3E Multi-objective optimization of hexane oil distillation process based on multi-strategy ensemble optimization algorithm

Hexane oil distillation is an important process in solvent oil production accompanied by high energy consumption and high emission. Therefore, the energetic, economic and environmental(3E) multi-objective optimization of hexane oil distillation process is of great significance for the sustainable development of solvent oil industry. Regarding slow convergence and easiness of trapping in local optimum for the conventional non-dominated sorting genetic algorithm (NSGA-II), a novel multi-strategy ensemble non-dominated sorting genetic algorithm (MENSGA-II) was proposed. In this algorithm, a guidance strategy based on the global and local optimal of individual neighborhood, was developed to accelerate the convergence speed of the algorithm. At the same time, the random limit walk strategy was introduced to improve the convergence and distribution of the solution set obtained. The MENSGA-II was applied to the typical test functions and the actual hexane oil distillation process. The results showed that the algorithm has advantages in stability, convergence speed and uniformity of the Pareto front. Compared with the actual operating condition, the annual gross profit of the distillation system under typical optimized conditions could be increased by 4.99×105USD/a, with energy consumption and CO2 emissions reduced by 5.09×102kW/a and 4.82×102kg/a, respectively.