On Design Mining: Coevolution and Surrogate Models

TL;DR

This paper explores design mining using coevolution and surrogate models to optimize complex physical systems like wind turbines through iterative, rapid prototyping and intelligent sampling strategies.

Contribution

It introduces a coevolutionary framework for design mining and demonstrates its application in optimizing a six-turbine wind array.

Findings

Effective sampling strategies for sub-designs

Successful surrogate modeling within coevolution

Optimized wind turbine array design

Abstract

Design mining is the use of computational intelligence techniques to iteratively search and model the attribute space of physical objects evaluated directly through rapid prototyping to meet given objectives. It enables the exploitation of novel materials and processes without formal models or complex simulation. In this paper, we focus upon the coevolutionary nature of the design process when it is decomposed into concurrent sub-design threads due to the overall complexity of the task. Using an abstract, tuneable model of coevolution we consider strategies to sample sub-thread designs for whole system testing and how best to construct and use surrogate models within the coevolutionary scenario. Drawing on our findings, the paper then describes the effective design of an array of six heterogeneous vertical-axis wind turbines.