The Prediction of Forming Limit Diagram of Low Carbon Steel Sheets Using Adaptive Fuzzy Inference System Identifier

The paper deals with devising the combination of fuzzy inference systems (FIS) and neural networks called the adaptive network fuzzy inference system (ANFIS) to determine the forming limit diagram (FLD). In this paper, FLDs are determined experimentally for two grades of low carbon steel sheets using out-of-plane (dome) formability test. The effect of different parameters such as work hardening exponent (n), anisotropy (r) and thickness on these diagrams were studied. The out-of-plane stretching test with hemispherical punch was simulated by finite element software Abaqus. The limit strains occurred with localized necking were specified by tracing the thickness strain and its first and second derivatives versus time at the thinnest element. In addition, to investigate the effect of different parameters such as work hardening exponent (n), anisotropy (r) and thickness on these diagrams, a machine learning algorithm is used to simulate a predictive framework. The method of learning algorithm uses the rudiments of neural computing through layering the FIS and using hybrid-learning optimization algorithm. In other words, for building the training database of ANFIS, the experimental work and finite element software Abaqus are used to obtain limit strains. Good agreement was achieved between the predicted data and the experimental results.