Keynote 1 - Prof. Jinfeng Liu

Challenges and Opportunities for Process Systems Engineering in Addressing Agricultural Water Sustainability

Prof. Jinfeng Liu
Department of Chemical and Materials Engineering, University of Alberta, Canada

Abstract: Water is essential for our daily life and is at the core of sustainable development. It is inextricably linked to climate change, agriculture, food security, health, equality, gender and education. Water supply crisis has been consistently recognized as one of the greatest global risks by the World Economic Forum. Population growth is the major factor causing the global water supply crisis. Water management is not a trivial concern, especially as food and water are inextricably linked. Agricultural irrigation consumes about 70% of the global fresh water withdrawals. As population growth continues, 60% more food will be needed to satisfy the demand of more than 9 billion people worldwide by 2050. However, in many regions, water allocated to irrigation is largely capped. The irrigation water-use efficiency worldwide is low (around 50% to 60%). New technologies for more efficient irrigation need to be developed; otherwise, water scarcity will become a global issue in the near future. In the current agricultural irrigation practice for large-scale agricultural fields, the amount of water to be irrigated and the time to apply the irrigation are determined in advance based on irrigators’ knowledge. The actual field conditions are generally not considered in determining the irrigation prescription. From a process systems engineering (PSE) perspective, the current irrigation practice is in “open-loop”. A “smarter” approach to agricultural irrigation is to close the decision-making loop to form “closed-loop” irrigation. In the closed-loop system, sensing instruments (e.g., soil moisture sensors, evapotranspiration (ET) gauge, thermal cameras) are used to collect various real-time field information (e.g., soil moisture, ET, temperature) regularly. The various field information is then fused together to get estimates of the entire field’s conditions. The estimated field conditions are then fed back to an adaptive control system. The adaptive control system calculates the best irrigation commands for the next few hours or day based on a field model, the estimated field conditions, local weather forecast as well as other pre-specified irrigation requirements. Due to significant nonlinearities, uncertainties, and very large sizes of the fields, there are many great challenges that need to be addressed. We have been working towards this closed-loop smart irrigation vision with our collaborators. I will share my views on the role of process systems engineering in this closed-loop smart irrigation vision, the great challenges and opportunities in modelling, sensing, and control of irrigation systems, and introduce some of our recent progress.


Dr. Jinfeng Liu is a Professor in the Department of Chemical and Materials Engineering at the University of Alberta. He received his PhD in Chemical Engineering from UCLA, and MSc and BSc both from Zhejiang University. His research interests are in the general area of process systems and control engineering. One of his current research focus areas is closed-loop smart agricultural irrigation for water sustainability. Dr. Liu has published 3 books, over 150 journal and conference papers, and edited a few special issues. He currently serves as the co-editor-in-chief for IChemE journal Digital Chemical Engineering, associate editors for IFAC Journal of Process Control, Control Engineering Practice, International Journal of Systems Science and MDPI journal Mathematics.

Keynote 2 - Thomas A. Badgwell and R. Donald Bartusiak

Three emerging technologies currently disrupting manufacturing and process control

Thomas A. Badgwell and R. Donald Bartusiak
Collaborative Systems Integration, United States

We are currently in the midst of a fourth industrial revolution (Industry 4.0 [1]), involving the large-scale automation of traditional manufacturing and industrial practices, made possible by recent developments in mathematical algorithms, computer hardware, and internet connectivity (Industrial Internet of Things (IIoT) [2]). While much of this work can be considered evolutionary in nature, in this presentation we highlight three emerging technologies that appear to be truly disruptive; that is, they are likely to have such a large impact that they will change the way theoreticians and practitioners think about and accomplish manufacturing and process control. These technologies are Economic Model Predictive Control (EMPC), Deep Reinforcement Learning (DRL), and Open Process Automation (OPA). Economic MPC (EMPC) is a relatively new technology that combines economic optimization with Model Predictive Control [3], two functions that are traditionally implemented separately. While the theory was worked out a few years ago [4], EMPC applications have only begun to appear recently. Professor Jim Rawlings and co- workers, for example, presented a successful EMPC implementation for the Stanford University campus heating and cooling system [5]. Recent theoretical work has shown that scheduling problems, which are usually approached from the point of view of static optimization, can also be considered as a special case of closed-loop EMPC [6]. This unification of closed-loop scheduling, economic optimization, and dynamic control has shed new light on such problems as rescheduling in the face of disturbances, and provides academics with a completely new framework for viewing and analyzing scheduling problems. Practitioners now have, for the first time, the hope of combining three disparate levels in the traditional control hierarchy into a single, harmonious layer. Reinforcement Learning (RL) is a Machine Learning (ML) technology in which a computer agent learns, through trial and error, the best way to accomplish a particular task [7]. Deep Learning (DL) is a technology in which neural networks with a large number of intermediate layers are used to model relationships [8]. Using DL to parametrize the policy and value function of an RL agent leads to Deep Reinforcement Learning (DRL) technology, which allows an agent to achieve superhuman performance for some tasks. In 2017, for example, a DRL agent named AlphaGo soundly defeated the reigning world champion Go player [9]. Applications of this technology to manufacturing and process control systems are currently under study [10]. It is likely that DRL will not replace currently successful control algorithms such as PID and MPC, but will rather takeover some of the mundane tasks that humans perform to manage automation and control systems. For example, it appears that a DRL agent can learn how to tune PID loops effectively [11]. Other possibilities include advising operators during transient and upset conditions, mitigating disturbances such as weather events, and detecting and mitigating unsafe operations [10]. The industrial automation marketplace, comprised of Distributed Control System (DCS), Programmable Logic Controller (PLC), and Supervisory Control and Data Acquisition (SCADA) technology offerings, will soon experience a historic, game-changing disruption with the emergence of Open Process Automation (OPA) technology. Manufacturers, whose innovations have been constrained for decades by the limitations of closed, proprietary systems, will soon experience the benefits of open, interoperable, resilient, secure-by-design automation systems, made possible by the development of the consensus-based Open Process Automation Standard (O-PAS) by the Open Process Automation Forum (OPAF) [12]. Once O-PAS certified automation systems become widespread, vendors will see the market for their products and services expand significantly as the visions of I4.0 and the IIoT are realized. Academics and technology developers will see more opportunities to test their solutions as it becomes easier to deploy them. Dr. Don Bartusiak, co-director of OPAF, summarizes their progress to date in a paper published recently in Control Engineering Practice [12].


  • [1] Y Liao, F Deschamps, EdFR Loures, LFP Ramos, “Past, present, and future of Industry 4.0 - a systematic literature review and research agenda proposal”, Intl J Production Research, 55 (12), 3609-3629, (2017).
  • [2] H Boyes, B Hallaq, J Cunningham, T Watson, “The industrial internet of things (IIoT): An analysis framework”, Computers in Industry, 101, 1–12, (2018).
  • [3] SJ Qin, TA Badgwell, “A survey of industrial model predictive control technology”, Control Engineering Practice 11 (7), 733-764, (2003).
  • [4] JB Rawlings, D Angeli, CN Bates, “Fundamentals of economic model predictive control”, 51 st Conference on Decision and Control, 3851-3861, (2012).
  • [5] JB Rawlings, NR Patel, MJ Risbeck, CT Maravelias, MJ Wenzel, RD Turney, “Economic MPC and real-time decision making with application to large-scale HVAC energy systems”, Computers & Chemical Engineering, 114 (6), 89-98, (2018).
  • [6] MJ Risbeck, CT Maravelias, JB Rawlings, “Unification of Closed-Loop Scheduling and Control: State-space Formulations, Terminal Constraints, and Nominal Theoretical Properties”, Computers & Chemical Engineering, 129 (10), (2019).
  • [7] RS Sutton, AG Barto, “Reinforcement Learning – An Introduction”, The MIT Press, (2018).
  • [8] I Goodfellow, Y Bengio, A Courville, “Deep Learning”, The MIT Press, (2016).
  • [9] D Silver, A Huang, CJ Maddison, A Guez, L Sifre, G Van Den Driessche, J Schrittwieser, I. Antonoglou, V Panneershelvam, M Lanctot, “Mastering the game of Go with deep neural networks and tree search”, Nature 529, 484–489 (2017).
  • [10] J Shin, TA Badgwell, KH Liu, JH Lee, “Reinforcement Learning – Overview of recent progress and implications for process control”, Computers & Chemical Engineering, 127, 282- 294 (2019).
  • [11] TA Badgwell, KH Liu, NA Subrahmanya, WD Liu, MH Kovalski, “Adaptive PID Controller Tuning via Deep Reinforcement Learning”, U.S. patent 1095073, granted February 9, 2021.
  • [12] RD Bartusiak, S Bitar, DL DeBari, BG Houk, D Stevens, B Fitzpatrick, P Sloan, “Open Process Automation: A Standards-Based, Open, Secure, Interoperable Process Control Architecture”, Control Engineering Practice 121, 105034, (2022).


Thomas A. (Tom) Badgwell Ph.D., is Chief Technology Officer with Collaborative Systems Integration and lives in Clinton, New Jersey. He received a BS degree from Rice University and MS and PhD degrees from the University of Texas at Austin, all in Chemical Engineering. Tom’s career has focused on modeling, optimization, and control of chemical processes, with past positions at SETPOINT, Fisher/Rosemount, Rice University, Aspen Technology and ExxonMobil. He is a fellow of AIChE and a past Director of the CAST division, from which he received the Computing Practice Award in 2013. He has served as an Associate Editor for the Journal of Process Control, and as an Industrial Trustee of the CACHE Corporation. He was inducted into Control Magazine’s Automation Hall of Fame in 2022.

Don Bartusiak is currently President of Collaborative Systems Integration and Co-chair of The Open Process Automation Forum of The Open Group. In October 2020, Don retired as Chief Engineer, Process Control for ExxonMobil Research and Engineering with 33 years of experience. At ExxonMobil, he implemented real-time artificial intelligence, linear and nonlinear model predictive control, and real-time optimization applications. From 1977 to 1984, he was a Research Engineer for Bethlehem Steel. Don received a BS from the University of Pennsylvania and MS and PhD degrees from Lehigh University. He has published 10 journal articles and is co-inventor on 5 patents.

Keynote 3 - Prof. Manabu Kano

Developing Medical and Healthcare Services Based on Heart Rate Variability Analysis: Opportunities and Challenges

Prof. Manabu Kano
Department of Systems Engineering, Kyoto University, Japan

Abstract: We have a dream that one day epileptic patients will be able to live their lives without worrying about seizures. If seizures cannot be controlled by medication, it is necessary to predict their onset in advance to at least prevent accidents that may lead to death or injury. We have developed an epileptic seizure prediction system, consisting of a wearable electrocardiograph (ECG) and a smartphone. This system performs heart rate variability (HRV) analysis based on R-R interval (RRI) data and fault detection, e.g., multivariate statistical process control (MSPC), which is familiar to our community. HRV is a noninvasive indicator of autonomic nervous system activities, and it is useful for developing various medical and healthcare services. In this presentation, I will introduce several services that we have developed so far, including epileptic seizure prediction, sleep apnea syndrome (SAS) screening, and driver’s drowsiness detection. In addition, I would like to point out opportunities and challenges in the medical/healthcare field, which seem interesting to and can be solved by process control researchers and engineers.


Dr. Manabu Kano is a professor of the Department of Systems Science, Kyoto University. He received BS, MS, and PhD degrees from the Department of Chemical Engineering, Kyoto University, in 1992, 1994, and 1999. He has been working at Kyoto University since 1994. From 1999 to 2000, he was a Visiting Scholar with Ohio State University, U.S. His research interest has focused on applying systems approach and data analytics to various problems related to manufacturing processes and medical and healthcare services. He started a medical venture company ‘Quadlytics Inc.’ in 2018.

Dr. Kano was a recipient of many awards, including the Best Paper Awards and the Technology Awards from the Society of Instrument and Control Engineers (SICE), the Sawamura Paper Award from the Iron and Steel Institute of Japan (ISIJ), and the Outstanding Paper Awards of J. Chem. Eng. Japan and the Technology Award from the Society of Chemical Engineers, Japan (SCEJ).

Keynote 4 - Rohit Patwardhan

Data Stories from the Frontline – The Analytics and AI Chronicles

Rohit Patwardhan
Saudi Aramco

Abstract: The well instrumented process industry collects vast amounts of structured and unstructured data from its assets in real time. Some of this data gets stored as conventional time series data while some is processed to generate alarms, alerts and other types of unstructured data. Harnessing this data which is rich in diversity, volume, , and velocity, to generate actionable insights is a challenge that is best tackled through the use of advanced analytics. The area of advanced analytics has been expanding rapidly with the exponential rise of artificial intelligence (AI) tools that are capable of processing complex data types such as video and audio. In this talk, applications involving operational data and advanced analytics tools that are used to generate predictive and prescriptive insights, will be shared. The case studies illustrate the different data types present in industry – time series data, alarm and event data and image data – and the machine learning methods used to analyze them in order to generate insights. The applications discussed cover a spectrum of advanced analytics techniques ranging from conventional time series analysis, spectral analysis, clustering, convolutional neural networks and text analytics. In conclusion, some perspectives on the future role of advanced analytics and AI technologies in the process industry are shared.

Keynote 5 - Lidia Auret

Practical process monitoring and smart sensors in the mineral processing industry

Lidia Auret
Stone Three, South Africa

Abstract: Mineral processing involves the conversion of mined ore to valuable concentrates through size reduction (crushing and grinding) and separation processes (typically flotation). Challenges exist that complicate the implementation of advanced control technologies in mineral processing: ore properties (such as composition, size distribution and liberation of valuable minerals) are difficult to measure in real-time; size reduction and separation processes are difficult to model accurately; flowsheets are highly connected through recycle streams; and many disturbances are present. Over the last decade and more, machine learning methods have been proposed to address some of these control challenges. The most successful industrial application of such methods has been the use of computer vision to estimate ore size distribution and flotation properties. Other opportunities for machine learning to augment control include process monitoring, but data-driven fault diagnosis has not seen widespread transfer from theory to practice in mineral processing applications. This talk will give an overview of what is involved in the industrial application of smart sensors for computer vision as well as process monitoring. Challenges of translating theory to practice will be highlighted (including aspects of cost-benefit analysis of such technologies, and the importance of end-to-end design – from detection to intervention), and opportunities for moving theory and practice closer together through appropriate benchmark simulations and data sets will be discussed.

Keynote 6 - Prof. Bhavik R. Bakshi

Towards Harmony between Industrial and Ecological Systems: Opportunities for Advanced Control

Prof. Bhavik R. Bakshi
William G. Lowrie Department of Chemical and Biomolecular Engineering, Ohio State University

Abstract: The system boundary of conventional engineering excludes the role played by ecosystems. This is despite the fact that no industrial or human activity is possible without the goods and services provided by nature. All definitions of sustainability require staying within nature’s capacity, but most methods for sustainable engineering have not imposed this requirement. The framework of techno-ecological synergy (TES) aims to develop mutually beneficial relationships between industrial and ecological systems. More than a dozen theoretical and applied case studies have demonstrated the many economic, environmental, and social benefits of TES systems. However, these studies do not consider the spatial and temporal variation of ecological systems. In this presentation, we will introduce the framework of TES and the substantial challenges and opportunities it poses in the design and operation of dynamic TES systems. Some of the challenges include, managing the desire for homeostasis of engineered systems versus the homeorhetic nature of ecosystems, addressing ecological phenomena occurring over time scales of minutes to decades and over spatial scales of meters to hundreds of kilometers. We formulate dynamic TES as an integrated design and control problem and demonstrate its application to a chemical manufacturing process operated in synergy with the surrounding vegetation that mitigates air pollutants. Our approach relies on Bayesian optimization and accounts for trade-off between the cost to company and cost to society.