Comparison of Optimization of Exergy Efficiency of a Crude Distillation Unit Using Artificial Neural Network (ANN) and Response Surface Methods (RSM)

Abstract

The study carried out simulation of the Crude Distillation Unit (CDU) of the New Port Harcourt Refinery (NPHR) and performed exergy analysis of the Refinery. The Crude Distillation Unit (CDU) of the New Port Harcourt refinery was simulated using HYSYS (2006.5).
 The Atmospheric Distillation Unit (ADU) which is the most inefficient unit and where major separation of the crude occurs was focused on. The simulation result was exported to Microsoft Excel Spreadsheet for exergy analysis. The ADU was optimized using statistical method and Artificial Neural Network. Box-Behnken model was applied to the sensitive operating variables that were identified. The statistical analysis of the RSM was carried out using Design Expert (6.0). Matlab software was used for the Artificial Neural Network. All the operating variables were combined to give the best optimum operating conditions.
 Exergy efficiency of the ADU was 51.9% and 52.4% when chemical exergy was included and excluded respectively. The optimum operating conditions from statistical optimization (RSM) are 586.1 K for liquid inlet temperature, 595.5 kPa for liquid inlet pressure and condenser pressure of 124 kPa with exergy efficiency of 69.6% which is 33.0% increment as compared to the base case.
 For the ANN optimization, the exergy efficiency of the ADU was estimated to be 70.6%. This gave an increase of 34.9% as compared to the base case.
 This study concluded that enormous improvement can be achieved both in design feasibility and improved efficiency if the feed operating parameters and other sensitive parameters are carefully chosen. Furthermore, ANN optimization gave better exergy efficiency of 70.6% than RSM optimization of 69.6%.

Modeling and optimization of small-scale NF/RO seawater desalination using the artificial neural network (ANN)

“…In this current work, the artificial neural network was used due to their flexibility to conform to any type of data set and due to their success with various engineering problems [40][41][42][43][44][45].…”