Back Back
Index Index Next Next

Thesis: Integrated bio-inspired Design by AI – Baruah

  • Intro
  • Technical Aspects

Information

Primary software used Python
Software version 1.0
Course Computational Intelligence for Integrated Design
Primary subject AI & ML
Secondary subject Machine Learning
Level Advanced
Last updated November 19, 2024
Keywords

Responsible

Teacher
Faculty

Thesis: Integrated bio-inspired Design by AI – Baruah 0/1

Thesis: Integrated bio-inspired Design by AI – Baruah link copied

Integrated bio-inspired Design by AI: Using cell structure patterns to train an AI model to explore topology design ideas – Namrata Baruah

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.

Baruah Video Presentation

APA: Baruah, N. (2022). Integrated Bio-Inspired Design by AI [Master thesis, TU Delft]. https://repository.tudelft.nl/record/uuid:6cc837f2-f9ff-4f23-af87-1ac4ba7fb5e6

Here you can find the repository of the master thesis Integrated bio-inspired Design by AI – Baruah

Project Information

  • Title: Integrated Bio-Inspired Design by AI
  • Author(s): Namrata Baruah
  • Year: 2022
  • Link: https://repository.tudelft.nl/record/uuid:6cc837f2-f9ff-4f23-af87-1ac4ba7fb5e6
  • Type: Master thesis, Building Technology
  • ML tags: Variational Autoencoder
  • Topic tags: Generative Design, Structure Design
Start Start

Thesis: Integrated bio-inspired Design by AI – Baruah 1/1

Technical Aspects link copied

Software & Plug-ins Used

  • Rhinoceros, Grasshopper for modelling the patterns of the cellular solids and testing of the AI model
  • Python using Tensor-Flow, Keras library for writing the AI model and CNN
  • Google Collab for coding the VAE model
  • Rhinoceros, Grasshopper, Karamba for the FEM analysis (structural performance analysis)

Workflow

Diagramatic representation of the Research Approach (Image copyright remains with paper author(s). Used with permission.)

Process

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

 

Sampling of Generated Patterns (Image Copyright remains with paper authors. Used with Permission.)

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.

New topology design ideas from generated patterns (Image Copyright remains with paper authors. Used with Permission.)

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.

Previous chapter Previous chapter Next chapter Next chapter