Multi-Objective Optimization of a Crude Oil Hydrotreating Process with a Crude Distillation Unit Based on Bootstrap Aggregated Neural Network Models

This paper presents the multi-objective optimization of a crude oil hydrotreating (HDT) process with atmospheric distillation unit using data-driven models based on bootstrap aggregated neural networks. Hydrotreating whole has economic benefit compared to conventional individual products. In order overcome difficulty in developing accurate mechanistic and computational burden utilizing such optimization, networks are utilized develop reliable for this process. Reliable optimal operating conditions derived by solving problem incorporating minimization widths model prediction confidence bounds as additional objectives. The is solved goal-attainment method. proposed method demonstrated HDT simulated Aspen HYSYS. Validation results HYSYS simulation demonstrates that technique effective.