2026 ASEE Annual Conference & Exposition

The United States Coast Guard regulates maritime vessels, including those equipped with hybrid hydrogen-powered propulsion systems and artificial intelligence (AI). The sponsor for this project is the USCG Marine Safety Center. The goal of this project is to create a small-scale hybrid power vessel that automatically switches between energy sources of hydrogen and batteries using both a traditionally coded algorithm and a machine learning algorithm. Hydrogen-powered vessels often use hybrid energy systems that store energy in batteries alongside hydrogen-generated power. This allows the vessel to draw power from multiple energy sources in different circumstances to most efficiently meet the load demand. Additionally, automatic transitions between energy sources allow for the maximization of efficiency and reduce the demand on the vessel crew. In highly complex systems in which large amounts of data can be collected, artificial intelligence systems show promise in improving efficiency. Therefore, this project will incorporate machine learning algorithms as testing progresses. The operational objectives that support the project goal are the design of a vessel hull, a propulsion system, an electrical power circuit, and an energy management algorithm; the simulation of these systems to verify their effectiveness, the construction of these systems, the integration of these systems into a single vessel, and the incorporation of a machine learning energy management algorithm.

This multidisciplinary project includes 5 students: two mechanical engineering majors to design and manufacture the vessel hull and propulsion system, two electrical engineering majors to design and manufacture the power circuit and algorithm, and a cyber systems major to collect data and design and create a machine learning power management algorithm. The vessel hull will be approximately 4.5 feet in length, 1.5 feet in width, and propelled using a 200-watt brushless motor propeller. The power circuit will supply and store energy via a 200-watt (W) hydrogen Proton Exchange Membrane (PEM) and two 6-volt, 7-amp-hour batteries. The circuit will be managed using an 8-module relay and an Arduino Mega. The data collected from testing the small-scale vessel with procedural code automation will be used to train the machine learning algorithm.

Authors
  1. Taylor Anne Lynch United States Coast Guard Academy [biography]
  2. Hudson Holden United States Coast Guard Academy [biography]
  3. Dr. Tooran Emami Ph. D. United States Coast Guard Academy [biography]
Download paper (1.04 MB)

Are you a researcher? Would you like to cite this paper? Visit the ASEE document repository at peer.asee.org for more tools and easy citations.

» Download paper

« View session

For those interested in:

  • computer science
  • engineering
  • engineering technology
  • Faculty
  • information technology
  • undergraduate
  • professional