About the Instructor

Mahdi Fard


Mahdi Fard is an architect, computational designer and lead developer of Caddisfly 01.01, an exclusive Grasshopper3D add-on for detail designing free-from structures which brought up Ardaena.com as a network for professionals. He is known for his research on integrated design in architecture. Mahdi works with data flows from different disciplines especially when it comes to engineering design, through a diverse range of algorithmic engineering consultancy for projects in Iran. His research is now dedicated to artificial intelligence, and is working on generative design based on functional paradigms through geometry.


Course curriculum

    1. Introduction

    2. Course Files

    3. Introduction: Structural Free-Form Intelligent Data Manipulation by Machine Learning (ML)

    4. Free-Form Structure Generator Definition in Grasshopper3D

    5. Karamba3D - Recording DATA and Iterations

    6. Machine learning Process - Recursive one via Py

    7. Power Bi - Bonus Lesson

About this course

  • 7 lessons


Prerequisite Plug-ins, covering the 3 major sections besides Grasshopper3D (GH)

  1. Design: WeaverBird, Kangaroo, Mesh +, LunchBox

  2. Engineering: Karamba3D, TTtoolBox, Galapagos, Python 3.0, Anaconda 3, Jupyter Notebook (Py Packages: NumPy, Pandas, Seaborn, MatplotLib), Microsoft Excel

  3. Data Structures: No Plugin here but GH

Description

The idea of using Karamba3D is found upon having design and analysis in an integrated mode towards optimization processes. This is the main stream of this workshop comprises the path to understand how design works accentuated via material impact, different load cases, how form follows forces, diversity of supports’ locations and more importunate of whether design iterations are qualified enough to be considered reliable to discuss as an optimized iteration.

The joint section would be set by using different machine learning (ML) approaches to surrogate optimization results in a feature based clustering setting. We will use *.csv files and logs as our reports, dedicate the clustering to study which design has what characteristic.

Accordingly, we are going to use Jupyter Notebook via Anaconda, so every aspect of such a procedure could be achieved conveniently. The final back and forth data collection, model generation and optimization would be converged to ML based analysis. It is assumed that every group could demonstrate the whole open-source surrogate optimization that is to suggest by this workshop, as a procedure of how data manipulation besides high qualified algorithms can make a difference within conceptual structural analysis towards a reliable yet flexible decision-making.

  • Base Modeling with Kangaroo

  • Structural Analysis via Karamba3D

  • GA Optimization and Data Recording

  • K-Means Clustering via Python, Anaconda and Jupyter

Start learning

Available Now

Mahdi Fard is a leading computational designer and machine learning researcher, teaching on Performance Network, DigitalFUTURES World, and ParametricArchitecture. We have created a dedicated learning channel to provide you with his latest research on freeform structures, artificial intelligence and generative design.
Get started