Physical-data driven intelligent shear wall building structure design method and device

Abstract

The invention provides a physics-data driven intelligent shear wall building structure design method and device. The method comprises the steps of obtaining a to-be-processed building design drawing and a basic condition text, inputting the building design drawing and the basic condition text into a structure design model to obtain a structure design drawing, wherein the structure design model is obtained by performing structure design drawing generation capability training and physical performance optimization training on a physical-data driven generative adversarial network, vectorizing the structure design drawing and the building design drawing to obtain a structure design result of the shear wall building. According to the physical-data-driven intelligent shear wall building structure design method and device provided by the invention, structure design drawing generation capability training and physical performance optimization are performed on the physical-data-driven generative adversarial network; the obtained structure design model can generate a structure design drawing better meeting actual design requirements according to a building design drawing and a basic condition text, and the structure design efficiency and reliability are improved.

Description

Technical field [0001] The present invention relates to the field of building structural design and machine learning, in particular, to a physical-data-driven intelligent shear wall building structure design method and apparatus. Background technique [0002] At present, the structural plan for shear wall buildings is generally completed by experienced engineers. Due to excessive management experience, it is difficult to effectively promote applications, and the labor design process consumes time consuming, the intelligence is insufficient, and the efficiency is low. In order to meet the rapid development needs of intelligent construction, the intelligent structure design method came into being. [0003] However, due to the physical law of structural design, the expression of the image data is significantly different from the expression of the image data, so that the neural network can only be effective in learning the image data characteristics, and cannot read and learn physics...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a physical-data-driven intelligent shear wall building structure design method and device to solve the problem that the shear wall building structure design method in the prior art cannot simultaneously learn physical laws and data experience through intelligent algorithms, resulting in Defects of low referenceability of structural design results

Images