Radial forging force prediction through MR, ANN, and ANFIS models

The application of finite element method and intelligent systems techniques to predict the applied force during the radial forging process is studied. Radial forging is a unique process used for the precision forging of round and tubular components, with or without an internal profile. More than 800 radial forging machines are currently operating worldwide. Since the maximum forging force per die is constant, determining the die force before the process can prevent die damage and material wastage. Then, the results of the FE simulation are applied for two intelligent forecasting systems in artificial neural network and adaptive neuro-fuzzy inference system. Initial billet temperature, die inlet angle, feed rate, and reduction in cross-section are applied as input parameters, and radial forging force is applied as the output parameter. Finally, the results of these two intelligent systems are compared with the multiple regressions method. A sensitivity analysis is carried out to determine how the radial forging force is influenced by the input parameters.