Enhancing fault characterisation in composites using infrared thermography: a bee colony optimisation approach with self-organising maps

This work presents an innovative approach aimed at enhancing the characterisation of discontinuities through the processing of thermographic images. The proposed methodology combines self-organising maps (SOM) with bio-inspired parameter optimisation through bee colony optimisation technique. The primary focus is on improving the quality of the fault quantification metric known as the signal-to-noise ratio (SNR). The goal is to achieve a better fault visualisation, ultimately contributing to the advance of thermography as a non-destructive technique. To validate this novel approach, an experiment was conducted using pulsed thermography on a unidirectional carbon laminate piece measuring 33 ✕100 mm. This specimen was intentionally equipped with three artificial delaminations positioned at different depths on specific layers. The results were then compared against conventional approaches such as principal component analysis, partial least-squares regression and polynomial approximation. The findings from this experiment demonstrated the potential of the proposed approach, i.e. the bee colony optimisation coupled with SOM, on the characterisation of discontinuities using infrared thermography data. There was a 15% improvement on the SNR when using the proposed approach over the other tested approaches. This research makes a noteworthy contribution by offering a promising technique for both the detection and characterisation of faults in composite materials.