What does this research mean for the field?

An in-situ defect detection framework combining acoustic signal analysis and a ResNet18 convolutional neural network can identify process-induced defects in wire arc additive manufacturing with 93.67% accuracy. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The study aims to develop an effective framework for detecting defects in wire arc additive manufacturing using acoustic signal analysis and deep learning.

June 6, 2026Proceedings of the Institution of Mechanical Engineers Part B Journal of Engineering Manufacture

In-situ defect detection in wire arc additive manufacturing of mild steel using deep learning

View Full Paper

Ask AI

Bookmark

Authors

MSMuhammad SaadGhulam Ishaq Khan Institute of Engineering Sciences and Technology MJMassab JunaidGhulam Ishaq Khan Institute of Engineering Sciences and Technology AAArsalan ArifGhulam Ishaq Khan Institute of Engineering Sciences and Technology

Discussion

Member takes

Implication

Randomized trial demonstrates in-situ defect detection in additive manufacturing, suggesting improved process monitoring.

Key Points

The study aims to develop an effective framework for detecting defects in wire arc additive manufacturing using acoustic signal analysis and deep learning.
Captured acoustic emissions during welding using an electret microphone.
Converted signals into time-frequency spectrograms using short-time Fourier transform (STFT).
Employed a ResNet18 CNN with transfer learning for multi-class classification of welding conditions.
Achieved an overall accuracy of 93.67% across four classes of defects.
Demonstrated distinct acoustic features related to weld quality and defect formation mechanisms.
Proposed method is simpler and more cost-effective compared to conventional monitoring systems.

Cite This Study

Saad et al. (2026) studied this question.

synapsesocial.com/papers/6a23bb9a71a5da9775e7718d https://doi.org/10.1177/09544054261452058

View Full Paper

Ask AI

Bookmark

In-situ defect detection in wire arc additive manufacturing of mild steel using deep learning

Discussion

Member takes

Implication

Key Points

Cite This Study

In-situ defect detection in wire arc additive manufacturing of mild steel using deep learning

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider