CN-122020827-A - Low-carbon assembled building simulation design method and system based on three-dimensional model

CN122020827ACN 122020827 ACN122020827 ACN 122020827ACN-122020827-A

Abstract

The application relates to the technical field of low-carbon assembly type building simulation design, in particular to a three-dimensional model-based low-carbon assembly type building simulation design method and system, wherein the method comprises the steps of constructing a three-dimensional BIM model of an assembly type building, and obtaining performance data of each assembly node in each dimension in a preset simulation period in a real-time simulation manner; the method comprises the steps of obtaining performance controllable evaluation values of all assembly nodes, obtaining comprehensive performance scores and performance reliability indexes of all assembly nodes, obtaining performance variation ranges and failure probabilities of all assembly nodes under random working conditions, updating performance prediction values of all assembly nodes, and realizing low-carbon assembly type building simulation design based on a three-dimensional model. According to the application, the sampling convergence efficiency can be greatly improved on the premise of ensuring the simulation precision, so that the fine performance evaluation and low-carbon optimization design of the assembly node are realized.

Inventors

LUO ZHIXING
LU MEI

Assignees

西安建筑科技大学

Dates

Publication Date: 20260512
Application Date: 20260415

Claims (10)

1. The low-carbon assembled building simulation design method based on the three-dimensional model is characterized by comprising the following steps of: constructing a three-dimensional BIM model of the fabricated building, and performing real-time simulation to obtain performance data of each fabricated node in each dimension in a preset simulation period; Analyzing all performance data by using a fuzzy comprehensive evaluation algorithm and an objective weighting method to obtain performance controllable evaluation values of all assembly nodes, wherein the performance controllable evaluation values are used for measuring the comprehensive performance excellent degree of all the assembly nodes in all the dimensions, and further extracting the potential feature scores of all the assembly nodes in all the dimensions by combining a dimension reduction analysis method so as to represent the performance quality degree of all the assembly nodes in all the dimensions; the method comprises the steps of obtaining comprehensive performance scores of all assembly nodes through all performance data, training an integrated learning regression model through potential feature scores and comprehensive performance scores obtained through calculation by utilizing historical performance data, predicting the comprehensive performance scores of all the assembly nodes based on the potential feature scores by using the trained integrated learning regression model, and further obtaining performance reliability indexes of all the assembly nodes; And based on the performance reliability index, the sampling distribution of the Monte Carlo simulation method is adaptively adjusted to obtain the performance variation range and the failure probability of each assembly node under the random working condition, and the performance variation range and the failure probability are integrated into a three-dimensional BIM model, so that the performance prediction value of each assembly node is updated to realize the low-carbon assembly type building simulation design based on the three-dimensional model.
2. The three-dimensional model-based low-carbon fabricated building simulation design method of claim 1, wherein the performance data comprises: stress data, deformation data and ultimate bearing capacity data under the structural safety dimension; surface temperature data, heat flux density data and heat bridge effect intensity data under the thermal energy-saving dimension; Actual installation deviation data and component clearance data in the construction quality dimension.
3. The three-dimensional model-based low-carbon fabricated building simulation design method according to claim 1, wherein the performance controllable evaluation value obtaining process is as follows: the method comprises the steps of taking performance data in all dimensions as input of a fuzzy comprehensive evaluation algorithm, outputting membership vectors of all assembly nodes in all dimensions, and calculating to obtain membership scores of all assembly nodes in all dimensions by combining score vectors corresponding to preset comment sets; And the performance controllable evaluation value is obtained through the membership score and the weight obtained by using an objective weighting method.
4. The three-dimensional model-based low-carbon fabricated building simulation design method of claim 3, wherein the performance controllable evaluation value is a weighted sum of membership scores of all the dimensions of each fabricated node, and wherein the weight of the membership score of each fabricated node in each dimension is a weight of each dimension obtained by using an objective weighting method.
5. The three-dimensional model-based low-carbon fabricated building simulation design method according to claim 1, wherein the potential feature score obtaining process is as follows: According to the performance data of each assembly node in each dimension and the performance controllable evaluation value of each assembly node, a factor analysis method is adopted to obtain the factor score of each assembly node in each factor, and the factor score is used as the potential feature score of each assembly node in each dimension.
6. The three-dimensional model-based low-carbon fabricated building simulation design method according to claim 3, wherein the comprehensive performance score obtaining process is as follows: calculating the average value of the normalized values of the performance data of each assembly node in each dimension, recording the average performance level of each assembly node in each dimension, and taking the weighted sum of the average performance levels of each assembly node in all dimensions as the comprehensive performance score of each assembly node, wherein the weight of the average performance level of each assembly node in each dimension is the weight of each dimension obtained by using an objective weighting method.
7. The three-dimensional model-based low-carbon fabricated building simulation design method as set forth in claim 1, wherein the performance reliability index is obtained by the following steps: and predicting the comprehensive performance scores of all the assembly nodes by using each basic regression model in the ensemble learning regression model, and taking the average value of the comprehensive performance scores of all the assembly nodes obtained by predicting all the basic regression models as the performance reliability index of each assembly node.
8. The three-dimensional model-based low-carbon fabricated building simulation design method according to claim 1, wherein the adaptively adjusting the sampling distribution of the monte carlo simulation based on the performance reliability index comprises: The variance of normal sampling distribution is adjusted by utilizing the performance reliability index of each assembly node, specifically, the initial variance obtained based on measurement data in the historical actual engineering is amplified by the performance reliability index, and the larger the performance reliability index is, the smaller the amplifying effect of the initial variance is, otherwise, the larger the amplifying effect of the initial variance is.
9. The three-dimensional model-based low-carbon fabricated building simulation design method according to claim 8, wherein the variance adjustment formula is: In the formula (I), in the formula (II), Representing the adjusted normal sampling distribution variance; Representing an initial variance; a performance reliability index representing the assembly node; Representing a preset adjustment intensity coefficient; representing a sigmoid function.
10. A three-dimensional model-based low-carbon fabricated building simulation design system comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor, when executing the computer program, implements the steps of the three-dimensional model-based low-carbon fabricated building simulation design method according to any one of claims 1 to 9.

Description

Low-carbon assembled building simulation design method and system based on three-dimensional model Technical Field The application relates to the technical field of low-carbon assembly type building simulation design, in particular to a three-dimensional model-based low-carbon assembly type building simulation design method and system. Background The low-carbon assembly type building simulation design of the three-dimensional model is based on three-dimensional digital technologies such as a BIM model and the like, and the full-flow simulation is carried out on the construction mode of prefabricated components and field assembly, so that the field is popularized along with the BIM technology, and the development of the field is realized from the early geometric model display to a collaborative simulation platform of an integrated structure and a carbon footprint. Through the virtual construction optimization scheme, material waste and field energy consumption are greatly reduced, assembly precision and construction efficiency are improved, and construction period is shortened. The connection behavior of the assembly node has high complexity and relates to the coupling effect of various physical processes such as material nonlinearity, contact friction, grouting material solidification and the like. Meanwhile, uncertain factors such as deviation of installation positions, insufficient grouting compactness and the like exist in actual construction. In the prior art, local node mechanics simulation is mainly performed by means of high-precision finite element analysis, however, in the prior art, a simplified model is generally adopted for pursuing efficiency, comprehensive influence under a multi-factor coupling environment is difficult to consider, and a simulation result is difficult to support fine performance evaluation and low-carbon optimization design of an assembly node. Disclosure of Invention In view of the above, it is necessary to provide a three-dimensional model-based low-carbon fabricated building simulation design method and system, which can greatly improve sampling convergence efficiency on the premise of ensuring simulation accuracy, so as to realize fine performance evaluation and low-carbon optimization design of assembly nodes, compared with the traditional three-dimensional model-based low-carbon fabricated building simulation design method: in a first aspect, an embodiment of the present application provides a three-dimensional model-based low-carbon fabricated building simulation design method, including the steps of: constructing a three-dimensional BIM model of the fabricated building, and performing real-time simulation to obtain performance data of each fabricated node in each dimension in a preset simulation period; Analyzing all performance data by using a fuzzy comprehensive evaluation algorithm and an objective weighting method to obtain performance controllable evaluation values of all assembly nodes, wherein the performance controllable evaluation values are used for measuring the comprehensive performance excellent degree of all the assembly nodes in all the dimensions, and further extracting the potential feature scores of all the assembly nodes in all the dimensions by combining a dimension reduction analysis method so as to represent the performance quality degree of all the assembly nodes in all the dimensions; the method comprises the steps of obtaining comprehensive performance scores of all assembly nodes through all performance data, training an integrated learning regression model through potential feature scores and comprehensive performance scores obtained through calculation by utilizing historical performance data, predicting the comprehensive performance scores of all the assembly nodes based on the potential feature scores by using the trained integrated learning regression model, and further obtaining performance reliability indexes of all the assembly nodes; And based on the performance reliability index, the sampling distribution of the Monte Carlo simulation method is adaptively adjusted to obtain the performance variation range and the failure probability of each assembly node under the random working condition, and the performance variation range and the failure probability are integrated into a three-dimensional BIM model, so that the performance prediction value of each assembly node is updated to realize the low-carbon assembly type building simulation design based on the three-dimensional model. In one embodiment, the performance data includes: stress data, deformation data and ultimate bearing capacity data under the structural safety dimension; surface temperature data, heat flux density data and heat bridge effect intensity data under the thermal energy-saving dimension; Actual installation deviation data and component clearance data in the construction quality dimension. In one embodiment, the performance controllable evaluation value obtaining p