Optimisation of methanol distillation using GA and neural network hybrid

Distillation is an energy-intensive non-stationary process represented using non-linear model equations and involves multiple objectives. For such processes, data-based multi-objective optimization methods are more suitable compared to conventional non-linear optimization methods. Therefore, a surrogate-assisted multi-objective optimization (SAMOO) approach is developed by hybridizing an artificial neural network (ANN) and genetic algorithm (GA) to simultaneously minimize the annualized capital expenditure cost (ACAPEX) and annualized operational expenditure cost (AOC) for the methanol separation process. The approach is then extended for operational optimization to maximize methanol purity and minimize heat duty. The Pareto optimal fronts obtained using the data-based SAMOO approach are found to be very close to the optimization results obtained using the actual physics-based Aspen Plus model. The coupling of the genetic algorithm and ANN modeling in SAMOO approach reduces the computing time of optimization by similar to 50% with nearly the same results as that of the physics-based model.