Temporal denoising and deep feature learning for enhanced defect detection in thermography using stacked denoising convolution autoencoder

•Temporal denoising of thermal profiles along with deep feature learning for enhanced defect detection in FMTWI is highlighted through a stacked denoising convolution autoencoder.•Adequate data preparation and training strategies enhanced defect signatures.•Temporal signal-to-noise ratio and defect...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Infrared physics & technology Jg. 143; S. 105612
Hauptverfasser:	Yerneni, Naga Prasanthi, Ghali, V.S., Vesala, G.T., Wang, Fei, Mulaveesala, Ravibabu
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier B.V 01.12.2024
Schlagworte:	CFRP Feature learning Frequency modulated thermography Median filtering Mild steel Signal-to-noise ratio Stacked denoising convolution autoencoder Frequency modulated thermography Mild steel Stacked denoising convolution autoencoder Feature learning Signal-to-noise ratio CFRP Median filtering
ISSN:	1350-4495
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	•Temporal denoising of thermal profiles along with deep feature learning for enhanced defect detection in FMTWI is highlighted through a stacked denoising convolution autoencoder.•Adequate data preparation and training strategies enhanced defect signatures.•Temporal signal-to-noise ratio and defect SNR in both denoised and latent layers support the suitability of proposed methodology. Thermal wave imaging uses the temporal temperature distribution over the object’s surface for subsurface analysis. However, the noise generated during experimentation corrupts this temporal history and hampers the detection of defect signatures. As denoising of the temporal thermal history enhances the defect detectability, this study offers a Stacked Denoising Convolution Autoencoder (SDCAE) in frequency-modulated thermal wave imaging with one-dimensional convolution layers to reduce noise in temporal thermal evolution and train high-level features resulting in improved defect signs. Experimental results on mild steel and carbon fiber reinforced polymer specimens with different sizes of defects at various depths demonstrate that integrating temporal denoising and deep feature learning techniques into a single novel framework significantly improved defect detectability. In addition, defect signal-to-noise ratios of the denoised thermal data and latent space of the proposed model compared to conventional autoencoder and dimensionality reduction techniques recommend the superiority of the proposed method.
ISSN:	1350-4495
DOI:	10.1016/j.infrared.2024.105612