Development of Soft Sensor for Crude Distillation Unit

The stringent quality requirement of petroleum products in a highly competitive market
makes on-line monitoring and control of product properties essential. Unfortunately,
few online sensors are available and they are difficult to maintain. Besides, the use of
original True Boiling Point (TBP) data as initially established in the laboratory for pure
crudes cannot be expected to predict the fractionators' performance later when the crude
composition may have changed or blended with other crude oils.
It is, therefore, necessary to develop 'soft sensors' to predict the quality using other
easily measurable secondary variables. This project focuses on understanding the soft
sensor termed as "Generalized Cut-point Control (GCC)" which uses the crude true
boiling point (TBP) curve and other operating parameters such as flow rates,
temperatures and pressures in the crude distillation unit (CDU) to predict the product
properties. Product composition and properties such as Flash Points, Freeze Points and
product compositions have been predicted using the TBP temperatures.
Soft sensor implementation in refineries has significant benefit. Therefore, there is a
great need for better understanding of this technology to sustain the continuity of its
application.