On-line optimization model design of gasoline blending system under parametric uncertainty

On-line optimization model design is one of the most important works for gasoline blending system because of its direct controlling to distributed control system (DCS). A new on-line optimization model using chance constraint stochastic program is presented in this paper. Different from former on-line models, the new one has the ability to process the parametric uncertainty during on-line gasoline blending, and takes the execution operations of DCS into account. On the other hand, hybrid intelligent algorithm based on neural network (NN) and genetic algorithm (GA) is applied to solve the presented model in our research. The proposed on-line optimization model design is illustrated with some blender simulation studies based on the information at Daqing refinery, China.