Graduate Thesis Or Dissertation
 

Data-Driven Environmentally Sustainable Product Design: A Shift Toward Increased use of Sustainable Design Activities in the Early Design Phase

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/9019s940f

Descriptions

Attribute NameValues
Creator
Abstract
  • Modern product design drives the boundaries of innovation by encompassing complex Design-for-X objectives, and the inclusion of multidimensional stakeholders. This growing complexity in product design has left design teams unequipped, as classical design theory is bounded by designer experience, expertise, and cognition. One novel approach to tackling product complexity is to leverage data into improved design processes through data-driven design methods. In this dissertation, data-driven design approaches are presented as a means to explore applied knowledge discovery in product data, with a particular focus on function-based design, life cycle inventory, and life cycle assessment data. Using artificial intelligence approaches ranging from decision trees to graph neural networks, and statistical methods such as kernel density estimation, function-based sustainable design is more readily achievable. This dissertation presents methods for introducing sustainable design knowledge in the early stages of product design through the use of data-driven approaches on historic LCA product data. Here, functional modeling is identified as the entry point to the early design phase that can be altered to meet sustainable design objectives. By using data-driven design methods, components are related to functional performance and estimated environmental impact. The culmination of this work is the creation of a probabilistic data-driven methodology that assesses the environmental impact of functional chains and provides component suggestions that reduce potential environmental impact. The research presented in this dissertation begins with an introduction to data-driven design literature and research opportunities (manuscript one). From these opportunities, manuscripts two and three introduce two function-based design methods for aiding in component function assignment and automated functional modeling. Manuscripts four and five introduce novel sustainable methods that realize the goals of this dissertation to create data-driven sustainable design methods applicable to the early design phase. Expanding on this work, the disparity in product data encourages the exploration of richer data sets. By leveraging multiple data sources, including manufacturing, digital, and other life cycle data, we can look forward to novel approaches in data-driven design for knowledge enrichment in function-based sustainable design.
License
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details FerreroVincenzoJ2021.pdf 2021-05-24 Public Download