Improving Design Optimization and Optimization-based Design Knowledge Discovery
MetadataShow full item record
The use of design optimization in the early stages of architectural design process has attracted a high volume of research in recent years. However, traditional design optimization requires a significant amount of computing time, especially when there are multiple design objectives to achieve. What’s more, there is a lack of studies in the current research on automatic generation of architectural design knowledge from optimization results. This paper presents computational methods for creating and improving a closed loop of design optimization and knowledge discovery in architecture. It first introduces a design knowledge-assisted optimization improvement method with the techniques - offline simulation and Divide & Conquer (D&C) - to reduce the computing time and improve the efficiency of the design optimization process utilizing architectural domain knowledge. It then describes a new design knowledge discovery system where design knowledge can be discovered from optimization through an automatic data mining approach. The discovered knowledge has the potential to further help improve the efficiency of the optimization method, thus forming a closed loop of improving optimization and knowledge discovery. The validations of both methods are presented in the context of a case study with parametric form-finding for a nursing unit design with two design objectives: minimizing the nurses’ travel distance and maximizing daylighting performance in patient rooms.
Divide and Conquer
Su, Zhouzhou (2015). Improving Design Optimization and Optimization-based Design Knowledge Discovery. Doctoral dissertation, Texas A & M University. Available electronically from