Architecture, Building and Planning - Theses

Permanent URI for this collection

http://hdl.handle.net/11343/280

Filters

2022 2
1 1
2
Reset filters

Settings
Statistics
Citations
End date: 2022 × Start date: 2020 × Subject: Artificial Intelligence ×

Search Results

Now showing 1 - 2 of 2
  • Item
    Thumbnail Image
    Expertise, playfulness, analogical reasoning: Three learning mechanisms to train Artificial Intelligence for design applications
    Mirra, Gabriele ( 2022)
    Following the success of AI in statistical regression, image generation, and decision-making tasks, new computational tools based on AI have been proposed for design applications since 2014. Engineers have used AI models to improve the efficiency of software for structural analysis and optimisation, whereas architects have started exploring the potential of AI tools for image generation to support conceptual design. This thesis aims to demonstrate that AI can support the design process at an even deeper level. In other words, AI models can autonomously learn design strategies and interact with a designer to suggest design options that are unconstrained and unbiased by a formal description of the design problem, which is often required in structural optimisation applications. AI models can also learn to produce technical descriptions of a design object, whereas current applications of AI in architectural design primarily focus on synthesising visual output. To do so, this thesis examines how AI models can be trained in architectural and structural design and how the trained AI models can be integrated with CAD software to support the design process. This thesis takes the view that training AI in design can be considered as training a novice designer. Therefore, in line with early studies in AI in design conducted in the 1990s, this thesis examines how AI can simulate a designer’s cognition and, in particular, acquire design knowledge by simulating three learning mechanisms relevant to design education: expertise, playfulness, and analogical reasoning. In design education, expertise is related to studying and analysing design precedents; playfulness is linked to model-making, and analogical reasoning pertains to finding inspiration in domains other than architecture, such as nature, art, music, and literature. Through a set of applications, the thesis shows how AI models can be trained in design by simulating the three learning mechanisms and how the trained AI models can be interfaced with CAD software. The applications aim to open a new path for research in AI in design by demonstrating that AI can effectively simulate some aspects of human cognition and interact with a designer through an exchange of visual information. The designer can decide to use the outputs obtained through the interaction with these tools to inform different stages of the design process, which could include problem-framing and decision-making. Although no given tool can be guaranteed to expand a designer’s creativity or automatically lead to outstanding design solutions, the AI models described in this thesis reveal a certain degree of autonomy and thus have a higher potential than other computational techniques to support the design process at a deep level.
  • Item
    No Preview Available
    An automated knowledge-based decision support system for managing non-conformances on Australia's large infrastructure projects
    Adio, Obafemi Adekunle ( 2022)
    The construction industry in Australia and most of the developed world has underperformed in its response to ongoing challenges posed by globalisation, increased competition, pressure to improve productivity, demand for better project performance, and pressure to deliver profit to stakeholders. A central underperformance area is a failure to deliver a project to meet a set of requirements agreed as part of the contract (non-conformance). The inability to adequately manage non-conformances and their attendant impacts often result in cost and time overrun, among others. The underperformance of the construction industry is also evident in the high rate of recurring non-conformances across projects, which may create ongoing maintenance challenges due to defects arising during the design life of a product. To minimise non-conformances and their impact, construction companies must capture, document, and disseminate knowledge and lessons from previous project non-conformances to translate them into improvements to prevent future recurrence of similar non-conformances. However, non-conformance lessons are currently unstructured and inadequately disseminated in the construction industry, with projects placing a high premium on experience. Different functional areas within projects sometimes operate in silos by circulating information within their immediate groups only. Disseminating knowledge and lessons from previous project non-conformances will result in more efficient and effective construction processes that will deliver projects on time and budget, reduce safety incidents, and meet all stakeholder requirements. Such dissemination will also help construction companies develop organisational intelligence to increase their competitive edge when bidding for new projects. Hence, this research developed an automated knowledge-based decision support system (KBDSS) for managing non-conformances on infrastructure construction projects. The KBDSS is equipped with artificial intelligence to classify non-conformances from across multiple projects in one place and analyse them. Project participants can thereby gain timely access to relevant information and knowledge from past non-conformances to enhance their decision-making. Four main questions underpinned this research: “How do construction companies perceive and rate quality in comparison to other project constraints?”, “How important are non-conformance lessons to the corporate strategy for future projects?”, “How are non-conformances currently managed on construction projects?”, and “How can an automated knowledge-based decision support system (KBDSS) for extracting, analysing, and disseminating non-conformances be developed for Australia’s infrastructure projects?” This research adopted the design science research paradigm to understand the theory of non-conformances, how it has been managed, and the existing gaps in theory and practice to develop a KBDSS that meets the expectation of the infrastructure construction projects. A total of 13,940 non-conformance data from 15 infrastructure projects by a tier-one construction company in Australia were accessed, with 11,334 of them thoroughly reviewed. A total of 60 interviews were conducted in the first instance with stakeholders in the infrastructure construction industry and participants from five major infrastructure projects across Australia with a combined value of over AU$15 billion. The roles of respondents included project managers, design managers, quality managers and project engineers. The 11,334 non-conformance data from the selected projects were analysed, revealing a lack of adequate classification and dissemination of non-conformance lessons using existing systems. The data analysis culminated in developing and validating the KBDSS prototype to support decision-making in non-conformance management on infrastructure projects.