Manufacturing Futures Initiative

A new controlled polymerization methodology for additive manufacturing of materials can overcome barriers to producing soft robotics, such as artificial skin sensors and artificial muscles.

Krzysztof Matyjaszewski (Chemistry), Tomasz Kowalewski (Chemistry), and Carmel Majidi (Mechanical Engineering)

The ability to more accurately predict the impacts of emerging technologies on labor markets can be achieved through a novel approach that combines engineering and economic cost models.

Laurence Ales (Tepper School of Business), Brian K. Kovak (H. John Heinz III College of Information Systems and Public Policy), and Katie Whitefoot (Engineering and Public Policy and Mechanical Engineering)

By combining engineering production modeling and empirical shop-floor data, researchers can develop a method to quantify the implications of emerging technologies for the nature of work and wages, which will allow them to accurately advise small to medium manufacturing enterprises on decisions to invest in technology.

Erica Fuchs (Engineering and Public Policy) and Katie Whitefoot (Mechanical Engineering and Engineering and Public Policy)

Tools can be developed to optimize design part structure, machine process parameters, and part layout in order to significantly reduce the cost of metal additive manufacturing.

Kate S. Whitefoot (Engineering and Public Policy and Mechanical Engineering), Burak Kara (Mechanical Engineering), and Burak Ozdoganlar (Mechanical Engineering) 

Commercial implementation of metal additive manufacturing in parts and systems can be accelerated using decision science and machine learning to improve part selection.

Erica Fuchs (Engineering and Public Policy), Alex Davis (Engineering and Public Policy), and Parth Vaishnav (Engineering and Public Policy)

A novel approach to 3-D printing materials using a support bath can greatly expand the types of polymers that can be 3-D printed, the throughput (speed) of the printing process, and the complexity and mechanical properties of the printed parts.

Adam Feinberg (Biomedical Engineering and Materials Science and Engineering) and Burak Ozdoganlar (Mechanical Engineering)

Machine learning can be used to develop a better, more predictive understanding of additive manufactured parts and processes through implementing tools that rapidly evaluate powder feedstocks and part microstructures and that afford process monitoring capabilities at the melt pool and layer levels.

Liz Holm (Materials Science and Engineering), Jack Beuth (Mechanical Engineering), Burak Kara (Mechanical Engineering), Barnabas Poczos (College of Engineering's Machine Learning Department), Anthony D. Rollett (Materials Science and Engineering), Mahadev Satyanarayanan (School of Computer Science)

Machine learning interfaces used for workforce development in areas such as cell manufacturing can enable workers to rapidly gain expertise by comparing images in a large data set in order to accurately identify cell conditions and suggest actions.

Chinmay Kulkarni (Human Computer Interaction Institute) and Rebecca Taylor (Mechanical Engineering and Biomedical Engineering)

Real-time advanced robotic manufacturing can be used to produce concrete façade panels with designed surface geometries that improve building efficiency.

Researchers

Dana Cupkova (Architecture), Joshua Bard (Architecture), Newell Washburn (Chemistry and Materials Science and Engineering), and Garth Zeglin (Robotics Institute)

Software engineering concepts, such as modularity, can be used to increase the flexibility of computer aided design tools used for 3-D printed parts and speed up the iterative process of making parts.

Scott Hudson (School of Computer Science) and Simon Lucey (Robotics Institute)