Building automation construction site intelligent management system based on big data

Abstract

The invention belongs to the field of intelligent management, and relates to a building automation construction site intelligent management system based on big data, and the system comprises a building construction size qualification analysis module, a reinforcing steel bar quality qualification judgment module, a building construction quality qualification judgment module, a building construction model splicing module, a fabricated residence qualification judgment module and the like. The method comprises the steps that firstly, building component size data are collected, an actual model is created in BIM software, and the area qualification degree is analyzed; then, steel bar distribution and defects are analyzed based on the model, and steel bar quality is judged. And then, the building component quality is judged and early warning is performed by integrating the area and the steel bar quality. And if all the components are qualified, simulating splicing to obtain an integral model, and judging the qualification of the integral model. And finally, carrying out field assembly and concrete filling, collecting images, analyzing wall pollution and defects, comprehensively evaluating the quality of the fabricated residence and carrying out early warning. The system ensures comprehensive quality detection and qualification judgment of the assembly type residence from components to the whole.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent management and relates to a building automation construction site intelligent management system based on big data. Background Art

[0002] With the rapid development of information technology, the construction industry is undergoing a transformation from traditional construction mode to intelligent and automated construction mode. This transformation aims to improve construction efficiency, reduce safety risks, achieve refined management, and promote the development of green buildings. Especially in the construction management of building components, the traditional manual management method can no longer meet the current construction industry's high requirements for efficiency, quality and safety.

[0003] Although the existing intelligent management system for building automation construction sites based on big data meets certain needs, it still has limitations, which are specifically reflected in the following aspects: 1. The existing technology has obvious limitations in analyzing the overall quality of prefabricated residential building components. It has failed to organically combine key factors such as residential size and steel bar quality for in-depth analysis to comprehensively evaluate the overall quality, and lacks the steps of simulating the splicing of building models of various building components to verify the splicing effect in advance. As a result, it is difficult to grasp the relationship between various factors and their synergistic impact on the final quality, which limits the in-depth understanding of building quality. In addition, it is impossible to fully and intuitively present the complete state of the components after splicing before actual construction, making it difficult for potential problems such as component mismatch and unreasonable design to be discovered and corrected in time before construction.

[0004] 2. Most existing technologies lack an effective mechanism to promptly determine whether the quality of prefabricated housing is qualified and issue an early warning after the construction is completed. Usually, quality problems are only discovered when they appear during subsequent use. It is impossible to detect potential quality risks in advance and take corresponding measures before delivery for use. This makes it possible for houses with quality problems to be delivered directly, causing many subsequent inconveniences and safety risks to users. Summary of the invention

[0005] In view of this, in order to solve the problems raised in the above background technology, a building automation construction site intelligent management system based on big data is proposed.

[0006] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides a building automation construction site intelligent management system based on big data, including: a building construction size qualification analysis module: used to collect the size data of each building component of the prefabricated house, and create an actual building model of each building component of the prefabricated house in the building information model software based on the size data of each building component of the prefabricated house, and then analyze the area qualification index of each building component of the prefabricated house.

[0007] Steel bar quality qualification judgment module: It is used to analyze the distribution qualification index and defect degree index of the steel bars in each building component of the prefabricated house based on the actual building model of each building component of the prefabricated house, and then analyze the quality qualification index of the steel bars in each building component of the prefabricated house.

[0008] Building construction quality qualification judgment module: used to analyze the quality qualification index of each building component of the prefabricated house based on the area qualification index of each building component of the prefabricated house and the quality qualification index of the steel bars, judge whether the quality of each building component of the prefabricated house is qualified, and then issue an early warning.

[0009] Building construction model splicing module: when the quality of each building component of the prefabricated house is qualified, the actual building model of each building component of the prefabricated house is simulated and spliced ​​to obtain the actual building model of the prefabricated house after splicing, and then judge whether the actual building model of the prefabricated house after splicing is qualified.

[0010] Prefabricated house qualification judgment module: when the actual building model of the assembled prefabricated house is qualified, the prefabricated house is assembled on site and concrete is filled into it, and images of the prefabricated house after concrete filling are collected by drones from various angles, and the pollution degree index and defect degree index of the wall surface of the prefabricated house after concrete filling are analyzed respectively, and then the comprehensive quality qualification degree index of the prefabricated house after concrete filling is analyzed, to judge whether the quality of the prefabricated house after concrete filling is qualified, and to issue an early warning.

[0011] Database: used to store the standard dimensions of each building structure of prefabricated housing, the standard bending angles, standard hook lengths and standard straight segment lengths of various types of steel bars in building components, the standard anchorage lengths, standard protective layer thicknesses and standard spacing between corresponding steel bars and their adjacent steel bars at each installation position of each type of building component.

[0012] Compared with the prior art, the present invention has the following beneficial effects: (1) By collecting the dimensional data of each building component of the prefabricated house, the present invention creates a building model of each building component of the prefabricated house, and then analyzes the area qualification index of each building component of the prefabricated house, so as to identify in advance those problems that may be exposed only during the actual assembly process. Through such early analysis, these potential problems can be discovered during the component production stage or before entering the site, and timely adjustments or replacements can be made to avoid delays in construction time and increased costs at the construction site.

[0013] (2) The present invention analyzes the distribution qualification index and defect degree index of the steel bars in each building component of the prefabricated house based on the building model of each building component of the prefabricated house, and then analyzes the quality qualification index of the steel bars in each building component of the prefabricated house. It can accurately grasp the actual conditions of the steel bars in the components from multiple dimensions, and is no longer limited to the detection of a few indicators such as the conventional strength of the steel bars. Instead, it fully considers key factors such as whether its distribution is reasonable and whether there are defects, so that the quality qualification index of the steel bars can be obtained more accurately.

[0014] (3) The present invention simulates and splices the architectural models of the various building components of the prefabricated house to obtain the architectural model of the assembled prefabricated house, and then determines whether the architectural model of the assembled prefabricated house is qualified, thereby reducing the temporary adjustment, cutting, reprocessing and other operations required at the construction site due to problems such as component mismatch and unreasonable design.

[0015] (4) The present invention assembles the various building structures of the prefabricated house on site and fills the concrete when the architectural model of the prefabricated house is qualified after being assembled, then collects the image of the prefabricated house after filling, analyzes its pollution degree index and defect degree index to obtain a comprehensive quality qualification degree index, and judges whether the quality is qualified and issues a warning based on this. This method can avoid the delivery of unqualified prefabricated houses through timely quality analysis and warning, thereby greatly reducing the high costs caused by rework, maintenance and other operations due to quality problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a schematic diagram of the connection of each module of the system of the present invention.

[0018] Figure 2 The present invention is a specific step for analyzing the area qualification index of the building components of the prefabricated house in the system of the present invention.

[0019] Figure 3 The present invention provides specific steps for analyzing the defect index of steel bars in building components of prefabricated houses in the system of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] See also Figure 1 As shown, the present invention provides a big data-based intelligent management system for building automation construction sites, including: a building construction size qualification analysis module, a steel bar quality qualification judgment module, a building construction quality qualification judgment module, a building construction model splicing module, a prefabricated housing qualification judgment module and a database.

[0022] The steel bar quality qualified judgment module is respectively connected to the building construction size qualified analysis module, the building construction quality qualified judgment module and the database, the building construction quality qualified judgment module is respectively connected to the steel bar quality qualified judgment module and the building construction model splicing module, the building construction model splicing module is respectively connected to the building construction quality qualified judgment module and the prefabricated housing qualified judgment module, and the database is respectively connected to the building construction size qualified analysis module, the steel bar quality qualified judgment module and the prefabricated housing qualified judgment module.

[0023] Building construction dimension qualification analysis module: used to collect dimension data of each building component of the prefabricated house, create actual building models of each building component of the prefabricated house in the building information model software based on the dimension data of each building component of the prefabricated house, and then analyze the area qualification index of each building component of the prefabricated house.

[0024] As a preferred embodiment, the specific process of collecting the dimensional data of each building component of the prefabricated house is: scanning each building component of the prefabricated house by a three-dimensional laser scanner to obtain the dimensional data of each building component of the prefabricated house.

[0025] The specific process of creating the architectural model of each building component of the prefabricated house in the building information model software based on the size data of each building component of the prefabricated house is as follows: based on the size data of each building component of the prefabricated house, create the basic template of each building component in the BIM software. For example, for the column component, according to its cross-sectional size, height and other data, draw the two-dimensional outline of the column in the modeling tool of the software, and then convert it into a three-dimensional solid model through operations such as stretching. The same method is applicable to other components such as beams, plates, walls, etc., and the corresponding basic three-dimensional models are created according to their respective size data.

[0026] After creating the basic component template, further add detailed features and related attributes to each component. For example, for beam components, in addition to basic dimensions, you can also add beam reinforcement information, concrete strength grade and other attributes. These attributes and details can be completed through the parameter setting function or special attribute editing panel provided by the software, and then create the architectural model of each building component of the prefabricated house.

[0027] See also Figure 2 As shown, further, the analysis of the area qualification index of each building component of the prefabricated house includes: A1, extracting the standard size of each building component of the prefabricated house from the database, and creating a standard building model of each building component of the prefabricated house in the building information model software based on the standard size of each building component of the prefabricated house;

[0028] A2. Calculate the surface contour area of ​​the actual building model and the standard building model of each building component of the prefabricated house through the area calculation function of the building information model software, obtain the surface contour area of ​​the actual building model and the standard building model, compare them, and obtain the difference between the surface contour area of ​​the actual building model of each building component of the prefabricated house and the corresponding surface contour area of ​​the corresponding standard building model, and use it as the area difference of each surface contour of each building component of the prefabricated house, recorded as Δarea jb , where j represents the number corresponding to the j-th building component of the prefabricated house, j=1,2,3,...G, and b represents the number corresponding to the b-th surface contour of the building component of the prefabricated house, b=1,2,3...B.

[0029] A3. Analyze the area qualification index dim of each building component of the prefabricated house j .

[0030] As a preferred embodiment, the specific calculation formula for analyzing the area qualification index of each building component of the prefabricated house is: Wherein Δarea′ represents the allowable area difference of the surface contours of the building components of the prefabricated house, and B represents the total number of surface contours of the building components of the prefabricated house.

[0031] The allowable area difference of the surface profile of the prefabricated residential building components is determined by professionals based on professional knowledge and experience.

[0032] The present invention collects the dimensional data of each building component of the prefabricated house, creates a building model of each building component of the prefabricated house, and then analyzes the area qualification index of each building component of the prefabricated house. It can identify in advance those problems that may be exposed only during the actual assembly process. Through this early analysis, these potential problems can be discovered during the component production stage or before entering the site, and timely adjustments or replacements can be made to avoid delays in construction time, increased costs, etc. at the construction site.

[0033] Steel bar quality qualification judgment module: It is used to analyze the distribution qualification index and defect degree index of the steel bars in each building component of the prefabricated house based on the actual building model of each building component of the prefabricated house, and then analyze the quality qualification index of the steel bars in each building component of the prefabricated house.

[0034] Furthermore, the specific process of analyzing the distribution qualification index of the steel bars in each building component of the prefabricated house is as follows: extracting the spacing between each steel bar and its adjacent steel bars, the anchorage length and the protective layer thickness of each type of each building component of the prefabricated house from the actual building model of each building component of the prefabricated house, and recording them as sp jgi 、an jgi and pr jgi , where g represents the number corresponding to the g-th type of steel bar, g = 1, 2, 3, ... J, and i represents the number corresponding to the i-th steel bar, i = 1, 2, 3, ... I.

[0035] The standard anchorage length, standard protective layer thickness and standard spacing between the corresponding steel bar and its adjacent steel bar at each installation position of each type of building components of the prefabricated house are extracted from the database, and then the standard anchorage length, standard protective layer thickness and standard spacing between the corresponding steel bar and its adjacent steel bar of each type of building components of the prefabricated house are screened out according to the position of each steel bar of each type in each building component of the prefabricated house, which are recorded as an′ jgi pr′ jgi and sp′ jgi .

[0036] Analyze the distribution qualification index of steel bars in each building component of prefabricated housing j ,

[0037] , ι1, ι2 and ι3 respectively represent the weights corresponding to the spacing between the steel bars and their adjacent steel bars of the type in the building components of the prefabricated house, the anchorage length of the steel bars and the thickness of the protective layer of the steel bars, and ι1+ι2+ι3=1, e represents a natural constant, J represents the total number of steel bar types in the building components of the prefabricated house, and I represents the total number of steel bars.

[0038] As a preferred embodiment, ι1, ι2 and ι3 can be set to 0.4, 0.3 and 0.3 respectively. The anchorage length of the steel bar is crucial to its stress transfer and bearing capacity in the concrete structure. The thickness of the protective layer can protect the steel bar from erosion by the external environment. The spacing between the steel bars affects the quality of concrete pouring. Therefore, in prefabricated residential building components, the weight of the anchorage length of the steel bar is higher than the weight of the spacing between the steel bars and the thickness of the steel bar protective layer.

[0039] The steel bars of each type in each building component of the prefabricated house include: transverse steel bars and longitudinal steel bars.

[0040] The specific process of extracting the spacing between each steel bar of each type in each building component of the prefabricated house and its adjacent steel bars is as follows: extracting the center point coordinates of each steel bar of each type in each building component of the prefabricated house by building information model software, comparing the center point coordinates of each steel bar with the center point coordinates of each adjacent steel bar, obtaining the spacing between each steel bar of each type in each building component of the prefabricated house and each steel bar of the corresponding type adjacent to it, and selecting the shortest spacing as the spacing between each steel bar of each type in each building component of the prefabricated house and its adjacent steel bars.

[0041] The specific process of extracting the anchorage length of each type of steel bar in each building component of the prefabricated house is as follows: based on the architectural model of each building component of the prefabricated house, the coordinates of the anchorage starting point and the anchorage ending point of each type of steel bar in each building component of the prefabricated house are extracted, and the coordinates are substituted into the Euclidean distance formula to obtain the straight-line distance from the anchorage starting point to the ending point of each type of steel bar in each building component of the prefabricated house, which is used as the anchorage length of each type of steel bar in each building component of the prefabricated house.

[0042] The coordinates of the anchoring starting points of various types of steel bars in various building components of the prefabricated house refer to the positions where the steel bars begin to be anchored.

[0043] For example, the starting point of the longitudinal reinforcement anchorage of the column is often at the top surface of the foundation or the bottom of the floor beam, where the reinforcement begins to extend into the column and play an anchoring role. Taking the same spatial coordinate system as an example, assuming that the column is located at a specific position in the building, the coordinates of the starting point of the longitudinal reinforcement anchorage (x2, y2, z2) are determined by the position of the column in the building plane and the arrangement of the reinforcement in the column section, and z2 is the height value corresponding to the top surface of the foundation or the bottom of the floor beam.

[0044] The coordinates of the anchorage termination points of various types of steel bars in various building components of the prefabricated house refer to the positions where the steel bars complete the anchorage function.

[0045] For example, the anchorage end point of the longitudinal reinforcement of the column, such as at the top of the floor beam, is the anchorage end point when the reinforcement extends into the beam to the specified anchorage length. Its coordinates (x3, y3, z3) are determined according to the position of the column in the building plane, the arrangement of the reinforcement in the column section, and the specified anchorage length. x3 and y3 will be determined according to the specific situation, and z3 is the height value corresponding to the top of the floor beam.

[0046] The specific process of extracting the protective layer thickness of each type of steel bar in each building component of the prefabricated house is as follows: based on the architectural model of each building component of the prefabricated house, the coordinates of each outer edge point of each type of steel bar in each building component of the prefabricated house and each point on the inner surface of the corresponding building component are extracted, and the coordinates are substituted into the Euclidean distance formula to obtain the distance from each outer edge point of each type of steel bar in each building component of the prefabricated house to each point on the inner surface of the corresponding building component, and the shortest distance from the outer edge point of each type of steel bar in each building component of the prefabricated house to the point on the inner surface of the corresponding building component is screened out, and the distance is used as the protective layer thickness of each type of steel bar in each building component of the prefabricated house.

[0047] See also Figure 3 As shown, further, the specific process of analyzing the defect degree index of the steel bars in each building component of the prefabricated house is: D1. Extracting the standard bending angle, standard hook length and standard straight segment length of each type of steel bars in each building component of the prefabricated house from the database.

[0048] D2. Extract the bending angles, hook lengths and straight segment lengths of various types of steel bars in various building components of the prefabricated house from the building models of the building components of the prefabricated house.

[0049] D3. Compare the bending angles of various steel bars in various building components of the prefabricated house with the standard bending angles of the corresponding steel bars to obtain the difference in bending angles of various steel bars in various building components of the prefabricated house, recorded as Δangle jg .

[0050] D4. According to the analysis method of the bending angle difference of each type of steel bar in each building component of the prefabricated house, the hook length difference and straight segment length difference of each type of steel bar in each building component of the prefabricated house are obtained in the same way, which are recorded as Δhook jg and Δline jg .

[0051] D5. Analyze the degree of defect index of steel bars in each building component of prefabricated housing j .

[0052] As a preferred embodiment, the bending angle of the steel bar is specifically: the angle between the two ends of the steel bar during the bending process; the hook length of the steel bar is specifically: the length of the hook-shaped part at the end of the steel bar; the straight segment length of the steel bar is specifically: the length of the continuous straight section of the steel bar before or after bending.

[0053] The specific calculation formula for analyzing the defect degree index of the steel bars in each building component of the prefabricated house is:

[0054] Among them, Δangle′, Δhook′ and Δline′ respectively represent the allowable bending angle difference, allowable hook length difference and allowable straight segment length difference of the steel bars in the building components of the prefabricated house, ε1, ε2 and ε3 respectively represent the weights corresponding to the bending angle difference, hook length difference and straight segment length difference of the steel bars in the building components of the prefabricated house, and ε1+ε2+ε3=1.

[0055] The ε1, ε2 and ε3 can be set to 0.4, 0.3 and 0.3 respectively. In terms of steel bar quality control, the bending angle is a key factor, because its non-conformity will affect the anchoring effect in concrete and the stress performance of building components; although the hook length and the straight segment length are important for the anchoring and force transmission of steel bars, their direct impact on structural safety is slightly weaker than the bending angle. Therefore, in prefabricated residential building components, the weight corresponding to the difference in the steel bar bending angle is greater than the weight corresponding to the difference in the hook length and the difference in the straight segment length.

[0056] The present invention analyzes the distribution qualification index and defect degree index of steel bars in each building component of the prefabricated house based on the building model of each building component of the prefabricated house, and then analyzes the quality qualification index of the steel bars in each building component of the prefabricated house. The actual condition of the steel bars in the components can be accurately grasped from multiple dimensions. The method is no longer limited to the detection of a few indicators such as the conventional strength of the steel bars, but fully considers key factors such as whether its distribution is reasonable and whether there are defects, so that the quality qualification index of the steel bars can be obtained more accurately.

[0057] Building construction quality qualification judgment module: used to analyze the quality qualification index of each building component of the prefabricated house based on the area qualification index of each building component of the prefabricated house and the quality qualification index of the steel bars, judge whether the quality of each building component of the prefabricated house is qualified, and then issue an early warning.

[0058] Furthermore, the specific calculation formula for analyzing the quality qualification index of the steel bars in each building component of the prefabricated house is: Wherein γ1 and γ2 represent the weights corresponding to the distribution qualification index and defect index of the steel bars in the building components of the prefabricated house, respectively, and γ1+γ2=1.

[0059] As a preferred embodiment, the γ1 and γ2 can be set to 0.6 and 0.4 respectively. The distribution of steel bars in prefabricated residential building components (including anchor length, protective layer thickness, steel bar spacing, etc.) is crucial to the safety, durability, and normal use performance of building components and the entire prefabricated residential structure from a macro perspective. The steel bar defect index is mainly related to its own morphological deviation (such as the difference in bending angle, hook length, straight segment length, etc.). Although it will affect the stress performance of the steel bar and its role in the structure, its influence range is more local than the distribution, and it mostly affects the combined performance of a single or local steel bar. Therefore, in prefabricated residential building components, the weight corresponding to the steel bar distribution qualification index is greater than the weight corresponding to the defect index.

[0060] Furthermore, the specific calculation process of analyzing the quality qualification index of each building component of the prefabricated house is as follows: j =dim j *β1+complete j *β2, where β1 and β2 represent the weight factors corresponding to the area qualification index of the building components of the prefabricated house and the quality qualification index of the steel bars, respectively, and β1+β2=1.

[0061] As a preferred embodiment, β1 and β2 can be set to 0.4 and 0.6 respectively. In the prefabricated residential building components, steel bars play a key role in bearing and reinforcement, and their quality is related to the overall mechanical properties and structural safety of the building components. Although the area qualification of building components has an impact on dimensional accuracy and assembly accuracy and is also very important, the structural safety hazards caused by unqualified steel bar quality are more serious, so the weight factor corresponding to the area qualification index of prefabricated residential building components is greater than the weight factor corresponding to the quality qualification index of steel bars.

[0062] Furthermore, the specific process of judging whether the quality of each building component of the prefabricated house is qualified is: comparing the qualification degree index of each building component of the prefabricated house with a preset qualification degree index threshold; if the qualification degree index of a certain building component of the prefabricated house is less than the preset qualification degree index threshold, then the building component of the prefabricated house is unqualified, and then the unqualified building components of the prefabricated house are obtained, and the unqualified building components of the prefabricated house are numbered, and then an early warning is issued.

[0063] As a preferred embodiment, after the early warning is issued, the manufacturing personnel of the building components are notified to re-customize.

[0064] The present invention analyzes the quality qualification index of each building component of the prefabricated house based on the area qualification index of each building component of the prefabricated house and the quality qualification index of the steel bar, judges whether the quality of each building component of the prefabricated house is qualified, and then issues an early warning, thereby achieving a comprehensive assessment of the component quality from multiple key factors. Size and steel bar quality are important factors affecting the performance of building components. Combining the two for analysis can more accurately reflect the actual quality status of the components, avoid the one-sidedness caused by relying solely on a single indicator to judge the quality, and thus more accurately judge whether the quality of each building component is qualified.

[0065] Building construction model splicing module: when the quality of each building component of the prefabricated house is qualified, the actual building model of each building component of the prefabricated house is simulated and spliced ​​to obtain the actual building model of the prefabricated house after splicing, and then judge whether the actual building model of the prefabricated house after splicing is qualified.

[0066] As a preferred embodiment, the specific process of judging whether the architectural model of the assembled prefabricated house is qualified is as follows: first, a laser rangefinder is used to measure multiple positions (such as two ends, the middle, etc.) of the splicing gaps between each building component of the assembled house and its adjacent components in the architectural model, and the width data of the splicing gaps between each building component of the assembled house and its adjacent components at different positions are obtained, and the maximum width of the splicing gaps between each building component of the assembled house and its adjacent components is screened out, and the maximum width of the splicing gaps between each building component of the assembled house and its adjacent components is compared with the set maximum allowable width of the splicing gaps between the building component and its adjacent components. When the maximum width of the splicing gap between a certain building component of the assembled house and its adjacent components is less than or equal to the set maximum allowable width of the splicing gaps between the building component and its adjacent components, the building component of the assembled house is qualified; otherwise, it is unqualified; when the maximum width of the splicing gaps between each building component of the assembled house and its adjacent components are all less than or equal to the set maximum allowable width of the splicing gaps between the building component and its adjacent components, the actual architectural model of the assembled house is qualified.

[0067] The maximum permissible width is usually set according to industry standards.

[0068] The present invention simulates and splices the architectural models of the various building components of the prefabricated house to obtain the architectural model of the spliced ​​prefabricated house, and then judges whether the architectural model of the spliced ​​prefabricated house is qualified, thereby reducing the temporary adjustment, cutting, reprocessing and other operations required at the construction site due to problems such as component mismatch and unreasonable design.

[0069] Prefabricated house qualification judgment module: when the actual building model of the assembled prefabricated house is qualified, the prefabricated house is assembled on site and concrete is filled into it, and images of the prefabricated house after concrete filling are collected by drones from various angles, and the pollution degree index and defect degree index of the wall surface of the prefabricated house after concrete filling are analyzed respectively, and then the comprehensive quality qualification degree index of the prefabricated house after concrete filling is analyzed, to judge whether the quality of the prefabricated house after concrete filling is qualified, and to issue an early warning.

[0070] Furthermore, the specific process of analyzing the pollution degree index of the wall surface of the prefabricated house after concrete filling is as follows: grayscale threshold segmentation processing is performed on the images of the prefabricated house at each angle after concrete filling to obtain the grayscale value of each pixel in the images of the prefabricated house at each angle after concrete filling, and the grayscale value of each pixel in the images at each angle is compared with the standard grayscale value interval of the pixel corresponding to the standard image of the surface of the building component corresponding to the prefabricated house. If the grayscale value of a pixel does not belong to the standard grayscale value interval of the pixel corresponding to the standard image of the surface of the building component corresponding to the prefabricated house, the pixel is marked as an abnormal pixel, and the number of abnormal pixels in the images of the prefabricated house at each angle after concrete filling is screened and counted, which is recorded as stains. d , where d represents the number corresponding to the d-th angle image of the prefabricated house after concrete filling, d = 1, 2, 3, ... D, and then the total number of pixels in each angle image of the prefabricated house after concrete filling is obtained, recorded as pixel d , analyze the pollution index of prefabricated houses after concrete filling,

[0071] As a preferred embodiment, the specific process of obtaining the standard grayscale value interval of the pixel points corresponding to the standard image of the surface of the building component corresponding to the prefabricated house is: extracting the standard image of the surface of the building component corresponding to the prefabricated house from the database, graying it, and obtaining the grayscale values ​​corresponding to the standard image of the surface of the building component corresponding to the prefabricated house, and then comparing and statistically obtaining the corresponding grayscale interval, which is then used as the standard grayscale value interval of the pixel points corresponding to the standard image of the surface of the building component corresponding to the prefabricated house.

[0072] The images at various angles of the prefabricated house after concrete filling specifically include: a front image, a side image and a back image of the prefabricated house after concrete filling.

[0073] Furthermore, the specific process of analyzing the defect degree index of the wall surface of the prefabricated house after concrete filling is as follows: based on the images of the prefabricated house at various angles after concrete filling, various defect types of the prefabricated house after concrete filling are identified by image processing technology, and the characteristic values ​​of various defect types of the prefabricated house after concrete filling are obtained by the measurement tool in the image processing software, which are recorded as length t , where t represents the number corresponding to the tth defect type of the prefabricated house after concrete filling, t = 1, 2, 3, ... T, and then the total number of defects in each defect type of the prefabricated house after concrete filling is counted, recorded as Total t .

[0074] Analyze the defect index crack of prefabricated houses after concrete filling. where length′ t and Total′ t They respectively represent the allowable characteristic value and the total number of allowable defects of the tth defect type of the prefabricated house after concrete filling, ρ1 and ρ2 respectively represent the weights corresponding to the characteristic value and the total number of defects of the defect type of the prefabricated house after concrete filling, and ρ1+ρ2=1, T represents the total number of defect types.

[0075] The ρ1 and ρ2 can be set to 0.7 and 0.3 respectively. The characteristic value of the defect type has a direct and critical impact on the quality of the house. It can more accurately reflect the substantial damage of each defect to the structural performance, usage function and appearance. However, the total number of defects is also a factor that cannot be ignored. Therefore, the weight corresponding to the characteristic value of the defect type of the prefabricated house after concrete filling is greater than the weight corresponding to the total number of defects.

[0076] The specific process of identifying various types of defects of prefabricated houses after concrete filling by image processing technology is as follows: according to the construction quality acceptance standards and relevant specifications, various types of defects (such as honeycomb surface, holes, cracks, etc.) that may appear after concrete filling and their typical characteristics are clarified. On this basis, a variety of feature extraction methods are used to determine possible defect areas, such as color feature extraction, setting a color threshold range according to the color difference between the defect area (such as honeycomb surface with relatively dark color, holes with mostly black or dark color inside, etc.) and the normal concrete surface, and extracting candidate areas where defects may exist; with the help of shape feature extraction, the edge shape of cracks is extracted by using algorithms such as Canny edge detection to obtain information such as length and direction, and the shape features of holes, honeycomb surface, etc. are refined by morphological operations; texture feature extraction is used, and grayscale co-occurrence matrix and other methods are used to analyze the texture parameters of different regions, and the texture parameter differences between the normal concrete surface and the suspected defective area are compared to assist in identifying defects.

[0077] The characteristic value of the honeycomb surface is the area of ​​the honeycomb surface; the characteristic value of the hole is the depth of the hole; and the characteristic value of the crack is the length of the crack.

[0078] First, according to the extracted defect features such as color, shape, texture, etc., a classification model is established by selecting appropriate classification methods such as support vector machine, artificial neural network, decision tree, etc. Taking support vector machine as an example, a large number of image samples with known defect types annotated are required as training data, and the extracted feature vector is used as input, and the corresponding defect type annotation is used as output for model training. After the training is completed, the model performance is evaluated by cross-validation and other methods. If it is not ideal, it is optimized by adjusting model parameters, increasing the number and quality of training data, and improving feature extraction methods. Finally, the image to be identified after preprocessing and feature extraction is input into the evaluated and optimized classification model, and the model determines the defect type in the image, thereby completing the identification of various defect types of prefabricated houses after concrete filling.

[0079] Furthermore, the specific process of judging whether the quality of concrete filling of the prefabricated house after concrete filling is qualified is: analyzing the comprehensive quality qualification index quality of the prefabricated house after concrete filling, Wherein δ1 and δ2 represent the weights corresponding to the pollution degree index and defect degree index of the wall surface of the prefabricated house after concrete filling, respectively, and δ1+δ2=1.

[0080] As a preferred embodiment, the δ1 and δ2 can be set to 0.3 and 0.7 respectively. The pollution degree of the house after concrete filling seems to be a superficial factor, but it will affect the appearance and long-term durability of the building. For example, residual stains and debris affect the appearance and may accelerate the aging and damage of concrete. The degree of defects in concrete filling is directly related to the structural safety and performance of the prefabricated house. Defects such as holes, cracks, and looseness will weaken the strength, stiffness and integrity of the concrete, affect the bearing capacity and stability, and even large cracks will endanger safety. Therefore, the weight corresponding to the defect degree index of the prefabricated house after concrete filling is greater than the weight corresponding to the pollution degree index.

[0081] The comprehensive quality qualification index of the prefabricated house after concrete filling is compared with the preset comprehensive quality qualification index threshold. If the comprehensive quality qualification index of the prefabricated house after concrete filling is greater than the preset comprehensive quality qualification index threshold, the comprehensive quality of the prefabricated house after concrete filling is qualified.

[0082] The present invention assembles the various building structures of the prefabricated house on site and performs concrete filling when the architectural model of the assembled prefabricated house is qualified. Then, the image of the prefabricated house after filling is collected, and its pollution degree index and defect degree index are analyzed to obtain a comprehensive quality qualification degree index. Based on this, it is judged whether the quality is qualified and an early warning is issued. This method can avoid the delivery and use of unqualified prefabricated houses through timely quality analysis and early warning, thereby greatly reducing the high costs caused by rework, maintenance and other operations due to quality problems.

[0083] Database: used to store the standard dimensions of each building structure of prefabricated housing, the standard bending angles, standard hook lengths and standard straight segment lengths of various types of steel bars in building components, the standard anchorage lengths, standard protective layer thicknesses and standard spacing between corresponding steel bars and their adjacent steel bars at each installation position of each type of building component.

[0084] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A building automation construction site intelligent management system based on big data, characterized by: include: Building construction size qualification analysis module: used to collect the size data of each building component of the prefabricated house, create the actual building model of each building component of the prefabricated house in the building information model software based on the size data of each building component of the prefabricated house, and then analyze the area qualification index of each building component of the prefabricated house; Steel bar quality qualification judgment module: used to analyze the distribution qualification index and defect degree index of steel bars in each building component of the prefabricated house based on the actual building model of each building component of the prefabricated house, and then analyze the quality qualification index of steel bars in each building component of the prefabricated house; Building construction quality qualification judgment module: used to analyze the quality qualification index of each building component of the prefabricated house based on the area qualification index of each building component of the prefabricated house and the quality qualification index of the steel bar, judge whether the quality of each building component of the prefabricated house is qualified, and then issue an early warning; Building construction model splicing module: when the quality of each building component of the prefabricated house is qualified, the actual building model of each building component of the prefabricated house is simulated and spliced ​​to obtain the actual building model of the prefabricated house after splicing, and then judge whether the actual building model of the prefabricated house after splicing is qualified; Prefabricated housing qualification judgment module: when the actual building model of the assembled prefabricated housing is qualified, the prefabricated housing is assembled on site and concrete is filled therein, and images of the prefabricated housing after concrete filling are collected by drone from various angles, and the pollution degree index and defect degree index of the wall surface of the prefabricated housing after concrete filling are analyzed respectively, and then the comprehensive quality qualification degree index of the prefabricated housing after concrete filling is analyzed, and whether the quality of the prefabricated housing after concrete filling is qualified is judged, and an early warning is issued; Database: used to store the standard dimensions of each building structure of prefabricated housing, the standard bending angles, standard hook lengths and standard straight segment lengths of various types of steel bars in building components, the standard anchorage lengths, standard protective layer thicknesses and standard spacing between corresponding steel bars and their adjacent steel bars at each installation position of each type of building component.

2. According to the big data-based building automation construction site intelligent management system of claim 1, it is characterized by: The analysis of the area qualification index of each building component of the prefabricated house includes: A1. extracting standard sizes of various building components of the prefabricated house from a database, and creating standard building models of various building components of the prefabricated house in a building information modeling software based on the standard sizes of various building components of the prefabricated house; A2. Calculate the surface contour area of ​​the actual building model and the standard building model of each building component of the prefabricated house through the area calculation function of the building information model software, obtain the surface contour area of ​​the actual building model and the standard building model, compare them, and obtain the difference between the surface contour area of ​​the actual building model of each building component of the prefabricated house and the corresponding surface contour area of ​​the corresponding standard building model, and use it as the area difference of each surface contour of each building component of the prefabricated house, recorded as Δarea jb , where j represents the number corresponding to the j-th building component of the prefabricated house, j=1,2,3,...G, and b represents the number corresponding to the b-th surface profile of the building component of the prefabricated house, b=1,2,3...B; A3. Analyze the area qualification index dim of each building component of the prefabricated house j .

3. The intelligent management system for building automation construction sites based on big data according to claim 2 is characterized by: The specific process of analyzing the distribution qualification index of the steel bars in each building component of the prefabricated house is as follows: The spacing, anchorage length and protective layer thickness between each steel bar and its adjacent steel bars of each type in each building component of the prefabricated house are extracted from the actual building model of each building component of the prefabricated house, and are recorded as sp jgi 、an jgi and pr jgi , where g represents the number corresponding to the g-th type of steel bar, g = 1, 2, 3, ... J, i represents the number corresponding to the i-th steel bar, i = 1, 2, 3, ... I; The standard anchorage length, standard protective layer thickness and standard spacing between the corresponding steel bar and its adjacent steel bar at each installation position of each type of building component of the prefabricated house are extracted from the database, and then the standard anchorage length, standard protective layer thickness and standard spacing between the corresponding steel bar and its adjacent steel bar of each type of building component of the prefabricated house are screened out according to the position of each steel bar of each type in each building component of the prefabricated house, and are respectively recorded as an jgi ,pr jgi and sp jgi ; Analyze the distribution qualification index of steel bars in each building component of prefabricated housing j , ι1, ι2 and ι3 respectively represent the weights corresponding to the spacing between the steel bars and their adjacent steel bars of the type in the building components of the prefabricated house, the anchorage length of the steel bars and the thickness of the protective layer of the steel bars, and ι1+ι2+ι3=1, e represents a natural constant, J represents the total number of steel bar types in the building components of the prefabricated house, and I represents the total number of steel bars.

4. The intelligent management system for building automation construction sites based on big data according to claim 3 is characterized by: The specific process of analyzing the defect index of the steel bars in each building component of the prefabricated house is as follows: D1. Extract the standard bending angle, standard hook length and standard straight segment length of various types of steel bars in various building components of prefabricated houses from the database; D2. Extracting the bending angles, hook lengths and straight segment lengths of various types of steel bars in various building components of the prefabricated house from the actual building models of the building components of the prefabricated house; D3. Compare the bending angles of various steel bars in various building components of the prefabricated house with the standard bending angles of the corresponding steel bars to obtain the difference in bending angles of various steel bars in various building components of the prefabricated house, recorded as Δangle jg ; D4. According to the analysis method of the bending angle difference of each type of steel bar in each building component of the prefabricated house, the hook length difference and straight segment length difference of each type of steel bar in each building component of the prefabricated house are obtained in the same way, which are recorded as Δhook jg and Δline jg ; D5. Analyze the degree of defect index of steel bars in each building component of prefabricated housing j .

5. The intelligent management system for building automation construction sites based on big data according to claim 4 is characterized by: The specific calculation formula for analyzing the quality qualification index of the steel bars in each building component of the prefabricated house is: Wherein γ1 and γ2 represent the weights corresponding to the distribution qualification index and defect index of the steel bars in the building components of the prefabricated house, respectively, and γ1+γ2=1.

6. The intelligent management system for building automation construction sites based on big data according to claim 5 is characterized by: The specific calculation process of analyzing the quality qualification index of each building component of the prefabricated house is as follows: j =dim j *β1+complete j *β2, where β1 and β2 represent the weight factors corresponding to the area qualification index of the building components of the prefabricated house and the quality qualification index of the steel bars, respectively, and β1+β2=1.

7. The intelligent management system for building automation construction sites based on big data according to claim 1 is characterized by: The specific process of judging whether the quality of each building component of the prefabricated house is qualified is as follows: The qualification index of each building component of the prefabricated house is compared with the preset qualification index threshold. If the qualification index of a building component of the prefabricated house is less than the preset qualification index threshold, the building component of the prefabricated house is unqualified, and then the unqualified building components of the prefabricated house are obtained, and the unqualified building components of the prefabricated house are numbered, and then an early warning is issued.

8. The intelligent management system for building automation construction sites based on big data according to claim 1 is characterized by: The specific process of analyzing the pollution degree index of the wall surface of the prefabricated house after concrete filling is as follows: The grayscale threshold segmentation process is performed on the images of each angle of the prefabricated house after concrete filling to obtain the grayscale value of each pixel in the images of each angle of the prefabricated house after concrete filling, and the grayscale value of each pixel in the image of each angle is compared with the standard grayscale value interval of the pixel corresponding to the standard image of the surface of the building component of the prefabricated house. If the grayscale value of a pixel does not belong to the standard grayscale value interval of the pixel corresponding to the standard image of the surface of the building component of the prefabricated house, the pixel is marked as an abnormal pixel. The number of abnormal pixels in the images of each angle of the prefabricated house after concrete filling is screened and counted, which is recorded as stains. d , where d represents the number corresponding to the d-th angle image of the prefabricated house after concrete filling, d = 1, 2, 3, ... D, and then the total number of pixels in each angle image of the prefabricated house after concrete filling is obtained, recorded as pixel d , analyze the pollution index of prefabricated houses after concrete filling, 9. The big data-based building automation construction site intelligent management system according to claim 8, characterized in that: The specific process of analyzing the defect degree index of the wall surface of the prefabricated house after concrete filling is as follows: Based on the images of the prefabricated house at various angles after concrete filling, the various defect types of the prefabricated house after concrete filling are identified by image processing technology, and the characteristic values ​​of the various defect types of the prefabricated house after concrete filling are obtained by the measurement tools in the image processing software, which are recorded as length t , where t represents the number corresponding to the tth defect type of the prefabricated house after concrete filling, t = 1, 2, 3, ... T, and then the total number of defects in each defect type of the prefabricated house after concrete filling is counted, recorded as Total t ; Analyze the defect index crack of prefabricated houses after concrete filling. where length′ t and Total′ t They respectively represent the allowable characteristic value and the total number of allowable defects of the tth defect type of the prefabricated house after concrete filling, ρ1 and ρ2 respectively represent the weights corresponding to the characteristic value and the total number of defects of the defect type of the prefabricated house after concrete filling, and ρ1+ρ2=1, T represents the total number of defect types.

10. The big data-based building automation construction site intelligent management system according to claim 9, characterized in that: The specific process of judging whether the quality of concrete filling of the prefabricated house after concrete filling is qualified is as follows: Analyze the comprehensive quality index of prefabricated housing after concrete filling. Wherein δ1 and δ2 represent the weights corresponding to the pollution degree index and defect degree index of the wall surface of the prefabricated house after concrete filling, respectively, and δ1+δ2=1; The comprehensive quality qualification index of the prefabricated house after concrete filling is compared with the preset comprehensive quality qualification index threshold. If the comprehensive quality qualification index of the prefabricated house after concrete filling is greater than the preset comprehensive quality qualification index threshold, the comprehensive quality of the prefabricated house after concrete filling is qualified.

Images