Large-scale Design Projects Research Articles

Evaluating large-language-model chatbots to engage communities in large-scale design projects

Abstract Recent advances in machine learning have enabled computers to converse with humans meaningfully. In this study, we propose using this technology to facilitate design conversations in large-scale urban development projects by creating chatbot systems that can automate and streamline information exchange between stakeholders and designers. To this end, we developed and evaluated a proof-of-concept chatbot system that can perform design conversations on a specific construction project and convert those conversations into a list of requirements. Next, in an experiment with 56 participants, we compared the chatbot system to a regular online survey, focusing on user satisfaction and the quality and quantity of collected information. The results revealed that, with regard to user satisfaction, the participants preferred the chatbot experience to a regular survey. However, we found that chatbot conversations produced more data than the survey, with a similar rate of novel ideas but fewer themes. Our findings provide robust evidence that chatbots can be effectively used for design discussions in large-scale design projects and offer a user-friendly experience that can help to engage people in the design process. Based on this evidence, by providing a space for meaningful conversations between stakeholders and expanding the reach of design projects, the use of chatbot systems in interactive design systems can potentially improve design processes and their outcomes.

A Conversation With … Adrian Fisher, the World's Leading Designer of Landscape Mazes.

A Conversation With … Adrian Fisher, the World's Leading Designer of Landscape Mazes.

Iterations as the result of social and technical factors: empirical evidence from a large-scale design project

Understanding the role of iterations is an important topic within design research and design practice. Iterations often involve rework and thus often increased costs and completion time. Many theories and studies ascribe iterations either to the social or technical complexity of the design process. Here, we join the two perspectives by analysing metadata of more than 3000 documents produced during the design of a biomass power plant. We gain insights by using network analysis and by visualising the temporal unfolding of the design process. Subsequently, we develop a statistical model to rigorously test multiple hypotheses showing that iterations are a combination of technical and social factors. The paper shows that iterations increase when the number of stakeholders/participants increases and when external suppliers are involved. Iterations are lower in presence of integrative activities. Furthermore, the paper shows the existence of synergistic interactions between nodes’ in-going and out-going flow in both activity and team networks associated with an increase in iterations.

Consolidation of Methods for Visualization and Management of Engineering Design Data Sets

Existing design support tools and methods struggle to deal with numerous data management situations that arise in medium and large-scale design projects. Authors analyse and compare the suitability and efficiency of several methods for managing and visualization of relationships between engineering objects and propose guidelines for building a framework/interface for consolidated usage of those methods in industrial practice. The proposed matrix- based consolidation methodology builds on findings gathered from two monitored design projects as well as previous research in areas of traceability and visualization. For engineering objects (data sets) that belong to one or two domains which are not hierarchically structured it is argued that a simple matrix interface is sufficient to record the relations. Furthermore, if the engineering objects are hierarchically structured the browser interface is suggested. In the most complex situation, where objects belong to multiple different domains the use of diagrams and digital whiteboards is suggested.

Connecting Practice to Research (and back to practice): Making the Leap from Design Practice to Design Research

The proliferation of research degrees in the subject of design reflects the growing importance of research-based approaches in this discipline. However, it is not unreasonable to suggest that design (being a creative, subjective and artifact-based activity) does not naturally lend itself to the scientific, objective and knowledge-based activity of research. As a result, design researchers who have practised as designers are still rare within the design research community. Of those that do make the transition from practice to research (and back), they often enter with a misinformed notion of ‘research’, which ranges from a view that design research consists of a large-scale design project, to one of scientific experimentation only. This paper draws from the experiences of the author who has undertaken and completed a research degree in the subject of Design. It is a response to difficulties faced by the author during her PhD experience and proposes to address the questions: Are there any similarities between practice and research that can be highlighted to enable designers to understand the requirements of research? What skills and knowledge can be derived from research, which can be brought back into design practice? How can we better prepare designers to undertake research? It is hoped that the issues expressed here will be a basis for continued discussion on how design education can begin to incorporate a research-based curriculum, and for professional bodies to promote the value of research to practitioners.

Decomposition of the Design Process

In concurrent engineering, an attempt is made to perform design and other related activities simultaneously rather than in series as in the case of traditional design. This may result in a reduction of the duration of the design project, cost savings, and better quality of the final design. However, the concurrent engineering approach might increase the complexity of the design process and make it more difficult to manage. One way to reduce the complexity of a large scale design project is to apply decomposition. This paper presents a methodology for decomposition of a design process to enhance concurrency. The incidence matrix is used to represent the relationship between tasks and design parameters. The decomposition of a task-parameter incidence matrix is discussed. The constraint-variable decomposition, which is a special case of the task-parameter decomposition, is also presented for the management of constraints. Clustering of tasks involved in the design process allows one to determine a potential group of tasks that might be performed simultaneously or tasks that need a special attention during the design process. As a result of decomposition, the design cycle might be reduced. Another advantage of grouping tasks is the simplification of scheduling and management of the design project. Finally, the proposed approach provides a systematic way of decomposing a design problem into subproblems.

A computer-based model for system level reliability and maintainability allocation

This paper describes computer-based heuristic models for Reliability and Maintainability (R&M) allocation for large systems. The model is an embellishment to the Maintenance Allocation Program (MAP) developed at McDonnell Douglas Corporation. The new version of MAP known as REMAP (Reliability Embellished MAP) is a decision support tool for contractors who are involved in large scale design projects such as aircraft design. The REMAP allows the user to give preliminary R&M information about the system. The REMAP gives “what if” changes on the requirements required to meet the desired design reliability specification.