MechE Seminar: Representing Knowledge for Data-Driven Design and Manufacturing

Thumbnail

Event details

Date 16.02.2022
Hour 16:0017:00
Speaker Mr Haluk Akay, Park Center for Complex Systems, Mechanical Engineering Department, Massachusetts Institute of Technology (MIT)
Location Online
Category Conferences - Seminars
Event Language English
Abstract: Artificial Intelligence has transformed the practice of fields such as Computer Vision and Natural Language Processing to deliver revolutionary technology including autonomous vehicle systems and automated language translation services. A similar data-driven transformation of design and manufacturing is necessary to guide engineers through complexity to develop next-generation sustainable products and production systems. Data is abundant from digitally documented early-stage design through final production processes, but this data is often unstructured, informal, and can be qualitative or textual in nature. Design and manufacturing data must be computationally interpretable in order for past documented knowledge to guide future engineering decision-making. In this seminar, I will present my research leveraging deep neural network-based language modeling to represent design and manufacturing data; specifically, textually described knowledge. I will also describe how such quantitative representation models make possible a wide range of applied AI methods for performing tasks such as evaluating functional interdependencies and extracting functional information from past design documentation. By learning from past engineering failures and achievements, Artificial Intelligence can be used to assist human designers’ decision-making for meeting the needs of society and the environment through data-driven sustainability.

Bio: Haluk Akay is a PhD candidate at the MIT Department of Mechanical Engineering, in the Park Center for Complex Systems, advised by Professor Sang-Gook Kim. He received his M.S. from MIT and his B.S. from Carnegie Mellon University, both in Mechanical Engineering. At MIT, his doctoral research applies Artificial Intelligence to design and manufacturing by developing methods for representing engineering knowledge for computational interpretability. His masters research focused on low-frequency vibrational energy harvesting, designing and fabricating MEMS piezoelectric devices and wearable energy harvesting systems resulting in patented technology. Previously, he has designed power electronics for Apple and fabricated carbon fiber Formula race car exteriors at Carnegie Mellon. He serves as a resident tutor in Baker House at MIT.

Practical information

  • General public
  • Free

Tags

MechE Seminar: Representing Knowledge for Data-Driven Design and Manufacturing

Share