摘要
For the reasons of safety and economy,it is desirable to be able to makeon-line predictions of the catalyst deactivation curve in RDS reactor system.Sinceon-line prediction methods are based on models,it becomes neccssary to determine themodel parameters for the real system.In order to facilitate this estimation of parameters,an RDS model,which was obtained from detail mass and energy balances,isparameterized and simplified.The coking effect of catalyst deactivation in our model isdescribed by a simple function,in which the number of parameters involved can be re-duced,from the model’s original fifteen,to ten.A method for determining the values of theparameters in the simplified model by the nonlinear programming method is proposed,and finally leading to an on-line deactivation curve forecast.
For the reasons of safety and economy,it is desirable to be able to make on-line predictions of the catalyst deactivation curve in RDS reactor system.Since on-line prediction methods are based on models,it becomes neccssary to determine the model parameters for the real system.In order to facilitate this estimation of parameters, an RDS model,which was obtained from detail mass and energy balances,is parameterized and simplified.The coking effect of catalyst deactivation in our model is described by a simple function,in which the number of parameters involved can be re- duced,from the model's original fifteen,to ten.A method for determining the values of the parameters in the simplified model by the nonlinear programming method is proposed, and finally leading to an on-line deactivation curve forecast.
