Design analysis method for dense array perforated wall plate
By constructing a neural network framework and training the neural network using finite element analysis cases, the problem of excessively long design and analysis time for dense array perforated wall panels was solved, enabling rapid and accurate design analysis and knowledge transfer.
CN121765831APending Publication Date: 2026-03-31CHENGDU AIRCRAFT DESIGN INST OF AVIATION IND CORP OF CHINA
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-04
- Publication Date
- 2026-03-31
AI Technical Summary
Technical Problem
The design and analysis of dense array perforated wall panels is too time-consuming, the mesh generation time is too long and the quality is difficult to guarantee, and there is a lack of efficient design and analysis methods.
Method used
A neural network framework is constructed, and the neural network is trained using component-level and structural-level finite element analysis cases. The equivalent stiffness is assigned through a non-perforated finite element model for rapid analysis. The neural network is then built to infer the equivalent stiffness of perforated wall panels of various forms.
Benefits of technology
It significantly shortens the design analysis time, improves design efficiency and quality, and enables the transfer of knowledge and experience.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN121765831A_ABST
Abstract
The invention belongs to the technical field of general structure design, and particularly relates to a design analysis method of a dense array perforated wallboard, aiming at the problem that the time for calculating the dense array perforated wallboard by a traditional finite element is too long, a neural network framework is constructed, and the method is used for analyzing the dense array perforated wallboard. A large number of element-level and structure-level finite element analysis cases of dense array openings are used as training samples of a neural network for network training, and finally the neural network achieves the function of rapidly extracting the equivalent stiffness of any dense array opening structure. A designer does not need to establish a finite element model with dense array trepanning characteristics, and only needs to establish a non-trepanning finite element model and then endow equivalent stiffness for analysis, so that the analysis time is greatly shortened. In addition, the established neural network looks like a'knowledge base 'which can be continuously accumulated and updated, so that the inheritance of knowledge and experience is realized.
Need to check novelty before this filing date? Find Prior Art