Despite the recognized importance of datasets in data-driven design approaches, their extensive study remains limited. We review the current landscape of design datasets and highlight the ongoing need for larger and more comprehensive datasets. Three categories of challenges in dataset development are identified. Analyses show critical dataset gaps in design process where future studies can be directed. Synthetic and end-to-end datasets are suggested as two less explored avenues. The recent application of Generative Pretrained Transformers (GPT) shows their potential in addressing these needs.

Generative design is now a core capability of today's CAD systems enabling broader exploration of the design space. This paper presents a desktop review of 15 tools with the aim of characterising where the tools are used in the design process and to what extent they can be considered creative.The results showed that, despite their increasing capabilities, GD tools are unable to exhibit all phases of creativity and cannot be applied in all stages of the design process. This highlights the criticality of the human in design providing opportunities for GD to augment designer creativity.

3D printing technologies, such as material extrusion (MEX), hold the potential to revolutionise manufacturing by providing individuals without traditional manufacturing capabilities with powerful and affordable resources. However, widespread adoption is impeded by the lack of user-friendly design tools due to the necessity of domain-specific expertise in computer-aided design (CAD) software and the overwhelming level of design freedom afforded by the MEX process. To overcome these barriers and facilitate the democratisation of design (DoD), this article introduces an innovative, generative-based design (GBD) methodology aimed at enabling non-technical users to create functional components independently. The novelty of this methodology lies in its capacity to simplify complex design tasks, making them more accessible to non-designers. The proposed methodology was tested in the design of a load-bearing part, yielding a functional component within two design iterations. A comparative analysis with the conventional CAD-based process revealed that the GBD methodology enables the DoD, reflected in a 68% reduction in design activities and a decrease in design difficulty of 62% in requisite know-how and a 55% in understanding. Through the creation and implementation of this methodology, the article demonstrates a pioneering integration of state-of-the-art techniques of generative design with design repositories enabling effective co-design with non-designers.

Contemporary digital in ear hearing aids are of significant importance for social participation of users with hearing impairments. Through the advancement of technology, extreme miniaturisation of these devices has been achieved. However, by no means all people who could benefit from a hearing aid actually use one. Cormack and Fortnum state that the majority (80%) of adults aged 55–74 years who would benefit from a hearing aid, do not use them. This is in line with Arnold and Makenzie who estimate a gap of a factor of 5 between people who would benefit from the use of a hearing aid than actually do acquire and use one. Even according to the statistics from the Federal Guild of Hearing Aid Acousticians in Germany, only 3.7 million use a hearing aid out of 5.4 million who have an induced hearing loss. This article explores the design space of fashionable analogue contemporary hearing aids.

Developments in artificial intelligence (AI) are opening the possibilities for the development of more advanced design tools. An example of these innovations are generative design tools, in which the generation of complex and high performing products is possible. This study investigates the use of generative design tools and how they may influence the design process and designer behaviour. Six interviews of interdisciplinary designers were conducted to understand the implications of using generative design tools. It was observed that generative design tools primarily allow for quantitative inputs to the tool while qualitative metrics, such as aesthetics, are considered indirectly by designers. The subjectivity of the designer and how they incorporate the quantitative and qualitative metrics in the generative design tool can lead to differing outcomes between designers. Notable differences in tool usage are also observed between expert and novice computational designers. Additional studies should be conducted to further understand the extent generative design tools impact the design process, designer behaviour, and design outcomes.

Generative Adversarial Networks (GANs) have shown stupendous power in generating realistic images to an extend that human eyes are not capable of recognizing them as synthesized. State-of-the-art GAN models are capable of generating realistic and high-quality images, which promise unprecedented opportunities for generating design concepts. Yet, the preliminary experiments reported in this paper shed light on a fundamental limitation of GANs for generative design: lack of novelty and diversity in generated samples. This article conducts a generative design study on a large-scale sneaker dataset based on StyleGAN, a state-of-the-art GAN architecture, to advance the understanding of the performance of these generative models in generating novel and diverse samples (i.e., sneaker images). The findings reveal that although StyleGAN can generate samples with quality and realism, the generated and style-mixed samples highly resemble the training dataset (i.e., existing sneakers). This article aims to provide future research directions and insights for the engineering design community to further realize the untapped potentials of GANs for generative design.

Topology optimization has been identified as a powerful tool to improve aircraft structures for many years. Yet, innovative layouts have not been successfully implemented in commercial aircraft for several reasons. One reason identified by our research group is the lack of design constraints during topology optimization, such as buckling stability, which yields complex solutions that are not easily manufacturable. Second, the complexity of the resulting layouts makes integration with other systems highly challenging. With respect to these challenges, we propose a new heuristic layout optimization process: complexity-driven layout exploration for aircraft structures (CD-LEAS). The new process addresses the challenges of complexity and nonlinear constraints, such as buckling, in aircraft structure layout optimization. The novelty of CD-LEAS comes from the integration of a relative complexity metric as a driver to navigate the design space efficiently. Two case studies of commonly used stiffened panels are carried out to showcase the performance of the process. The results show that using complexity to navigate an explicit design space allows our process to quickly output a family of simple, light, stiff and buckling-resistant layouts.

Modern day building design projects require multidisciplinary expertise from architects and engineers across various phases of the design (conceptual, preliminary, and detailed) and construction processes. The Architecture Engineering and Construction (AEC) community has recently shifted gears toward leveraging design optimization techniques to make well-informed decisions in the design of buildings. However, most of the building design optimization efforts are either multidisciplinary optimization confined to just a specific design phase (conceptual/preliminary/detailed) or single disciplinary optimization (structural/thermal/daylighting/energy) spanning across multiple phases. Complexity in changing the optimization setup as the design progresses through subsequent phases, interoperability issues between modeling and physics-based analysis tools used at later stages, and the lack of an appropriate level of design detail to get meaningful results from these sophisticated analysis tools are few challenges that limit multi-phase multidisciplinary design optimization (MDO) in the AEC field. This paper proposes a computational building design platform leveraging concurrent engineering techniques such as interactive problem structuring, simulation-based optimization using meta models for energy and daylighting (machine learning based) and tradespace visualization. The proposed multi-phase concurrent MDO framework is demonstrated by using it to design and optimize a sample office building for energy and daylighting objectives across multiple phases. Furthermore, limitations of the proposed framework and future avenues of research are listed.

Manually exploring the solution space for different variants of a product for a given set of requirements is ineffective regarding product development time and adaptation to dynamic customer requirements. Variant generation coupled to optimization algorithms offers possibilities to search the solution space in an automated way. This paper provides a framework to build a generative parametric design environment for functional assemblies by implementing analysis as well as synthesis methods in computer-aided tools. The procedure is presented using the example of a coffee machine.

Design processes managed by algorithms provide solutions and improvements in terms of efficiency, performance, choice of materials, and cost optimization. It is a whole new approach to industrial design in which artificial intelligence participates directly in the design processes. The paper aims to investigate the way we design through algorithms, and consequent changes in thoughts, approaches, and generation of ideas that are rising determining new ways of defining things and their relations.

This paper presents models that identify two “cultures” of computational design practice. By reviewing the established culture of computational optimization efforts and contrasting it with the emerging work integrating human-factors into these optimizations, this paper argues that there are sets of key assumptions, outputs and tools that can be synthesized for a generalizable understanding of computational design. Furthermore, this synthesis facilitates the identification of key tools suited to computational design efforts seeking to integrate the complex data associated with human-factors.

Novel concepts are essential for design innovation and can be generated with the aid of data stimuli and computers. However, current generative design algorithms focus on diagrammatic or spatial concepts that are either too abstract to understand or too detailed for early phase design exploration. This paper explores the uses of generative pre-trained transformers (GPT) for natural language design concept generation. Our experiments involve the use of GPT-2 and GPT-3 for different creative reasonings in design tasks. Both show reasonably good performance for verbal design concept generation.

This work presents a methodology for the generation of novel 3D objects resembling wireframes of building types. These result from the reconstruction of interpolated locations within the learnt distribution of variational autoencoders (VAEs), a deep generative machine learning model based on neural networks. The data set used features a scheme for geometry representation based on a ‘connectivity map’ that is especially suited to express the wireframe objects that compose it. Additionally, the input samples are generated through ‘parametric augmentation’, a strategy proposed in this study that creates coherent variations among data by enabling a set of parameters to alter representative features on a given building type. In the experiments that are described in this paper, more than 150 k input samples belonging to two building types have been processed during the training of a VAE model. The main contribution of this paper has been to explore parametric augmentation for the generation of large data sets of 3D geometries, showcasing its problems and limitations in the context of neural networks and VAEs. Results show that the generation of interpolated hybrid geometries is a challenging task. Despite the difficulty of the endeavour, promising advances are presented.

Nowadays, a large number of different tools that support early phases of design are available to engineers. In the past decade a specialized set of CAD-based tools were developed, that support the ideation process by generating different design alternatives according to the criteria given by the designer. Two types of tools are discussed in this paper: topology optimization and generative design tools. To investigate to what extent these tools are suitable for use in early design phases and what are the main differences between them, a study was conducted on an industrial case.

The aim of this paper is to investigate the challenges associated with the industrial implementation of generative design systems. Though many studies have been aimed at validating either the technical feasibility or the usefulness of generative design systems, there is, however, a lack of research on the practical implementation and adaptation in industry. To that end, this paper presents two case studies conducted while developing design systems for industrial uses. The first case study focuses on an engineering design application and the other on an industrial design application. In both cases, the focus is on detail-oriented performance-driven generative design systems based on currently available computer-assisted design tools. The development time and communications with the companies were analyzed to identify challenges in the two projects. Overall, the results show that the challenges are not related to whether the design tools are intended for artistic or technical problems, but rather in how to make the design process systematic. The challenges include aspects such as how to fully utilize the potential of generative design tools in a traditional product development process, how to enable designers not familiar with programming to provide design generation logic, and what should be automated and what is better left as a manual task. The paper suggests several strategies for dealing with the identified challenges.

Architectural spatial design is a wicked problem that can have a multitude of solutions for any given brief. The information needed to resolve architectural design problems is often not readily available during the early conceptual stages, requiring proposals to be evaluated only after an initial solution is reached. This “solution-driven” design approach focuses on the generation of designs as a means to explore the solution space. Generative design can be achieved computationally through parametric and algorithmic processes. However, utilizing a large repertoire of organiational patterns and design precedent knowledge together with the precise criteria of spatial evaluation can present design challenges even to an experienced architect. In the implementation of a parametric design process lies an opportunity to supplement the designer's knowledge with computational decision support that provides real-time spatial feedback during conceptual design. This paper presents an approach based on a generative multiperformance framework, configured for generating and optimizing architectural designs based on a precedent design. The system is constructed using a parametric modeling environment enabling the capture of precedent designs, extraction of spatial analytics, and demonstration of how populations can be used to drive the generation and optimization of alternate spatial solutions. A pilot study implementing the complete workflow of the system is used to illustrate the benefits of coupling parametric modeling with structured precedent analysis and design generation.

Generative product design systems used in the context of mass customization are required to generate diverse solutions quickly and reliably without necessitating modification or tuning during use. When such systems are employed to allow for the mass customization of product form, they must be able to handle mass production and engineering constraints that can be time-consuming to evaluate and difficult to fulfill. These issues are related to how the constraints are handled in the generative design system. This article evaluates two promising sequential constraint-handling techniques and the often used weighted sum technique with regard to convergence time, convergence rate, and diversity of the design solutions. The application used for this purpose was a design system aimed at generating a table with an advanced form: a Voronoi diagram based structure. The design problem was constrained in terms of production as well as stability, requiring a time-consuming finite element evaluation. Regarding convergence time and rate, one of the sequential constraint-handling techniques performed significantly better than the weighted sum technique. Nevertheless, the weighted sum technique presented respectable results and therefore remains a relevant technique. Regarding diversity, none of the techniques could generate diverse solutions in a single search run. In contrast, the solutions from different searches were always diverse. Solution diversity is thus gained at the cost of more runs, but no evaluation of the diversity of the solutions is needed. This result is important, because a diversity evaluation function would otherwise have to be developed for every new type of design. Efficient handling of complex constraints is an important step toward mass customization of nontrivial product forms.