Dynamic modeling of crude oil fouling in an industrial preheat exchanger of CDU based on artificial neural networks

The objective of this paper is to investigate both static and dynamic approach of artificial neural network (ANN) modeling for prediction of crude oil fouling behavior in an industrial preheat exchanger of a CDU under wide range of operating conditions. Extensive research was conducted to obtain the numerous experimental fouling data, measured in an industrial preheat train as a function of operating conditions including tube and shell side inlet-outlet bulk temperatures, crude volume flow rate and cumulative time. Over 2000 total fouling data points obtained from Tehran oil refinery were used to develop the ANN model. A comparison between the experimental and predicted data reveals an overall mean relative error (MRE) of about 2.3% for all data in dynamic approach. In addition, the trend of both predicted results and experimental data are qualitatively consistent.

Keywords:

Fouling , Crude oil , Preheat exchanger , Dynamic modeling , Neural network