Richard has been with the Control Technologies group at Hatch for 13 years. He is responsible for supporting and developing control and automation solutions for some of Hatch’s key technologies. He has been involved in the design and delivery of several large-scale engineering projects of high-power electric smelting furnaces with responsibility for the control system and instrumentation. In addition, he has been involved in many smaller-scale projects ranging from modelling and simulation to process analysis and adaptation of instruments to new applications.
He has a background in multivariate statistical analysis, dynamic modeling, simulation, optimisation and advanced process control. A current area of interest is the application of data analytics and machine learning to leverage data to improve process operations. Richard holds a PhD in Process Systems & Control from the Dept. of Chemical Engineering at McMaster University.
Machine learning and how it applies to process engineers
There is currently a lot of talk in the media and throughout the industry around Machine Learning.
The focus of this presentation will be to demystify the topic and highlight areas of value and potential pitfalls. Case studies will be used to demonstrate how machine learning can be applied in ways that are relevant to process engineers. The importance of the process engineer as the subject-matter-expert (SME) in the application of any process related Machine Learning application will also be discussed.
Machine Learning (ML) has been gaining traction and as the field develops, organisations are looking to leverage their data and invest more in the technology to facilitate this. Rio Tinto’s Jadar project is one case where several opportunities are being explored. Some examples of how this project is looking to apply use Machine Learning will be reviewed.