Defect detection and characterization by laser vibrometry and neural networks

In this work Scanning Laser Doppler Vibrometry (SLDV) has been used to detect, localize and characterize defects in mechanical structures. After dedicated post-processing, a neural network is employed to classify LDV data with the aim of automating the detection procedure. The presented methodology has proved to be efficient to automatically recognize defects and also to determine their depth in composite materials. Furthermore, it is worth noting that the diagnostic procedure supplied correct results for the three investigated cases using the same neural network, which was trained with the samples generated by the Finite Element model of the aluminum plate. The proposed methodology was then applied for the detection of damages on real cases, as composite material panels. In addition, the versatility of the approach was demonstrated analyzing a Byzantine icon, which can be considered as a singular kind of composite structure.