Consistent and Minimal Springback Using a Stepped Binder Force Trajectory and Neural Network Control

One of the greatest challenges of manufacturing sheet metal parts is to obtain consistent part dimensions. Springback, the elastic material recovery when the tooling is removed, is the major cause of variations and inconsistencies in the final part geometry. Obtaining a consistent and desirable amount of springback is extremely difficult due to the nonlinear effects and interactions between process and material parameters. In this paper, the exceptional ability of a neural network along with a stepped binder force trajectory to control springback angle and maximum principal strain in a simulated channel forming process is demonstrated. When faced with even large variations in material properties, sheet thickness, and friction condition, the control system produces a robust final part shape.

[1]  Robert A. Ayres,et al.  SHAPESET: A process to reduce sidewall curl springback in high-strength steel rails , 1984 .

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[4]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[5]  R. H. Wagoner,et al.  Experimental Analysis of Blank Holding Force Control in Sheet Forming , 1993 .

[6]  Plane-Strain Tension Tests of Al 2008-T4 Sheets , 1993 .

[7]  A. P. Karafillis,et al.  Accommodation of Springback Error in Channel Forming Using Active Binder Force Control: Numerical Simulations and Experiments , 1996 .

[8]  Sungzoon Cho,et al.  Reliable roll force prediction in cold mill using multiple neural networks , 1997, IEEE Trans. Neural Networks.

[9]  Pf Thomson,et al.  Neural Network Approach for Prediction of Wrinkling Limit in Square Metal Sheet Under Diagonal Tension , 1997 .

[10]  Brad L. Kinsey,et al.  An experimental study to determine the feasibility of implementing process control to reduce part variation in a stamping plant , 1997 .

[11]  A. Forcellese,et al.  Effect of the training set size on springback control by neural network in an air bending process , 1998 .

[12]  Jian Cao,et al.  USING NEURAL NETWORK FOR SPRINGBACK MINIMIZATION IN A CHANNEL FORMING PROCESS , 1998 .

[13]  Process control in sheet metal forming focused upon friction , 1998 .