Tag: evolutionary-algorithm

This session focuses on tools that link conceptual design decisions in architecture to quantitative and qualitiative performance metrics, such as structural material volume, energy consumption, daylighting quality, and formal and spatial qualities. Developed by the Digital Structures research group at MIT, these tools emphasize design over analysis, aiming to help designers explore a wide range of diverse, surprising, and high-performing alternatives for conceptual design problems. Participants will learn strategies for using the tools in their own practices to navigate conceptual building design problems in a flexible yet data-driven way.

This dissertation focuses on computational strategies for incorporating structural considerations into the earliest stages of the architectural design process. Because structural behavior is most affected by geometric form, the greatest potential for structural efficiency and a harmony of design goals occurs when global formal design decisions are made, in conceptual design. However, most existing computational tools and approaches lack the features necessary to take advantage of this potential: architectural modeling tools address geometry in absence of performance, and structural analysis tools require an already determined geometrical form. There is a need for new computational approaches that allow designers to explore the structural design space, which links geometric variation and performance, in a free and interactive manner. The dissertation addresses this need by proposing three new design space strategies. The first strategy, an interactive evolutionary framework, balances creative navigation of the design space with a focus on performance. The original contributions of this strategy center on enhanced opportunities for designer interaction and control. The second strategy introduces structural grammars, which allow for the formulation of broad and diverse design spaces that span across typologies. This strategy extends existing work in geometry-based shape grammars by incorporating structural behavior in novel ways. Finally, the third strategy is a surrogate modeling approach that approximates the design space to enable fast and responsive design environments. This strategy contributes new ways for non-experts to use this machine-learning-based methodology in conceptual design. These three complementary strategies can be applied independently or in combination, and the dissertation includes a discussion about possibilities and techniques for integrating them. Finally, the dissertation concludes by reflecting on its potential impact on design in practice, and by outlining important areas for future work. Key words: conceptual structural design, design space exploration, structural optimization, interactive evolutionary algorithm, structural grammar, surrogate modeling, structural design tools

This paper introduces a new computational approach for creative conceptual structural design, synthesizing an interactive evolutionary framework, a structural grammar strategy for trans-typological design, and a performance-focused surrogate modelling technique. By developing and integrating these three strategies into a unified design approach, this research enables architects and structural designers to explore broad ranges of conceptual design alternatives in an interactive way.

Since the introduction of finite element analysis software in the 1970s, structural engineers have become increasingly reliant on computational tools to carry out sophisticated simulations of structural performance. However, most structural analysis tools can only be used once there is a structure to be analyzed; they are not directly applicable in the design or synthesis of a new structural solution. This paper presents new research that expands the applicability of computation from structural analysis to structural design, with an emphasis on conceptual design applications. Specifically, this paper introduces a new interactive evolutionary framework implemented in a web-based structural design tool, structureFIT. This approach enables users to explore structural design options through an interactive evolutionary algorithm, and to further refine designs through a real-time analysis mode. This paper includes a critical background on optimization and its applications in structural design, an overview of the original interactive evolutionary framework, a description of the design tool, and a discussion of potential applications.

This paper presents a novel interactive evolutionary framework for conceptual structural design. In contrast with tools for structural analysis, tools for structural design should guide the design process by suggesting structurally efficient options, while allowing for a diversity of design choice. The framework proposed here implements an interactive evolutionary algorithm to achieve this behaviour. Additionally, a cohesive and intuitive graphical user interface is introduced. Finally, a novel approach to approximate the design space, and thereby improve the speed of the algorithm, using non-parametric regression is discussed.

Based on the framework developed for structureFIT, Stormcloud is a new component for Grasshopper and Rhino that allows any parametric model to be explored using an interactive evolutionary framework, combining quantitative performance analysis with qualitative designer input. Unlike structureFIT, Stormcloud can work with any model and geometry type that can be represented and analyzed in Grasshopper. The quantitative analysis is also flexible: it can use structural weight, like structureFIT, but users are also free to input their own objective functions computed using other plugins or user-defined expressions.

Stormcloud is currently available for download as part of the Design Space Exploration tool suite on at Food4Rhino here.

This paper addresses the need to consider both quantitative performance goals and qualitative requirements in conceptual design. A new computational approach for design space exploration is proposed that extends existing interactive evolutionary algorithms for increased inclusion of designer preferences, overcoming the weaknesses of traditional optimization that have limited its use in practice. This approach allows designers to set the evolutionary parameters of mutation rate and generation size, in addition to parent selection, in order to steer design space exploration. This paper demonstrates the potential of this approach through a numerical parametric study, a software implementation, and series of case studies.