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

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.

[1]  Andy J. Keane,et al.  A Knowledge-Based Approach To Response Surface Modelling in Multifidelity Optimization , 2003, J. Glob. Optim..

[2]  Tran-Viet Anh,et al.  Optimization of bending sequence in roll forming using neural network and genetic algorithm , 2011 .

[3]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[4]  M. R. Morovvati,et al.  Initial Blank Optimization in Multilayer Deep Drawing Process Using GONNS , 2010 .

[5]  Ali Mkaddem,et al.  Experimental approach and RSM procedure on the examination of springback in wiping-die bending processes , 2007 .

[6]  Mahdi Mahfouf,et al.  Genetic algorithms and hybrid neural network modelling for aluminium stress—strain prediction , 2003 .

[7]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[8]  Sutasn Thipprakmas.  Finite element analysis of punch height effect on V-bending angle , 2010 .

[9]  Mohammad Bakhshi-Jooybari,et al.  Modeling of spring-back in V-die bending process by using fuzzy learning back-propagation algorithm , 2011, Expert Syst. Appl..

[10]  Saeed Setayeshi,et al.  Prediction of influence parameters on the hot rolling process using finite element method and neural network , 2009 .

[11]  Tran-Viet Anh,et al.  Development of two-phase neural network-genetic algorithm hybrid model in modeling damage evolution in roll forming of aluminum sheet , 2013 .

[12]  Joaquim Ciurana,et al.  Springback determination of sheet metals in an air bending process based on an experimental work , 2007 .

[13]  M. Bozdemir,et al.  Artificial Neural Network Analysis of Springback in V Bending , 2008 .

[14]  Fang Wang,et al.  Knowledge based neural models for microwave design , 1997, 1997 IEEE MTT-S International Microwave Symposium Digest.

[15]  Uday B. Desai,et al.  Studies on the prediction of springback in air vee bending of metallic sheets using an artificial neural network , 2000 .

[16]  Mohammad Bakhshi-Jooybari,et al.  The study of spring-back of CK67 steel sheet in V-die and U-die bending processes , 2009 .