On Design Mining: Coevolution and Surrogate Models
This work addresses the challenge of managing complexity in design mining for physical objects, such as wind turbines, but appears incremental as it builds on existing coevolutionary models and surrogate techniques.
The paper tackled the problem of coevolutionary design processes in design mining by exploring strategies for sampling sub-thread designs and using surrogate models, resulting in the effective design of an array of six heterogeneous vertical-axis wind turbines.
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.