Multi-curvature surface modeling design optimization method and system based on BIM technology

Abstract

The present application provides a multi-curvature surface modeling design optimization method and system based on BIM technology, which relates to the field of data optimization technology. The method includes: obtaining first multi-curvature surface information of a target surface designed using BIM, classifying and obtaining first design rationality parameters; performing construction error analysis based on the first multi-curvature surface information, processing and obtaining first construction error parameters, and performing correction processing to obtain first corrected design rationality parameters; analyzing the first surface strength of the first multi-curvature surface information, obtaining the load-bearing information of the target surface, and configuring design weights and load-bearing weights; calculating the first design rationality parameters and the first surface strength based on the design weights and load-bearing weights, obtaining the first surface design fitness, performing design optimization, and obtaining optimal multi-curvature surface information. This solves the technical problem that the prior art lacks quantitative evaluation methods in the multi-curvature surface modeling design process, resulting in many defects in the design scheme.

Description

Technical Field

[0001] The present invention relates to the field of data optimization, and in particular to a multi-curvature surface modeling design optimization method and system based on BIM technology. Background Art

[0002] In the surface design of irregular buildings with multiple curvatures, traditional methods usually rely on the designer's experience and judgment, but lack quantitative evaluation methods, which leads to many defects in the design schemes. For example, the degree of curvature mutation in the surface transition is difficult to accurately quantify, resulting in excessive construction difficulty; or the lack of analysis of curvature distribution and load-bearing information may lead to safety hazards such as local stress concentration. Summary of the Invention

[0003] The present invention addresses the technical problem that in the prior art, there is a lack of quantitative evaluation methods in the design process of multi-curvature curved surface modeling, which leads to many defects in the design scheme. The present invention provides a multi-curvature curved surface modeling optimization method and system based on BIM technology.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides a multi-curvature surface modeling design optimization method based on BIM technology, comprising:

[0006] Acquire first multi-curvature surface information of a target surface designed using BIM, process to obtain a first curvature mutation, and classify to obtain a first design rationality parameter;

[0007] Performing a construction error analysis based on the first multi-curvature surface information to obtain a first construction error parameter, and correcting the first design rationality parameter to obtain a first corrected design rationality parameter;

[0008] Analyzing the first surface strength of the first multi-curvature surface information, obtaining the load-bearing information of the target surface, and configuring the design weight and the load-bearing weight in combination with the first construction error parameter;

[0009] According to the design weight and the load-bearing weight, the first design rationality parameter and the first curved surface strength are calculated to obtain the first curved surface design fitness, and the multi-curvature curved surface design optimization is performed to obtain the optimal multi-curvature curved surface information.

[0010] In a second aspect, the present invention provides a multi-curvature surface modeling design optimization system based on BIM technology, comprising:

[0011] A rationality evaluation module is used to obtain first multi-curvature surface information of a target surface designed using BIM, process and obtain a first curvature mutation degree, and classify and obtain a first design rationality parameter;

[0012] an error correction module, configured to perform construction error analysis based on the first multi-curvature surface information, obtain a first construction error parameter, and correct the first design rationality parameter to obtain a first corrected design rationality parameter;

[0013] a weight configuration module, configured to analyze the first surface strength of the first multi-curvature surface information, obtain the load-bearing information of the target surface, and configure the design weight and the load-bearing weight in combination with the first construction error parameter;

[0014] The fitness optimization module is used to calculate the first design rationality parameter and the first surface strength according to the design weight and the load-bearing weight, obtain the first surface design fitness, perform multi-curvature surface design optimization, and obtain optimal multi-curvature surface information.

[0015] The beneficial effects of the present invention are:

[0016] Compared to existing technologies, this application first obtains the first multi-curvature surface information of the target surface designed using BIM, processes it to obtain the first curvature mutation, and classifies it to obtain the first design rationality parameter. This converts the abstract geometric characteristic (curvature mutation) into a quantifiable design rationality parameter. Secondly, construction error analysis is performed based on the first multi-curvature surface information, processing it to obtain the first construction error parameter. The first design rationality parameter is then corrected to obtain the first corrected design rationality parameter. This correction of the first design rationality parameter is performed from the perspective of constructibility, providing reliable support for subsequent design optimization. Thirdly, the first surface strength of the first multi-curvature surface information is analyzed to obtain the load-bearing information of the target surface. Design weights and load-bearing weights are configured based on the first construction error parameters, providing the necessary data support for subsequent design optimization. Finally, based on the design weights and load-bearing weights, the first design rationality parameter and the first surface strength are calculated to obtain the first surface design fitness. Multi-curvature surface design optimization is then performed to obtain the optimal multi-curvature surface information. This method comprehensively considers both the design and actual load-bearing safety conditions, and through iterative optimization, the optimal multi-curvature surface information is obtained.

[0017] Through the above technical solution, this application deeply integrates artificial intelligence models with BIM technology, comprehensively considers factors such as design aesthetics, design feasibility, and load-bearing safety in the design process, and uses quantitative surface design adaptability to evaluate different design schemes. After multiple rounds of iterative optimization of design schemes, the optimal multi-curvature surface information is obtained. In this way, design optimization is achieved and many defects in the design scheme are effectively avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of the process of the multi-curvature surface modeling optimization method based on BIM technology provided by the present invention;

[0019] Figure 2 This is a structural schematic diagram of the multi-curvature surface modeling optimization system based on BIM technology provided by the present invention.

[0020] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0021] Rationality assessment module 11, error correction module 12, weight configuration module 13, fitness optimization module 14. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0024] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0025] Example 1, as Figure 1 As shown, the embodiment of the present invention provides a multi-curvature surface modeling design optimization method based on BIM technology, including:

[0026] S10: Acquire first multi-curvature surface information of a target surface designed using BIM, process to obtain a first curvature mutation, and classify to obtain a first design rationality parameter;

[0027] In the design of multi-curvature surfaces, the more surfaces and the more complex the curvature, the richer the shape and the more visually appealing it is. However, if the transitions between adjacent surfaces are not smooth, this can lead to visual abruptness and compromise the rationality of the design. Therefore, the rationality of the de-curving design can be assessed by evaluating the smoothness of the transitions between adjacent surfaces.

[0028] In response to the above problems, the present application obtains the first multi-curvature surface information of the target surface designed using BIM, processes and obtains the first curvature mutation degree, inputs the design rationality classification table, and classifies to obtain the first design rationality parameter.

[0029] Specifically, step S10 in the method includes:

[0030] Acquire first multi-curvature surface information of a target surface designed using BIM, wherein the first multi-curvature surface information includes a plurality of connected first curvature surfaces, each of which includes first curvature information;

[0031] Calculating the curvature deviation amplitude of the first curvature information of every two adjacent first curvature surfaces to obtain multiple curvature deviation amplitudes, and calculating the average to obtain the first curvature mutation degree;

[0032] According to the first curvature mutation degree, a first design rationality parameter is obtained through classification.

[0033] In an embodiment of the present application, first, the first multi-curvature surface information of the target surface designed using BIM is obtained, wherein the first multi-curvature surface information includes multiple connected first curvature surfaces, each of which includes first curvature information. Specifically, the first multi-curvature surface information of the target surface is extracted from the BIM model. The first multi-curvature surface information is composed of multiple connected first curvature surfaces (i.e., sub-surface patches) (such as NURBS surfaces and B-spline surfaces), and each first curvature surface includes first curvature information (such as Gaussian curvature or principal curvature). Exemplarily, the NURBS surface of the target surface is extracted using the BIM model, and the principal curvature information (K1, K2, etc.) of each surface patch is obtained.

[0034] Secondly, the curvature deviation amplitude of the first curvature information of each two adjacent first curvature surfaces is calculated to obtain multiple curvature deviation amplitudes, and the average is calculated to obtain the first curvature mutation degree, wherein the curvature deviation amplitude is the absolute value difference of the curvature of two adjacent first curvature surfaces. For example, the curvature deviation amplitude of surface A and surface B is |K A -K BFor example, the connection boundaries of all adjacent surface patches are traversed, and the absolute difference in curvature of each pair of adjacent surfaces is calculated to obtain multiple curvature deviation amplitudes (such as 0.21, 0.23, 0.20, 0.19, and 0.17). The average is then calculated to obtain the first curvature mutation degree (such as 0.20). The first curvature mutation degree quantifies the overall smoothness of the target surface. A higher mutation degree (for example, >0.25) indicates that the connection between adjacent surfaces is less smooth, which may indicate a design error. A lower mutation degree (for example, <0.10) indicates a smoother surface transition, which conforms to the principle of structural rationality.

[0035] Finally, based on the first curvature abruptness, a first design rationality parameter is obtained through classification. Specifically, the first curvature abruptness is input into a pre-constructed design rationality classification table, and the classification mapping is used to obtain the first design rationality parameter. The first design rationality parameter is negatively correlated with the first curvature abruptness. This is because a larger first curvature abruptness indicates less smooth transitions between adjacent surfaces and lower design rationality. For example, the first curvature abruptness (e.g., 0.20) is input into a pre-constructed design rationality classification table, and the classification mapping is used to obtain the first design rationality parameter (e.g., 80). The first design rationality parameter quantifies the rationality of the overall design of the target surface. The smoother the transition between adjacent surfaces in the current surface design, the larger the first design rationality parameter.

[0036] Specifically, the “obtaining a first design rationality parameter by classification according to the first curvature mutation degree” includes:

[0037] According to the design data records of multi-curvature surfaces, a set of sample curvature mutations is collected, and the design rationality levels of different sample curvature mutations are marked to obtain a set of sample design rationality parameters. Among them, the sample curvature mutation is negatively correlated with the sample design rationality parameters.

[0038] Based on the sample curvature mutation degree set and the sample design rationality parameter set, construct a plurality of design rationality mapping pairs and construct a design rationality classification table;

[0039] The first curvature mutation degree is input into the design rationality classification table, and the first design rationality parameter is obtained through classification mapping.

[0040] In the present embodiment, data preparation is first performed. Specifically, based on the design data records of multi-curvature surfaces, a set of sample curvature mutations is collected. Different sample curvature mutations are manually labeled with a design rationality level (e.g., a quantitative rationality score, where a higher rationality score represents a more reasonable design). This yields a set of sample design rationality parameters. The sample curvature mutation and the sample design rationality parameters are negatively correlated, i.e., the greater the curvature mutation, the lower the design rationality.

[0041] Secondly, based on the set of sample curvature mutations and the set of sample design rationality parameters, multiple design rationality mapping pairs are constructed to construct a design rationality classification table. For example, based on the set of sample curvature mutations (e.g., curvature mutation intervals: <0.10, [0.10-0.15), [0.15-0.20), [0.20-0.25), [0.25-0.30), ...) and the set of sample design rationality parameters (e.g., rationality scores: 95, 85, 80, 70, 60, ...), design rationality mapping pairs are constructed to form a design rationality classification table.

[0042] Finally, the first curvature abruptness is input into the design rationality classification table, and classification mapping is performed to obtain a first design rationality parameter. Specifically, the first curvature abruptness of the current design is input into the design rationality classification table, and interval matching is used to output a quantified first design rationality parameter. For example, the first curvature abruptness (e.g., 0.20) is input into the design rationality classification table, and classification mapping is performed to obtain a first design rationality parameter (e.g., 80). The first design rationality parameter quantifies the rationality of the overall design of the target surface. The smoother the transition between adjacent surfaces in the current surface design, the larger the first design rationality parameter.

[0043] In summary, compared with the existing technology, the present application obtains the first multi-curvature surface information of the target surface designed using BIM, processes it to obtain the first curvature mutation degree, inputs the design rationality classification table, and classifies it to obtain the first design rationality parameter. In this way, the abstract geometric characteristics (curvature mutation degree) are converted into quantifiable design rationality parameters.

[0044] S20: performing construction error analysis based on the first multi-curvature surface information to obtain a first construction error parameter, and correcting the first design rationality parameter to obtain a first corrected design rationality parameter;

[0045] In actual construction, the more curved surfaces there are and the more complex the curvature, the greater the curvature error during construction (such as welding). The greater the error, the less reasonable the design. Therefore, surface information can be used to predict and analyze the curvature error that may occur during construction, evaluate design rationality, and adjust the first design rationality parameter accordingly.

[0046] In response to the above problems, the present application performs construction error analysis based on the first multi-curvature surface information, processes to obtain a first construction error parameter, corrects the first design rationality parameter, and obtains a first corrected design rationality parameter.

[0047] Specifically, step S20 in the method includes:

[0048] Inputting the first multi-curvature surface information into a construction error predictor, and predicting and outputting a first construction error parameter, wherein the construction error predictor is constructed based on machine learning and trained using a sample multi-curvature surface information set and a sample construction error parameter set, and the first construction error parameter includes a construction curvature error amplitude;

[0049] The first design rationality parameter is corrected according to the first construction error parameter to obtain a first corrected design rationality parameter.

[0050] In the embodiment of the present application, the first construction error parameter is first obtained. Specifically, the first multi-curvature surface information is input into the construction error predictor, and the prediction output is used to obtain the first construction error parameter, wherein the construction error predictor is constructed based on machine learning and is trained using a sample multi-curvature surface information set and a sample construction error parameter set. The first construction error parameter includes a construction curvature error amplitude, and the construction curvature error amplitude = |design surface information - actual surface information| / design surface information. For example, the curvature of the design surface is 0.25m -1 The measured curvature is 0.23m -1 , then the error margin = |0.25-0.23| / 0.25=8%.

[0051] For example, a construction error predictor can be constructed using a three-stage gradient boosting decision tree (GBDT) ensemble learning framework. The input layer extracts 128-dimensional multi-curvature surface features (such as key parameters like Gaussian curvature) from the BIM model. Feature importance screening and nonlinear relationship modeling are performed using 100 pre-trained decision trees (maximum depth 7 layers, learning rate 0.05). During the model training phase, the sample multi-curvature surface information set and the sample construction error parameter set are divided into training, validation, and test sets in a ratio of 7:1.5:1.5. This serves as training data. The Huber loss function is then used to suppress measurement outliers, and the construction curvature error magnitude is output. Convergence is considered achieved when the prediction accuracy on the validation set exceeds 95%, and training is terminated to obtain the construction error predictor. Finally, the test set is used to evaluate the model's generalization ability to ensure that it can accurately predict the first construction error parameter.

[0052] For example, the first multi-curvature surface information (such as curvature 0.20m -1 ) is input into the construction error predictor, and the prediction output is the first construction error parameter (such as 5.2%). The more curved surfaces and the more complex the curvature, the greater the curvature error amplitude (the first construction error parameter) that occurs during construction.

[0053] Next, the first design rationality parameter is corrected based on the first construction error parameter to obtain a first corrected design rationality parameter. Specifically, an allowable construction error parameter is obtained, and then a ratio of the allowable construction error parameter to the first construction error parameter is calculated. The first design rationality parameter is corrected to obtain the first corrected design rationality parameter.

[0054] Furthermore, the “correcting the first design rationality parameter according to the first construction error parameter to obtain a first corrected design rationality parameter” includes:

[0055] Get the allowable construction error parameters;

[0056] The ratio of the allowable construction error parameter to the first construction error parameter is calculated, and the first design rationality parameter is corrected and calculated to obtain a first corrected design rationality parameter.

[0057] In an embodiment of the present application, the allowable construction error parameter can first be obtained according to the construction contract specifications or industry standards. The allowable construction error parameter reflects the allowable construction error threshold. For example, the allowable construction error parameter of the concrete structure surface obtained according to the industry standard is ±5%.

[0058] Secondly, the ratio of the allowable construction error parameter to the first construction error parameter is calculated, and the first design rationality parameter is corrected and calculated to obtain a first corrected design rationality parameter, wherein the first corrected design rationality parameter = The larger the first construction error parameter, the larger the construction error that may occur in the current surface design, and the smaller the corresponding design rationality parameter. For example, the first design rationality parameter (such as 80) is obtained through classification mapping in the above steps, the construction error parameter is allowed to be ±5%, and the first construction error parameter obtained by prediction output is 5.2%. Then the first corrected design rationality parameter = ,In this way, after evaluating the possible errors in actual construction, the ,first design rationality parameters were corrected, and more accurate and ,comprehensive first corrected design rationality parameters were obtained.

[0059] In summary, compared with the existing technology, the present application performs construction error analysis based on the first multi-curvature surface information, processes to obtain the first construction error parameter, corrects the first design rationality parameter, and obtains the first corrected design rationality parameter. In this way, the construction deviation of different curvature schemes can be accurately predicted through the curvature error amplitude, and the first design rationality parameter is corrected from the construction feasibility level, providing reliable support for subsequent design optimization.

[0060] S30: Analyze the first surface strength of the first multi-curvature surface information, obtain the load-bearing information of the target surface, and configure the design weight and the load-bearing weight in combination with the first construction error parameter;

[0061] During the surface design process, in addition to considering the design aesthetics and design feasibility, the bearing load of the surface is an important factor that needs special consideration during the design process. Moreover, the design aesthetics is often negatively correlated with load safety. If the load does not meet the standard, it may cause safety hazards such as stress concentration.

[0062] To address the above problem, the present application analyzes the first surface strength of the first multi-curvature surface information, obtains the load-bearing information of the target surface, and configures the design weight and load-bearing weight based on the load-bearing information and the first construction error parameter.

[0063] Specifically, step S30 in the method includes:

[0064] Inputting the first multi-curvature surface information into a surface strength analyzer, and outputting a first surface strength, wherein the surface strength analyzer is trained using a sample multi-curvature surface information set and a sample surface strength set;

[0065] Acquiring bearing information of the target curved surface, wherein the bearing information includes the bearing load of the target curved surface;

[0066] The design weight and the bearing weight are configured according to the bearing information and the first construction error parameter.

[0067] In an embodiment of the present application, the first multi-curvature surface information (such as curvature, material yield strength, Poisson's ratio, etc.) is first input into a pre-trained surface strength analyzer, and the first surface strength is obtained as output, wherein the surface strength analyzer is trained using a sample multi-curvature surface information set and a sample surface strength set, and the first surface strength reflects the surface's ability to resist instability. The greater the first surface strength, the stronger the surface's ability to resist instability.

[0068] For example, the surface strength analyzer can adopt a graph neural network (GNN) architecture, with nodes mapped to NURBS surface information and edge weights associated with curvature gradient transmission relationships. The input layer receives the topological matrix of the first multi-curvature surface information (such as mechanical parameters such as material yield strength and Poisson's ratio), and generates implicit stress field distribution through three-layer graph convolution (GCN) processing. The output layer regresses and calculates the first surface strength (unit: kN / m 2, with an accuracy of ±3%). Furthermore, 5,000 sets of surface strengths of parameterized surfaces under different working conditions can be obtained from an enterprise-level finite element sample library. This data is then divided into a training set, a validation set, and a test set with a ratio of 7:1.5:1.5. This serves as training data. The Huber loss function is then used to suppress outliers in the measurements, and the first surface strength is output. Convergence is considered achieved when the prediction accuracy on the validation set exceeds 95%, and training is terminated to obtain the surface strength analyzer. Finally, the test set is used to evaluate the model's generalization ability to ensure that it can accurately predict the first surface strength.

[0069] For example, the first multi-curvature surface information (such as curvature 0.20m -1 , material yield strength 300MPa) input to the surface strength analyzer, the output is the first surface strength (such as 85kN / m 2 ), the greater the strength of the first surface, the stronger the surface's ability to resist instability.

[0070] Secondly, the load-bearing information of the target surface is obtained, wherein the load-bearing information includes the load of the target surface, and the load-bearing load is the quantitative sum of all external forces that the surface structure needs to withstand during its service. For example, in the BIM system, the load-bearing load can be automatically obtained through a multi-level data fusion engine: first, the material property library (density, thickness) of the surface component is parsed to calculate the permanent load, and then the live load of the "Load Code" is intelligently matched according to the spatial function label; the geographic climate database is synchronously connected to generate the benchmark wind / snow load, and the non-uniform wind pressure distribution of the surface is calculated through the CFD plug-in, and finally the load combiner is used to calculate the load (for example, 90kN / m 2 ).

[0071] Finally, the design weight and the bearing weight are configured based on the bearing information and the first construction error parameter. Specifically, the ratio of the bearing information to the first curved surface strength is calculated, and the preset bearing weight is adjusted and calculated to obtain an adjusted bearing weight. The average construction error parameter is then obtained, and then the ratio of the average construction error parameter to the first construction error parameter is calculated. The preset design weight is adjusted and calculated to obtain an adjusted design weight. Finally, the design weight and the bearing weight are allocated and calculated based on the adjusted bearing weight and the adjusted design weight.

[0072] Furthermore, the “configuring the design weight and the bearing weight according to the bearing information and the first construction error parameter” includes:

[0073] Calculating a ratio of the load-bearing information to the first curved surface strength, and adjusting the preset load-bearing weight to obtain an adjusted load-bearing weight;

[0074] Get the average construction error parameter;

[0075] Calculating a ratio of the average construction error parameter to the first construction error parameter, and adjusting the preset design weight to obtain an adjusted design weight;

[0076] According to the adjusted bearing weight and the adjusted design weight, the design weight and the bearing weight are obtained by allocation calculation.

[0077] In the embodiment of the present application, the ratio of the bearing information to the first curved surface strength is first calculated, and the preset bearing weight is adjusted and calculated to obtain the adjusted bearing weight, wherein the adjusted bearing weight = The preset load weight is a load weight pre-set by those skilled in the art according to the actual application scenario, for example, 0.5. For example, the load information is 90kN / m 2 , the first surface strength is 85kN / m 2 , the default load weight is 0.5, then adjust the load weight = The greater the load-bearing information, the greater the external force that the target surface needs to withstand during service, and a larger weight needs to be configured. In this way, the preset load-bearing weight is adjusted and calculated based on the actual load-bearing information of the target surface. During the adjustment calculation process, when the load-bearing information is greater than the first surface strength, the weight is amplified, and when the load-bearing information is less than the first surface strength, the weight is reduced.

[0078] Secondly, obtain the average construction error parameter. For example, the enterprise-level historical engineering database can be used to retrieve surface information similar to the target surface and historical construction error parameters for application scenarios, and the average value can be taken to obtain the average construction error parameter. For example, the average construction error parameter calculated for a certain surface information and a specific application scenario is 4.5%. The average construction error parameter reflects the historical average construction error situation, and the first construction error parameter can be corrected and calculated based on this.

[0079] Next, the ratio of the average construction error parameter to the first construction error parameter is calculated, and the preset design weight is adjusted to obtain the adjusted design weight, wherein the adjusted design weight = ( The preset design weight is a design weight pre-set by those skilled in the art based on the actual application scenario, for example, 0.5. For example, if the average construction error parameter is 4.5%, the first construction error parameter is 5.2%, and the preset design weight is 0.5, then the adjusted design weight = First, the larger the construction error parameter, the greater the construction difficulty and the lower the design feasibility, and a smaller design weight needs to be configured. In this way, the preset design weight is adjusted and calculated based on the average construction error parameter.

[0080] Finally, based on the adjusted bearing weight and the adjusted design weight, the design weight and bearing weight are allocated and calculated, where the design weight = adjusted design weight / (adjusted bearing weight + adjusted design weight), and the bearing weight = adjusted bearing weight / (adjusted bearing weight + adjusted design weight). For example, if the adjusted design weight is 0.43 and the adjusted bearing weight is 0.53, then the design weight = 0.43 / (0.43 + 0.53) = 0.45, and the bearing weight = 0.53 / (0.43 + 0.53) = 0.55.

[0081] In summary, compared with the existing technology, this application analyzes the first surface strength of the first multi-curvature surface information, obtains the load-bearing information of the target surface, and configures the design weight and load-bearing weight based on the load-bearing information and the first construction error parameter, thereby providing necessary data support for subsequent design optimization.

[0082] S40: Calculating the first design rationality parameter and the first curved surface strength according to the design weight and the load-bearing weight to obtain the first curved surface design fitness, performing multi-curvature curved surface design optimization, and obtaining optimal multi-curvature curved surface information.

[0083] In the above steps, the design feasibility and safety performance of the surface are taken into consideration. Therefore, the surface design optimization can be carried out based on this. By adjusting the surface design parameters and iterative optimization, the optimal multi-curvature surface information can be obtained.

[0084] In response to the above problems, this application calculates the first design rationality parameter and the first surface strength based on the design weight and the load-bearing weight, obtains the first surface design adaptability, performs multi-curvature surface design optimization, and obtains the optimal multi-curvature surface information.

[0085] Specifically, step S40 in the method includes:

[0086] Obtain average design rationality parameters;

[0087] Calculating a ratio of the first design rationality parameter to an average design rationality parameter to obtain a first design coefficient, and calculating a ratio of the first curved surface strength to the load-bearing information to obtain a first load-bearing coefficient;

[0088] Using the design weight and the load weight, a weighted calculation is performed on the first design coefficient and the first load coefficient to obtain a first curved surface design fitness;

[0089] The design optimization of the multi-curvature surface information is continued, and after convergence, the optimal multi-curvature surface information with the maximum surface design fitness is obtained.

[0090] In the present embodiment, an average design rationality parameter is first obtained. For example, the average design rationality parameter can be obtained by searching historical similar projects and calculating them. Alternatively, the average design rationality parameter can be used as a horizontal comparison benchmark for the current surface design rationality based on a preset industry benchmark value in the BIM model library (e.g., the average design rationality parameter for a certain surface design field is 75).

[0091] Next, the ratio of the first design rationality parameter to the average design rationality parameter is calculated to obtain a first design coefficient, and the ratio of the first curved surface strength to the load-bearing information is calculated to obtain a first load-bearing coefficient, wherein the first design coefficient = the first design rationality parameter / the average design rationality parameter, and the first load-bearing coefficient = the first curved surface strength / the load-bearing information. For example, the first design rationality parameter is 80, the average design rationality parameter is 75, and the first curved surface strength is 85 kN / m 2 , the load information is 90kN / m 2 , then the first design coefficient = 80 / 75 = 1.1, and the first load coefficient = 85 / 90 = 0.94.

[0092] Again, the design weight and the load weight are used to perform weighted calculation on the first design coefficient and the first load coefficient to obtain the first surface design fitness, where the first surface design fitness = For example, the design weight is 0.45, the load weight is 0.55, the first design coefficient is 1.1, and the first load coefficient is 0.94, then the first surface design fitness = ,In this way, the design and actual load conditions are comprehensively considered, ,and the current surface design fitness is quantitatively analyzed.,The greater the first surface design fitness is, the better the current design scheme is.

[0093] Finally, the multi-curvature surface design optimization is continued, and after convergence, the optimal multi-curvature surface information with the highest surface design fitness is obtained. For example, by adjusting the surface curvature distribution, reducing the curvature mutation, increasing the local surface thickness, and improving the strength, the fitness converges after 5 iterations, and the optimal multi-curvature surface information is obtained.

[0094] In summary, compared with the existing technology, the present application calculates the first design rationality parameter and the first surface strength according to the design weight and the load-bearing weight, obtains the first surface design adaptability, performs multi-curvature surface design optimization, and obtains the optimal multi-curvature surface information. In this way, the design and actual load-bearing safety conditions are comprehensively considered, and the optimal multi-curvature surface information is obtained through iterative optimization.

[0095] In summary, the embodiments of the present application have at least the following technical effects:

[0096] Compared with the existing technology, this application first obtains the first multi-curvature surface information of the target surface designed using BIM, processes it to obtain the first curvature mutation degree, inputs the design rationality classification table, and classifies it to obtain the first design rationality parameter. In this way, the abstract geometric characteristics (curvature mutation degree) are converted into quantifiable design rationality parameters.

[0097] Secondly, this application performs construction error analysis based on the first multi-curvature surface information, processes to obtain the first construction error parameter, corrects the first design rationality parameter, and obtains the first corrected design rationality parameter. In this way, the first design rationality parameter is corrected from the construction feasibility level through the curvature error amplitude, providing reliable support for subsequent design optimization.

[0098] Again, this application analyzes the first surface strength of the first multi-curvature surface information, obtains the load-bearing information of the target surface, and configures the design weight and load-bearing weight based on the load-bearing information and the first construction error parameter, thereby providing necessary data support for subsequent design optimization.

[0099] Finally, this application calculates the first design rationality parameter and the first surface strength based on the design weight and the load-bearing weight, obtains the first surface design adaptability, performs multi-curvature surface design optimization, and obtains the optimal multi-curvature surface information. In this way, the design and actual load-bearing safety conditions are comprehensively considered, and the optimal multi-curvature surface information is obtained through iterative optimization.

[0100] Through the above technical solution, this application deeply integrates artificial intelligence models with BIM technology, comprehensively considers factors such as design aesthetics, design feasibility, and load-bearing safety in the design process, and uses quantitative surface design adaptability to evaluate different design schemes. After multiple rounds of iterative optimization of design schemes, the optimal multi-curvature surface information is obtained. In this way, design optimization is achieved and many defects in the design scheme are effectively avoided.

[0101] Example 2, as Figure 2 As shown, based on the same inventive concept as the multi-curvature surface modeling optimization method based on BIM technology provided in Example 1, the embodiment of the present invention also provides a multi-curvature surface modeling optimization system based on BIM technology, including:

[0102] A rationality evaluation module 11 is configured to obtain first multi-curvature surface information of a target surface designed using BIM, process and obtain a first curvature mutation degree, and classify and obtain a first design rationality parameter;

[0103] an error correction module 12, configured to perform construction error analysis based on the first multi-curvature surface information, obtain a first construction error parameter, and correct the first design rationality parameter to obtain a first corrected design rationality parameter;

[0104] A weight configuration module 13 is configured to analyze the first surface strength of the first multi-curvature surface information, obtain the load-bearing information of the target surface, and configure a design weight and a load-bearing weight in combination with the first construction error parameter;

[0105] The fitness optimization module 14 is used to calculate the first design rationality parameter and the first surface strength according to the design weight and the load weight, obtain the first surface design fitness, perform multi-curvature surface design optimization, and obtain optimal multi-curvature surface information.

[0106] The rationality evaluation module 11 is specifically used to:

[0107] Acquire first multi-curvature surface information of a target surface designed using BIM, wherein the first multi-curvature surface information includes a plurality of connected first curvature surfaces, each of which includes first curvature information;

[0108] Calculating the curvature deviation amplitude of the first curvature information of every two adjacent first curvature surfaces to obtain multiple curvature deviation amplitudes, and calculating the average to obtain the first curvature mutation degree;

[0109] According to the first curvature mutation degree, a first design rationality parameter is obtained through classification.

[0110] Furthermore, the “obtaining a first design rationality parameter by classification according to the first curvature mutation degree” includes:

[0111] According to the design data records of multi-curvature surfaces, a set of sample curvature mutations is collected, and the design rationality levels of different sample curvature mutations are marked to obtain a set of sample design rationality parameters. Among them, the sample curvature mutation is negatively correlated with the sample design rationality parameters.

[0112] Based on the sample curvature mutation degree set and the sample design rationality parameter set, construct a plurality of design rationality mapping pairs and construct a design rationality classification table;

[0113] The first curvature mutation degree is input into the design rationality classification table, and the first design rationality parameter is obtained through classification mapping.

[0114] The error correction module 12 is specifically configured to:

[0115] Inputting the first multi-curvature surface information into a construction error predictor, and predicting and outputting a first construction error parameter, wherein the construction error predictor is constructed based on machine learning and trained using a sample multi-curvature surface information set and a sample construction error parameter set, and the first construction error parameter includes a construction curvature error amplitude;

[0116] The first design rationality parameter is corrected according to the first construction error parameter to obtain a first corrected design rationality parameter.

[0117] Furthermore, the “correcting the first design rationality parameter according to the first construction error parameter to obtain a first corrected design rationality parameter” includes:

[0118] Get the allowable construction error parameters;

[0119] The ratio of the allowable construction error parameter to the first construction error parameter is calculated, and the first design rationality parameter is corrected and calculated to obtain a first corrected design rationality parameter.

[0120] The weight configuration module 13 is specifically configured to:

[0121] Inputting the first multi-curvature surface information into a surface strength analyzer, and outputting a first surface strength, wherein the surface strength analyzer is trained using a sample multi-curvature surface information set and a sample surface strength set;

[0122] Acquiring bearing information of the target curved surface, wherein the bearing information includes the bearing load of the target curved surface;

[0123] The design weight and the bearing weight are configured according to the bearing information and the first construction error parameter.

[0124] Furthermore, the “configuring the design weight and the bearing weight according to the bearing information and the first construction error parameter” includes:

[0125] Calculating a ratio of the load-bearing information to the first curved surface strength, and adjusting the preset load-bearing weight to obtain an adjusted load-bearing weight;

[0126] Get the average construction error parameter;

[0127] Calculating a ratio of the average construction error parameter to the first construction error parameter, and adjusting the preset design weight to obtain an adjusted design weight;

[0128] According to the adjusted bearing weight and the adjusted design weight, the design weight and the bearing weight are obtained by allocation calculation.

[0129] The fitness optimization module 14 is specifically configured to:

[0130] Obtain average design rationality parameters;

[0131] Calculating a ratio of the first design rationality parameter to an average design rationality parameter to obtain a first design coefficient, and calculating a ratio of the first curved surface strength to the load-bearing information to obtain a first load-bearing coefficient;

[0132] Using the design weight and the load weight, a weighted calculation is performed on the first design coefficient and the first load coefficient to obtain a first curved surface design fitness;

[0133] The design optimization of the multi-curvature surface information is continued, and after convergence, the optimal multi-curvature surface information with the maximum surface design fitness is obtained.

[0134] In summary, the embodiments of the present application have at least the following technical effects:

[0135] Compared with the existing technology, the present application first obtains the first multi-curvature surface information of the target surface designed using BIM through a rationality assessment module, processes and obtains the first curvature mutation, classifies and obtains the first design rationality parameter, and converts the abstract geometric characteristics (curvature mutation) into quantifiable design rationality parameters. Secondly, through the error correction module, construction error analysis is performed based on the first multi-curvature surface information, and the first construction error parameter is obtained through processing. The first design rationality parameter is corrected to obtain the first corrected design rationality parameter. The first design rationality parameter is corrected from the perspective of construction feasibility, providing reliable support for subsequent design optimization. Thirdly, through the weight configuration module, the first surface strength of the first multi-curvature surface information is analyzed to obtain the load-bearing information of the target surface. The design weight and load-bearing weight are configured in combination with the first construction error parameter, providing necessary data support for subsequent design optimization. Finally, the fitness optimization module calculates the first design rationality parameters and the first surface strength based on the design weight and load-bearing weight, obtaining the first surface design fitness. Multi-curvature surface design optimization is then performed to obtain the optimal multi-curvature surface information. This optimal multi-curvature surface information is obtained through iterative optimization, taking into account both the design and actual load-bearing safety conditions. In this way, different design solutions are evaluated using quantitative surface design fitness. After multiple rounds of design optimization, the optimal multi-curvature surface information is obtained, achieving design optimization and effectively avoiding many design flaws.

[0136] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0137] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0138] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0139] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0141] Although preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts become known.

[0142] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. The multi-curvature surface modeling optimization method based on BIM technology is characterized by: The method comprises: Acquire first multi-curvature surface information of a target surface designed using BIM, process to obtain a first curvature mutation, and classify to obtain a first design rationality parameter; Performing a construction error analysis based on the first multi-curvature surface information to obtain a first construction error parameter, and correcting the first design rationality parameter to obtain a first corrected design rationality parameter; Analyzing the first surface strength of the first multi-curvature surface information, obtaining the load-bearing information of the target surface, and configuring the design weight and the load-bearing weight in combination with the first construction error parameter; According to the design weight and the load-bearing weight, the first correction design rationality parameter and the first surface strength are calculated to obtain the first surface design fitness, and the multi-curvature surface design optimization is performed to obtain the optimal multi-curvature surface information.

2. The multi-curvature surface modeling optimization method based on BIM technology according to claim 1 is characterized in that: Acquire first multi-curvature surface information of the target surface designed using BIM, process to obtain a first curvature mutation, and classify to obtain a first design rationality parameter, including: Acquire first multi-curvature surface information of a target surface designed using BIM, wherein the first multi-curvature surface information includes a plurality of connected first curvature surfaces, each of which includes first curvature information; Calculating the curvature deviation amplitude of the first curvature information of every two adjacent first curvature surfaces to obtain multiple curvature deviation amplitudes, and calculating the average to obtain the first curvature mutation degree; According to the first curvature mutation degree, a first design rationality parameter is obtained through classification.

3. The multi-curvature surface modeling optimization method based on BIM technology according to claim 2 is characterized in that: According to the first curvature mutation degree, a first design rationality parameter is obtained by classification, including: According to the design data records of multi-curvature surfaces, a set of sample curvature mutations is collected, and the design rationality levels of different sample curvature mutations are marked to obtain a set of sample design rationality parameters. Among them, the sample curvature mutation is negatively correlated with the sample design rationality parameters. Based on the sample curvature mutation degree set and the sample design rationality parameter set, construct a plurality of design rationality mapping pairs and construct a design rationality classification table; The first curvature mutation degree is input into the design rationality classification table, and the first design rationality parameter is obtained through classification mapping.

4. The multi-curvature surface modeling optimization method based on BIM technology according to claim 1 is characterized in that: Performing a construction error analysis based on the first multi-curvature surface information to obtain a first construction error parameter, and correcting the first design rationality parameter to obtain a first corrected design rationality parameter, including: Inputting the first multi-curvature surface information into a construction error predictor, and predicting and outputting a first construction error parameter, wherein the construction error predictor is constructed based on machine learning and trained using a sample multi-curvature surface information set and a sample construction error parameter set, and the first construction error parameter includes a construction curvature error amplitude; The first design rationality parameter is corrected according to the first construction error parameter to obtain a first corrected design rationality parameter.

5. The multi-curvature surface modeling optimization method based on BIM technology according to claim 4 is characterized in that: Correcting the first design rationality parameter according to the first construction error parameter to obtain a first corrected design rationality parameter includes: Get the allowable construction error parameters; The ratio of the allowable construction error parameter to the first construction error parameter is calculated, and the first design rationality parameter is corrected and calculated to obtain a first corrected design rationality parameter.

6. The multi-curvature surface modeling optimization method based on BIM technology according to claim 1 is characterized in that: Analyzing the first surface strength of the first multi-curvature surface information, obtaining the load-bearing information of the target surface, and configuring the design weight and the load-bearing weight in combination with the first construction error parameter, including: Inputting the first multi-curvature surface information into a surface strength analyzer, and outputting a first surface strength, wherein the surface strength analyzer is trained using a sample multi-curvature surface information set and a sample surface strength set; Acquiring bearing information of the target curved surface, wherein the bearing information includes the bearing load of the target curved surface; The design weight and the bearing weight are configured according to the bearing information and the first construction error parameter.

7. The multi-curvature surface modeling optimization method based on BIM technology according to claim 6 is characterized in that: Configuring a design weight and a bearing weight according to the bearing information and the first construction error parameter includes: Calculating a ratio of the load-bearing information to the first curved surface strength, and adjusting the preset load-bearing weight to obtain an adjusted load-bearing weight; Get the average construction error parameter; Calculating a ratio of the average construction error parameter to the first construction error parameter, and adjusting the preset design weight to obtain an adjusted design weight; According to the adjusted bearing weight and the adjusted design weight, the design weight and the bearing weight are obtained by allocation calculation.

8. The multi-curvature surface modeling optimization method based on BIM technology according to claim 1 is characterized in that: Calculating the first correction design rationality parameter and the first curved surface strength to obtain the first curved surface design fitness, performing multi-curvature curved surface design optimization, and obtaining optimal multi-curvature curved surface information, including: Obtain average design rationality parameters; Calculating a ratio of the first corrected design rationality parameter to the average design rationality parameter to obtain a first design coefficient, and calculating a ratio of the first curved surface strength to the load-bearing information to obtain a first load-bearing coefficient; Using the design weight and the load weight, a weighted calculation is performed on the first design coefficient and the first load coefficient to obtain a first curved surface design fitness; The design optimization of the multi-curvature surface information is continued, and after convergence, the optimal multi-curvature surface information with the maximum surface design fitness is obtained.

9. The multi-curvature surface modeling optimization system based on BIM technology is characterized by: Used to perform the method according to any one of claims 1 to 8, comprising: A rationality evaluation module is used to obtain first multi-curvature surface information of a target surface designed using BIM, process and obtain a first curvature mutation degree, and classify and obtain a first design rationality parameter; an error correction module, configured to perform construction error analysis based on the first multi-curvature surface information, obtain a first construction error parameter, and correct the first design rationality parameter to obtain a first corrected design rationality parameter; a weight configuration module, configured to analyze the first surface strength of the first multi-curvature surface information, obtain the load-bearing information of the target surface, and configure the design weight and the load-bearing weight in combination with the first construction error parameter; The fitness optimization module is used to calculate the first correction design rationality parameter and the first surface strength according to the design weight and the load weight, obtain the first surface design fitness, perform multi-curvature surface design optimization, and obtain optimal multi-curvature surface information.

Images