Study of using ANFIS to the prediction in the bore-expanding process

This paper develops a forward model and inverse model for the adaptive network fuzzy inference system (ANFIS) to the prediction in the sheet bore-expanding process. After using the dynamic finite element method to establish the basic database under various working conditions, an efficient rule database and optimal distribution of membership function will be constructed from the hybrid-learning algorithm of ANFIS. As a verification of this system, the deformed circle hole diameter D is compared between ANFIS, FEM, and experimental results. In the forward model, it is proved that ANFIS can efficiently predict the deformed circle hole diameter D successfully from the database constructed by punch radius RP, die radius RD, and initial circle hole diameter D0. In the inverse model, the initial circle hole diameter D0 is predicted to obtain a desired target deformed circle hole diameter D after forming. From this forward and inverse investigation, the ANFIS is proved to supply a useful optimal soft computing approach in the forming category .