Identification of failure modes in GFRP using PVDF sensors: ANN approach

Acoustic emission (AE) is a highly promising technique for evaluation of composite materials. For reliable automatic damage monitoring with polyvinylidene fluoride (PVDF) film sensors, it is important to identify matrix and fiber failure related AE signals in the presence of noise. In the experiments carried out, multi-layered glass fiber reinforced plastics (GFRP) composites were fabricated with three different stacking sequences (0°/0°, 0°/90° and ±45°) and AE signals were picked up with a surface mounted PVDF film during static tensile load. The AE signals were classified using an artificial neural network (ANN). The results reveal that different failure mechanisms in composites can be characterized with ANN.