Use of the support vector machine (SVM) algorithm to predict geometrical accuracy in the manufacture of molds via single point incremental forming (SPIF) using aluminized steel sheets

In the present work, use of support vector machine (SVM) algorithm is proposed to generate models that allow predicting geometrical accuracy molds manufactured via single point incremental forming (SPIF) using aluminized steel sheets DX51D AS120 B CO. For this purpose, 27 were manufactured, dummy technique, and employing different process parameters (tool diameter, spindle speed, feed rate, step size) toolpath strategies (contour-parallel, spiral, radial). The geometrically characterized by means a coordinate measuring machine: transverse profile each mold was measured compared with expected theoretical profile. Three values extracted from comparison: area between two profiles, moment inertia respect Y-axis difference in height profiles at mid-point mold. increases if these decrease. model achieved best results one associated real (correctly classified instances = 90%; kappa statistic 0.8). This generated LibSVM (linear kernel) evaluating only three five (strategy, tool diameter size). addition, maps drawn up show briefly which higher molds: contour-parallel strategy, equal 12 mm small size values.