BIM (Building Information Modeling) and intelligent algorithm-based curved wooden keel deepening design method

Abstract

The invention relates to the technical field of building keel design, in particular to a curved surface wood keel deepening design method based on BIM and an intelligent algorithm. The method comprises the following steps that S1, mathematical modeling of curved surface wooden keel segments for curved surface building keel design is constructed; s2, parameterizing the position of a splicing point on each keel segment; and S3, through two-stage multi-objective optimization, the segmented design of the curved surface wood keel of the curved surface building keel design is optimized. According to the curved-surface wood keel deepening design method based on the BIM and the intelligent algorithm, a mathematical model and a corresponding calculation formula of curved-surface wood keel (CWK) segmentation of curved-surface building keel design are constructed, so that factory manufacturing and field assembly factors can be comprehensively considered; and meanwhile, efficient work is performed through three parameterization methods including a'each keel method ', a'common straight reference line method' and a'common curved reference line method ', and a scheme which better fits the preference of a designer can be generated while the optimization efficiency is improved through a two-stage optimization strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of building keel design, and in particular to a method for in-depth design of curved wooden keels based on BIM and intelligent algorithms. Background Art

[0002] Curved building keel design has been widely used in recent years, especially in the design of large public building keels, due to its flowing visual dynamic effect, seamless integration with the natural environment, and ability to meet specific functional requirements (such as acoustic propagation in concert halls). The design and construction of curved building keel design incorporate the most advanced concepts and technologies in contemporary building keel design, including computer-aided design, computer-aided engineering, and computer-aided manufacturing. In the design and construction process, the formwork keel is a key link, which directly affects the aesthetics and quality of the finished product of the curved building keel design. Considering the convenience of processing and environmental protection factors, curved wooden keel (CWK) is usually selected as the formwork for curved building keel design.

[0003] CWK's design, manufacturing and assembly process Figure 1 The building keel designer designs the curved appearance of the building keel according to the functional and aesthetic requirements, while the structural engineer determines the arrangement of the keel based on the force analysis (see Figure 1 (a)). After completing the keel layout design, the designer will carry out specific keel design based on the model. The first step is the segmentation and layout of CWK ( Figure 1 (b)). Next, the factory produces CWK segments according to the cutting diagram ( Figure 1 (c)) and finally assembled at the construction site ( Figure 1 (d)). CWK segmentation and arrangement (see Figure 1 (a) and Figure 1 (b)) is the basis of its manufacturing and assembly. Therefore, the requirements of manufacturing and assembly must be fully considered in the design. However, research in this area is still relatively scarce. The current design process mainly relies on manual operation by designers. Although some processes have been automated, full automation and intelligence have not yet been achieved.

[0004] To this end, a method for in-depth design of curved wooden keels based on BIM and intelligent algorithms was designed to provide another technical solution to the above technical problems. Summary of the invention

[0005] Based on this, it is necessary to provide a curved wooden keel in-depth design method based on BIM and intelligent algorithm to solve the technical problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0007] A method for in-depth design of curved wooden keels based on BIM and intelligent algorithms, the steps are as follows:

[0008] S1: Mathematical modeling of curved wooden keel segments for curved building keel design;

[0009] S2: parameterize the position of the joint points on each keel segment;

[0010] S3: Optimize the segmented design of curved wooden keels for curved building keels through two-stage multi-objective optimization;

[0011] S4: for the optimization completed in step S3, numbering of each segment is performed;

[0012] S5: Arrange the encoded segments completed in step S4.

[0013] As a preferred implementation of the method for in-depth design of curved wooden keels based on BIM and intelligent algorithms provided by the present invention, in the step S1, mathematical modeling of curved wooden keel segments for curved building keel design is constructed, and the steps are as follows:

[0014] The curved wooden keel designed for the curved building keel is divided into three layers, of which the innermost layer is the "inner layer", and the other two layers are the outer layers, and the two outer layers are symmetrically distributed on the outside of the inner layer;

[0015] Determine the joint points between adjacent layers, and the direction of each joint point should be perpendicular to the tangent line of the curve;

[0016] All the tying steel belts that divide the curved wooden keel into sections of the curved building keel design should be arranged in the same straight line;

[0017] Design the splicing points of different segments on different straight lines.

[0018] As a preferred implementation of the method for in-depth design of curved wooden keels based on BIM and intelligent algorithms provided by the present invention, the segments of the curved wooden keels of each curved building keel design are cut from standard wooden boards of fixed sizes.

[0019] As a preferred implementation of the method for in-depth design of curved wooden keels based on BIM and intelligent algorithms provided by the present invention, in step S2, the position of the joint points on each keel segment is parameterized, and the steps are as follows:

[0020] The geometric center line of each keel is used as a reference line, and the position of the cutting point is optimized along the reference line;

[0021] Determine the cutting point of each keel section through a common straight reference line;

[0022] The cutting points of the longer curved keels are determined by the common curved reference line.

[0023] As a preferred implementation of the method for in-depth design of curved wooden keels based on BIM and intelligent algorithms provided by the present invention, the cutting point of each keel is determined by a common straight reference line, and the steps are as follows:

[0024] A common straight reference line is set at a position perpendicular to the horizontal plane, and the x and y coordinates of the starting point and the end point of the common straight reference line are the average values ​​of the x and y coordinates of the starting point and the end point of each keel center line, and the z coordinate of the common straight reference line is the minimum and maximum z values ​​of the starting point and the end point of the keel center line;

[0025] Optimizing the position of the cutting point along the common straight line, specifically, optimizing the cutting point by using the proposed two-stage multi-objective optimization algorithm;

[0026] A horizontal plane is constructed at the optimized cutting point to intersect with the center line of each keel, and the cutting point of each keel is determined;

[0027] The steps of determining the cutting point of the longer curved keel through the common curved reference line are as follows:

[0028] The center line of the longest CWK is set as the common curve reference line, and the CWK segments are evenly divided.

[0029] As a preferred implementation of the method for in-depth design of curved wooden keels based on BIM and intelligent algorithms provided by the present invention, in step S3, data of corresponding segmentation schemes and their objective function values ​​are generated through two-stage multi-objective optimization, and the steps are as follows:

[0030] The parent generation is selected through the tournament selection method, and then the offspring generation is generated using the two-point crossover operator and mutation operator;

[0031] Merge the generated offspring with the parent generation and perform non-dominated sorting and crowding distance sorting;

[0032] Individuals with higher frontier grades or smaller crowding distances are selected until the number of individuals in the new population is equal to the initial population;

[0033] The initial population of each stage is optimized through two-stage multi-objective optimization and dynamic crossover and mutation operations are adopted;

[0034] The different initial design populations obtained through each stage are used as the input of the NSGA-II algorithm;

[0035] Obtain data corresponding to the segmentation scheme and its objective function value.

[0036] As a preferred implementation of the method for in-depth design of curved wooden keels based on BIM and intelligent algorithms provided by the present invention, the initial population of each stage is optimized through two-stage multi-objective optimization and dynamic crossover and mutation operations are adopted, and the steps are as follows:

[0037] In the first stage, the initial population is generated by replicating uniformly segmented individuals;

[0038] In the second stage, the initial population is generated by replicating the best individuals selected at the end of the first stage of evolution.

[0039] As a preferred implementation of the method for in-depth design of curved wooden keels based on BIM and intelligent algorithms provided by the present invention, in step S4, the optimization completed in step S3 is processed by numbering each segment, and the steps are as follows:

[0040] Determine the geometric center of each segment;

[0041] Use K-means clustering to cluster the z coordinates of the centers;

[0042] When the z-values ​​of the segment centers are clustered, the corresponding segments will be grouped in turn;

[0043] Encode each group according to letters + numbers.

[0044] As a preferred implementation of the method for in-depth design of curved wooden keels based on BIM and intelligent algorithms provided by the present invention, in step S5, the coded segments completed in step S4 are nested, and the steps are as follows:

[0045] In the step S5, the encoded segments completed in the step S4 are arranged in the following steps:

[0046] Get the original center position (x) of each CWK segment i ,y i ,z i ) and its converted corresponding bit

[0047] ″″″

[0048] Set (x i ,y i ,z i ), get the position conversion parameter (x i -x i ,y i -y i ,z i -z i ), where i represents the number of CWK;

[0049] ″′

[0050] According to the corresponding conversion parameters (x i -x i ,y i -y i ,z i -z i ) Convert the original position of the segmented encoding.

[0051] It can be seen without a doubt that the above-mentioned technical solution of the present application can definitely solve the technical problem to be solved by the present application.

[0052] At the same time, through the above technical solutions, the present invention has at least the following beneficial effects:

[0053] 1. The present invention provides a method for in-depth design of curved wooden keels based on BIM and intelligent algorithms. By constructing a mathematical model of CWK segmentation and a corresponding calculation formula, the factors of factory manufacturing and on-site assembly can be comprehensively considered. At the same time, three parameterization methods, namely "each keel method", "common straight reference line method" and "common curved reference line method" can be used for efficient work. A two-stage optimization strategy can also be used to improve the optimization efficiency while generating a solution that better fits the designer's preferences.

[0054] 2. The present invention automatically and efficiently groups and arranges the coded segments on the standard board through parallel grouping and nesting procedures to ensure accurate positioning of the CWK segment coding.

[0055] 3. The present invention realizes the automated manufacturing design of CWK based on BIM technology and intelligent algorithm.

[0056] 4. The present invention uses Grasshopper software as the BIM platform to visualize the entire design process, which is convenient for designers to use interactively.

[0057] 5. The present invention can quickly generate multiple solutions that meet the designer's preferences through a two-stage optimization method based on the intelligent algorithm based on NSGA-II, thereby accelerating the design process.

[0058] 6. The present invention inputs the design into a CWK model, and outputs the design into a CWK segment with coding after material cutting and layout, which can be directly used for processing, manufacturing and subsequent assembly. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 Schematic diagram of the design process of curved wooden keel (CWK) designed for existing curved building keels;

[0061] Figure 2 It is a schematic diagram of the method framework of the present invention;

[0062] Figure 3 It is a schematic diagram of the assembly and manufacturing details of the present invention;

[0063] Figure 4 Schematic diagram of different parameterization methods of the present invention;

[0064] Figure 5 It is a schematic diagram of the workflow of the two-stage optimization process of the present invention;

[0065] Figure 6 It is a schematic diagram of the coding and arrangement process of the present invention;

[0066] Figure 7 It is a schematic diagram of the automatic segmented coding of the present invention;

[0067] Figure 8 Schematic diagram of preliminary material cutting and arranging results of the present invention;

[0068] Fig. 9 It is a schematic diagram of the initial situation of CWK in the case of the present invention;

[0069] Fig.10 It is a schematic diagram of the preliminary arrangement result of the optimization algorithm in the case of the present invention;

[0070] Fig.11 It is a schematic diagram of the sample arrangement results in the case of the present invention. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0072] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.

[0073] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features and technical solutions in the embodiments may be combined with each other.

[0074] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0075] Reference Figure 2-Figure 8 , a detailed design method for curved wooden keels based on BIM and intelligent algorithms.

[0076] Using Grasshopper as the BIM design platform, refer to Figure 2 , Figure 2 The five modules of the framework are presented in Figure 1: (1) mathematical modeling of CWK segmentation, (2) parameterization, (3) two-stage multi-objective optimization, (4) automated cluster encoding, and (5) parallel automatic nesting.

[0077] (1) Mathematical modeling of CWK segmentation

[0078] 1.1. Design conditions

[0079] In order to realize the manufacture and assembly of CWK, it must be divided into wooden sections, such as Figure 3 As shown in the figure. In construction, CWK usually consists of three layers. The innermost layer is called the "inner layer", while the two outer layers are called the "outer layers", and the two are symmetrically distributed. CWK segmentation needs to meet a variety of constraints, which can be mainly divided into two categories: on-site assembly constraints and factory manufacturing constraints.

[0080] A. On-site assembly constraints

[0081] First, ensuring that each segment can be assembled into a complete CWK structure is a basic requirement. Secondly, for ease of manufacturing and assembly, the two "outer" segments must be symmetrical in position and geometry. In addition, to ensure the stability of the keel, the joints between adjacent layers cannot be too close or too far. Finally, to facilitate on-site assembly by workers and ensure the correct transfer of structural loads, the direction of each joint should be perpendicular to the tangent of the curve.

[0082] B. Factory manufacturing constraints:

[0083] CWK segments are processed in the factory using CNC cutting machines. All CWK segments are cut from standard wooden boards of fixed sizes, such as Figure 3 As shown in Figure 2. Since the CWK segment and the standard wood board have the same thickness, only the planar segment needs to be considered. Therefore, the factory manufacturing constraint is that the segment must be able to be cut from the standard board.

[0084] 1.2. Design goals

[0085] While considering the structural reliability and convenience of the assembly process after on-site assembly, it is also necessary to take into account the material saving of factory manufacturing. Therefore, the optimization design goals of the CWK segment should cover three aspects: structural safety, on-site assembly convenience and factory manufacturing efficiency.

[0086] A) Structural safety objectives

[0087] To ensure that the structure can bear load evenly after installation, the CWK segment should not be too short. Too short a segment will lead to too concentrated splicing points, thus causing significant stress changes.

[0088] B) On-site assembly target

[0089] To facilitate the operation of on-site workers, all tying steel belts should be arranged in the same straight line. This alignment method can simplify the scaffolding layout and make the assembly process simpler and more efficient. To ensure good load-bearing alignment of the tying steel belts, the splicing points of different segments need to be designed on different straight lines, such as Figure 3 shown.

[0090] The fewer straight lines the splice points are arranged in, the less lashing and scaffolding arrangements are required, which reduces labor requirements, another on-site assembly goal.

[0091] C) Factory manufacturing goals

[0092] To improve the efficiency of the material nesting tool, too long segments should be avoided, because too long segments will reduce the efficiency of cutting and nesting. Therefore, it is necessary to minimize the segment length.

[0093] (2) Parameterization

[0094] The variable used to optimize the CWK segment design is the location of the splicing point. If the location of the splicing point on each keel is parameterized, such as Figure 4 As shown in (a), the geometric center line of each keel is used as the reference line, and the position of the cutting point can be optimized along the reference line. However, due to the large number of design constraints and multiple objective constraints, this parameterization method may make it difficult for the algorithm to quickly converge to the optimal or near-optimal solution.

[0095] like Figure 4 As shown in (b), the common reference line is perpendicular to the horizontal plane, and the x and y coordinates of its starting point and end point are the average values ​​of the x and y coordinates of the starting point and end point of each keel centerline, and the z coordinates are the minimum and maximum z values ​​of the starting point and end point of the keel centerline. Subsequently, the positions of the cutting points are optimized along the common straight line, and horizontal planes are constructed at these cutting points to intersect with the center lines of each keel, thereby determining the cutting points of each keel segment. This parameterization method reduces the number of parameters while ensuring that the splicing points are aligned along the common straight line (horizontal plane).

[0096] However, since the curved keel may have a long horizontal distance, using the above common straight reference line may cause some CWK segments to be too long because these segments have a low probability of being split, such as Figure 4 (b) is shown as the CWK segmentation between planes A and B. Therefore, by using the common curved reference line method, as Figure 4(c) The common curve reference line is the center line of the longest CWK. When the center line of the longest CWK is used as the reference line, the probability of all CWK segments being segmented is more uniform. Therefore, the variable of the CWK segment is the position of the cutting point on the center axis of the longest keel, that is, {joint1, joint2, …, joint i ,}.

[0097] (3) Two-stage multi-objective optimization

[0098] 3.1 Fitness Function

[0099] Equation (1) represents the first objective function, which aims to minimize the CWK segmentation The maximum length of the segment to avoid too long segment. is the maximum length threshold set by the designer, and C1 is a constant used to balance the objective functions of different orders of magnitude. Similarly, equation (2) represents the second objective function, which aims to maximize the minimum length of the CWK segment. To ensure that all optimization objectives are minimized, the inverse of the second objective function is taken, where C2 is a constant similar to C1 and is the minimum length threshold set by the designer.

[0100] In order to facilitate construction, equation (3) represents the minimization of the number of straight lines where the CWK splicing points are located, the number of segments and, equation (4) represents the minimization of the type of segment length, Indicates the location of the splicing point, Represents the length of the segment, where C3 and C4 are constants similar to C1.

[0101] In order to make the CWK segment length more concentrated near the average length and reduce the number of segments that are too short or too long, a fifth optimization objective is proposed, as shown in equations (5) and (6), where C5 is a constant similar to C1.

[0102]

[0103] In the above formula, represents the length of the i-th CWK segment, Indicates the maximum value of the CWK segment length. Indicates the minimum value of the CWK segment length, {} indicates a set, and num() indicates the type of value in the calculated set. Indicates the height of the horizontal line where the splicing point is located, N indicates the number of CWK segments, μ seg is the mean of the CWK segment lengths. C1, C2, C3, C4, and C5 are different constants used to balance objective functions of different magnitudes.

[0104] 3.2 Two-stage optimization process

[0105] Figure 5 (NSGA-II algorithm section) shows the process of the NSGA-II algorithm. First, the parent generation is selected by the tournament selection method, and then the offspring is generated using the two-point crossover operator and the mutation operator. Next, the generated offspring is merged with the parent generation, and non-dominated sorting (i.e., sorting the individuals in the population according to the dominance relationship and assigning them to different non-dominated fronts) and crowding distance sorting (i.e., calculating the crowding distance of the individuals in each non-dominated front) are performed. Individuals with higher frontier levels or smaller crowding distances are selected until the number of individuals in the new population is equal to the number of individuals in the initial population.

[0106] In order to generate a large number of design solutions close to the designer's preferences and quickly obtain the optimal solution, a two-stage evolutionary optimization method is proposed ( Figure 5 ), aims to optimize the initial population at each stage, and adopts dynamic crossover and mutation operations. In the first stage, the initial population is generated by replicating uniform segmented individuals. Uniform segmented individuals refer to the variable parameters obtained by dividing the selected keel into segments of equal length (i.e., ). In the second stage, the best individuals selected at the end of the first stage of evolution are replicated. Generate the initial population.

[0107] Figure 5 The two-stage multi-objective optimization process is presented. The different initial design populations obtained through the above stages, i.e., different CWK segmentation schemes, are used as inputs to the NSGA-II algorithm. Subsequently, the corresponding objective function values ​​of these design variables are calculated in GH and input into the NSGA-II algorithm. Finally, the data of the corresponding segmentation schemes and their objective function values ​​are obtained.

[0108] The multi-objective optimization problem of CWK segmentation can be expressed by equation (7), where F1(x), F2(x), F3(x), F4(x), and F5(x) are defined by equations (1) to (6), respectively, and x represents the design variable.

[0109] Min F(X)={F1(x),F2(x),F3(x),F4(x),F5(x)} (7)

[0110] In order to better balance global search and local search, the second stage uses smaller crossover and mutation probabilities than the first stage, and increases the crossover distribution index and mutation distribution index. These two parameters are crucial in the NSGA-II algorithm and help improve the precision of the search.

[0111] In addition, the stopping criterion for each stage is to reach the preset maximum number of optimization generations, and the crossover probability and mutation probability are set to fixed values.

[0112] (4) Automated cluster coding

[0113] After completing the CWK segment design optimization, each segment needs to be numbered for subsequent processing and installation. Figure 6 Demonstrates the workflow of encoding and nesting.

[0114] During the construction of CWK, since there are many and similar segments, the segments need to be numbered for easy identification. The segments will be installed in order from bottom to top, so it is necessary to first identify the different segment groups and assign them numbers.

[0115] Since the construction sequence is bottom-up, segments at similar heights are grouped for installation. First, the geometric center of each segment is determined, and then the z coordinates of these centers are clustered using K-means clustering. K-means clustering is a commonly used unsupervised learning algorithm that iteratively divides data into K clusters to minimize the sum of the distances from each data point to its cluster center. When the z values ​​of the segment centers are clustered, the corresponding segments are grouped in turn. Figure 7 (a) shows the cluster centers and results of the z value, and different colors represent different cluster centers and groups.

[0116] Next, encode each group separately, such as Figure 7 (b), where letters represent groups and numbers represent the installation order within each group.

[0117] (5) Parallel automatic nesting

[0118] After segmentation and coding, the coded segments are obtained. If all the segments are directly input into the nesting tool at this time, a nesting result will be generated. However, this method will arrange the segments of different heights on the same plate, and construction can only start after all the segments are produced, which brings inconvenience to the construction progress. In addition, the number of CWK segments is large and the size is relatively small compared to the standard plate, which increases the complexity of the nesting process. Single-threaded nesting calculation cannot take advantage of the multi-threading capabilities of the computer, resulting in slow nesting performance.

[0119] Therefore, a parallel arrangement scheme for grouped CWK segments is proposed, such as Figure 7 The design results are shown in Figure 6 The CWK segments are entered in groups and the standard plates are replicated accordingly based on the number of CWK segments. The data is then entered into the OpenNest plugin in Grasshopper.

[0120] In addition, the original center position (x) of each CWK segment is obtained. i ,y i ,z i ) and its transformed corresponding position (xi ′,y i ′,z i ′), we can get the position conversion parameter (x i ′-x i ,y i ′-y i ,z i ′-z i ), where i represents the CWK number. Then, according to the corresponding conversion parameter (x i ′-x i ,y i ′-y i ,z i ′-z i ) Convert the original position of the segmented encoding.

[0121] Since CWK consists of three layers and the outer layer is symmetrical, one layer of CWK can be obtained by copying another layer. To distinguish the three layers of keels, the prefix "I-" for the inner layer keel and "O-" for the outer layer keel are added to the CWK segment code to achieve renaming.

[0122] To optimize material utilization, the last board of each group ( Figure 8 The combined sheets are prioritized for fabrication and then allocated to their respective groups.

[0123] Specific implementation case reference Figure 9-11 .

[0124] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for in-depth design of curved wooden keels based on BIM and intelligent algorithms, characterized in that: Here are the steps: S1: Mathematical modeling of curved wooden keel segments for curved building keel design; S2: parameterize the position of the joint points on each keel segment; S3: Optimize the segmented design of curved wooden keels for curved building keels through two-stage multi-objective optimization; S4: for the optimization completed in step S3, numbering of each segment is performed; S5: Arrange the encoded segments completed in step S4.

2. According to claim 1, a method for in-depth design of curved wooden keels based on BIM and intelligent algorithms is characterized in that: In the step S1, a mathematical modeling of a curved wooden keel segment for a curved building keel design is constructed, and the steps are as follows: The curved wooden keel designed for the curved building keel is divided into three layers, of which the innermost layer is the "inner layer" and the other two layers are the outer layers, and the two outer layers are symmetrically distributed on the outside of the inner layer; Determine the joint points between adjacent layers, and the direction of each joint point should be perpendicular to the tangent line of the curve; All the tying steel belts that divide the curved wooden keel into sections of the curved building keel design should be arranged in the same straight line; Design the splicing points of different segments on different straight lines.

3. The method for in-depth design of curved wooden keels based on BIM and intelligent algorithms according to claim 2 is characterized in that: The curved timber keel segments of each curved building keel design are cut from standard wooden boards of fixed sizes.

4. The method for in-depth design of curved wooden keels based on BIM and intelligent algorithms according to claim 1 is characterized in that: In step S2, the position of the splicing point on each keel segment is parameterized, and the steps are as follows: The geometric center line of each keel is used as a reference line, and the position of the cutting point is optimized along the reference line; Determine the cutting point of each keel section through a common straight reference line; The cutting points of the longer curved keels are determined by the common curved reference line.

5. The method for in-depth design of curved wooden keels based on BIM and intelligent algorithms according to claim 4 is characterized in that: The steps of determining the cutting point of each keel section by a common straight reference line are as follows: A common straight reference line is set at a position perpendicular to the horizontal plane, and the x and y coordinates of the starting point and the end point of the common straight reference line are the average values ​​of the x and y coordinates of the starting point and the end point of each keel center line, and the z coordinate of the common straight reference line is the minimum and maximum z values ​​of the starting point and the end point of the keel center line; Optimizing the location of the cutting points along the common straight line; A horizontal plane is constructed at the optimized cutting point to intersect with the center line of each keel, and the cutting point of each keel is determined; The steps of determining the cutting point of the longer curved keel through the common curved reference line are as follows: The center line of the longest CWK is set as the common curve reference line, and the CWK segments are evenly divided.

6. The method for in-depth design of curved wooden keels based on BIM and intelligent algorithms according to claim 1 is characterized in that: In the step S3, the data of the corresponding segmentation scheme and its objective function value are generated through two-stage multi-objective optimization, and the steps are as follows: The parent generation is selected through the tournament selection method, and then the offspring generation is generated using the two-point crossover operator and mutation operator; Merge the generated offspring with the parent generation and perform non-dominated sorting and crowding distance sorting; Individuals with higher frontier grades or smaller crowding distances are selected until the number of individuals in the new population is equal to the initial population; The initial population of each stage is optimized through two-stage multi-objective optimization and dynamic crossover and mutation operations are adopted; The different initial design populations obtained through each stage are used as the input of the NSGA-II algorithm; Obtain data corresponding to the segmentation scheme and its objective function value.

7. The method for in-depth design of curved wooden keels based on BIM and intelligent algorithms according to claim 6 is characterized in that: The initial population of each stage is optimized through two-stage multi-objective optimization and dynamic crossover and mutation operations are adopted. The steps are as follows: In the first stage, the initial population is generated by replicating uniformly segmented individuals; In the second stage, the initial population is generated by replicating the best individuals selected at the end of the first stage of evolution.

8. The method for in-depth design of curved wooden keels based on BIM and intelligent algorithms according to claim 1 is characterized in that: In step S4, the optimization completed in step S3 is processed by numbering each segment, and the steps are as follows: Determine the geometric center of each segment; Use K-means clustering to cluster the z coordinates of the centers; When the z-values ​​of the segment centers are clustered, the corresponding segments will be grouped in turn; Encode each group according to letters + numbers.

9. The method for in-depth design of curved wooden keels based on BIM and intelligent algorithms according to claim 1, characterized in that: In the step S5, the encoded segments completed in the step S4 are arranged in the following steps: Get the original center position (x) of each CWK segment i ,y i ,z i ) and its transformed corresponding position (x′ i ,y′ i ,z′ i ), obtain the position conversion parameter (x′ i -x i ,y′ i -y i ,z′ i -z i ), where i represents the number of CWK; According to the corresponding transformation parameters (x′ i -x i ,y′ i -y i ,z′ i -z i ) Convert the original position of the segmented encoding.

Images