Optimization of pulsed thermography inspection by partial least-squares regression

This paper introduces and tests a statistical correlation method for the optimization of the pulsed thermography inspection. The method is based on partial least squares regression, which decomposes the thermographic PT data sequence obtained during the cooling regime into a set of latent variables. The regression method is applied to experimental PT data from a carbon fiber-reinforced composite with simulated defects. The performance of the regression technique is evaluated in terms of the signal-to-noise ratio. The results showed an increase in the SNRs for 96% of the defects after processing the original sequence with PLSR.