The Optimal Control of Heuristic Dynamic Programming in Molecular Distillation

Molecular distillation technology is a kind of industrial separation technology, which can greatly improve the purity and yield of the product. However, due to the process of molecular distillation is very complex, it is difficult to establish a precise mathematical model to realize an expected control. So, in this paper, considering that BP neural network can approximate any nonlinear system, a large amount of off-line experimental data is used to establish the model of molecular distillation system by BP neural network. To obtain optimal control in molecular distillation, Heuristic Dynamic Programming technique is applied. The simulation example is provided to demonstrate the validity of the derived optimal control scheme.