{"647514":{"#nid":"647514","#data":{"type":"event","title":"PhD Proposal by Zhaoyi Xu","body":[{"value":"\u003Cp\u003EZhaoyi Xu\u003Cbr \/\u003E\r\n(Advisor: Prof. Joseph H. Saleh]\u003Cbr \/\u003E\r\nwill propose a doctoral thesis entitled,\u003Cbr \/\u003E\r\nDeep Prognostic and Transfer Learning for Accurate Remaining Useful Life\u003Cbr \/\u003E\r\nPrediction with Uncertainty Quantification\u003Cbr \/\u003E\r\nOn\u003Cbr \/\u003E\r\nTuesday, May 25 at 11:00 a.m.\u003Cbr \/\u003E\r\nBluejeans: https:\/\/bluejeans.com\/876523583\u003Cbr \/\u003E\r\nAbstract\u003Cbr \/\u003E\r\nUnexpected failures in engineering systems or equipment often lead to significant disruptions and\u003Cbr \/\u003E\r\nlosses. A key output of equipment prognostic is the estimation of remaining useful life (RUL) of the system\u003Cbr \/\u003E\r\nunder consideration. Accuracy in RUL prediction is important to sustain equipment reliability, reduce total\u003Cbr \/\u003E\r\nmaintenance costs, and prevent unexpected failures. This thesis addresses two prevalent challenges in\u003Cbr \/\u003E\r\ndata-driven RUL prediction related to model accuracy and model generalization.\u003Cbr \/\u003E\r\nIn Part I, this thesis addresses two aspects of the model accuracy challenge in data-driven RUL\u003Cbr \/\u003E\r\nprediction, namely the robustness to noise in sensor data and prognostic datasets, and the nonstationarity\u003Cbr \/\u003E\r\nor time-dependency of system degradation and RUL prediction given sensor data. A highly\u003Cbr \/\u003E\r\naccurate RUL prediction model is developed with uncertainty quantification, which integrates and\u003Cbr \/\u003E\r\nleverages the advantages of deep learning and nonstationary Gaussian process regression (DL-NSGPR).\u003Cbr \/\u003E\r\nThe model is then subjected to critical evaluation, and its performance benchmarked against other datadriven\u003Cbr \/\u003E\r\nRUL prediction models. Computational experiments show that the DL-NSGPR significantly\u003Cbr \/\u003E\r\noutperforms other current best-in-class models, and the etiology for this performance differential is\u003Cbr \/\u003E\r\nidentified and discussed.\u003Cbr \/\u003E\r\nIn Part II, currently work-in-progress, this thesis will address select aspects of the model generalization\u003Cbr \/\u003E\r\nchallenge. Two hypotheses for transfer learning related to RUL predictions are proposed, one related to\u003Cbr \/\u003E\r\nparameter transfer, and one to domain adaptation. Part II will design computational experiments and test\u003Cbr \/\u003E\r\nboth hypotheses. It will then compare and benchmark the performance of the two proposed transfer\u003Cbr \/\u003E\r\nlearning approaches. The best-in-class, if any, will be subjected to further critical assessment and its\u003Cbr \/\u003E\r\npotential for generalization examined.\u003Cbr \/\u003E\r\nCommittee\u003Cbr \/\u003E\r\n\uf0b7 Prof. Joseph H. Saleh \u0026ndash; School of Aerospace Engineering (advisor)\u003Cbr \/\u003E\r\n\uf0b7 Prof. Dimitri Mavris\u0026ndash; School of Aerospace Engineering\u003Cbr \/\u003E\r\n\uf0b7 Prof. Eric Feron\u0026ndash; School of Aerospace Engineering\u003Cbr \/\u003E\r\n\uf0b7 Dr. Evangelos Theodorou \u0026ndash; School of Aerospace Engineering\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Deep Prognostic and Transfer Learning for Accurate Remaining Useful Life Prediction with Uncertainty Quantification"}],"uid":"27707","created_gmt":"2021-05-17 17:35:03","changed_gmt":"2021-05-17 17:35:03","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2021-05-25T12:00:00-04:00","event_time_end":"2021-05-25T14:00:00-04:00","event_time_end_last":"2021-05-25T14:00:00-04:00","gmt_time_start":"2021-05-25 16:00:00","gmt_time_end":"2021-05-25 18:00:00","gmt_time_end_last":"2021-05-25 18:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"102851","name":"Phd proposal"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}