Springback adaptive-predictive control

In the sheet metalforming springback may lead to afterward unacceptable dimensions and problems during assembling, thereby negatively affecting the quality of the product. In the case of thin sheet metalforming the springback is the main component of manufacturing error. Moreover, inconsistency in springback adds to difficulties in obtaining consistent product quality. In this paper, the authors propose a novel method of springback adaptive and predictive control based on modeling using Support Vector Machine (SVM). SVM is used for developing the separation limits of domains with higher or lower springback parameter values, compared with springback reference values obtained using a finite-element analysis (FEA) software package. Simulating the proposed method resulted in an increase in efficiency for the case of thin sheets with large dispersion of geometrical and material characteristics.