Show simple item record

dc.contributor.authorArtan, Unal
dc.contributor.authorFernando, Heshan
dc.contributor.authorMarshall, Joshua A.
dc.date.accessioned2021-07-12T17:51:53Z
dc.date.available2021-07-12T17:51:53Z
dc.date.issued2021-07-12
dc.identifier.urihttp://hdl.handle.net/1974/28954
dc.description.abstractThis paper presents an excavation material classification methodology that uses wavelet analysis and unsupervised learning on acceleration measurements. The technique was validated by using acceleration data that were acquired from three inertial measurement units (IMUs) on an instrumented 1-tonne capacity wheel loader. One IMU was installed on the loader’s boom and two on the bucket. The acceleration signals were logged for 32 manual excavation trials in three excavation materials with different rock size distributions, and the data were processed offline. The continuous wavelet transform was applied to the acceleration signals to extract features from the acceleration signals. The results show that classifying the wavelet feature set using an unsupervised k-means algorithm provides an average material classification accuracy of 81 %, when attempting to simultaneously classify all three materials.en
dc.language.isoenen
dc.publisherIEEEen
dc.relationStrategic Partnerships Grantsen
dc.subjectmining automationen
dc.subjectroboticsen
dc.subjectmachine learningen
dc.subjectwavelet analysisen
dc.subjectproprioceptive sensingen
dc.subjectrock fragmentationen
dc.subjectconstruction automationen
dc.subjectautonomous excavationen
dc.subjectclusteringen
dc.subjectmaterial classificationen
dc.titleAutomatic material classification via proprioceptive sensing and wavelet analysis during excavationen
dc.typepreprinten
project.funder.identifierhttp://dx.doi.org/10.13039/501100000038en
project.funder.nameNatural Sciences and Engineering Research Council of Canadaen
oaire.awardNumberNETGP 508484 - 17en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record