Tutorial & Workshops
Tutorial & Workshops
Workshop 1:
Advanced Alarm Management and Design for Complex Industrial Facilities
Main Organizers
Wenkai Hu, China University of Geosciences, China
Sirish L. Shah, University of Alberta, Canada
Tongwen Chen, University of Alberta, Canada
Co-organizers
Jiandong Wang, Shandong University of Science and Technology, China
Fan Yang, Tsinghua University, China
Masaru Noda, Fukuoka University, Japan
Statement of Objectives
The objective of this workshop is to introduce participants to ideas and solutions for improved alarm management based on seamless integration of information from process and alarm databases complemented with process connectivity information. Process-data based alarm system design aims at obtaining optimal alarm parameters for filters, deadbands, delay timers, and alarm limits, based on evaluation metrics, including alarm detection delay and false and missed alarm rates. The advanced alarm analytics tools that will be presented at this workshop are able to detect nuisance alarms and discover hidden patterns from alarm and event historian using statistical learning and data mining approaches. Historical datasets combined with process topology information make it possible to capture propagation paths of abnormalities and thus can help with root cause analysis.
The focus of this workshop is to present recent advances and new techniques of industrial alarm management using sensor and alarm data analytics. The emphasis in this workshop will be on how to conduct advanced data analytics to extract useful in-formation from data to help in designing optimal alarm systems, finding out problems, and discovering hidden patterns. Interesting topics covered in this workshop include correlated alarms, alarm floods, alarm system design, causality inference, root cause analysis, and visualization.
Intended audience
The intended audience for this workshop would be industrial practitioners working on real alarm managing problems, vendors designing alarm systems, researchers studying advanced alarm management solutions, graduate students with interests in data science and its application to solve industrial problems.
Speakers
Sirish L. Shah, University of Alberta, Canada
Sirish L. Shah has been with the University of Alberta since 1978, where he held the NSERC-Matrikon-Suncor-iCORE Senior Industrial Research Chair in Computer Process Control from 2000 to 2012. He is the recipient of the Albright & Wilson Americas Award of the Canadian Society for Chemical Engineering (CSChE) in 1989, the Killam Professor in 2003, the D.G. Fisher Award of the CSChE for significant contributions in the field of systems and control, the ASTECH award in 2011 and the 2015-IEEE Transition to Practice award. The main areas of his current research are process and performance monitoring, analysis and rationalization of alarm systems. He has co-authored three books, the first titled, Performance Assessment of Control Loops: Theory and Applications, a second titled Diagnosis of Process Nonlinearities and Valve Stiction: Data Driven Approaches, and a more recent monograph on Capturing Connectivity and Causality in Complex Industrial Processes. He is Emeritus Professor at the University of Alberta, a Fellow of the Canadian Academy of Engineering and the Chemical Institute of Canada.
Tongwen Chen, University of Alberta, Canada
Tongwen Chen is presently a Professor and Tier 1 Canada Research Chair in Intelligent Monitoring and Control in the Department of Electrical and Computer Engineering at the University of Alberta, Edmonton, Canada. He received the B.Eng. degree in Automation and Instrumentation from Tsinghua University (Beijing) in 1984, and the M.A.Sc. and Ph.D. degrees in Electrical Engineering from the University of Toronto in 1988 and 1991, respectively. His research interests include computer and network based control systems, process safety and alarm systems, and their applications to the process and power industries. He has served as an Associate Editor for several international journals, including IEEE Transactions on Automatic Control and Automatica. He is a Fellow of IEEE, IFAC, as well as the Canadian Academy of Engineering.
Masaru Noda, Fukuoka University, Japan
Masaru Noda is a professor in Department of Chemical Engineering at Fukuoka University, Japan. He received the B.Eng., M.Eng., and Ph.D. degrees in Chemical Engineering from Kyoto University in 1994, 1996 and 2000, respectively. His main research focus is on plant operational data analysis for safe process operation.
Jiandong Wang, Shandong University of Science and Technology, China
Jiandong Wang is presently a full professor of College of Electrical Engineering and Automation at the Shandong University of Science and Technology, Qingdao, Shandong Province, China. He received a B.E. in automatic control from Beijing University of Chemical Technology, Beijing, China, in 1997, and an M.Sc and Ph.D. in Electrical and Computer Engineering from the University of Alberta, Canada, in 2003 and 2007, respectively. From 1997 to 2001, he was a Control Engineer with the Beijing Tsinghua Energy Simulation Company, Beijing, China. From February 2006 to August 2006, he was a Visiting Scholar at the Department of System Design Engineering at the Keio University, Japan. From December 2006 to October 2016, he was an assistant/associate/full Professor with the College of Engineering, Peking University, China.
Fan Yang, Tsinghua University, China
Fan Yang received the B.Eng. degree in Automation and the Ph.D. degree in Control Science and Engineering from Tsinghua University, Beijing, China, in 2002 and 2008, respectively. After working as a Postdoctoral Fellow with Tsinghua University and the University of Alberta, he joined the Department of Automation, Tsinghua University in 2011, where he is currently an Associate Professor. His research interests include topology modeling of large-scale processes, abnormal events monitoring, process hazard analysis, and smart alarm management. He was a recipient of the Young Research Paper Award from the IEEE Control Systems Society Beijing Chapter in 2006, the Outstanding Graduate Award from Tsinghua University in 2008, the Science and Technology Progress Award from the Chinese Association of Automation in 2018, and the Teaching Achievement Awards from Tsinghua University in 2012, 2014, and, 2016 and from the Chinese Association of Automation in 2016.
Wenkai Hu, China University of Geosciences, China
Wenkai Hu received the B.Eng. and M.Sc. degrees in Power and Mechanical Engineering from Wuhan University, Wuhan, Hubei, China, in 2010 and 2012, respectively, and the Ph.D. degree in Electrical and Computer Engineering from the University of Alberta in 2016. He worked as a Post-Doctoral Fellow from Oct. 2016 to Sep. 2018, and a Research Associate from Nov. 2018 to Feb. 2019 in the University of Alberta. He is currently a Professor with China University of Geosciences, Wuhan, China. His research interests include advanced alarm monitoring, process control, and data mining for complex industrial processes.
List of topics
The following topics will be discussed in this workshop. Each topic will be accompanied by one or more industrial case studies to convey the practical value of advanced alarm management techniques.
Smart analytic tools for advanced alarm management
The process industry is awash with all types of data archived over many years: sensor data, alarm data with operator actions to ‘navigate’ the process to operate safely at desired conditions and process models that are used for advanced control. The fusion of information from such disparate sources of process data is the key step in devising strategies for a smart analytics platform for safe and autonomous process operation. The purpose of this talk is to present results and strategies that will ultimately lead to safe and optimal autonomous or semi-autonomous process operation.
Evaluation methods of plant alarm systems
This presentation will introduce two evaluation methods for plant alarm systems. The first method is for identifying sequential alarms hidden in plant operational data using dot matrix analysis. Dot matrix analysis is one of the sequence alignment methods for identifying similar regions in a pair of DNA or RNA sequences. The second evaluation method uses an operator model that mimics humans’ fault detection and identification (FDI) behavior. The operator model automatically produces an FDI track in an emergency after a malfunction occurs. By analyzing the FDI tracks after causing all the assumed malfunctions in the plant, we can evaluate the performances of the alarm system. The results of the case studies demonstrate the usefulness of those evaluation methods.
Advanced alarm data analytics
This presentation will show the applicability and effectiveness of statistical approaches and data mining techniques in discovering meaningful patterns from historical alarm data, such as mode-based alarms, frequent alarm flood patterns, and alarm response workflow models. Design of alarm data visualization will also be discussed.
Design of alarm systems and root-cause analysis of alarms
This presentation will introduce design of univariate alarm systems including alarm delay times and deadbands, operating-zone-based multivariate alarm systems, and root-cause analysis of alarms based on the clusters of similar data segments in historical databases.
Multivariate alarm strategies and analysis methods
This presentation will introduce advanced alarms based on process data analytics and correlation/causality analysis based on process and alarm data mining in combination with process connectivity knowledge, with applications to root cause analysis of propagated or even plant-wide abnormalities.
Program
|
1:00 – 1:15 p.m. |
Opening Remarks and Introduction Tongwen Chen, University of Alberta, Canada |
| 1:15 – 2:00 p.m. |
Smart analytic tools for advanced alarm management Sirish L. Shah, University of Alberta, Canada |
| 2:00 – 2:45 p.m. |
Evaluation Methods of Plant Alarm Systems |
| 2:45 – 3:00 p.m. | Coffee Break |
| 3:00 – 3:45 p.m. | Advanced Alarm Data Analytics Wenkai Hu, China University of Geosciences, China |
| 3:45 – 4:30 p.m. | Design of Alarm Systems and Root-Cause Analysis of Alarms Jiandong Wang, Shandong University of Science and Technology, China |
|
4:30 – 5:15 p.m. |
Multivariate Alarm Strategies and Analysis Methods Fan Yang, Tsinghua University, China |
| 5:15 – 5:30 p.m. | General Questions and Answers, and Discussions (Moderated by Tongwen Chen) |
Workshop 2:
Recent advances and future trends in basics and applications of Gaussian processes
Main Organizer
Takamitsu Matsubara, Graduate School of Science and Technology, Nara Institute of Science and Technology, Nara, Japan
Co-organizer
Satoshi Satoh, Graduate School of Engineering, Osaka University, Osaka, Japan
Statement of Objectives
The Gaussian processes that appeared in the machine learning field since around 2000 are extensively utilized in various application fields because of their mathematical simplicity and ease of handling in Bayesian reasoning. They have also been recently drawing much attention in the field of control engineering such as control theory and system identification in particular for stochastic systems. In this workshop, we will have four invited speakers from such various fields as modeling, robotics, reinforcement learning, and control theory, to discuss the recent advances and future trends in basics and applications of Gaussian processes.
Intended audience
Engineers, researchers, and graduate students who are interested in AI, machine learning, robotics, modeling, stochastic systems, and control engineering.
Speakers
Professor Daichi Mochihashi, The Institute of Statistical Mathematics, Japan
Daichi Mochihashi received BS from the University of Tokyo, MS and PhD from Nara Institute of Science and Technology in 1998, 2000, and 2005, respectively. After working at ATR Spoken language research laboratories and NTT CS labs, he has been an associate professor at the Institute of Statistical Mathematics, Tokyo, Japan since 2011. His research mainly focuses on statistical natural language processing, but is also interested in Bayesian machine learning and robotics related to languages.
Professor Jaime Valls Miro, University of Technology, Sydney, Australia
Jaime Valls Miro received his B.Eng. and M.Eng. in Computer Science (Systems Engineering) from the Valencia Polytechnic University (UPV, Spain), in 1990 and 1993 respectively. He received his Ph.D. in robotics and control systems from Middlesex University (UK) in 1998, and worked in the underwater robotics industry as a software and control systems analyst until 2003. In 2004 he joined the Centre for Autonomous Systems in UTS (Australia), where he is currently an Associate Professor. His areas of interest span across the field of robotics, most notably modelling sensor behaviours for perception and action, computational Intelligence in human-robot interaction – particularly advocating for the use of machine learning tools such as Bayesian Networks, Gaussian Processes etc and with a special focus on Assistive Robotics, and mapping and planning in unstructured environments. In the last few years he has devoted this combined interest in pursuing a better understating of condition assessment sensing for critical water mains in close collaboration with the water industry. He is a Committee Member and regular reviewer at the top robotics conferences (ICRA, IROS …) and journals (AURO, FSR, Robotica, etc).
Professor Takamitsu Matsubara, Nara Institute of Science and Technology, Japan
Takamitsu Matsubara received his B.E. in electrical and electronic systems engineering from Osaka Prefecture University, Osaka, Japan, in 2003, an M.E. in information science from the Nara Institute of Science and Technology, Nara, Japan, in 2005, and a Ph.D. in information science from the Nara Institute of Science and Technology, Nara, Japan, in 2007. From 2005 to 2007, he was a research fellow (DC1) of the Japan Society for the Promotion of Science. From 2013 to 2014, he was a visiting researcher of the Donders Institute for Brain Cognition and Behaviour, Radboud University Nijmegen, Nijmegen, The Netherlands. He is currently an associate professor at the Nara Institute of Science and Technology and a visiting researcher at the ATR Computational Neuroscience Laboratories, Kyoto, and AIST, Tokyo, Japan His research interests are machine learning and control theory for robotics.
Dr. Yuji Ito, Toyota Central R&D Labs, Japan
Yuji Ito received his B.S., M.S., and Ph.D. degrees from Nagoya University, Japan, in 2009, 2011, and 2014, respectively. Since 2011, he has been with TOYOTA CENTRAL R&D LABS., INC., Japan. His research interests include data-driven control, stochastic control, optimal control, and tactile sensors. He is a member of SICE and IEEE.
List of topics
Gaussian Processes for Recognizing Motions in Robotics
Gaussian process (GP) is a mathematically elegant paradigm for dealing with stochastic trajectories and their fluctuations inherent to robotics. In this talk, I will briefly introduce the machinery of Gaussian processes from a viewpoint of extended linear regression, and describe our work on recognizing motions (running, walking, grasping, throwing, ..) only from the observed time series of the angles of joints of a robot. Using a dynamic programming and MCMC, our model can recognize motions and the number of such motions in a completely unsupervised way, also leveraging the hierarchical Dirichlet processes.
Exploiting GPs for Information-theoretic Robotic Mapping
The talk will describe a framework for autonomous robotic mapping that uses Gaussian Processes (GPs) to model high-dimensional dense maps. Robotic mapping is traditionally implemented using occupancy grid representations. The occupancy grid representation relies on the assumption of independence between grid cells and ignores structural correlations present in the environment. An incremental GP occupancy mapping technique that is computationally tractable for online map building and represents a continuous model of uncertainty over the map spatial coordinates will be described. This representation is particularly suited for robotic exploration with imperfect stated information. The standard way to represent geometric frontiers extracted from occupancy maps is to assign binary values to each grid cell. This notion can be now extended to novel probabilistic frontier maps computed efficiently using the gradient of the GP occupancy map. The intuition behind a mutual information-based greedy exploration technique built on that representation will be provided. A primary motivation is the fact that high-dimensional map inference requires fewer observations, leading to faster map entropy reduction during exploration for map building scenarios.
Multimodal Gaussian Process Policy Search for Robot Control
Policy search reinforcement learning using non-parametric policy models is a promising approach for learning of continuous robot control from data with high-dimensional, non-linear and redundant sensory inputs as observations. However, previous methods cannot capture the multimodality in control policies, which is often required for various robotics tasks. In this talk, we will discuss a novel policy search reinforcement learning algorithm that can deal with multimodality in control policies based on Overlapping Sparse Pseudo-input Mixtures of Gaussian Processes (OMSGPs). Its application to several robot control problems will be also discussed.
Design of Feedback Controllers Based on Gaussian Process Regression
Gaussian process (GP) regression is a promising method for identifying uncertain systems as data-driven GP models using a training data set of the systems. The GP models avoid overfitting to the data, need little knowledge of the systems, and obtain the uncertainty. Recently, various methods focus on controlling the GP models and designing flexible controllers using the GP regression. This talk will introduce approaches to design feedback controllers based on the GPs.
Program
September 10 Tuesday 2019 1:00 p.m.-5:00p.m.
| 1:00 p.m. | Opening, Tutorial presentation & Remarks Takamitsu Matsubara, Nara Institute of Science and Technology, Japan |
|
1:05 p.m. – 2:00 p.m. |
Gaussian processes for recognizing Motions in robotic Daichi Mochihashi, The institute of Statistical Mathematics, Japan |
|
2:00 p.m. – 2:55 p.m. |
Exploiting GPs for Information-theoretic Robotic Mapping Jaime Valls Miro, University of Technology, Sydney, Australia |
|
2:55 p.m. – 3:30 p.m. |
coffee break |
|
3:30 p.m. – 4:25 p.m. |
Multimodal Gaussian Process Policy Search for Robot Control Takamitsu Matsubara, Nara Institute of Science and Technology, Japan |
|
4:25 p.m. – 5:20 p.m. |
Design of Feedback Controllers Based on Gaussian Process Regression Yuji Ito, Toyota Central R&D Labs, Japan |
|
5:20 p.m. – 5:25 p.m. |
Concluding Remarks Satoshi Satoh, Osaka University, Japan |
Tutorial 1:
Introduction to Haptics – sensing, feedback, and sensory evaluation
Main Organizer
Yuichi Kurita, Hiroshima University, Japan
Co-organizer
Taku Hachisu, University of Tsukuba, Japan
Yasutoshi Makino, the University of Tokyo, Japan
Masashi Nakatani, Keio University, Japan
Shogo Okamoto, Nagoya University, Japan
Toshiaki Tsuji, Saitama University, Japan
Shunsuke Yoshimoto, The University of Tokyo, Japan
Statement of Objectives
This tutorial aims at introducing haptics technology to the community and encouraging audience to employ haptic technology in their research. Our tutorial is dedicated to haptics, which is multidisciplinary research field including electrical, mechanical and system engineering and sensory evaluation of human. We selected representative invited speakers who are working on different research methodologies in Haptics. We plan to provide the overview of the state of art in haptics research and possible applications using force feedback and touch devices. Besides, we will provide introductory knowledge on how to evaluate subjective sensory evaluation in human.
Intended audience
Audience who are interested in multidisciplinary research field including electrical, mechanical, system engineering and sensory evaluation of human users.
Speakers
Dr. Yuichi Kurita
Yuichi Kurita received a Ph.D. degree in information science from Nara Institute of Science and Technology (NAIST), Japan in 2004. From 2005 to 2007, he was a Research Associate with the Graduate School of Engineering at Hiroshima University, Japan. From 2007 to 2011, he was an Assistant Professor with the Graduate School of Information Science at NAIST. During 2010-2011, he was a visiting scholar in the School of Mechanical Engineering at the Georgia Institute of Technology, USA. Since 2011, he has joined the Graduate School of Engineering at Hiroshima University as an Associate Professor, and is a Professor from 2018. He is also appointed to the Assistant to President by Special Appointment, and Special Assistant to the Dean (International Collaborative Research) from 2018. He has also worked as a researcher in JST PRESTO from 2011.
http://www.bsys.hiroshima-u.ac.jp/~kurita/index_e.html
Dr. Taku Hachisu
Taku Hachisu received his PhD degree in engineering from the University of Electro-Communications, Tokyo, Japan in 2015. Since 2015, He is a Researcher of University of Tsukuba. His research interests include augmented/virtual reality, haptics, human-computer interactions, and wearable devices.
http://hachisu.net/
Dr. Yasutoshi Makino
Yasutoshi Makino received his Ph.D. in Information Science and Technology from the Univ. of Tokyo in 2007. He worked as a researcher for two years in the Univ. of Tokyo and an assistant professor at Keio University from 2009 to 2013. From 2013 he moved to the Univ. of Tokyo as a lecturer, and he is an associate professor in the Department of Complexity Science and Engineering in the University of Tokyo from 2017. His research interest includes haptic interactive systems.
http://www.hapis.k.u-tokyo.ac.jp/
Dr. Masashi Nakatani
After receiving his Ph.D. from the University of Tokyo, Masashi Nakatani worked for four years in the cosmetic industry and returned to academic research and started neuroscience study of touch at Keio University and at Columbia University Medical Center. He is currently conducting research on haptics science and the human body’s perception of touch, while pursuing to make a connection between haptic research outcomes in academia and industrial applications.
http://touchlab.sfc.keio.ac.jp/
http://www.merkel.jp/
Dr. Shogo Okamoto
Shogo Okamoto received a Ph.D. in information sciences from Tohoku University in 2010. Since then, he has been with Nagoya University. Currently, he is an associate professor at the Department of Mechanical Systems Engineering. His research interest includes haptics and assistive robotics.
http://www.mech.nagoya-u.ac.jp/asi/ja/member/shogo_okamoto/
https://researchmap.jp/read0153218/?lang=english
Dr. Toshiaki Tsuji
Toshiaki Tsuji received his Ph. D degree in integrated design engineering from Keio University, Yokohama, Japan, in 2006. He is currently an Associate Professor in Department of Electrical and Electronic Systems, Saitama University. His research interests include motion control, haptics and rehabilitation robots.
http:/ /robotics.ees.saitama-u.ac.jp/index.html
Dr. Shunsuke Yoshimoto
Shunsuke Yoshimoto received the Ph.D. degree in engineering from Osaka University, Osaka, Japan, in 2012. From 2012 to 2019, he was an Assistant Professor with the Graduate School of Engineering Science, Osaka University. Since 2019, he has been a lecturer with the School of Engineering, the University of Tokyo. His research interests include haptic engineering and biomedical instrumentation.
http://www.aml.t.u-tokyo.ac.jp/~yoshimoto
List of topics
Haptics
Tactile/force sensation
Human factors in human-machine interface and interaction
Human-computer interaction
Wearable devices
Assistive robotics
Rehabilitation robots
Biomedical instrumentation
Motion control
Augmented/virtual reality
Program (tentative)
September 10 Tuesday 2019 1:00 p.m.-5:00p.m.
| 1:00 p.m. | Introduction |
|
1:10 p.m. – 1:40 p.m. |
Taku Hachisu, ‘haptics technologies for human-computer and human-human interactions’ |
|
1:40 p.m. – 2:10 p.m. |
Masashi Nakatani, ‘Sensory evaluation in haptics’ |
|
2:10 p.m. – 2:40 p.m. |
Yasutoshi Makino, ‘Haptic information in human behavior’ |
|
2:40 p.m. – 3:00 p.m. |
coffee break |
|
3:00 p.m. – 3:30 p.m. |
Shogo Okamoto, ‘Introduction to vibrotactile stimuli. Easy-to-use and instrumental technique’ |
|
3:30 p.m. – 4:00 p.m. |
Shunsuke Yoshimoto, ‘Smart sensing technologies for human touch’ |
|
4:00 p.m. – 4:30 p.m. |
Yuichi Kurita, ‘Evaluation of force feeling and its applications’ |
|
4:30 p.m. – 5:00 p.m. |
Toshiaki Tsuji, ‘High Dynamic Range Force/torque Sensing for Motion Skill Analysis’ |
| 5:00 p.m.- | Closing |
Tutorial 2:
Process Data Analytics
Main Organizer
Sirish L. Shah, University of Alberta, Canada
Co-organizer
Bhushan Gopaluni, University of British Columbia, Canada
Biao Huang, University of Alberta, Canada
Manabu Kano, Kyoto University, Japan
Statement of Objectives
We are currently at the cusp of the fourth industrial revolution (4IR) or Industry 4.0 that is poised to reshape all the sectors of economy and society with an unprecedented depth and breadth. Emerging technologies including complex organization and systems, smart sensing, industrial robotics, industrial wireless communications, industrial Internet-of-Things (IIoT), Internet-of-Moving-Things (IoMT), industrial cloud, industrial big data and cyber-physical systems (CPS) have become hotspots of research and innovation globally. Industry 4.0 is driven by the advancements in digitalization, artificial intelligence and advanced analytics, massive computing power, inexpensive memory and the enormous volumes of data that are being collected.
The process industries are in a unique position to benefit from Industry 4.0, as they have the right infrastructure, and are in possession of massive amounts of heterogeneous industrial data. Industry 4.0 is poised to provide economic and competitive advantages in the face of ever-increasing demands on energy, environment and quality by providing a level of automation and efficiency never seen before. Process industries have been using data analytics in various forms for more than three decades. In particular, statistical techniques, such as principal components analysis (PCA), partial least squares (PLS), canonical variate analysis (CVA); and time-series methods for modelling, such as maximum-likelihood and prediction-error methods have been successfully applied on industrial data. Recent developments in artificial intelligence, machine learning and advanced analytics provide a new opening for leveraging industrial data for solving complex systems engineering problems.
The emphasis in this workshop will be on tools and techniques that help in the process of understanding data and discovering information that will lead to predictive monitoring and diagnosis of process faults, design of soft-sensors, process performance monitoring and on-line modeling methods.
Highly interconnected process plants are now common and monitoring and analysis of root causes of process abnormality including predictive risk analysis is non-trivial. It is the extraction of information from the fusion of process data, alarm and event data and process connectivity that should form the backbone of a viable process data analytics strategy and this will be the main focus of this workshop.
Intended audience
The intended audience for this workshop would be industrial practitioners of control including vendors working in the area of on-line data logging and archiving, graduate students with interests in statistical learning and data science and academics.
Speakers
Bhushan Gopaluni, University of British Columbia, Canada
Bhushan Gopaluni is a professor in the Department of Chemical and Biological Engineering and an Associate Dean for Education and Professional Development in the Faculty of Applied Science at the University of British Columbia. He is also an associate faculty in the Institute of Applied Mathematics, the Institute for Computing, Information and Cognitive Systems, Pulp and Paper Center and the Clean Energy Research Center. He was the Elizabeth and Leslie Gould Teaching Professor from 2014 to 2017. He is currently an associate editor for Journal of Process Control, The Journal of Franklin Institute. He received a Ph.D. from the University of Alberta in 2003 and a Bachelor of Technology from the Indian Institute of Technology, Madras in 1997 both in the field of chemical engineering. From 2003 to 2005 he worked as an engineering consultant at Matrikon Inc. (now Honeywell Process Solutions) during which he designed and commissioned multivariable controllers in British Columbia’s pulp and paper industry, and implemented numerous controller performance monitoring projects in the Oil & Gas and other chemical industries. He is the recipient of several awards that include Province of Alberta Graduate Fellowship, Captain Thomas Farell Graduate Memorial Scholarship from the University of Alberta and the prestigious Killam Teaching Prize and the Dean’s service medal from the University of British Columbia.
Biao Huang, University of Alberta, Canada
Biao Huang received the B.Sc. and M.Sc. degrees in automatic control from the Beijing University of Aeronautics and Astronautics, Beijing, China, in 1983 and 1986, respectively, and the Ph.D. degree in process control from the University of Alberta, Edmonton, AB, Canada, in 1997. He joined the University of Alberta, in 1997, as an Assistant Professor with the Department of Chemical and Materials Engineering, where he is currently a Professor. He is the Industrial Research Chair in Control of Oil Sands Processes with Natural Sciences and Engineering Research Council of Canada. He has applied his expertise extensively in industrial practice particularly in oil sands industry. His current research interests include process control, system identification, control performance assessment, Bayesian methods, and state estimation. He is a fellow of the Canadian Academy of Engineering and the Chemical Institute of Canada. He is currently Editor-in-Chief for IFAC journal Control Engineering Practice.
Manabu Kano, Kyoto University, Japan
Manabu Kano received bachelor’s, master’s, and Ph.D. degrees from the Department of Chemical Engineering, Kyoto University, in 1992, 1994, and 1999, respectively. He was an Instructor with Kyoto University since 1994. From 1999 to 2000, he was a visiting scholar with Ohio State University, U.S. Since 2012, he has been a Professor of Systems Science, Kyoto University. His research interest has covered process, medical, and agricultural systems engineering, particularly real-world data analysis. He was a recipient of many awards, including the Best Paper Award and the Technology Award from the Society of Instrument and Control Engineers (SICE), the Instrumentation, Control and System Engineering Research Award from the Iron and Steel Institute of Japan (ISIJ), and the Outstanding Paper Award and the Research Award for Young Investigators from the Society of Chemical Engineers, Japan (SCEJ).
Sirish L. Shah, University of Alberta, Canada
Sirish L. Shah is Emeritus Professor at the University of Alberta where he held the NSERC-Matrikon-Suncor-iCORE Senior Industrial Research Chair in Computer Process Control from 2000 to 2012. The main area of his current research is process and performance monitoring, system identification and design, analysis and rationalization of alarm systems. He has co-authored three books, the first titled “Performance Assessment of Control Loops: Theory and Applications”, a second titled “Diagnosis of Process Nonlinearities and Valve Stiction: Data Driven Approaches” and a more recent brief monograph titled, “Capturing Connectivity and Causality in Complex Industrial Processes”. He is a fellow of the Canadian Academy of Engineering and the Chemical Institute of Canada.
List of topics
The following topics will be discussed in this workshop. Each topic will be accompanied by one or more industrial case study to convey the utilitarian value of the learning, discovery and diagnosis from process data.
1. Overview of the broad analytics area with emphasis on its use in the process industry.
2. Basic definitions and introduction to supervised and unsupervised learning: simple regression, classification and clustering.
3. Data visualization methods; examination and analysis of data in a multivariate framework (in the temporal as well as the spectral domains).
4. Multivariate methods for data analysis and soft-sensor design: PCA and PLS.
5. Elements of statistical inference, soft-sensor design, adaptive modeling.
6. A brief overview of latest developments in machine learning and their impact on the process industry.
7. Future areas to explore in the use of statistical learning, data science and analytics for improved process operation.
Program
|
9:00 – 11:00 a.m. |
Introduction to process data analytics, visual analytics and information-theory based approaches for causality analysis (Shah) |
|
11:00 – 11:15 a.m. |
Coffee break |
|
11:15 a.m. – 12:45 p.m. |
Process Data Analytics: Algorithms, tools and case studies (Huang) |
|
12:45 – 1:30 p.m. |
Lunch break |
|
1:30 – 3:00 p.m. |
Virtual sensing technology (Soft-sensor) and Just-In-Time (adaptive) modeling (Kano) |
|
3:00 – 3:15 p.m. |
Coffee break |
|
3:15 – 5:00 p.m. |
Advanced Learning Algorithms: Artificial neural networks, deep learning and deep reinforcement learning. (Gopaluni) |
|
5:00 – 5:30 p.m. |
More industrial case studies, General discussion and Q & A session |