Assoc. Prof. Ke Yan
China Jiliang University, China
Speech Title: Data-driven Fault Detection and Diagnosis following Intelligence Programming with Machine Learning and Data Augmentation
Data-driven fault detection and diagnosis (FDD) solutions are highly demanded for smart building/city design, total energy performance improvement, electrical and electronic infrastructure maintenance, automation for constructions and many cross-discipline applications using modern AI, IoT, sensor networks and data analytics technologies. In this seminar, a specific FDD application will be introduced, namely, FDD for the heating, ventilation and air-conditioning (HVAC) systems. The motivation of proposing data-driven solutions to the HVAC FDD problem will first be introduced. Secondly, the methodologies that we proposed and developed in the past five years will be briefly described, which include semi-supervised learning, data augmentation and unsupervised learning. Last, the trends of using machine learning technology in the field of FDD are summarized and discussed. Some on-going projects and future works of us will also be introduced.
Ke Yan received both bachelor and Ph.D. degrees of computer science from School of Computing (SoC), National University of Singapore (NUS), Singapore in 2006 and 2012 respectively. He worked in Masdar Institute of Science and Technology (MIST) campus, Khalifa University, Abu Dhabi, UAE as a post-doctoral researcher from 2012 to 2014. Dr. Yan is actively engaged in cross-discipline research fields, including machine learning, artificial intelligence, cyber intelligence, applied mathematics, sustainability, applied energy and etc. He has published more than 60 full length papers with highly ranked conferences and journals, such as International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), Association for the Advancement of Artificial Intelligence (AAAI), IEEE Transactions on Industrial Informatics (TII), IEEE Transactions on Sustainable Energy (TSE), IEEE Transactions on Systems, Man and Cybernetics: Systems (SMCA), IEEE Access, Applied Energy (AE), Future Generation Computer Systems (FGCS), Energy and Buildings (ENB), Building and Environment (BAE) and International Journal of Refrigeration (JIJR).
严珂：新加坡国立大学博士，阿联酋马斯达尔研究所博士后，中国计量大学信息工程学院计算机应用技术专业副教授，新加坡国立大学客座研究员，SCI期刊IEEE/ACM Transactions on Computational Biology and Bioinformatics（TCBB），IEEE Transactions on Industrial Informatics (TII) Sensors MDPI, Building and Environment编委。主要研究方向为人工智能，包括机器学习、数据挖掘、深度学习等方法应用于能源控制领域的研究课题。主持国家自然科学基金项目两项，浙江省自然科学基金一项。截止目前，共计发表SCI论文76篇，其中，近三年发表的一作或通讯作者SCI论文37篇，包括中科院大类分区一区和二区论文18篇。部分重要成果发表在世界顶尖杂志和会议上，包括IEEE Transactions on Sustainable Energy, Energy and Buildings, Information Sciences, AAMAS, AAAI, IEEE Transactions on Systems, Man and Cybernetics: Systems, IEEE Access, Future Generation Computer Systems, Neurocomputing, Journal of Mathematical Biology等。 Google scholar引用总数已经达到1500余次。H-index为20。