> Summary

The purpose of this thesis is to investigate design concepts using AI-generated patterns in shell structures. After selecting perforation patterns found in nature, the author trains an AI model to generate new patterns based on the training data. The aim of this research is to compare natural and AI-generated patterns to verify if the AI model generates a bigger variety of patterns while maintaining good structural performance. 

The AI model used in this thesis is a Variational AUtoencoder (VAE). 

The steps followed in building the model are: 

• Creating a continuous and uniform database by defining the parametric grashopper model variables such that generated 3D models have similarities 

• Formulating a parametric model in Grasshopper to create 3D models of lattice patterns 

• Augmentation of the Grasshopper-generated data for the deep convolutional neural networks to run properly 

• Training a VAE model with 80% of the data in the dataset and using the rest of the data to validate the training 

Following the training of the VAE model, numerous variations of 2D image patterns were generated. The author selected the most distinct patterns and extracted the sharper ones to edit.  

To use the generated patterns in the conceptual design phase of shell structures, a workflow was created. It contains the following steps: 

• Extraction of the geometries from a 2D image which is translated to a data structure that can be used to control a parametric model 

• Creating the shell form where the pattern will morph onto 

• Morphing the pattern on the shell 

• Performing FEM analysis on the morphed shell to check its structural performance 

LIMITATIONS: The dataset used to train the AI contains only 2D images of cellular solid structures.  The dataset was limited to small number of patterns.