Aromatic Hydrocarbon Isomerization Process Optimization based on IDE and AOS

Based on artificial neural networks model, the aromatic hydrocarbon isomerization process optimization is a large-scale and nonlinear optimization problem. According to the character of the optimization problem, a novel intelligent differential evolution (IDE) algorithm containing an adaptive mutation operator, in which the mutation probability is determined according to the evolved generations, and an adaptive optimization strategy (AOS) of adaptive extended operation constraint conditions were proposed to optimize operation conditions. Satisfactory result was obtained. The adaptive mutation operator makes the individuals diversity at the initial generations to overcome the premature, and reduces the mutation probability gradually during the evolutionary process to preserve the excellent individuals at the terminal generations and enhance the probability of obtained the global optimal solution. The comparison results demonstrate that IDE´s on-line and off-line performances are all superior to those of DE, the probability of obtained the global optimal solution is larger than that of DE, and that the parameter sensitivity degree of IDE is lower than that of DE