Our research activities mainly focus on process control and data analytics. Specifically, the research activities in process control includes control performance assessment, state estimation, fault diagnosis and soft sensing. The research activities in data analytics include process identification, Bayesian inference, process monitoring, data-based optimization and machine learning. Our research outcomes have been widely applied in industrial processes particularly oil sands processes.
Everyone in a process plant, from plant managers to engineers to technicians, relies on a massive amount of data, which plays a significant role in daily analysis and decision making. Common process control practice is to develop models based on data and then controllers with the aid of process knowledge. But as modern process data has increased in dimensionality, diversity and complexity, traditional analytical tools have been unable to keep up with this onslaught of complex data. High dimensionality of data and irregularities during data collection pose many challenges in modeling, analysis and control design, thereby casting serious doubt on the validity of traditional techniques. As a result, the process control research community is under ever increasing pressure to deliver analytic tools to cope with the challenges of the modern day practices of the process industries. Responding to this pressure and motivated by the real-life challenges faced by process industries, we endeavor to provide a solution to fundamental problems encountered in process identification, fault detection and soft sensing in the presence of high dimensionality and irregularities in modern datasets. Our research program will develop new analytics techniques by which this enormous amount of data can be fruitfully utilized, to achieve safe and intelligent process operations.
Not only do we develop new techniques, but also we apply the techniques to industries. While the economic benefits to oil sands development are evident, sustainable development of this valuable Canadian resource requires that the costs of oil extraction as well as environmental consequences be minimized. Over the last decade, due to the global demand, the oil sands industry has undergone an unprecedented development accompanied by a significant increase of production costs. Market reality requires strategic oil sands development and calls for reduction of operation costs. However, the search for solutions to the sustainable oil sands development (e.g. water use, greenhouse gas emissions, tailings) has focused on the processes that make up the oil sands operation. Our research takes a different approach by focusing on the systems that control these processes. Process control systems are critical because they allow for steady and safe process operations, efficient production, consistent product quality, less waste, and better control of emissions. Achieving better process control in the oil sands industry is not simply a matter of importing technologies from other industries. Control systems in the oil sands industry face unique challenges. Our research is aimed at developing solutions that will lead to innovative estimation, monitoring and data-mining technologies in addition to supporting and improving the established solutions for the industry. Specifically, solutions for sensors, process safety and optimal operation are developed. These practical solutions are backed by sound fundamental research. Through our research program, we will also extend the breadth and depth of Canada's oil sands expertise by creating a pool of highly trained engineers in process systems engineering and control. Our integrated program will enable collaboration with industry to convert research outcomes into implemented solutions, and train highly qualified personnel with excellent job prospects.
Keywords: Process Control, System Identification, State Estimation, Fault Detection and Diagnosis, Data Analytics, Bayesian Methods, Control Performance Monitoring, Soft Sensors