Data-driven fault diagnosis and prognosis for process faults using principal component analysis and extreme learning machine
I am studying process system engineering at the School of Engineering, Newcastle University. I am in my third year of PhD. My main research direction is Fault Prognosis and Fault Magnitude Estimation Based on Hybrid Computational Intelligence and Data Analysis Techniques for Industrial Processes.
Dr. Hao Qin, received the B.Eng. degree with First Class Honous in Mechanical Design, Manufacturing from University of Shanghai for Science and Technology, China, in 2011, the M.Sc. degree in Engineering Design from University of Bath, UK, in 2012, and the Ph.D. degree in Engineering Design from University of Portsmouth, UK, in 2016. From 2016 to 2017, he was a Lecture in Mechanical Design in the Engineering Department of University of Exeter, UK. He is currently a Research Fellow in the Intelligent Modelling Department of Guangdong Institute of Intelligent Manufacturing. His research interests include knowledge capture and reuse, knowledge management for engineering design, knowledge graph, and intelligent design.
Distributed Fault Diagnosis and Prognosis of Nonlinear Mechatronic System Using Adaptive Biogeography-based Optimization
Paper ID: GF-002771.
Title: “Distributed Fault Diagnosis and Prognosis of Nonlinear Mechatronic System Using Adaptive Biogeography-based Optimization”
Chenyu Xiao received the B.E. degree in automation in 2016 from the Hefei University of Technology, Hefei, China. He is currently working toward the Ph.D. degree in electrical engineering with the School of Electrical and Automation Engineering, Hefei University of Technology, Hefei, China. His research interests include fault diagnosis and prognosis of hybrid systems, bond graph modeling, and evolutionary algorithms.
Improved Process Fault Diagnosis by Using Neural Networks with Andrews Plot and Autoencoder
Shengkai Wang, a PhD from Newcastle University. The main research field is chemical process fault diagnosis. The main research content is process monitoring based on hybrid intelligent techniques.Research interest: neural networks, process fault detection and diagnosis,and multivariate statistical data analysis.
Zeitfenster der Veranstaltung (1)
02:45pm - 05:15pm