Derivative BIM component automatic generation method based on i-GBDT technology
An automatic generation and component technology, applied in the field of BIM modeling, can solve problems such as drawing accuracy errors, poor matching and compatibility, poor drawing standardization, etc., and achieve the effect of improving efficiency and extraction efficiency
Active Publication Date: 2022-08-02
CHUZHOU UNIV +3
View PDF11 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003]
At present, the algorithms and functions of the existing mainstream BIM modeling software in China are poor in matching and compatibility with design and construction drawings, and the problem of drawing accuracy errors caused by poor drawing standardization is further amplified. Therefore, a more effective method is needed. The automatic modeling method combined with the artificial intelligence recognition algorithm can reduce the influence of drawing accuracy on the modeling software, so as to realize the real "turnover" and bring new opportunities for the development of BIM technology
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0041] The invention provides a method for automatically generating generative BIM components based on i-GBDT technology. As shown in Figure 1-6:
[0042] The present invention automatically generates instances based on Revit-based BIM structural components:
[0043] Taking the construction drawing of a building structure as the object of turning over the model, through the establishment of a data set, the convolutional neural network recognizes the image, the i-GBDT creates a decision tree, and finally the image data is exported. Refer to the specific steps figure 1 The shown process is implemented, including the following steps:
[0044] Step 1: Use Navicat to create a MySQL database and enter the construction drawings of the beam leveling method as the data set identified by the beam leveling method. Based on the Python3-TensorFlow open source machine learning platform, input the VGG16 source code for training, and get the trained convolutional layer.
[0045] Step 2: I...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a derivative BIM component automatic generation method based on an i-GBDT technology. The method comprises the steps that a basic data set is established based on a standard construction drawing; identifying and extracting image features of the proposed construction drawing through the trained convolutional neural network, performing feature processing in cooperation with a ReLU nonlinear activation function, and outputting component image information in the construction drawing; establishing an initial learning device through a gradient decision tree algorithm, calculating a loss function gradient value, carrying out continuous iteration, and carrying out linear optimization to calculate an optimal learning rate so as to obtain an optimal classifier; taking component size information in the basic data set as attribute parameters, entering an optimal classifier to predict and analyze the identified construction drawing component image information, and outputting component image information with high fitting degree; component image information obtained through prediction serves as output data, parameter matching is conducted on the output data and a standard construction drawing in the basic data set, and IFC format information is generated; and importing the IFC format information into BIM modeling software, and automatically generating a corresponding BIM model.
Description
technical field [0001] The invention relates to the technical field of BIM modeling, in particular to an automatic generation method for generative BIM components based on i-GBDT technology. Background technique [0002] As a representative, BIM technology has been widely used in the planning, design, construction and operation stages of the engineering construction field, and has exerted energy efficiency in many industries such as hydropower and transportation. As the underlying information carrier of BIM technology implementation, BIM model's modeling efficiency directly affects the depth of BIM technology promotion and application. [0003] At present, the algorithms and functions of the existing mainstream BIM modeling software in China have poor matching and compatibility with design and construction drawings. The problem of the influence of drawing accuracy errors caused by poor drafting standardization has been further magnified. Therefore, a more effective method is...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/13G06N3/04G06N3/08
CPCG06F30/13G06N3/08G06N3/045
Inventor 张昊周逸飞姜亚洲苏玛拉.德拉戈斯拉夫曹茂森德拉霍米尔·诺瓦克崔丽
Owner CHUZHOU UNIV