Testing for knowledge: maximising information obtained from fire tests by using machine learning techniques

Arjan Dexters, Stephen Welch, Grunde Jomaas, Rolff Ripke Leisted, Ruben Van Coile

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A machine learning (ML) algorithm was applied to predict the onset of flashover in 1:5 scale Room Corner Test experiments with sandwich panels. Towards this end, a penalized logistic regression model was chosen to detect the relevant variables and consequently provided a tool that can be used to make predictions of unseen samples. The method indicates that a deeper understanding of the contributing factors leading to flashover can be achieved. Furthermore, it allows a more nuanced ranking than currently offered by the commonly used classification methods for reaction to fire tests. The proposed methodology shows a substantial value in terms of guidance for future large and intermediate scale testing. In particular, it is foreseen that the method will be extremely useful for assessing and understanding the behaviour of innovative materials and design solutions.
Original languageEnglish
Title of host publicationProc. 15th International Conference and Exhibition on Fire Science & Engineering
PublisherInterscience Communications Ltd
Publication statusPublished - 3 Jul 2019
Event15th International Conference and Exhibition on Fire Science & Engineering
- Royal Holloway College, London, United Kingdom
Duration: 1 Jul 20193 Jul 2019
http://www.intersciencecomms.co.uk/html/conferences/Interflam/if19/if19cfp.htm

Conference

Conference15th International Conference and Exhibition on Fire Science & Engineering
Abbreviated titleInterflam 2019
Country/TerritoryUnited Kingdom
CityLondon
Period1/07/193/07/19
Internet address

Fingerprint

Dive into the research topics of 'Testing for knowledge: maximising information obtained from fire tests by using machine learning techniques'. Together they form a unique fingerprint.

Cite this