Data to Knowledge -The Role of Megavariate Modeling for Plant Performance Enhancement in the Oil, Gas and Petrochemical Industry

Process plant operation generates large quantities of data. The knowledge obtained from such data can be used for a variety of purposes such as inferential measurements and model predictive control. Careful variable selection and data preprocessing are required for developing adequate models from this data. The objective of this paper is to examine in detail the methods for developing successful empirical models from plant data. Three case studies have been presented from the hydrocarbon industry; heat exchanger model by neural networks to be used in model predictive control, development of a soft sensor for predicting propane concentration in a depropaniser column and heat exchanger fouling model to be used as part of a preventive maintenance tool. In all the cases, statistical model adequacy tests showed that careful selection of variables and post modeling analysis helped in developing models which were adequate for the intended purposes.