Feature Variables Based Predicting Modelfor Complex Production Process

A feature variables based predicting model for complex production process was presented. Comparing with traditional methods,it bypasses the mechanism analysis,using time series analysis technology and feature variables,selected from original dynamicaldatad which can reflect the operating mode of complex production process build a new kind of predicting model.The neural network realization of this model is discussed.The results obtained by simulation show the feasible of this method.