A pattern recognition system based on acoustic signals for fault detection on composite materials

The use of composite materials in industry applications is constantly growing. However, fault detection and prediction on these materials is not as simple as in traditional materials. Thus, the development of a methodology for fault detection is strictly necessary to ensure the integrity of a structure. This paper proposes a pattern recognition system that implements an Artificial Neural Network classifier to detect and classify damage on composite beams. Classifiers were trained and tested using acoustic signals emitted by healthy and damaged beams after an impulsive load was applied to them. Singular Value Decomposition was used to filter the acoustic signals whereas Principal Component Analysis was implemented to extract relevant information from the filtered signal. The extracted information was used as inputs to the classifier that was able to predict four different levels of damage on glass fiber and carbon fiber beams with more than 97% accuracy. These results suggest that the proposed methodology can be further investigated to develop a robust system for automatic detection of damage on composite structures.