Olivier, Laurentz EugeneMaritz, M.G. (Michael)Craig, Ian Keith2020-09-072020-09-072019Olivier, L.E., Maritz, M.G. & Craig, I.K. 2019, 'Deep convolutional neural network for mill feed size characterization', IFAC-PapersOnLine, vol. 54, no. 14, pp. 105-110.1474-6670 (print)2405-8963 (online)10.1016/j.ifacol.2019.09.172http://hdl.handle.net/2263/76055Knowing the characteristics of the feed ore size is an important consideration for operations and control of a run-of-mine ore milling circuit. Large feed ore variations are important to detect as they require intervention, whether it be manual by the operator or by an automatic controller. A deep convolutional neural network is used in this work to classify the feed ore images into one of four classes. A VGG16 architecture is used and the classifier is trained making use of transfer learning.en© 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd.Deep learningConvolutional neural networkTransfer learningMillingRun-of-mine oreArticle