In-situ surface porosity prediction in DED (directed energy deposition) printed SS316L parts using multimodal sensor fusion

• Published in: arXiv.org
• Main Authors: Karthikeyan, Adithyaa, Balhara, Himanshu, Hanchate, Abhishek, Lianos, Andreas K, Bukkapatnam, Satish TS
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 23.06.2024
• Subjects: Acoustic emission; Artificial neural networks; Deposition; Emission analysis; High frequencies; Machining; Melt pools; Melting; Pore formation; Porosity; Printing; Sensors; Signatures; Spectrograms; Time-frequency analysis; Tracks (paths); Waveforms

This study aims to relate the time-frequency patterns of acoustic emission (AE) and other multi-modal sensor data collected in a hybrid directed energy deposition (DED) process to the pore formations at high spatial (0.5 mm) and time (< 1ms) resolutions. Adapting an explainable AI method in LIME...