CSE Community Seminar
December 6, 2024, 12-1PM
Conference Room 45-432 in Building 45
Generative Artificial Intelligence for Performance and Constraint Informed Ship Design
Noah Joseph Bagazinski
Research Assistant at DeCoDE Lab, MIT
Abstract:
Ship design is a years-long process that requires balancing complex design trade-offs to create a ship that is efficient and effective. Finding new ways to improve the ship design process can lead to significant cost savings in ship design, manufacturing, and operation. One promising technology is generative artificial intelligence, which has been shown to reduce design cycle time and create novel, high-performing designs. This presentation showcases a conditional diffusion model that generates hull designs given specific constraints, such as the desired principal dimensions of the hull. In addition, this diffusion model leverages the gradients from a total resistance regression model to create low resistance designs. Five design test cases compared the diffusion model to a design optimization algorithm to create hull designs with low resistance. In all five test cases, the diffusion model was shown to create diverse designs with a total resistance less than the optimized hull, having resistance reductions in excess of 25%. The diffusion model also generated these designs without retraining.These reductions in drag will find cost saving opportunities for ship operators with reductions in fuel consumption. Future work intends to design marine structures, create packing arrangements, and generate systems level design of ships with a unified data-design pipeline.
December 6, 2024, CSE Community Seminar
Noah Joseph Bagazinski
Research Assistant at DeCoDE Lab, MIT