Data Mining to Support Engineering Design Decision


Jadhav, Pooja, Wong, Sylvia C, Wills, Gary B, Crowder, Richard M and Shadbolt, Nigel R (2007) Data Mining to Support Engineering Design Decision. In, Workshop on Semantic Web and Web 2.0 in Architectural, Product and Engineering Design, 6th International Semantic Web Conference (ISWC), Busan, Korea,

Download

[img] PDF
Download (337Kb)

Description/Abstract

The design and maintenance of an aero-engine generates a significant amount of documentation. When designing new engines, engi- neers must obtain knowledge gained from maintenance of existing engines to identify possible areas of concern. Firstly, this paper investigate the use of advanced business intelligence tenchniques to solve the problem of knowledge transfer from maintenance to design of aeroengines. Based on data availability and quality, various models were deployed. An asso- ciation model was used to uncover hidden trends among parts involved in maintenance events. Classification techniques comprising of various algorithms was employed to determine severity of events. Causes of high severity events that lead to ma jor financial loss was traced with the help of summarization techniques. Secondly this paper compares and evalu- ates the business intelligence approach to solve the problem of knowl- edge transfer with solutions available from the Semantic Web. The re- sults obtained provide a compelling need to have data mining support on RDF/OWL-based warehoused data.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Event Dates: 11 November 2007
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Web & Internet Science
Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Electronic & Software Systems
Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Agents, Interactions & Complexity
ePrint ID: 264807
Date Deposited: 12 Nov 2007 23:48
Last Modified: 27 Mar 2014 20:09
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/264807

Actions (login required)

View Item View Item

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics