Founding the mathematic model of refrigeration system's dynamic process is the basis of realizing the optimal control of refrigeration machines.Refrigeration evaporator is a kind of two-phase flow and heat exchange with complex process.For its obvious nonlinearity and uncertainty,it is difficult to describe by accurate theoretical model.This paper partitions the input data into some clusters by entropy method and competitive learning algorithm,then the on-line fuzzy identification of dynamic process mathematical model of evaporator is achieved by utilizing ultimate parameter which is ascertained by the recursive least-square(RLS).The simulation results show that fuzzy identification method is effective for on-line model process of evaporator in refrigeration system.The model has not only superior identification precise,but also quite perfect generalizable performance and traceable ability.