Damage identification in aluminum beams using support vector machine: Numerical and experimental studies

Support vector machine (SVM) has been established as a promising tool for classification and regression in many research fields recently. In the current research work, SVM is explored to find damage locations in aluminum beams using simulation data and experimental data. Displacement values corresponding to the first mode shape of the beam are used to predict the damage locations. Two boundary conditions namely fixed-free and fixed-fixed are considered for this study. Damages are introduced in the form of rectangular notches along the width of the beam at different locations. Numerical simulations using commercially available finite element (FE) package, Abaqus((R)) are first carried out on beam and mode shape data is extracted to train and test SVM with and without noise in data. To validate the predictions of damage locations based on simulation data, actual experimentations are conducted on aluminum beams of identical dimensions and boundary conditions. In the experimental study, a Laser Doppler Vibrometer (LDV) is used to extract the mode shape data. It is shown that SVM is capable to predict damage locations with a good accuracy and can be used as a promising tool in the field of structural health monitoring (SHM). Copyright (c) 2015 John Wiley & Sons, Ltd.