An Intelligent System for Estimation of Exergy Efficiency of Integrated Naphtha and Isomerization Process under Uncertainty

The integrated process of naphtha reforming and isomerization is energy-deficient; therefore, energy-efficient design is vital to make it sustainable and viable. Exergy analysis has been employed to carry out energy-efficient operations because of its ability to determine true thermodynamic potential and energy degradation in the process. However, it faces a challenge in coping with uncertainty in process conditions. In this work, an artificial neural network (ANN) was developed to study the effect of uncertain process conditions on exergy efficiency. First steady state exergy analysis was carried out in the Aspen HYSYS environment. The process has an overall exergy efficiency, irreversibility, and improvement potential of 50.57%, 34955.55 kW, and 17276.98 kW, respectively. Then a total of 100 data sets were generated under random uncertainty of −5% and +5% in the 33 process conditions, such as temperature, pressure, and mass flow rate. Then an ANN model was derived based on generated data to predict exergy efficiency.