AERO4River's Experimental Tests: Performance Comparison of Meta-Heuristics Applied to Optimal Signal Design for Parameter Identification

This dataset contains experimental tests used to develop the mathematical model of the second version of the AERO4River. The AERO4River is an autonomous surface vehicle based on a 3 degrees of freedom (DoF) catamaran-like vessel with an innovative air propulsion system with azimuth control. The tests were conducted in the open field, at UFJF Lake and João Penido Dam, in Minas Gerais, Brazil.

The shared data includes a total of 40 identification experiments performed with the SOESGOPE (Suboptimal Excitation Signal Generation and Optimal Parameter Estimation) method, investigating its applicability in the following metaheuristics: Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Bat Algorithm (BA), Whale Optimization Algorithm (WOA), Gray Wolf Optimizer (GWO), Salp Swarm Algorithm (SSA), Arithmetic Optimization Algorithm (AOA) and Multi-trial vector-based Differential Evolution (MTDE). In this context, the dataset includes 5 experiments designed for each technique and also 18 experiments used to validate the estimated model, all of which were captured in manual operational tests.

For more information on the AERO4River and the identification methodology, see the articles: (1)"Development of Optimal parameter estimation methodologies applied to a 3DOF autonomous surface vessel" (IEEE Access); (2) "Hull and Aerial Holonomic Propulsion System Design for Optimal Underwater Sensor Positioning in Autonomous Surface Vessels" (Sensors Article) and (3)"Project and Control Allocation of a 3DoF Autonomous Surface Vessel With Aerial Azimuth Propulsion System" (IEEE Acess).