Feature extraction and classification of multiple cracks from raw vibrational responses of composite beams using 1D-CNN network

Structures and components need to be constantly monitored to ensure good service life and avoid failures. Structural health monitoring is a wide-ranging concept that tries to ensure the safety of components and structures. Vibration responses of small and large structures contain information about these damages. In the present study, this information is extracted and used to classify the location and severity of cracks. For this purpose, an FE model of Glass Fibre Reinforced Plastic (GFRP) free-free beam is created for beams without any crack and beams with three crack locations and three crack severities. Finite Element (FE) model is validated using modal analysis and is used to generate vibration responses from simulated hammer strikes at different locations on the beam. The vibration data consists of responses of beams that have only one crack present at a time and when two cracks are present. A 1D-CNN network is trained on the generated vibrational responses to classify damage labels assigned for each crack location and crack severity. The network was tested using datasets containing only single crack instances and only dual crack instances. The trained networks were found to be 95% and 93% accurate in determining the damage class respectively. Furthermore, datasets of these two instances combined, containing responses when single cracks and dual cracks are present, were also investigated. These networks had an accuracy of 92%. Hence, in all these instances, the 1D-CNN network classifies the healthy and damaged conditions satisfactorily. There are two advantages of using such a technique. Firstly, this approach simplifies the two-step approach: one for feature extraction and another one for damage prediction into a single step. Secondly, the use of raw vibration data for damage prediction means that real-time damage detection is possible.