Process industries have been using data analytics in various forms for more than three decades. In particular, statistical techniques such as principal component analysis (PCA), partial least squares (PLS) and canonical variate analysis (CVA) have been used widely. This workshop introduces the essential machine learning algorithms and software tools for graduate students, experienced researchers and engineers working in the industry. In particular, several known and emerging applications of these algorithms in soft sensing, state and parameter estimation, process monitoring, fault detection and diagnosis, and control will be presented.
This AIChE short course built upon the ADCHEM workshop material that we developed. Additional case studies were included using the Volve/Equinor open dataset and presentation materials were revised such that more advanced machine learning tools were introduced.