Reconstruction of the Taguchi Orthogonal Arrays with the Support Vector Machines Method

Design of Experiment (DOE) is a widely used method for examining experiments especially in industrial production and robust design processes. This set statistical approaches which mathematical models are developed through experimental testing to estimate possible outputs given input values or parameters. The aims determine the main factors that affect results with smallest number studies. In this study, L16 (2^15) orthogonal array, was Taguchi parameter reconstructed Support Vector Machines learning model Pearson VII kernel function. With model, array elements were successfully classified 87.04%. new original compared 3.8% difference measured between their Signal Noise (S / N) ratios an exemplary experiment.