Artificial intelligence optimization offers a bunch of advantages for mechanical engineers, including faster and more accurate designs and simulations, improved efficiency, reduced development costs through process automation, and enhanced predictive maintenance and quality control.
“When people take into consideration mechanical engineering, they’re enthusiastic about basic mechanical tools like hammers and … hardware like cars, robots, cranes, but mechanical engineering could be very broad,” says Faez Ahmed, the Doherty Chair in Ocean Utilization and associate professor of mechanical engineering at MIT. “Inside mechanical engineering, machine learning, AI, and optimization are playing a giant role.”
In Ahmed’s course, 2.155/156 (AI and Machine Learning for Engineering Design), students use tools and techniques from artificial intelligence and machine learning for mechanical engineering design, specializing in the creation of recent products and addressing engineering design challenges.
Cat Trees to Motion Capture: AI and ML for Engineering Design
Video: MIT Department of Mechanical Engineering
“There’s a whole lot of reason for mechanical engineers to take into consideration machine learning and AI to essentially expedite the design process,” says Lyle Regenwetter, a teaching assistant for the course and a PhD candidate in Ahmed’s Design Computation and Digital Engineering Lab (DeCoDE), where research focuses on developing latest machine learning and optimization methods to review complex engineering design problems.
First offered in 2021, the category has quickly turn out to be certainly one of the Department of Mechanical Engineering (MechE)’s hottest non-core offerings, attracting students from departments across the Institute, including mechanical and civil and environmental engineering, aeronautics and astronautics, the MIT Sloan School of Management, and nuclear and computer science, together with cross-registered students from Harvard University and other schools.
The course, which is open to each undergraduate and graduate students, focuses on the implementation of advanced machine learning and optimization strategies within the context of real-world mechanical design problems. From designing bike frames to city grids, students take part in contests related to AI for physical systems and tackle optimization challenges in a category environment fueled by friendly competition.
Students are given challenge problems and starter code that “gave an answer, but [not] the perfect solution …” explains Ilan Moyer, a graduate student in MechE. “Our task was to [determine], how can we do higher?” Live leaderboards encourage students to repeatedly refine their methods.
Em Lauber, a system design and management graduate student, says the method gave space to explore the appliance of what students were learning and the practice skill of “literally the right way to code it.”
The curriculum incorporates discussions on research papers, and students also pursue hands-on exercises in machine learning tailored to specific engineering issues including robotics, aircraft, structures, and metamaterials. For his or her final project, students work together on a team project that employs AI techniques for design on a posh problem of their selection.
“It’s wonderful to see the varied breadth and prime quality of sophistication projects,” says Ahmed. “Student projects from this course often result in research publications, and have even led to awards.” He cites the instance of a recent paper, titled “GenCAD-Self-Repairing,” that went on to win the American Society of Mechanical Engineers Systems Engineering, Information and Knowledge Management 2025 Best Paper Award.
“The very best part concerning the final project was that it gave every student the chance to use what they’ve learned in the category to an area that interests them quite a bit,” says Malia Smith, a graduate student in MechE. Her project selected “markered motion captured data” and checked out predicting ground force for runners, an effort she called “really gratifying” since it worked so significantly better than expected.
Lauber took the framework of a “cat tree” design with different modules of poles, platforms, and ramps to create customized solutions for individual cat households, while Moyer created software that’s designing a brand new form of 3D printer architecture.
“If you see machine learning in popular culture, it’s very abstracted, and you’ve got the sense that there’s something very complicated happening,” says Moyer. “This class has opened the curtains.”
