Show simple item record

dc.contributor.authorTaylor, James
dc.contributor.authorConduit, B
dc.contributor.authorDickens, Anthony
dc.contributor.authorHall, C
dc.contributor.authorHillel, M
dc.contributor.authorMiller, RJ
dc.date.accessioned2019-04-12T23:30:06Z
dc.date.available2019-04-12T23:30:06Z
dc.date.issued2019
dc.identifier.isbn9780791858554
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/291532
dc.description.abstract<jats:title>Abstract</jats:title> <jats:p>The application of machine learning to aerospace problems faces a particular challenge. For successful learning a large amount of good quality training data is required, typically tens of thousands of cases. However, due to the time and cost of experimental aerospace testing, this data is scarce. This paper shows that successful learning is possible with two novel techniques: The first technique is rapid testing. Over the last five years the Whittle Laboratory has developed a capability where rebuild and test times of a compressor stage now take 15 minutes instead of weeks. The second technique is to base machine learning on physical parameters, derived from engineering wisdom developed in industry over many decades.</jats:p> <jats:p>The method is applied to the important industry problem of predicting the effect of blade damage on compressor operability. The current approach has high uncertainty, it is based on human judgement and correlation of a handful of experimental test cases. It is shown using 100 training cases and 25 test cases that the new method is able to predict the operability of damaged compressor stages with an accuracy of 2% in a 95% confidence interval; far better than is possible by even the most experienced compressor designers. Use of the method is also shown to generate new physical understanding, previously unknown by any of the experts involved in this work. Using this method in the future offers an exciting opportunity to generate understanding of previously intractable problems in aerospace.</jats:p>
dc.description.sponsorshipAerospace Technology Institute Rolls-Royce plc.
dc.publisherAmerican Society of Mechanical Engineers
dc.rightsAll rights reserved
dc.titlePredicting the operability of damaged compressors using machine learning
dc.typeConference Object
prism.publicationDate2019
prism.publicationNameProceedings of the ASME Turbo Expo
prism.volume2A-2019
dc.identifier.doi10.17863/CAM.38691
dcterms.dateAccepted2019-03-17
rioxxterms.versionofrecord10.1115/GT2019-91339
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2019-01-01
dc.contributor.orcidTaylor, James [0000-0002-1283-8228]
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.funder-project-idTechnology Strategy Board (113076)
cam.issuedOnline2019-11-05
pubs.conference-nameASME Turbo Expo 2019: Turbomachinery Technical Conference and Exposition
pubs.conference-start-date2019-06-17
cam.orpheus.successThu Nov 05 11:53:46 GMT 2020 - Embargo updated
pubs.conference-finish-date2019-06-21
rioxxterms.freetoread.startdate2020-01-01


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record