Fabricated building construction method based on BIM

Abstract

The invention relates to the technical field of buildings, and discloses a BIM (Building Information Modeling)-based fabricated building construction method, which comprises the following steps of: collecting data; obtaining all construction scheme sets of all types of buildings; obtaining building basic feature data of the target object, and obtaining a building category of the target object; obtaining a feasible construction scheme set; obtaining an optimal construction scheme; the optimal construction scheme can be obtained from the construction scheme set of the corresponding category only when the target object is placed in the corresponding building category, the suitability and accuracy of selection of the fabricated building construction method are improved, and meanwhile high efficiency is achieved; the same type of buildings have high similarity in the aspects of building area, spatial layout and the like, so that the possibility of the same type of buildings is higher, and the same construction scheme can be adopted; therefore, the final construction scheme is selected from the construction schemes of the corresponding types, the feasibility is highest, meanwhile, the selection range of the construction scheme is narrowed, and higher accuracy is achieved.

Description

Technical Field

[0001] The present invention relates to the field of building technology, and more specifically to a BIM-based prefabricated building construction method. Background Art

[0002] Building Information Modeling, or BIM, is a technology that collects and processes information about various construction projects, and then builds a three-dimensional model based on this data. It can help reference and analyze data from engineering projects to planning and design to maintenance and operation, and is conducive to the effective management of quality control of prefabricated buildings. Prefabricated buildings are buildings constructed by reliable connections of prefabricated components. The advantages of this type of building are fast construction speed, less waste of resources, labor savings, and improved building quality.

[0003] In the public document with publication number CN117495614A, a method for prefabricated building construction based on BIM is disclosed. According to the overall drawing design of the project, a three-dimensional model of the construction project is created using BIM technology. The three-dimensional model is used to optimize the design construction, plan, and operation plan. The drawings are reviewed in a three-dimensional visualization way to automatically find professional collision problems and promptly discover errors, omissions, and deficiencies in the drawings; main construction content; cast-in-place structure construction; prefabricated component construction; segmented cast-in-place and sleeve grouting; prefabricated component protection operations; in general, it has the advantages of creating a visual and informationized BIM model to enhance the collaborative design of architectural, structural, and electromechanical information, avoid errors, omissions, and deficiencies in the design of various disciplines, and improve the quality of the design.

[0004] However, there are differences in the construction focus and construction plan of different building types. For example, civil residential buildings usually use prefabricated concrete components, which are assembled by welding or bolting. They pay more attention to appearance effects and personalized design. Customized processing may be required during the component manufacturing process, and the construction period is relatively short through relatively small and complex processes such as the installation of a large number of production equipment. Industrial buildings mostly use steel structural components or container structures, emphasizing bearing capacity and fire resistance, and paying more attention to structural stability and durability. When manufacturing components, strict requirements are imposed, standardization is higher, and the scale is relatively large, with many professional equipment and a relatively long construction period. Therefore, different construction plans need to be designed for buildings of different building types to adapt to the actual needs of the buildings. At the same time, for buildings with different design parameters, corresponding construction plans are needed, and both construction progress and construction cost need to be considered.

[0005] In view of this, the present invention provides a BIM-based prefabricated building construction method to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a BIM-based prefabricated building construction method to solve the problems existing in the above-mentioned background technology.

[0007] The present invention provides the following technical solution: a BIM-based prefabricated building construction method, comprising the following steps: Step S01: Data collection: Obtain n historical design drawings of prefabricated buildings, build a three-dimensional model using BIM technology, and obtain building foundation feature data, building structure feature data, and building construction data; Step S02: clustering the building basic feature data collected in step S01 to obtain a set of all construction plans for each category of buildings; Step S03: Obtain the target design drawing, use BIM technology to build a three-dimensional model, obtain the building basic feature data of the target object, and obtain the building category of the target object; Step S04: Based on the set of construction plans corresponding to the building category, set constraints to obtain a construction plan that meets the construction progress conditions, use BIM technology to perform construction demonstration, and obtain a set of feasible construction plans; Step S05: Based on the obtained feasible construction plan set, an improved genetic algorithm is used to obtain the best construction plan; Step S06: Output the best construction plan as the construction method of the target object.

[0008] Preferably, the building basic characteristic data includes building area, number of floors and spatial layout data; the building structure characteristic data includes prefabricated component-related data of size, quantity and type of building prefabricated components; the building construction data is the construction plan of the building, and the construction plan specifically includes the construction process, construction process and construction cost data of the building; The target object is a prefabricated building for which a construction method needs to be obtained; the target design drawing is the design drawing corresponding to the target object.

[0009] Preferably, the specific method of obtaining a set of all construction schemes for buildings of each category in step S02 is: Step S11: construct a word vector conversion model to convert n pieces of building basic feature data of prefabricated buildings into corresponding word vectors in sequence; Step S12: Take the converted n word vectors as sample points, randomly select k sample points as initial cluster centers, and mark them as z1, z2, z3, ..., z k ; Step S13: record the sample points that are not used as cluster center points as calculation points and mark them as j1, j2, j3, ..., j n-k; Calculate the distance D from each calculation point to each cluster center in turn ba , the calculation formula is expressed as: , where D ba is the bth calculation point j b To the a-th cluster center z a The distance, where b = 1, 2, 3, ..., nk; a = 1, 2, 3, ..., k; R is the dimension of the sample point, u = 1, 2, 3, ..., R; j bu is the bth calculation point j b The coordinates in the u-th dimension, z au is the a-th cluster center z a Coordinates in the u-th dimension; Step S14: establishing corresponding k´ clusters based on the k cluster centers, k=k´; Step S15: calculate point j b The distance to each cluster center is compared, and the calculated point is assigned to the cluster corresponding to the cluster center closest to it; Step S16: set b=b+1, and jump back to step S15; Step S17: Repeat steps S15 to S16 until b=nk, and the loop ends, and the nk calculation points are all assigned to the corresponding clusters; Step S18: Recalculate the new cluster center coordinates of each cluster. The calculation formula is expressed as: , where z´ c is the new cluster center coordinate of the cth cluster, c=1, 2, 3, …, k´, y i is the coordinate of the i-th calculation point in the c-th cluster, i=1, 2, 3, …, I, I is the total number of calculation points in the c-th cluster, ; Step S19: Repeat steps S13 to S18 until the new cluster center coordinates of each cluster are recalculated in step S18. The loop ends when the new cluster center coordinates of each cluster calculated in the previous loop are consistent with the new cluster center coordinates of each cluster calculated in the previous loop; obtain the clusters and corresponding sample points corresponding to the k´ clusters.

[0010] Preferably, the sample points corresponding to the k´ clusters are the basic building feature data, and the prefabricated building category corresponding to the basic building feature data of the new cluster center point of each cluster is selected as the prefabricated building category of the cluster, which is the cluster corresponding to the cluster; the collection of construction plans of all sample points in the cluster is the set of construction plans for the building category corresponding to the cluster.

[0011] Preferably, the step S03 of acquiring the building category of the target object comprises the following steps: Step S21: converting the building basic feature data of the target object into a corresponding word vector through a word vector conversion model, and recording it as a target point; Step S22: record the target point as M, calculate the distance from the target point to the new cluster center point of each cluster in step S18, and arrange them in ascending order from small to large, and assign the target point to the cluster corresponding to the cluster center point closest to it, that is, the cluster corresponding to the cluster center point with the smallest distance value; The calculation formula is: , where D Mc is the distance between the target point and the new cluster center of the cth cluster, M u is the coordinate of the target point in the uth dimension, z´ cu is the new cluster center point z´ of the cth cluster c At the coordinate of the u-th dimension, R is the dimension in step S13, u=1, 2, 3, ..., R; Step S23: Output the building category corresponding to the cluster where the target point in step S22 is located.

[0012] Preferably, the specific method of obtaining a set of feasible construction solutions in step S04 is: Based on the building category corresponding to the cluster where the target point is located obtained in step S23, that is, the building category of the target object, a set of construction plans corresponding to the building category is obtained, which is recorded as U1; constraint conditions are set to obtain a set of construction plans that meet the construction progress conditions, which is recorded as U2; each construction plan in U2 is applied to the BIM model of the target object for construction demonstration, and a set of feasible construction plans is obtained, which is recorded as U3; The specific process of obtaining U2 is as follows: Setting Constraints Among them, JD u is the maximum construction completion time of the u-th construction scheme in U1, and YS is the maximum construction completion time of the target object; The construction plans that meet the constraints are re-labeled with digital labels, and all the construction plans that meet the constraints are formed into a set U2; The specific process of obtaining U3 is as follows: Each construction plan in U2 is applied to the BIM model of the target object for construction demonstration. Construction plans that fail in the demonstration are eliminated, and digital labels are used again for a new round of marking. The construction plans that are finally marked with digital labels form a set U3.

[0013] Preferably, the step S05 of obtaining the best construction plan includes the following steps: Step S31: Encode the construction plan in U3, obtain chromosomes, and construct an initial population; The construction plan is encoded as O, where O is the chromosome, and X chromosomes are randomly generated to form the initial population. ; Step S32: determining a fitness function; Step S33: performing natural selection on chromosomes in the population; Step S34: performing crossover recombination on chromosomes in the population; Step S35: mutating the chromosomes in the population; Step S36: Obtain a new population, preset the population generation to be L, the fitness threshold to be Q, L is an integer greater than 0, and Q is a real number greater than 0; loop steps S33 to S35 until the generation corresponding to the new population is L or the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold Q, the loop ends, and the construction plan corresponding to the chromosome with the maximum fitness in the new population is obtained, which is the optimal construction plan.

[0014] Preferably, the fitness function is expressed as: , where f r is the fitness of the rth chromosome, Cos r is the predicted construction cost of the construction plan corresponding to the rth chromosome; The method for obtaining the predicted construction cost is as follows: using the construction plan corresponding to the chromosome and the basic characteristic data of the target object building as research data, inputting the research data into the trained construction cost prediction model, and predicting the corresponding construction cost; The training method of the construction cost prediction model is specifically as follows: The building foundation characteristic data, building structure characteristic data and building construction data corresponding to a prefabricated building design drawing are taken as a set of analysis data, d sets of analysis data are collected in advance, and corresponding construction cost values ​​are obtained for the d sets of analysis data, where d is an integer greater than 1, and the analysis data and the corresponding construction cost values ​​are converted into a corresponding set of feature vectors; d=1, 2, 3, ..., n; Each set of feature vectors is used as the input of the construction cost prediction model. The construction cost prediction model uses a predicted construction cost value corresponding to each set of analysis data as output, and uses the actual construction cost value corresponding to each set of analysis data as the prediction target. The actual construction cost value can be obtained through the pre-collected construction data; the training target is to minimize the sum of the prediction errors of all analysis data; the formula of the prediction error is expressed as: , where ε p is the prediction error, p is the group number of the eigenvector corresponding to the analyzed data, θ p is the predicted construction cost value corresponding to the pth group of analysis data, μ pThe actual construction cost value corresponding to the pth group of analysis data is used to train the construction cost prediction model until the sum of the prediction errors reaches convergence and the training is stopped.

[0015] Technical effects and advantages of the present invention: The present invention is provided with step S03, which is conducive to placing the target object in the corresponding building category, so that the best construction plan can be obtained from the construction plan set of the corresponding category, thereby improving the suitability and accuracy of the selection of the prefabricated building construction method, and at the same time having high efficiency; the building area, spatial layout and other aspects of the same category of buildings are highly similar, so the greater the possibility of being the same type of building, the same construction plan can be adopted; therefore, selecting the final construction plan from the construction plans of the corresponding category has the highest feasibility, and at the same time narrows the scope of construction plan selection, which is more accurate.

[0016] The present invention is provided with step S04 and step S05, which is conducive to taking the construction progress as one of the constraints, and can further improve the adaptability of the subsequent construction plan on the basis of meeting the construction requirements of the project; at the same time, the BIM technology is used to demonstrate the construction plan that meets the constraints, so as to prevent the collision of prefabricated components when different construction plans are applied to the actual target object, and the construction cost is used as another constraint to select the best construction plan, so as to obtain the best prefabricated building construction method for the target object, and minimize the construction cost on the basis of meeting the construction progress, so that the best construction plan finally obtained can meet the construction progress, complete the construction smoothly and minimize the construction cost, so that buildings with different design parameters can be analyzed accordingly, so as to obtain a construction plan that is adapted to the actual needs, improve the adaptability of prefabricated building construction, and provide multiple guarantees for the prefabricated building construction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The present invention is a flowchart of the BIM-based prefabricated building construction method. DETAILED DESCRIPTION

[0018] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are only examples. The BIM-based prefabricated building construction method involved in the present invention is not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0019] like Figure 1 As shown, the present invention provides a BIM-based prefabricated building construction method, comprising the following steps: Step S01: Data collection: Obtain n copies of historical design drawings of prefabricated buildings, construct a three-dimensional model using BIM technology, and obtain building basic feature data, building structure feature data, and building construction data; the building basic feature data includes but is not limited to data such as building area, number of floors, and space layout; the building structure feature data includes but is not limited to prefabricated component-related data such as the size, quantity, and type of prefabricated components of the building; the building construction data is the construction plan of the building, and the construction plan specifically includes data such as the construction process, construction process, and construction cost of the building; Step S02: clustering is performed based on the building basic feature data collected in step S01 to obtain a set of all construction schemes for buildings of each category; buildings of the same category have high similarities in terms of building area, spatial layout, etc., so the greater the possibility that they are of the same type, the same construction scheme can be adopted; building types can be classified into residential buildings, public buildings, industrial buildings, agricultural buildings, etc. according to their use functions; buildings are classified based on historical data, which lays the foundation for subsequent analysis of target building categories and providing corresponding construction schemes; Step S03: Obtain the target design drawing, build a three-dimensional model using BIM technology, obtain the building basic feature data of the target object, and obtain the building category of the target object; the purpose is to place the target object in the corresponding building category so that the best construction plan can be obtained from the construction plan set of the corresponding category, thereby improving the suitability and accuracy of the selection of the prefabricated building construction method and having high efficiency; the target object is the prefabricated building for which the building construction method needs to be obtained; the target design drawing is the design drawing corresponding to the target object; Step S04: Based on the set of construction plans corresponding to the building category, set constraints to obtain construction plans that meet the construction progress conditions, use BIM technology to perform construction demonstrations, and obtain a set of feasible construction plans; the purpose is to use the construction progress as one of the constraints. The construction progress requirements of different building projects are different. Therefore, using the construction progress as one of the constraints to select the construction plan can further improve the adaptability of the subsequent construction plan on the basis of meeting the construction requirements of the project; at the same time, use BIM technology to perform construction demonstrations on the construction plans that meet the constraints to prevent the collision of prefabricated components when different construction plans are applied to the actual target object. Therefore, the set of feasible construction plans obtained is a set of plans that can successfully complete the construction; Step S05: Based on the obtained feasible construction plan set, an improved genetic algorithm is used to obtain the best construction plan; the construction cost is used as another constraint condition to select the best construction plan, so as to obtain the best prefabricated building construction method for the target object, and minimize the construction cost on the basis of meeting the construction schedule, so that the best construction plan finally obtained can meet the construction schedule, complete the construction smoothly and minimize the construction cost, so that buildings with different design parameters can be analyzed accordingly, so as to obtain a construction plan that is suitable for them and meets the actual needs, thereby improving the adaptability of prefabricated building construction and providing multiple guarantees for the prefabricated building construction process; Step S06: Output the best construction plan as the construction method of the target object.

[0020] In this embodiment, it should be specifically explained that the construction plan in the building construction data is all construction plan data such as the collected historical successful construction plan, the construction plan or construction specification issued by a professional organization in the construction field, and the construction plan formulated by professional and technical personnel in the field; the construction plan data includes but is not limited to the construction process, construction process and construction cost, which is specifically reflected in the connection method of prefabricated components, construction production data, transportation data, labor data, etc.; production data includes but is not limited to production time, production quantity, etc.; transportation data includes but is not limited to transportation time, transportation cost, transportation quantity, etc.; labor data includes but is not limited to the number of workers, labor cost, working time, etc.; The improved genetic algorithm integrates the trained neural network model into the fitness calculation of the improved genetic algorithm, which can give full play to the nonlinear and multimodal agricultural product storage environment data modeling capabilities of the neural network and effectively capture complex data relationships; based on the parallel computing processing mechanism, the computing efficiency is improved, and the construction plan effect is evaluated through deep learning technology, thereby improving the pertinence and effectiveness of building construction management; fully utilizes the building foundation feature data, building structure feature data and building construction data, and captures complex data relationships through deep learning technology, which can comprehensively and accurately understand the construction conditions of different buildings, and provide customized construction plans for different buildings, thereby effectively improving the quality of building construction.

[0021] In this embodiment, it should be specifically explained that the specific method of obtaining a set of all construction plans for buildings of each category in step S02 is: Step S11: construct a word vector conversion model to convert n pieces of building basic feature data of prefabricated buildings into corresponding word vectors in sequence; the word vector conversion model is a BERT semantic model, which is a prior art means and will not be described in detail in this implementation; Step S12: Take the converted n word vectors as sample points, randomly select k sample points as initial cluster centers, and mark them as z1, z2, z3, ..., z k ; Step S13: record the sample points that are not used as cluster center points as calculation points and mark them as j1, j2, j3, ..., j n-k ; Calculate the distance D from each calculation point to each cluster center in turn ba , the calculation formula is expressed as: , where D ba is the bth calculation point j b To the a-th cluster center z a The distance, where b = 1, 2, 3, ..., nk; a = 1, 2, 3, ..., k; R is the dimension of the sample point, u = 1, 2, 3, ..., R; j bu is the bth calculation point j b The coordinates in the u-th dimension, z au is the a-th cluster center z a Coordinates in the u-th dimension; Step S14: establishing corresponding k´ clusters based on the k cluster centers, k=k´; Step S15: calculate point j b The distance to each cluster center is compared, and the calculated point is assigned to the cluster corresponding to the cluster center closest to it; Step S16: set b=b+1, and jump back to step S15; Step S17: Repeat steps S15 to S16 until b=nk, and the loop ends, and the nk calculation points are all assigned to the corresponding clusters; Step S18: Recalculate the new cluster center coordinates of each cluster. The calculation formula is expressed as: , where z´ c is the new cluster center coordinate of the cth cluster, c=1, 2, 3, …, k´, y i is the coordinate of the i-th calculation point in the c-th cluster, i=1, 2, 3, …, I, I is the total number of calculation points in the c-th cluster, ; Step S19: Repeat steps S13 to S18 until the new cluster center coordinates of each cluster are recalculated in step S18, and the loop ends when the new cluster center coordinates of each cluster calculated in the previous loop are consistent; obtain the clusters and corresponding sample points corresponding to the k' clusters; The sample points corresponding to the k´ clusters are the basic building feature data, and the prefabricated building category corresponding to the basic building feature data of the new cluster center point of each cluster is selected as the prefabricated building category of the cluster, which is the cluster corresponding to the cluster; the collection of construction plans of all sample points in the cluster is the construction plan set of the building category corresponding to the cluster; illustratively, if the prefabricated building category corresponding to the basic building feature data of the cluster center point of the k´th cluster is a residential building, then the prefabricated buildings corresponding to the sample points of the cluster are all residential buildings, that is, the cluster corresponding to the cluster is the residential building category, and the construction plan set corresponding to the residential building category is the collection of construction plans corresponding to all sample points.

[0022] In this embodiment, it should be specifically explained that the step S03 of obtaining the building category of the target object includes the following steps: Step S21: converting the building basic feature data of the target object into a corresponding word vector through a word vector conversion model, which is recorded as a target point; the word vector model is the same as that in step S11; Step S22: record the target point as M, calculate the distance from the target point to the new cluster center point of each cluster in step S18, and arrange them in ascending order from small to large, and assign the target point to the cluster corresponding to the cluster center point closest to it, that is, the cluster corresponding to the cluster center point with the smallest distance value; The calculation formula is: , where D Mc is the distance between the target point and the new cluster center of the cth cluster, M u is the coordinate of the target point in the uth dimension, z´ cu is the new cluster center point z´ of the cth cluster c At the coordinate of the u-th dimension, R is the dimension in step S13, u=1, 2, 3, ..., R; Step S23: Output the building category corresponding to the cluster where the target point in step S22 is located.

[0023] In this embodiment, it should be specifically explained that the specific method of obtaining a set of feasible construction solutions in step S04 is: Based on the building category corresponding to the cluster where the target point obtained in step S23 is located, that is, the building category of the target object, a set of construction schemes corresponding to the building category is obtained, which is recorded as U1; constraint conditions are set to obtain a set of construction schemes that meet the construction progress conditions, which is recorded as U2; each construction scheme in U2 is applied to the BIM model of the target object for construction demonstration, and a set of feasible construction schemes is obtained, which is recorded as U3; the feasible construction scheme set is a construction scheme in which the construction demonstration process will not cause collision of prefabricated components, failure of grouting holes to discharge grout smoothly during grouting, and mismatch of lifting points, which will lead to the inability to carry out construction normally; The specific process of obtaining U2 is as follows: Setting Constraints Among them, JD u is the maximum construction completion time of the u-th construction scheme in U1, and YS is the maximum construction completion time of the target object; The construction plans that meet the constraints are re-labeled with digital labels, and all the construction plans that meet the constraints are formed into a set U2; The specific process of obtaining U3 is as follows: Apply each construction plan in U2 to the BIM model of the target object for construction demonstration, eliminate the construction plans that fail in the demonstration process, use digital labels to perform a new round of marking, and finally form a set U3 of construction plans marked with digital labels; The construction plan that failed in the demonstration is a construction plan in which the construction cannot proceed normally due to collision of prefabricated components, failure of grouting holes to smoothly discharge grout during grouting, and mismatch of lifting points.

[0024] In this embodiment, it should be specifically explained that the step S05 of obtaining the best construction plan includes the following steps: Step S31: Encode the construction plan in U3, obtain chromosomes, and construct an initial population; The construction plan is encoded as O, where O is the chromosome, and X chromosomes are randomly generated to form the initial population. ; Step S32: determining a fitness function; Step S33: performing natural selection on chromosomes in the population; Step S34: performing crossover recombination on chromosomes in the population; Step S35: mutating the chromosomes in the population; Step S36: obtain a new population, the preset population generation number is L, the fitness threshold is Q, L is an integer greater than 0, and Q is a real number greater than 0; loop steps S33 to S35 until the generation number corresponding to the new population is L or the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold Q, the loop ends, and the construction plan corresponding to the chromosome with the maximum fitness in the new population is obtained, which is the best construction plan; illustratively, if the preset population generation number is 1, the chromosomes in the initial population are subjected to natural selection, crossover recombination, and mutation to obtain a new population, and the generation number corresponding to the new population is 1 at this time, so the loop ends; The fitness threshold Q is preset by those skilled in the art according to the accuracy of the algorithm. The population algebra L is obtained by those skilled in the art using a genetic algorithm multiple times under multiple sets of different building foundation feature data, building structure feature data and building construction data to obtain the corresponding construction plan. In each process of using the genetic algorithm, when the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold Q, the cycle ends and the algebra corresponding to the new population is obtained; the largest algebra among the multiple algebras is taken as the population algebra L.

[0025] In this embodiment, it should be specifically explained that the natural selection is carried out by combining the elite method and the rotation method; the elite method produces F1 offspring chromosomes, and for a population with a capacity of X, the fitness corresponding to the X chromosomes is arranged from large to small, and each of the F1 chromosomes at the front produces a offspring chromosome; the rotation method produces F2 offspring chromosomes, that is, X chromosomes produce F2 offspring chromosomes according to the corresponding rotation probability; F1+F2=X, so as to keep the offspring population capacity U unchanged and the population generation number increases; The expression of the rotation probability is: , where ζ r is the rotation probability corresponding to the rth chromosome; In the step S34, E chromosomes are randomly selected from the population for crossover recombination to obtain E new chromosomes; the crossover recombination adopts the PMX method, which is a prior art method and is not described in detail in this embodiment; after the chromosome crossover recombination, the fitness of the E chromosomes is calculated, the fitness of the E new chromosomes and the fitness of the E chromosomes are sorted from large to small and a sorting table is generated, and the E chromosomes in the sorting table are replaced with the E chromosomes for crossover recombination in the population in positive order; in this embodiment, E=0.7X is preferred, and if the calculated E is not an integer, E is rounded up to ensure that the calculated E is an integer; In step S25, the mutation probability is preset to V, and the X chromosomes in the population are mutated according to the mutation probability. The mutation method is to randomly select the positions of two genes in the chromosome and exchange the values ​​of the two genes. In this embodiment, V=0.02 is preferred. The mutation probability is preset by those skilled in the art according to the algorithm efficiency and algorithm accuracy.

[0026] In this embodiment, it should be specifically explained that the expression of the fitness function is: , where f r is the fitness of the rth chromosome, Cos r is the predicted construction cost of the construction plan corresponding to the rth chromosome; The method for obtaining the predicted construction cost is as follows: using the construction plan corresponding to the chromosome and the basic characteristic data of the target object building as research data, inputting the research data into the trained construction cost prediction model, and predicting the corresponding construction cost; The training method of the construction cost prediction model is specifically as follows: The building foundation characteristic data, building structure characteristic data and building construction data corresponding to a prefabricated building design drawing are used as a set of analysis data, d sets of analysis data are collected in advance, and corresponding construction cost values ​​are obtained for the d sets of analysis data, where d is an integer greater than 1, and the analysis data and the corresponding construction cost values ​​are converted into a corresponding set of feature vectors; the construction cost values ​​corresponding to the analysis data are obtained by technical personnel in the field of cost statistics and calculation in the historical construction process, and d sets of analysis data are collected. Under the conditions of each set of analysis data, the construction cost values ​​in the actual building construction process are comprehensively analyzed; d=1, 2, 3, ..., n; Each set of feature vectors is used as the input of the construction cost prediction model. The construction cost prediction model uses a predicted construction cost value corresponding to each set of analysis data as output, and uses the actual construction cost value corresponding to each set of analysis data as the prediction target. The actual construction cost value can be obtained through the pre-collected construction data; the training target is to minimize the sum of the prediction errors of all analysis data; the formula of the prediction error is expressed as: , where ε p is the prediction error, p is the group number of the eigenvector corresponding to the analyzed data, θ p is the predicted construction cost value corresponding to the pth group of analysis data, μ p The actual construction cost value corresponding to the pth group of analysis data is used to train the construction cost prediction model until the sum of the prediction errors reaches convergence and the training is stopped; The construction cost prediction model is specifically a deep network model.

[0027] In this embodiment, it should be specifically explained that this embodiment only selects one target object. If there are multiple target objects that need to obtain construction methods, multiple target objects can be input for analysis at the same time, and it is only necessary to distinguish the marking symbols of each parameter.

[0028] The present invention provides a BIM-based prefabricated building construction method, comprising the following steps: Step S01: Data collection: Obtain n historical design drawings of prefabricated buildings, build a three-dimensional model using BIM technology, and obtain building foundation feature data, building structure feature data, and building construction data; Step S02: clustering the building basic feature data collected in step S01 to obtain a set of all construction plans for each category of buildings; Step S03: Obtain the target design drawing, use BIM technology to build a three-dimensional model, obtain the building basic feature data of the target object, and obtain the building category of the target object; Step S04: Based on the set of construction plans corresponding to the building category, set constraints to obtain a construction plan that meets the construction progress conditions, use BIM technology to perform construction demonstrations, and obtain a set of feasible construction plans; if the set of construction plans that meet the construction progress conditions is an empty set, return to step S03 and directly execute step S06 while sending an early warning instruction, otherwise continue to execute step S04; Step S05: Based on the obtained feasible construction plan set, an improved genetic algorithm is used to obtain the best construction plan; if the feasible construction plan set is an empty set, return to step S04 and directly execute step S06 while sending an early warning instruction, otherwise continue to execute step S05; Step S06: Output data for human-computer interaction display and receive warning instructions; when the warning instructions are received, a construction plan warning is issued. At this time, there is no construction plan that meets the construction requirements. Technical personnel in this field are required to design a new targeted construction plan. After the design is completed, it is entered and stored to facilitate the acquisition of the construction method next time.

[0029] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0030] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A BIM-based prefabricated building construction method, characterized by: The following steps are involved: Step S01: Data collection: Obtain n historical design drawings of prefabricated buildings, build a three-dimensional model using BIM technology, and obtain building foundation feature data, building structure feature data, and building construction data; Step S02: clustering the building basic feature data collected in step S01 to obtain a set of all construction plans for each category of buildings; Step S03: Obtain the target design drawing, use BIM technology to build a three-dimensional model, obtain the building basic feature data of the target object, and obtain the building category of the target object; Step S04: Based on the set of construction plans corresponding to the building category, set constraints to obtain a construction plan that meets the construction progress conditions, use BIM technology to perform construction demonstration, and obtain a set of feasible construction plans; Step S05: Based on the obtained feasible construction plan set, an improved genetic algorithm is used to obtain the best construction plan; Step S06: Output the best construction plan as the construction method of the target object.

2. The BIM-based prefabricated building construction method according to claim 1, characterized in that: The basic building feature data include building area, number of floors and spatial layout data; The building structure characteristic data includes the size, quantity and type of prefabricated components of the building; the building construction data is the construction plan of the building, and the construction plan specifically includes the construction process, construction process and construction cost data of the building; The target object is a prefabricated building for which a construction method needs to be obtained; the target design drawing is the design drawing corresponding to the target object.

3. The BIM-based prefabricated building construction method according to claim 1, characterized in that: The specific method of obtaining a set of all construction plans for each type of building in step S02 is: Step S11: construct a word vector conversion model to convert n pieces of building basic feature data of prefabricated buildings into corresponding word vectors in sequence; Step S12: Take the converted n word vectors as sample points, randomly select k sample points as initial cluster centers, and mark them as z1, z2, z3, ..., z k ; Step S13: record the sample points that are not used as cluster center points as calculation points and mark them as j1, j2, j3, ..., j n-k ; Calculate the distance D from each calculation point to each cluster center in turn ba , the calculation formula is expressed as: , where D ba is the bth calculation point j b To the a-th cluster center z a The distance, where b = 1, 2, 3, ..., nk; a = 1, 2, 3, ..., k; R is the dimension of the sample point, u = 1, 2, 3, ..., R; j bu is the bth calculation point j b The coordinates in the u-th dimension, z au is the a-th cluster center z a Coordinates in the u-th dimension; Step S14: establishing corresponding k´ clusters based on the k cluster centers, k=k´; Step S15: calculate point j b The distance to each cluster center is compared, and the calculated point is assigned to the cluster corresponding to the cluster center closest to it; Step S16: set b=b+1, and jump back to step S15; Step S17: Repeat steps S15 to S16 until b=nk, and the loop ends, and the nk calculation points are all assigned to the corresponding clusters; Step S18: Recalculate the new cluster center coordinates of each cluster. The calculation formula is expressed as: , where z´ c is the new cluster center coordinate of the cth cluster, c=1, 2, 3, …, k´, y i is the coordinate of the i-th calculation point in the c-th cluster, i=1, 2, 3, …, I, I is the total number of calculation points in the c-th cluster, ; Step S19: Repeat steps S13 to S18 until the new cluster center coordinates of each cluster are recalculated in step S18. The loop ends when the new cluster center coordinates of each cluster calculated in the previous loop are consistent with the new cluster center coordinates of each cluster calculated in the previous loop; obtain the clusters and corresponding sample points corresponding to the k´ clusters.

4. The BIM-based prefabricated building construction method according to claim 3, characterized in that: The sample points corresponding to the k´ clusters are the basic building feature data. The prefabricated building category corresponding to the basic building feature data of the new cluster center point of each cluster is selected as the prefabricated building category of the cluster, which is the cluster corresponding to the cluster; the collection of construction plans of all sample points in the cluster is the construction plan set of the building category corresponding to the cluster.

5. The BIM-based prefabricated building construction method according to claim 3, characterized in that: The step S03 of acquiring the building category of the target object comprises the following steps: Step S21: converting the building basic feature data of the target object into a corresponding word vector through a word vector conversion model, and recording it as a target point; Step S22: record the target point as M, calculate the distance from the target point to the new cluster center point of each cluster in step S18, and arrange them in ascending order from small to large, and assign the target point to the cluster corresponding to the cluster center point closest to it, that is, the cluster corresponding to the cluster center point with the smallest distance value; The calculation formula is: , where D Mc is the distance between the target point and the new cluster center of the cth cluster, M u is the coordinate of the target point in the uth dimension, z´ cu is the new cluster center point z´ of the cth cluster c At the coordinate of the u-th dimension, R is the dimension in step S13, u=1, 2, 3, ..., R; Step S23: Output the building category corresponding to the cluster where the target point in step S22 is located.

6. The BIM-based prefabricated building construction method according to claim 5, characterized in that: The specific method of obtaining a set of feasible construction solutions in step S04 is: Based on the building category corresponding to the cluster where the target point is located obtained in step S23, that is, the building category of the target object, a set of construction plans corresponding to the building category is obtained, which is recorded as U1; constraint conditions are set to obtain a set of construction plans that meet the construction progress conditions, which is recorded as U2; each construction plan in U2 is applied to the BIM model of the target object for construction demonstration, and a set of feasible construction plans is obtained, which is recorded as U3; The specific process of obtaining U2 is as follows: Setting Constraints Among them, JD u is the maximum construction completion time of the u-th construction scheme in U1, and YS is the maximum construction completion time of the target object; The construction plans that meet the constraints are re-labeled with digital labels, and all the construction plans that meet the constraints are formed into a set U2; The specific process of obtaining U3 is as follows: Each construction plan in U2 is applied to the BIM model of the target object for construction demonstration. Construction plans that fail in the demonstration are eliminated, and digital labels are used again for a new round of marking. The construction plans that are finally marked with digital labels form a set U3.

7. The BIM-based prefabricated building construction method according to claim 6, characterized in that: The step S05 of obtaining the best construction plan includes the following steps: Step S31: Encode the construction plan in U3, obtain chromosomes, and construct an initial population; The construction plan is encoded as O, where O is the chromosome, and X chromosomes are randomly generated to form the initial population. ; Step S32: determining a fitness function; Step S33: performing natural selection on chromosomes in the population; Step S34: performing crossover recombination on chromosomes in the population; Step S35: mutating the chromosomes in the population; Step S36: Obtain a new population, preset the population generation to be L, the fitness threshold to be Q, L is an integer greater than 0, and Q is a real number greater than 0; loop steps S33 to S35 until the generation corresponding to the new population is L or the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold Q, the loop ends, and the construction plan corresponding to the chromosome with the maximum fitness in the new population is obtained, which is the optimal construction plan.

8. The BIM-based prefabricated building construction method according to claim 7, characterized in that: The expression of the fitness function is: , where f r is the fitness of the rth chromosome, Cos r is the predicted construction cost of the construction plan corresponding to the rth chromosome; The method for obtaining the predicted construction cost is as follows: using the construction plan corresponding to the chromosome and the basic characteristic data of the target object building as research data, inputting the research data into the trained construction cost prediction model, and predicting the corresponding construction cost; The training method of the construction cost prediction model is specifically as follows: The building foundation characteristic data, building structure characteristic data and building construction data corresponding to a prefabricated building design drawing are taken as a set of analysis data, d sets of analysis data are collected in advance, and corresponding construction cost values ​​are obtained for the d sets of analysis data, where d is an integer greater than 1, and the analysis data and the corresponding construction cost values ​​are converted into a corresponding set of feature vectors; d=1, 2, 3, ..., n; Each set of feature vectors is used as the input of the construction cost prediction model. The construction cost prediction model uses a predicted construction cost value corresponding to each set of analysis data as output, and uses the actual construction cost value corresponding to each set of analysis data as the prediction target. The actual construction cost value can be obtained through the pre-collected construction data; the training target is to minimize the sum of the prediction errors of all analysis data; the formula of the prediction error is expressed as: , where ε p is the prediction error, p is the group number of the eigenvector corresponding to the analyzed data, θ p is the predicted construction cost value corresponding to the pth group of analysis data, μ p The actual construction cost value corresponding to the pth group of analysis data is used to train the construction cost prediction model until the sum of the prediction errors reaches convergence and the training is stopped.

Images