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