Optimizing bio-inspired propulsion systems using genetic algorithm

Optimization is an important part of the development of an efficient propulsion system. The biomimetic marine propulsion system, known as oscillating foil, has recently seen an upswing in interest. However, optimization of movement patterns for these systems which has a potentially large payoff is yet to be researched in detail. Because of its biomimetic origin and problem type compatibility, genetic algorithm (GA) is a promising option for optimizing movement of oscillating foil propulsion systems. This paper proposes a system that implements a GA to optimize the movement patterns for oscillating foils using a physical rig. It also explores the feasibility of the application of GA to optimize movement patterns for oscillating foils. The experiment setup is a fully autonomous physical simulation of a real world application of a marine propulsion system. The usage of a physical environment is a proof of a quick and reliable way of calculating fitness for this application. Our proposed system is able to find optimal movement patterns for most of the experimental cases. The results also show that optimizing oscillating foil movement patterns using GA together with a physical test system is a viable option.