The Machine-Learning models thrive on data. The more data available, or creatable, the more defined is the problem representation, and the more accurate is the obtained prediction. This presents a challenge for physical, material datasets, specifically those related to fabrication systems, in which data is tied to physical artefacts which necessitate fabrication, digitisation and formatting to be used as input for predictive models. In this paper we present a design-based methodology to producing a material dataset for statistically modelling the curing of cellulose-based 3d-printed components, as well as associated methods for geometric data encoding, tolerance-informed data augmentation and statistical modelling. The focus of the paper is on the digital workflows and considerations for dataset composition - the material case of 3d-printing cellulose is secondary. We use a built 3d-printed demonstrator wall as a material dataset, through which we generate datapoints that stem from a real design-scenario and inform the fabrication model. Using a feature-engineering approach, select geometrical features are encoded numerically. We perform statistical analysis on the data, and test different shallow models and neural networks. We report on the successful training of a Polynomial Kernel Ridge Regressor to predict the vertical shrinkage of the pieces from wet print to dry element.

Combining graph-based parametric design with metaheuristic solvers has to date focused solely on performance-based criteria and solving clearly defined objectives. In this article, we outline a new method for combining a parametric modelling environment with an interactive Cluster-Orientated Genetic Algorithm. In addition to performance criteria, evolutionary design exploration can be guided through choice alone, with user motivation that cannot be easily defined. As well as numeric parameters forming a genotype, the evolution of whole parametric definitions is discussed through the use of genetic programming. Visualisation techniques that enable mixing small populations for interactive evolution with large populations for performance-based optimisation are discussed, with examples from both academia and industry showing a wide range of applications.

Self-organizing construction is an emerging subdomain for on-site construction robots. This not only presents new challenges for robotics, but due to the stochasticity involved in such systems, impacts the modeling and prediction of resulting built structures. Self-organizing models have been explored by architects for generative design and for optimization, but so far have infrequently been studied in the context of construction. Here we present a strategy for architects to design with non-deterministic self-organizing behaviors, using interactive evolution to incorporate user judgment. We introduce our "Integrated Growth Projection" method, having implemented it into a software pipeline for early phase design. We test the software with an initial user group of architects, to see whether the method and pipeline helps them design a non-deterministic self-organizing behavior. The user group creates several hybrid controllers that reliably solve their chosen design tasks.

Parametric modelling software often maintains an explicit history of design development in the form of a graph. However, as the graph increases in complexity it quickly becomes inflexible and unsuitable for exploring a wide design space. By contrast, implicit low-level rule systems can offer wide design exploration due to their lack of structure, but often act as black boxes to human observers with only initial conditions and final designs cognisable. In response to these two extremes, the authors propose a new approach called Meta-Parametric Design, combining graph-based parametric modelling with genetic programming. The advantages of this approach are demonstrated using two real case-study projects that widen design exploration whilst maintaining the benefits of a graph representation.

Evolutionary methods with artificial selection have been shown to be an effective human-computer technique for exploring design spaces with unknown goals. This paper investigates an interactive evolution of visual programs currently used in popular parametric modelling software. Although parametric models provide a useful cognitive artifact for designers to interact with, they are often bound by their topological structure with the designer left to adjusting (or optimising) metric variables as part of a design search. By allowing the topological structure of the graph to be evolved as well as the parameters, artificial selection can be employed to explore a wider design space more suited to the early design stage.

This paper describes the work of Ramboll Computational Design during the design and construction of the Ongreening Pavilion timber gridshell. The structural approach involved form-finding bending-active timber laths, connected at intersections to form a doubly curved shell. The resulting form was simple to fabricate and assemble, realised using 6.5 mm thick Finnish birch plywood laths that could achieve high curvature while maintaining desired strength. Due to the random nature of the final lath topology, the resulting structure was extremely stiff in spite of its low material weight, acting similarly to a continuous monocoque. The fully demountable shell was first erected at Ecobuild 2014 in London.