Improved knowledge-based neural network (KBNN) model for predicting spring-back angles in metal sheet bending

• Published in: International journal of modeling, simulation and scientific computing Vol. 5; no. 2; p. 1350026
• Main Authors: Bui, Tinh Quoc, Tran, Anh Viet, Shah, Abid Ali
• Format: Journal Article
• Language: English
• Published: Hackensack World Scientific Publishing Company 01.06.2014; World Scientific Publishing Co. Pte., Ltd
• Subjects: Artificial neural networks; Empirical analysis; Finite element method; Knowledge base; Knowledge management; Mathematical models; Metal sheets; Multilayer perceptrons; Neural networks; Process parameters; Response surface methodology; Uranium; genetic algorithm; optimization algorithm; spring-back angles; knowledge-based neural network; Metal sheet bending
• ISSN: 1793-9623; 1793-9615
• DOI: 10.1142/S1793962313500268

We develop an efficiently improved knowledge-based neural network (KBNN) associated with optimization algorithms and finite element analysis (FEA) to accurately predict spring-back angles in metal sheet bending. The well-known V and U prevalent processes of bending are considered. The KBNN predictive results are based on the empirical model and artificial neural network (ANN) modeling. The empirical model is constructed from the FEA results using response surface method, while the multilayer perceptron is employed to create the ANN. The trained KBNN can accurately model the relationship between the spring-back angles and process parameters. The obtained results are validated against other existing methods showing a high accuracy.