The optimization of artificial intelligence offers many benefits for mechanical engineers, including faster and more accurate projects and simulations, better performance, reduced development costs by automating the process and increased prognostic control and quality control.
“When people think about mechanical engineering, they think about basic mechanical tools, such as hammers and … equipment such as cars, robots, cranes, but mechanical engineering is very wide,” says Faez Ahmed, chairman of Doherta in the use of oceans and a professor of mechanical engineering in MIT. “As part of mechanical engineering, machine learning, artificial intelligence and optimization, they play a big role.”
On the Ahmeda course, 2.155/156 (AI and machine learning for engineering designing), students use tools and techniques of artificial intelligence and machine learning for mechanical engineering design, focusing on creating new products and solving design problems of engineering.
Cat trees for capturing traffic: AI and ML for engineering design
VIDEO: MIT Department of Mechanical Engineering
“There are many reasons why mechanics engineers think about machine learning and artificial intelligence to basically accelerate the design process,” says Lyle Regenwetter, course didactic assistant and a doctoral student in the field of AHMED design calculations and digital engineering (decoding), where research focuses on developing new methods of learning and optimization for the purpose problems with engineering design.
For the first time in 2021, the class quickly became one of the most popular offers other than core, attracting students from branches at the Institute, including mechanical and civic engineering, aeronautics and astronautics.
The course, which is open to both bachelor students and doctoral students, focuses on implementing advanced machine learning and optimization strategies in the context of real mechanical problems. From bicycle frame design to city networks, students participate in AI competitions in the field of physical systems and challenges related to optimization in a class -powered class -friendly class.
Students have problems with the challenge and the start code, which “gave the solution, but (not) the best solution …” explains Ilan Moyer, a graduate of Meche. “Our task was (determining) how can we do better?” The number of live leaders encourage students to constantly improve their methods.
EM Lauber, a graduate of system design and management, claims that the process gave the space to examine the use of what they learned, and the skills of exercise “literally how to cod it”.
The curriculum includes discussions on research documents, and students conduct practical machine learning exercises adapted to specific engineering problems, including robotics, aircraft, structures and metamaterials. For the last project, students work together on a team project that uses AI techniques to design a complex problem.
“It is great to see the diverse width and high quality of class projects,” says Ahmed. “Student projects from this course often lead to research publications and even led to prizes.” Cites an example of the last article entitled “Gencad-Self-Reparing“It won the American Society of Momanical Engineers Systems Engineering, Information and KnowGhate Management 2025 Best Paper Award.
“The best in the final project was that it gave each student the opportunity to use what they learned in the classroom to the area that they are very interested in,” says Malia Smith, a PhD student at Meche. Her project chose “designed intercepted data” and looked at predicting ground force for runners, the effort she calls “really satisfying” because he acted much better than expected.
Lauber took the framework of the “Cat tree” project with various pole, platforms and ramps to create non -standard solutions for individual Cat households, while Moyer has created a software that designs a new type of 3D printer architecture.
“When you see machine learning in popular culture, it is very abstract and you have the impression that something very complicated is happening,” says Moyer. “This class has opened curtains.”
