PCA-Guided Autoencoding for Structured Dimensionality Reduction in Active Infrared Thermography

TL;DR

This paper introduces a PCA-guided autoencoding framework for structured dimensionality reduction in active infrared thermography, improving defect detection by capturing complex features while maintaining a structured latent space.

Contribution

It proposes a novel PCA distillation loss and a neural network-based evaluation metric to enhance autoencoder performance for thermographic defect characterization.

Findings

Outperforms state-of-the-art methods on PVC, CFRP, and PLA samples.

Improves contrast and SNR in thermographic defect detection.

Provides a structured latent space beneficial for downstream analysis.

Abstract

Active Infrared thermography (AIRT) is a widely adopted non-destructive testing (NDT) technique for detecting subsurface anomalies in industrial components. Due to the high dimensionality of AIRT data, current approaches employ non-linear autoencoders (AEs) for dimensionality reduction. However, the latent space learned by AIRT AEs lacks structure, limiting their effectiveness in downstream defect characterization tasks. To address this limitation, this paper proposes a principal component analysis guided (PCA-guided) autoencoding framework for structured dimensionality reduction to capture intricate, non-linear features in thermographic signals while enforcing a structured latent space. A novel loss function, PCA distillation loss, is introduced to guide AIRT AEs to align the latent representation with structured PCA components while capturing the intricate, non-linear patterns in thermographic signals. To evaluate the utility of the learned, structured latent space, we propose a neural network-based evaluation metric that assesses its suitability for defect characterization. Experimental results show that the proposed PCA-guided AE outperforms state-of-the-art dimensionality reduction methods on PVC, CFRP, and PLA samples in terms of contrast, signal-to-noise ratio (SNR), and neural network-based metrics.