Application of constitutive description and integrated ANFIS – ICA analysis to predict hot deformation behavior of Sn-5Sb lead-free solder alloy

Abstract Prediction of the high temperature characteristics of an alloy is an important step to understand its performance in hot working conditions. In this context, hot compression tests of Sn-5Sb solder alloy were carried out under different hot deformation conditions, i.e., temperature range of 300, 330, 360 and 400 K and strain rate range of 0.01, 0.005, 0.001 and 0.0005 1/s. High temperature behavior of lead free solder alloy was estimated using adaptive neuro-fuzzy inference system (ANFIS). The model combined linguistic-based data mining approach of fuzzy inference in the company of the learning ability of artificial neural network during training and experimental data sets were used for validation of inference system. In comparison with strain-dependent Arrhenius type constitutive equation, the reliability of the suggested ANFIS model has been tested against experimental values using standard statistical criteria. Based on the fitness function obtained from well-trained ANFIS model, the optimization model of hot processing parameters for solder alloy was successfully established using imperialist competitive algorithm (ICA). Besides, the hot working efficiency is delineated in the processing maps using Prasad proposed dynamic materials model. Consequently, it can be suggested that the hybrid structure of ANFIS and ICA provides a new approach in optimization of processing parameters in the field of hot deformation.