No abstract

Adaptive architecture is expected to improve the performance of buildings and create more efficient building systems. One of the major research areas under this scope is the adaptive behavior of structural elements affected by load distribution. In order to achieve this, current studies develop structures that adapt by either following a database of precalculated equilibrium solutions or using self-learning algorithms to acquire active control systems to structures. This paper examined a case study element, which demonstrates an adaptive behavior in real time, based on self-learning abilities. The focus of this experiment was to gain control over a structural system as a whole (not only on a singular component) according to both objective and subjective parameters, that is, both load distribution parameters and spatial parameters, which are design related. The examined structural element was a canopy, situated in a dynamic environment that brought a change in the element's load distribution. The learning ability was given by applying a supervised learning algorithm-Artificial Neural Network (ANN)-on a physical prototype. The ANN was trained by an optimized database of finite solutions, which was created by a Genetic Algorithm. Through this method, complex calculations are conducted ''offline'', and the component operates in a ''decision-making'' mode in real time, adapting to a versatile environment while using minimal computational resources. Results show that the case study successfully exhibited self-learning and acquired the ability to adapt to unpredictable changing forces while keeping certain design requirements. This method can be applied over different structural elements (fac xade elements, canopies, structural components, etc.) to achieve adaptation to various parameters with an unpredictable pattern, such as human behavior or weather conditions.

Additive manufacturing with mud has the potential to reintroduce traditional materials within our contemporary design culture, answering the current demands of sustainability, energy efficiency and cost in construction. Building upon previous research, this study proposes the design and test of real-scale wall elements that aim to take advantage of both the novel material fabrication process as well as the significant thermodynamic properties of the material to achieve a performative passive material system for bioclimatic architecture. Although this project is still at an early stage, the presented study demonstrates the potential of combining 3D printing of mud with performance analysis and simulation for the optimization of a wall prototype.

The synthesis of human design inspiration and serendipity and the use of digital tools has been the aim of much architectural research over the last 50 years. Theodoros Galanos and Angelos Chronis from the Austrian Institute of Technology in Vienna describe the AI tools they have developed to achieve real‐time, dynamic representation of design performance and design intent.

The present research investigates the potential for reducing the environmental impacts of structural systems through a more efficient use of materials. The main objective of this research is to explore and to develop a holistic and integrated methodology that utilises Building Information Modelling's (BIM) capabilities combined with structural analysis and Life Cycle Assessment (LCA) as well as a two-staged structural optimisation solver that achieves efficient and environmentally responsible steel design solutions. The implemented workflow utilises Autodesk Revit -BIM, Tally -LCA and Autodesk Robot -Structural Analysis. RobOpt is the plug-in that has been established using the Application Programming Interface (API) of Robot and the .NET framework of C♯, and it inherits several structural functionalities based on Robot Finite Element Method (FEM) engine. The proposed RobOpt application can be accessed via a graphic user interface (GUI) within the Robot software. The developed BIM-enabled optimisation methodology could be utilised as a design tool to inform early stage structural design solutions. A prototypical steel framed structural system under certain loads has been explored. The resulting bespoke I-beam sections from the custom genetic algorithm (GA) optimisation demonstrate that significant savingsup to 21% -can be achieved in all tested environmental indicators when compared to the standard UK catalogue of steel sections. Considering all, the proposed framework constitutes a useful and an intuitive workflow, which aims to quantify the environmental savings of structural systems by utilising, advanced computational analysis and common construction techniques.