In the four basic factors on the intellectualization of sheet metal forming, the real-time identification of the material performance parameter and the prediction of the optimum technological parameter are the most complicated ones. The accuracy of identification and prediction will have direct effect on the success of the intelligence control. Taking the intelligence control of rectangular box as an object of study, feed forward neural network model based on LM algorithm had been established to realize material properties and friction coefficient for deep drawing of rectangular box. By means of real-time monitoring and measuring to identify the material performance parameters and to predict the optimum technological parameters, and a satisfied accuracy of convergence is achieved.