB value is truncated to (0~255). RGB (0,0,0) black means it can be covered. Based on engineering experience, the large tower crane SYT80A (T6010-6) is placed first to gradually cover the entire map.

[0191] According to engineering experience, the tower crane is most likely to be arranged near the core tube and can cover the material yard area, initializing the probability distribution of prior information , according to probability sampling and encoding, 20 groups of scheme codes are set to initialize the population; the fixed probabilities of crossover and mutation are set to 0.4 and 0.1, and the maximum number of evolutions is set to 5000 times. After the calculation is completed, the scheme with the lowest price is selected as the selection and layout scheme.

[0192] The present invention effectively visualizes the tower crane selection and layout process, and visualizes the lifting weight requirements by region, which greatly improves the efficiency of program developers, facilitates construction workers to intuitively understand the program, and creates economic benefits.

[0193] The present invention effectively transforms the problems of tower crane selection, layout and other scheme preparation into mathematical processes, thereby improving computability and optimization efficiency.

[0194] On the basis of genetic algorithm, the present invention sets engineering prior knowledge, integrates engineering experience, effectively constrains the direction of solution optimization, and improves the efficiency of optimization.

[0195] The invention is not only applicable to the selection and layout optimization of tower cranes, but also applicable to the selection and layout problems of other construction equipment, has a wide application range, and is easy to promote.

[0196] The present invention is described above by way of example in conjunction with the accompanying drawings. It is obvious that the specific implementation of the present invention is not limited to the above-mentioned method. As long as various improvements are made using the method concept and technical solution of the present invention, or are directly applied to other occasions without improvement, they are all within the protection scope of the present invention.

Claims

1. A tower crane selection and site visualization layout intelligent positioning method, characterized in that: The following steps are involved: S1. Conduct on-site survey of the construction site, process the site CAD drawings according to the layout of the above-ground buildings, underground pipelines, and temporary construction facilities, divide the areas according to the lifting requirements, calculate the lifting weight requirements of each area, obtain the lifting weight distribution map, divide the site area according to the above-ground and underground environmental boundaries, and obtain the regional restriction distribution map; S2. Convert the pre-processed CAD drawing into image data, grayscale, Gaussian blur, and threshold the image, perform contour detection, and segment the connected areas of the site; map the lifting weight requirements and area restrictions of the segmented areas to the color domain through a normalized mapping function to form a lifting weight field of the site on the map. , space field ; S3. Investigate the tower crane models available in the construction area, and draw a coverage image based on the model data of the tower crane products, the lifting arm length and the maximum lifting weight of the tower crane. Use the normalized mapping function to map the lifting capacity field of the tower crane. At the same time, the size of the foundation, the attachment method, the size of the attachment structure, and the spatial field of the tower crane are preliminarily designed. ; S4. Visual positioning is carried out according to the principle of non-collision of the space field and the crane's lifting capacity field covering the site's lifting capacity field, and the overall lifting demand. Select a tower crane with corresponding capacity and Lifting capacity of mobile tower crane , calculate the pixels of the image in real time, calculate whether the lifting capacity meets the requirements and whether the space field collides through the discriminant function, and display it visually on the image, and gradually calculate the remaining lifting requirements And add tower cranes until it fully meets the construction needs; S5. Adopt the genetic algorithm improved based on engineering prior knowledge to intelligently optimize the visual layout process of tower cranes and find the lowest price solution while meeting the lifting capacity requirements and avoiding space collisions.

2. According to claim 1, a tower crane selection and site visualization layout intelligent positioning method is characterized in that: S1 includes the following steps: S11. Conduct on-site survey of the construction site to determine the spatial restricted areas of building height and traffic lines in the above-ground environment, the restricted areas of the on-site working surface of the on-site material warehouse, material yard, and mixing station, and the restricted areas of the tower crane foundation of the underground pipeline; S12, standardize the CAD drawing, remove the dimension marks and text, and draw the restricted area boundary in step S11 on the CAD drawing to obtain a regional restriction distribution map; S13. Calculate the lifting capacity requirements of each area according to the construction drawing, redivide the area according to the lifting capacity and environmental boundaries, draw it on the CAD drawing, and obtain a lifting capacity distribution map for computer vision processing.

3. The method for intelligent positioning of tower crane selection and site visualization layout according to claim 2 is characterized in that: S2 includes the following steps: S21, converting the standardized drawing into image data, performing grayscale processing, Gaussian blurring, thresholding processing, and contour detection on the image, obtaining contour data of the lifting weight distribution and contour data of the spatial restricted area, and saving these contour data as a tree structure for subsequent calculations; S22, using the depth-first search-based contour tree retrieval method to retrieve the contour line of the weight distribution map, in the standardized drawing image, click a point in the area ,calculate The area where the point is located is calculated as follows: ； In the formula, Indicates The number of pixels clicked; express The outer boundary contour of the area where the point is located; express The coordinates of the pixel point; Indicates the number of the retrieved contour line; The value range is from 1 to , Indicates the number of key pixels on the contour line; express The coordinates of the point; calculate The Euclidean distance from each connected region boundary is determined The outer boundary of the region to which the point belongs; S23, further searched All sub-contours of , ,,,, , further solving for The formula for the area is as follows: ； Segment the connected domains of all different lifting weights in the lifting weight distribution graph; S24, will Lifting capacity of the area , after normalization, we get , further mapped to the color domain using the interpolation function, and assigned to Area, visualize the lifting weight, the color interpolation function is as follows: ； In the formula, Indicates the color after mapping; and Indicates the colors corresponding to the low and high bits of the lifting weight, and takes values ​​in RGB or HSV space; S25, repeat steps S22-S24 to convert the weight distribution diagram into a visual lifting weight field ; S26, using the method of steps S22-S25 to convert the regional restriction distribution map into a visualized spatial field , the color interpolation function uniformly takes the same color .

4. The method for intelligent positioning of tower crane selection and site visualization layout according to claim 3 is characterized in that: S3 includes the following steps: S31. Investigate the tower crane models available in the construction area, and compile statistics on the types, parameters, and rental prices of tower cranes, crawler cranes, and truck cranes; S32. For a type of tower crane, a coverage image is drawn based on the data of the tower crane's boom length and maximum lifting weight. Calculate the color at the center point: ； The calculation formula for pixels in the crane coverage area is as follows: ； In the formula, Indicates the distance from the farthest end to the center of the tower crane's coverage area; Indicates the Euclidean distance between points in the region and the center point; Forming the lifting capacity field of the tower crane ; S33. Preliminarily design the foundation size, attachment method, and attachment structure size of the tower crane according to the specifications, and use the method of steps S22-S25 to construct a visual spatial field of the tower crane. , the color interpolation function uniformly takes the same color .

5. The method for intelligent positioning of tower crane selection and site visualization layout according to claim 4 is characterized in that: S4 includes the following steps: S41. According to the specifications and on-site construction requirements, the lifting capacity of different types of mobile tower cranes is visualized. , at the site's lifting weight field Explore reasonable solutions by moving up and down, perform real-time lifting capacity judgment, spatial collision judgment, and cost calculation, select tower cranes in batches, give priority to selecting larger tower cranes according to lifting capacity requirements, gradually comply with the judgment principles, and calculate the overall lifting requirements of the site lifting capacity distribution diagram : ； In the formula, , , Represents the pixel value of a point in the site lifting weight distribution map; Calculate the overall lifting capacity of each type of tower crane : ； In the formula, , , Indicates The pixel value of the point in the lifting capacity map of the tower crane; S42, real-time lifting capacity determination, the determination principle is based on the lifting capacity of the tower crane Lifting capacity of the site The coverage capability of Next, select the closest of Corresponding to a tower crane , the lifting capacity field , superimposed on the lifting weight field of the site ,move The center coordinates of the circle are used to determine the lifting weight of the superimposed state in real time. The determination formula is as follows: ； In the formula, Indicates The color value of the pixel after the superposition; Indicates the color value of each pixel after the last overlay; Tower crane The color value of each pixel; , Indicates the offset distance of the center point of the tower crane relative to the center point of the site; The calculation result uses the RGB value (0~255) to truncate, and visual color judgment is used to determine whether the tower crane can cover the lifting demand in the area. RGB (0,0,0) is black, which means it can cover; Further calculation of After the stacking, the remaining lifting requirements ; ； In the formula, , , Indicates The pixel value of the point in the site lifting weight distribution map after the superposition; S43, perform spatial identification in real time. The identification principle is that the tower crane and its lower foundation do not conflict with existing structures or structures to be built on the ground or underground. Space field The space field with the venue Superposition, in step S42, the coordinate position is spatially determined, and the determination formula is as follows: ； There is no space conflict.

6. S44, according to the tower crane model from large to small, then crawler crane, truck crane, the first The next choice is closest to of For the corresponding tower crane, step S41-S43 is repeated step by step until the judgment requirements are fully met: ； The remaining areas are equipped with mobile lifting equipment to meet lifting needs.

7. The method for intelligent positioning of tower crane selection and site visualization layout according to claim 5 is characterized in that: S5 contains the following steps: S51. Coding scheme for tower crane and its location , combined with prior knowledge to initialize the population, prioritize the placement of heavy tower cranes near the heavy lifting area, and convert the engineering prior information of tower cranes attached to existing building structures into probability distribution , when the population is randomly initialized, the solution population is formed by probability sampling; S52, calculate the fitness, the fitness function is as follows: ； In the formula, Indicates the total price of renting a tower crane; Indicates constraint processing. Set constraints according to the space judgment and lifting weight judgment methods. When the judgment passes Take 1, if not passed Take 0; S53. Select a solution with large fitness for crossover and mutation operations, and set the probability parameter to the product of fixed probability and prior probability: Position Crossover: ; Position variation: ; S54, generate a new population, recalculate the fitness, and update the probability distribution according to the fitness gradient ; S55, repeat steps S52-S54 until the maximum number of evolutions is reached End of time; S56. Select the plan with the lowest total price as the final tower crane selection and layout plan.

Images