ACOUSTIC EMISSION SIGNAL PROCESSING STUDY OF NANOINDENTATION ON THIN FILM STACK STRUCTURES USING GAUSSIAN MIXTURE MODEL

This investigation utilizes a material testing system that integrates acoustic emission (AE) testing with a nanoindentation system for crack generation and detection in Al-Cu top thin-film stack structures. The suitability of using the AE method was verified with scanning electron microscope (SEM) images of indent cross-sections. In order to cluster the AE signals based on a different physical meaning, a signal processing approach based on the Gaussian mixture model (GMM) clustering algorithm was applied. Principal component analysis (PCA) and autoencoder feature extraction methods were used to reduce the dimension of the signal. This signal processing approach has the promising ability to distinguish AE events associated with crack formation and metal layer plastic deformation. This integrated test system and signal processing approach provide a high-resolution mechanical testing platform for studying and enabling automatic, non-destructive crack detection in wafer probing.