Automatic Parametric Modeling Technique for Structural Design Standardization

Abstract

The challenge in designing new three-dimensional (3D) shapes is that considerable manual effort is required for repeated designing and verification to satisfy the required specifications. Extracting and standardizing parametric design rules from a designed 3D shape dataset will be useful for drastically reducing the design time. This paper describes a framework of automatically generating parametric models, design rules, in order to standardize designs for structural systems. In this framework, a design dataset whose dimensions and shapes have parametric relationships with a target shape is extracted using a new retrieval method. This method is an improvement of a conventional similar shape retrieval method. After the extraction of the design dataset, the corresponding parts between the collected shapes are automatically identified and parametric models are automatically generated. This new similar shape retrieval method has two improvements over the conventional method that uses images of 3D shapes captured from multiple directions. First, 3D shapes are converted to unit shapes by stretching or shrinking along each axis. Second, similar shapes are extracted using a special artificial intelligence (AI) model that learns parametric relationships. The effectiveness of the proposed framework is evaluated using the 3D shape data of various structural shapes. Although the accuracy rate of similar-shape retrieval based on parametric relationships was 62% in the conventional method, by using unit shapes and special AIs, it was improved to 99% in the new method. Moreover, the corresponding parts between similar shapes were automatically identified, and parametric models were automatically generated. The effectiveness of this framework has been demonstrated.

Keywords

• Automatic design
• image recognition AI
• parametric model
• similar shape retrieval
• standardization
• unit shape