This course may be taken individually or as part of the Professional Certificate Program in Design & Manufacturing or the Professional Certificate Program in Machine Learning & Artificial Intelligence.
Over the next few decades, industries around the world will transition to a new economy in which highly complex, customizable products will be manufactured by on-demand flexible robotic systems. In a number of fields, this change is already underway—for example, 3D printers are revolutionizing the production of consumer, aerospace, automotive, and medical parts.
This course provides an introduction to developing intelligent design and manufacturing workflows. Over the course of five days, you will explore advanced manufacturing hardware and learn about methods for creating customizable design templates, and virtual product testing. In this course, you will also:
- Explore performance-driven and generative design workflows that automatically translate functional specifications of objects to manufacturable designs
- Discover AI/machine learning methods that enable design automation and customization
- Learn how AI methods can be used in a manufacturing workflow for automated inspections and improved performance
Participant Takeaways
- Learn how to develop an intelligent design and manufacturing workflow.
- Understand capabilities and limitations of current advanced manufacturing hardware.
- Understand geometric representations for digital manufacturing.
- Design and manufacture objects using advanced manufacturing.
- Learn how to mass customize designs using parametric models.
- Learn how to predict design performance using virtual testing and numerical simulation.
- Understand performance-driven design workflow.
- Understand principles of generative design.
- Design objects using topology optimization methods.
- Experience designing and optimizing objects across multiple domains.
- Learn how AI methods can aid design workflows.
- Design and build a data-driven (machine learning) model.
- Learn how to design training datasets from image collections.
- Learn how data-driven models can be used for product customization.
- Understand AI tools for manufacturing.
Who Should Attend
This course is designed for engineers, designers, product managers, marketing directors, scientists and educators in industries that are involved in translating concepts to physical objects/products. Relevant areas include consumer products, medical devices, textile, packaging, electronics, automotive, aerospace, and defense.
Requirements
Laptops or tablets with Windows and with which you have administrator privileges are required for this course.
Program Outline
Day 1
Morning: 9 am – 12 pm
- Computational design and manufacturing workflow
- Overview of advanced manufacturing processes
- Digital design representations
Afternoon: 1 pm – 5 pm
- From geometry to hardware abstraction languages
- Lab 1: Designing and printing models using a virtualized 3D printer
- Customizable designs using parametric modelling
Day 2
Morning: 9 am – 12 pm
- Advanced design customization: procedural modeling and geometric deformation methods
- Lab 2: Designing customizable models for additive manufacturing
Afternoon: 1 pm – 5 pm
- Predicting design performance using simulation methods
- Lab 3: Predicting design performance for additive manufacturing
- Inverse methods and performance-driven design
Day 3
Morning: 9 am – 12 pm
- Introduction to optimization
- Topology optimization
- Lab 4: Design for AM using topology optimization
Afternoon: 1 pm – 5 pm
- Optimizing design for multiple objectives
- Interactive design applications
- Optimizing designs across multiple domains
Day 4
Morning: 9 am – 12 pm
- Introduction to AI and machine learning
- Symbolic AI methods for computational design
- Machine learning methods (including neural networks)
Afternoon: 1 pm – 5 pm
- Lab 5: Designing and building a machine learning model
- Advanced AI tools for design customization (deep neural networks, convolutional neural networks)
- Lab 6: Advanced AI methods for design customization
Day 5
Morning: 9 am – 12 pm
- AI methods for representing design spaces (generative models, autoencoders, GANs)
- Automated discovery of optimal designs
- Intelligent manufacturing systems
Afternoon: 1 pm – 5 pm
- Advanced AI tools for manufacturing process optimization (Bayesian optimization)
- Lab 7: Process optimization using Bayesian optimization
- Course review: developing an intelligent computational design and manufacturing workflow
Links & Resources
News & Articles
- How to design and control robots with stretchy, flexible bodies:Optimizing soft robots to perform specific tasks is a huge computational problem, but a new model can help. MIT News, November 22, 2019
- Automated system generates robotic parts for novel tasks. MIT News, July 12, 2019
- MIT Researchers Automate Reverse Engineering of 3D Models. 3D Printing Industry, January 3, 2019
- Custom robots in a matter of minutes: CSAIL’s “Interactive Robogami” lets you design and 3-D print origami-inspired robots from 2-D designs. MIT News, August 23, 2017
- Designing the microstructure of printed objects: Software lets designers exploit the extremely high resolution of 3-D printers. MIT News, August 3, 2017
- Reshaping computer-aided design: CSAIL’s InstantCAD allows manufacturers to simulate, optimize CAD designs in real-time. MIT News, July 24, 2017
- Design your own custom drone: CSAIL system lets users design and fabricate drones with a wide range of shapes and structures. MIT News, December 5, 2016
- Designing for 3-D printing: “Foundry” tool from the Computer Science and Artificial Intelligence Lab lets you design a wide range of multi-material 3-D-printed objects. MIT News, October 11, 2016
- Customizing 3-D printing: Design tool lets novices do in minutes what would take experts in computer-aided design hours. MIT News, September 3, 2015
- CSAIL team puts design in your hands: Fab By Example lets you quickly create thousands of custom designs for furniture, go-carts, and more. MIT News, August 11, 2014
The type of content you will learn in this course, whether it's a foundational understanding of the subject, the hottest trends and developments in the field, or suggested practical applications for industry.
How the course is taught, from traditional classroom lectures and riveting discussions to group projects to engaging and interactive simulations and exercises with your peers.
What level of expertise and familiarity the material in this course assumes you have. The greater the amount of introductory material taught in the course, the less you will need to be familiar with when you attend.