Data-driven sustainable ship design using Axiomatic Design and Bayesian Network Model
Name
Fardelas_2021_IOP_Conf._Ser.__Mater._Sci._Eng._1174_012003.pdf
Size
659.16 KB
Format
Adobe PDF
Checksum (MD5)
a9c1c6c9df5906ef2f273e24d2a35008
Author(s)
Fardelas, G
Kim, S G
Date Issued
August 1, 2021
Journal
IOP Conference Series: Materials Science and Engineering
Publisher
IOP Publishing
Citation
G Fardelas and S G Kim 2021 IOP Conf. Ser.: Mater. Sci. Eng. 1174 012003.
Version
Final published version
Abstract
Environmental sustainability, as well as social and economic well-being, must be considered in every stage of a product lifecycle, from conceptual design to its retirement. Even though this sustainability-centric approach represents a critical driver for innovation, it also increases the design complexity. Nowadays, the maritime transport accounts for a large share of transport demand, and the importance of sustainable ship design is increasingly growing, not only for ethical and legislative but also for competitive reasons. The design of a sustainable ship considering all those aspects is a complex process in this regard. One way to manage the complexity is to identify and avoid the functional couplings at the early stage of the design process. This paper presents the conceptual design of a merchant ship's conventional propulsion system with a view to the Axiomatic Design framework and known sustainable engineering principles. We also explore the Bayesian machine learning interface to propose a data-driven method for calculating the probability of achieving specific sustainability-related functional requirements. Data-driven Bayesian reasoning can also be used to select the best design parameter among the proposed alternatives as well as to identify hidden design couplings that have not identified by the designers in the conceptual design stage.
Subjects
General Medicine
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
System Design and Management Program.
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1088/1757-899x/1174/1/012003
