Design Exploration by Using a Genetic Algorithm and the Theory of Inventive Problem Solving (TRIZ)
Hydra Lab at the University of Michigan, Taubman College of Architecture and Urban Planning
Automation in Construction
This paper presents a computational design exploration method called GA+TRIZ, which aids designers in defining the design problem clearly, making a parametric model where pertinent variables are included, obtaining a series of suitable solutions, and resolving existing conflicts among design objectives. The goal is to include the designer's qualitative and performance-based quantitative design goals in the design process, while promoting innovative ideas for resolving contradictory design objectives. The method employed is a Genetic Algorithm (GA), earlier implemented in an automated design exploration process called ParaGen, in combination with the Theory of Inventive Problem Solving (TRIZ), a novel methodology to assist architects and structural engineers in the conceptual phase of design. The GA+TRIZ method promotes automated design exploration, investigation of unexpected solutions, and continuous interaction with the computational generating system. Finally, this paper presents two examples that illustrate how the GA+TRIZ method assists designers in problem structuring, design exploration, and decision-making.
© 2022 Elsevier
Locate the Document
Khodadadi, A., & von Buelow, P. (2022). Design exploration by using a genetic algorithm and the Theory of Inventive Problem Solving (TRIZ). Automation in Construction, 141, 104354.