Design Mining Interacting Wind Turbines

TL;DR

This paper advances the design of vertical-axis wind turbines by evaluating surrogate-assisted evolutionary algorithms with physical prototypes, exploring different models, training methods, and collaboration schemes to improve efficiency.

Contribution

It introduces new surrogate modelling and evolutionary techniques, compares their accuracy, and explores innovative training and collaboration strategies for wind turbine design.

Findings

Different surrogate models vary in accuracy for fitness estimation.

Temporal windowing affects surrogate model training effectiveness.

Enhanced local search improves design optimization.

Abstract

An initial study of surrogate-assisted evolutionary algorithms used to design vertical-axis wind turbines wherein candidate prototypes are evaluated under fan generated wind conditions after being physically instantiated by a 3D printer has recently been presented. Unlike other approaches, such as computational fluid dynamics simulations, no mathematical formulations were used and no model assumptions were made. This paper extends that work by exploring alternative surrogate modelling and evolutionary techniques. The accuracy of various modelling algorithms used to estimate the fitness of evaluated individuals from the initial experiments is compared. The effect of temporally windowing surrogate model training samples is explored. A surrogate-assisted approach based on an enhanced local search is introduced; and alternative coevolution collaboration schemes are examined.