Optimization Method and System for Construction Decision-making of Prefabricated Isolation Wards Based on BIM Model

Abstract

The present invention belongs to the technical field of construction decision-making optimization, and discloses an assembly isolation ward construction decision-making optimization method and system based on a BIM model. The method includes collecting three-dimensional point cloud data of the main building construction and collecting construction process data; constructing an actual three-dimensional model based on the point cloud data, generating a standard three-dimensional model in combination with electronic drawings, and generating a construction accuracy error and deviation evaluation value through feature extraction and quality comparison; using the deviation evaluation value and construction process data to evaluate the construction progress; inputting the construction progress, deviation evaluation value, current unit time construction progress difference, next unit time planned construction progress data, and the weather duration suitable for operation in the next unit time into a pre-trained construction optimization model to obtain the next unit time construction plan data; directly associating specific positions, with clear responsibility division and improved execution efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of construction decision optimization, and particularly relates to a construction decision optimization method and system for prefabricated isolation wards based on a BIM model. Background Art

[0002] Traditional building construction methods have many problems, such as long construction periods, high resource consumption, difficult-to-guarantee building quality, and complex on-site construction that is easily affected by external factors such as weather. In contrast, prefabricated buildings, as an innovative construction model with prefabricated components at the core, have significantly shortened the construction time, reduced resource waste, and also improved the controllability and stability of construction quality. Due to its efficient and environmentally friendly characteristics, prefabricated buildings have received extensive attention and application in recent years and have become an important trend in the development of the construction industry.

[0003] As an advanced digital building design and management tool, BIM technology has been widely used in the construction industry. Through BIM technology, building information can be comprehensively digitally managed and visually presented, which not only improves the design efficiency, reduces errors in the design stage, but also provides strong data support for the building construction process, greatly improving the construction efficiency and quality. For the construction of infectious disease emergency medical facilities with strong completion date restrictions, traditional construction schedule adjustments highly rely on the subjective experience of managers and lack a unified quantitative standard. For example, the compensation plan for lagging construction periods is usually based on fuzzy judgments, which are prone to unreasonable resource allocation due to individual experience differences, resulting in problems such as insufficient compensation or excessive investment. This subjectivity not only reduces the execution efficiency but also makes it difficult to trace responsibilities through data, exacerbating management chaos. Summary of the Invention

[0004] The purpose of the present invention is to provide a construction decision optimization method and system for prefabricated isolation wards based on a BIM model to solve the technical problems raised in the background art.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions: A construction decision optimization method for prefabricated isolation wards based on a BIM model, including:

[0006] Collecting the three-dimensional point cloud data of the building main body construction and collecting the construction process data;

[0007] Constructing an actual three-dimensional model based on the point cloud data, generating a standard three-dimensional model in combination with the electronic drawings, and generating a construction accuracy error and deviation evaluation value through feature extraction and quality comparison;

[0008] Using the deviation evaluation value and the construction process data to evaluate the construction progress and reflecting the real construction progress;

[0009] Input the construction progress, deviation evaluation value, construction progress difference in the current unit time, planned construction progress data in the next unit time, and weather duration suitable for operation in the next unit time into the pre-trained construction optimization model to obtain the construction plan data for the next unit time; the construction plan data for the next unit time includes the consumption data of each type of inventory material, the attendance data of each type of work, and the operation duration of key equipment.

[0010] The construction precision error is the positioning deviation of the movable components in the isolation ward.

[0011] The calculation method of the positioning deviation of the movable components in the isolation ward includes:

[0012] According to the characteristic information of the ward movable components extracted from the actual 3D model and the standard 3D model, obtain the center point coordinates of each ward movable component respectively.

[0013] By comparing the coordinate differences of the horizontal, vertical, and longitudinal axes of the corresponding ward movable components in the standard and actual 3D models, calculate the positioning deviation of the movable components in the isolation ward one by one using the 3D Euclidean distance formula.

[0014] The deviation evaluation value is obtained by calculating the average value of the positioning deviation of the movable components in the isolation ward respectively, and then weighted summing according to the preset weight.

[0015] Further, the construction process data includes material consumption data, labor data, and the operation duration of key equipment; the material consumption data includes the consumption quantity of each type of inventory material.

[0016] The labor data includes the attendance data of each type of work and the weather duration suitable for operation, and the attendance data includes the number of attendees and the attendance duration.

[0017] Further, input the construction process data into the pre-constructed construction progress quantification model to output the construction progress. The construction progress quantification model is trained based on historical labor data and historical construction progress, and the construction progress quantification model is one of the Naive Bayes model and the Support Vector Machine model.

[0018] Further, the method also includes obtaining the comprehensive efficiency evaluation result. The obtaining method of the comprehensive efficiency evaluation result includes: dividing the deviation evaluation value level by the preset two-level deviation threshold, and combining the construction progress for combined determination.

[0019] Further, the training method of the construction optimization model includes:

[0020] Using historical feature data and planned labels as a sample set, dividing the sample set into a training set and a test set, constructing a classifier, using the historical feature data in the training set as input data, using the historical planned labels in the training set as output data, training the classifier to obtain an initial classifier, and using the test set to test the initial classifier, and outputting a classifier that meets the preset accuracy as a construction optimization model;

[0021] Set planned labels for each group of construction plan data for the next unit time; historical feature data includes construction progress, deviation evaluation value, construction progress difference in the current unit time, planned construction progress data for the next unit time, and the weather duration suitable for operation in the next unit time.

[0022] An assembly-type isolation ward construction decision optimization system based on a BIM model, implementing the assembly-type isolation ward construction decision optimization method based on the BIM model, including:

[0023] The first acquisition module: acquiring the building main body construction three-dimensional point cloud data and collecting the construction process data;

[0024] The modeling and analysis module: constructing an actual three-dimensional model based on the point cloud data, generating a standard three-dimensional model in combination with the electronic drawings, and generating construction accuracy errors and deviation evaluation values through feature extraction and quality comparison;

[0025] The evaluation module: using the deviation evaluation value and the construction process data to evaluate the construction progress and reflecting the real construction progress;

[0026] The decision optimization module: based on the construction progress, deviation evaluation value, construction progress difference in the current unit time, planned construction progress data for the next unit time, and the weather duration suitable for operation in the next unit time, inputting into a pre-trained construction optimization model to obtain the construction plan data for the next unit time; the construction plan data for the next unit time includes the consumption data of each inventory material, the attendance data of each type of work, and the operation duration of key equipment.

[0027] Beneficial effects:

[0028] The present invention integrates construction progress, deviation evaluation values, construction progress differences in the current unit time, planned construction progress data for the next unit time, and the weather duration suitable for operation in the next unit time to achieve collaborative optimization of multiple factors. The output construction plan data for the next unit time (such as consumption data of each inventory material, attendance data of each type of work, operation duration of key equipment, etc.) is directly associated with specific positions, with clear responsibility division, improving execution efficiency. Through the deep binding of the BIM model and progress data, "geometry - resource - progress" visual linkage is achieved, optimizing material inventory and equipment scheduling. The model is trained using historical feature data to endow the system with self-learning ability, adapting to different project complexities and continuously improving prediction accuracy, providing a reusable intelligent management paradigm for high-tempo projects such as prefabricated buildings. Compared with traditional prefabricated construction, it can effectively shorten the construction period of isolation wards, effectively reduce rework costs, and provide fast, accurate, and reliable technical support for the construction of emergency medical facilities in public health events. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0030] Figure 1 Shows the module structure diagram of the prefabricated isolation ward construction decision optimization system based on the BIM model of the present invention;

[0031] Figure 2 Shows the schematic diagram of the training process of the construction progress quantification model of the present invention;

[0032] Figure 3 Shows the schematic diagram of the method flow of the prefabricated isolation ward construction decision optimization based on the BIM model of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] Embodiment 1

[0034] Please refer to Figure 1 As shown, this embodiment provides a prefabricated isolation ward construction decision optimization system based on the BIM model, including a first collection module, a modeling and analysis module, an evaluation module, a second collection module, and a decision optimization module; each module is connected by wired and / or wireless means to achieve data transmission.

[0035] First data collection module: Collects three-dimensional point cloud data of the main building body through a drone and collects construction process data; uses the drone equipment for aerial photography, equipped with sensors such as high-resolution cameras or lidar, and conducts aerial photography on a predetermined flight path to collect three-dimensional point cloud data of the main building body under construction.

[0036] The construction process data is the construction process data within the current unit time, including the used construction period, material consumption data, labor data, and the operation duration of key equipment.

[0037] Among them, the material consumption data includes the consumption of each kind of inventory material, and the inventory materials such as medical devices, enclosure structures, ventilation structures, horizontal load-bearing members, vertical traffic members, and vertical load-bearing structures.

[0038] The labor data includes the attendance data of each type of work and the weather duration suitable for operation;

[0039] Labor data: Covers types of work such as steel structure workers, formwork workers, and crane operators. Through the docking of the attendance equipment with the system, the attendance number and attendance duration of each type of work are collected in real time.

[0040] The weather duration suitable for operation: Based on the real-time weather information obtained from the meteorological website at the construction site, according to the requirements of the main building projects such as prefabricated buildings (such as mainly sunny and cloudy days), the cumulative value of the weather duration suitable for operation within the unit attendance duration is statistically calculated.

[0041] The key equipment includes key construction machinery such as tower cranes, truck cranes, negative pressure exhaust equipment, and purification air duct processing equipment.

[0042] Modeling and analysis module: Based on the point cloud data, constructs an actual three-dimensional model, combines with the electronic drawings to generate a standard three-dimensional model, and generates the construction precision error and deviation evaluation value through feature extraction and quality comparison. And visually annotates the areas with deviations in the actual three-dimensional model to facilitate timely correction of the main building body during the construction process.

[0043] The actual three-dimensional model will present the geometric shape and spatial layout of the main building body under construction. Three-dimensional modeling software such as BIM software or other existing three-dimensional modeling software; the deviation evaluation value can reflect the rework cost of the construction. The larger the deviation evaluation value, the longer the rework duration represents, and it also indicates that there is a phenomenon of "inflated" actual completion progress.

[0044] It should be noted that the actual three-dimensional model during the construction process is not the completed main building body. The reason is that it is convenient to correct the errors that occur to the main building body in real time during the construction process and reduce the later rework cost.

[0045] The electronic construction drawings of the main construction building include floor plans, elevation views, sectional views, etc. The electronic construction drawings of the main construction building are reference bases during the construction process, used to guide construction work and record design intentions.

[0046] The construction precision error is the positioning deviation of the movable components in the isolation ward, specifically covering the positioning deviation of medical device installation, the positioning deviation of the enclosure structure (such as walls), the positioning deviation of the ventilation structure (such as doors, window openings, lighting components, etc.), the positioning deviation of the horizontal load-bearing components (such as floor slabs, floor surfaces), the positioning deviation of the vertical transportation components (such as staircase structures), and the positioning deviation of the vertical load-bearing structure (load-bearing columns).

[0047] The calculation method for the positioning deviation of the movable components in the isolation ward includes:

[0048] According to the characteristic information of the ward movable components extracted from the actual 3D model and the standard 3D model, the center point coordinates of each ward movable component are obtained respectively.

[0049] By comparing the differences in the horizontal, vertical, and longitudinal axis coordinates of the corresponding ward movable components in the standard and actual 3D models, the positioning deviation of the movable components in the isolation ward is calculated one by one using the three-dimensional Euclidean distance formula, quantifying the spatial deviation between construction and design. The Euclidean distance synthesizes the deviations in the three axial directions of the three-dimensional space, avoiding the neglect of single-direction errors and more truly reflecting the overall position offset.

[0050] In this embodiment, the center point coordinates are used to calculate the positioning deviation, which can effectively reduce the data calculation volume and improve the computer operation efficiency. The reason is that, for example, through the wall position deviation, the side length error, thickness error, and inclination error of a single wall can be deduced. If the wall is a quadrilateral wall, the length errors corresponding to the four sides, the corresponding width errors, and the corresponding inclination errors need to be calculated in sequence, resulting in a large computer operation volume.

[0051] Since the staircase is different from the shapes of doors, window openings, and floor surfaces, in this embodiment, the center point coordinates of the staircase top surface are the center point coordinates of the connection line between the midpoint of the protruding edge of the first staircase and the midpoint of the protruding edge of the last staircase. By calculating the positioning deviation of the vertical transportation components, it is also possible to infer whether there is an error in the number of staircase steps.

[0052] The deviation evaluation value is generated by calculating the average value of the positioning deviation of the ward movable components respectively and then weighted summing according to the preset weights, finally generating an evaluation value that comprehensively reflects the overall deviation between construction and design.

[0053] Input the construction process data into the pre-constructed construction progress quantification model to output the construction progress; the construction progress includes meeting expectations, falling short of expectations, and exceeding expectations.

[0054] Evaluation module: It evaluates the construction progress by using the deviation evaluation value and construction process data. The evaluated construction progress is the real progress after eliminating the "inflation". The construction progress is the corrected used construction period, reflecting the real construction progress.

[0055] As Figure 2 shown, specifically, the construction progress quantification model is trained based on historical labor data, deviation evaluation value and historical construction progress. The construction progress quantification model is one of the Naive Bayes model and the Support Vector Machine model, specifically as follows:

[0056] Taking the historical labor data, deviation evaluation value and historical construction progress as the sample set, dividing the sample set into a training set and a test set, constructing a classifier, taking the historical labor data and deviation evaluation value in the training set as input data, taking the historical construction progress in the training set as output data, training the classifier to obtain an initial classifier, and using the test set to test the initial classifier, and outputting the classifier that meets the preset accuracy as the construction progress quantification model.

[0057] Import the electronic construction drawings of the construction building main body into 3D modeling software, extract the feature information of the standard 3D model and the actual 3D model, and the comprehensive analysis of the construction quality can be realized. By comparing and analyzing the feature information of the ward activity components extracted from the actual 3D model and the standard 3D model, the construction precision error can be generated and visually marked in the actual 3D model, so as to timely correct the building main body during the construction process. In the process of comparing and analyzing the feature information of the ward activity components, the central point coordinates are used to calculate the ward activity components, which can not only effectively reduce the data calculation amount and improve the computer operation efficiency, but also deduce the error of the specific overall feature information.

[0058] Real-time collection of labor data can dynamically obtain construction process data such as material consumption data, labor data, and key equipment operation duration, helping to grasp the construction progress in real time and carry out progress analysis and evaluation; inputting the labor data into the construction progress quantification model and outputting the construction progress, which is convenient to timely discover progress problems and make targeted adjustments and optimizations.

[0059] The second collection module is used to collect the construction progress difference in the current unit time, the planned construction progress data in the next unit time, the weather duration suitable for operation in the next unit time, and the deviation evaluation value.

[0060] The construction progress difference is the difference between the construction height of the building main body in the current unit time and the predetermined construction height of the building main body in the current unit time; the planned construction progress data in the next unit time is the predetermined construction height of the building main body in the next unit time.

[0061] The decision-making optimization module inputs the construction progress, deviation evaluation value, construction progress difference in the current unit time, planned construction progress data in the next unit time, and the weather duration suitable for operation in the next unit time into a pre-trained construction optimization model to obtain the construction plan data in the next unit time; the construction plan data in the next unit time includes the consumption data of each type of inventory material, the attendance data of each type of work, and the operation duration of key equipment.

[0062] The deviation evaluation value determines the amount of project work to be compensated in the next stage, thereby affecting the input intensity of the construction plan data in the next unit time. For example, a 10% lag requires an additional 20% of manpower or equipment duration in the next stage to catch up with the progress; the construction progress difference in the previous unit time is the absolute value of the difference between the construction progress and the total construction period, reflecting immediate problems and requiring targeted adjustment of the strategy in the next stage; the planned construction progress data in the next unit time serves as the initial reference data, and the adjustment needs to superimpose a compensation amount on it; the weather duration suitable for operation in the next unit time reflects the available operation weather duration (such as "the effective construction duration in the next 7 days is 40 hours"), which restricts the actual available time, and the consumption data of each type of inventory material, the attendance data of each type of work, and the operation duration of key equipment are determined by dynamic adjustment of the above relevant data.

[0063] The training method of the construction optimization model includes:

[0064] Using the historical feature data and the planned label as a sample set, dividing the sample set into a training set and a test set, constructing a classifier, using the historical feature data in the training set as input data, using the historical planned label in the training set as output data, training the classifier to obtain an initial classifier, and using the test set to test the initial classifier, and outputting a classifier that meets the preset accuracy as the construction optimization model; the construction optimization model is one of the naive Bayes model and the support vector machine model.

[0065] Setting a planned label for each set of construction plan data in the next unit time; the historical feature data includes the construction progress, deviation evaluation value, construction progress difference in the current unit time, planned construction progress data in the next unit time, and the weather duration suitable for operation in the next unit time; converting the historical feature data into a corresponding set of feature vectors. The historical feature data and the planned label are pre-collected training data that meet the construction quality and construction period restrictions.

[0066] By collecting construction progress, deviation evaluation values, construction progress differences in the current unit time, planned construction progress data for the next unit time, and the weather duration suitable for operation in the next unit time, more comprehensive factors are considered to predict the construction plan data for the next unit time. The construction plan data for the next unit time includes the consumption data of each type of inventory material, the attendance data of each type of work, and the operation duration of key equipment. The arrangement of data is detailed, and the responsibilities can be assigned according to the construction plan data for the next unit time, improving the execution effect. Secondly, through the prediction of the construction optimization model, the standards are unified, avoiding the differences caused by relying on the experience arrangement of construction personnel, and laying a solid foundation for the successful delivery of the project.

[0067] Embodiment 2

[0068] Refer to Figure 3 As shown, this embodiment provides an optimization method for the construction decision of prefabricated isolation wards based on a BIM model, including:

[0069] Collect the three-dimensional point cloud data of the building main body construction and collect the construction process data;

[0070] Construct an actual three-dimensional model based on the point cloud data, generate a standard three-dimensional model in combination with the electronic drawings, and generate the construction accuracy error and deviation evaluation value through feature extraction and quality comparison;

[0071] Evaluate the construction progress by using the deviation evaluation value and the construction process data;

[0072] Input the construction progress, deviation evaluation value, construction progress difference in the current unit time, planned construction progress data for the next unit time, and the weather duration suitable for operation in the next unit time into the pre-trained construction optimization model to obtain the construction plan data for the next unit time; the construction plan data for the next unit time includes the consumption data of each type of inventory material, the attendance data of each type of work, and the operation duration of key equipment.

[0073] What is not described in this application can be realized by adopting or referring to the existing technology.

[0074] Each embodiment in this specification is described in a progressive manner. The same or similar parts between each embodiment can be referred to each other, and the differences between each embodiment and other embodiments are emphasized.

[0075] The above are only the embodiments of this application and are not used to limit this application. For those skilled in the art, various changes and modifications can be made to this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims

1. An optimization method for the construction decision of prefabricated isolation wards based on BIM models, characterized in that, including: Collecting the three-dimensional point cloud data of the building main body construction and collecting the construction process data; Constructing an actual three-dimensional model based on the point cloud data, generating a standard three-dimensional model in combination with the electronic drawing, and generating the construction precision error and deviation evaluation value through feature extraction and quality comparison; Evaluating the construction progress by using the deviation evaluation value and the construction process data to reflect the real construction progress; Inputting the construction progress, deviation evaluation value, current unit time construction progress difference, next unit time planned construction progress data, and the weather duration suitable for operation in the next unit time into the pre-trained construction optimization model to obtain the next unit time construction plan data; the next unit time construction plan data includes the consumption data of each kind of inventory material, the attendance data of each type of work, and the operation duration of key equipment; The construction precision error is the positioning deviation of the movable components in the isolation ward; The calculation method of the positioning deviation of the movable components in the isolation ward includes: According to the feature information of the ward movable components extracted from the actual three-dimensional model and the standard three-dimensional model, the center point coordinates of each ward movable component are obtained respectively; By comparing the horizontal, vertical, and vertical axis coordinate differences of the corresponding ward movable components in the standard and actual three-dimensional models, the positioning deviation of the movable components in the isolation ward is calculated one by one by using the three-dimensional Euclidean distance formula; The deviation evaluation value is obtained by calculating the average value of the positioning deviation of the movable components in the isolation ward respectively and then weighted summing according to the preset weight.

2. The optimized method for making construction decisions of prefabricated isolation wards based on the BIM model according to claim 1, wherein, The construction process data includes material consumption data, labor data, and the operation duration of key equipment; the material consumption data includes the consumption quantity of each kind of inventory material; The labor data includes the attendance data of each type of work and the weather duration suitable for operation, and the attendance data includes the number of attendance and the attendance duration.

3. The optimized method for making construction decisions of prefabricated isolation wards based on the BIM model according to claim 2, characterized in that Inputting the construction process data into the pre-constructed construction progress quantification model, and outputting the construction progress. The construction progress quantification model is trained based on historical labor data and historical construction progress, and the construction progress quantification model is one of the naive Bayes model and the support vector machine model.

4. The optimized method for the construction decision-making of the prefabricated isolation ward based on the BIM model according to claim 3, characterized in that, The method further includes obtaining the comprehensive efficiency evaluation result, and the obtaining method of the comprehensive efficiency evaluation result includes: dividing the deviation evaluation value level by preset two-level deviation thresholds and making a combined determination in combination with the construction progress.

5. The prefabricated isolation ward construction decision optimization method based on the BIM model according to claim 4, wherein The training method of the construction optimization model includes: Taking the historical feature data and the planned label as the sample set, dividing the sample set into a training set and a test set, constructing a classifier, taking the historical feature data in the training set as the input data, taking the historical planned label in the training set as the output data, training the classifier to obtain an initial classifier, and using the test set to test the initial classifier, and outputting the classifier that meets the preset accuracy as the construction optimization model; Setting a planned label for each group of next unit time construction plan data; the historical feature data includes construction progress, deviation evaluation value, current unit time construction progress difference, next unit time planned construction progress data, and the weather duration suitable for operation in the next unit time.

6. An optimized system for the construction decision-making of prefabricated isolation wards based on BIM models, characterized in that, Implementing the prefabricated isolation ward construction decision optimization method based on the BIM model according to any one of claims 1-5, including: The first acquisition module: collecting the three-dimensional point cloud data of the building main body construction and collecting the construction process data; Modeling and Analysis Module: Construct an actual 3D model based on point cloud data, generate a standard 3D model in combination with electronic drawings, and generate construction accuracy error and deviation evaluation values through feature extraction and quality comparison; Evaluation Module: Evaluate the construction progress using the deviation evaluation value and construction process data to reflect the real construction progress; Decision-making and Optimization Module: Input the construction progress, deviation evaluation value, construction progress difference in the current unit time, planned construction progress data in the next unit time, and the weather duration suitable for operation in the next unit time into a pre-trained construction optimization model to obtain the construction plan data for the next unit time; The construction plan data for the next unit time includes the consumption data of each inventory material, the attendance data of each type of work, and the operation duration of key equipment.

Images