关键词: simulation;optimization;artificial neural network;genetic algorithm;simplex method; fluidized-bcdreactor;acrylonitrile

Abstract: A mathematical model is developed for an industrial acrylonitrile fluidized-bed reactor
based on arti-ficial neural networks. A new algorithm, which combines the characteristics
of both genetic algorithm (GA) andgeneralized delta-rule (GDR) is used to train artificial
neural network (ANN) in order to avoid search terminatedat a local optimal solution. For
searching the global optimum, a new algorithm called SM-GA, incorporating ad-vantages of
both simplex method (SM)and GA, is proposed and applied to optimize the operating
conditions of anacrylonitrile fluidized-bed reactor in industry.

Key words: simulation, optimization, artificial neural network, genetic algorithm, simplex method, fluidized-bcdreactor