What does this research mean for the field?

While artificial intelligence methodologies are highly effective for in-process prediction, early warning, and screening in directed energy deposition (DED) additive manufacturing, conventional inspection methods remain essential for direct measurement, validation, and qualification. Novelty: ClaimNovelty.SYNTHESIS. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To systematically evaluate artificial intelligence methodologies for quality control, defect detection, and real-time process monitoring in directed energy deposition metal additive manufacturing.

August 28, 2026Journal of Intelligent ManufacturingOpen Access

Artificial intelligence for quality control and monitoring in directed energy deposition metal additive manufacturing: applications, challenges, and opportunities

View Full Paper

Ask AI

Bookmark

Authors

BDBinoy Debnath TZTasbirul Alam Zihan CRCesar Ruiz

Discussion

Member takes

Overview

Systematic review reveals AI enhances defect detection and real-time monitoring in directed energy deposition additive manufacturing, indicating potential for automated closed-loop quality control.

Key Points

To systematically evaluate artificial intelligence methodologies for quality control, defect detection, and real-time process monitoring in directed energy deposition metal additive manufacturing.
Conducted a systematic literature review following PRISMA guidelines across 145 peer-reviewed articles published between 2015 and 2026.
Categorized quality defects into geometrical, morphological, and microstructural groups, comparing machine learning and deep learning models with conventional non-destructive evaluation methods.
Convolutional neural networks, random forests, and autoencoders successfully process thermal and optical signals to monitor melt pools and detect defects in real time.
Conventional inspection remains necessary for final part qualification, while artificial intelligence models primarily provide in-situ anomaly detection, process-state screening, and closed-loop control capabilities.
Major implementation hurdles include sensor reliability under harsh thermal gradients, limited training data, poor model interpretability, and weak generalization across diverse materials and geometries.

Cite This Study

Debnath et al. (2026) studied this question.

synapsesocial.com/papers/6a914602d15324a1df3a94d1 https://doi.org/10.1007/s10845-026-02931-2

View Full Paper

Ask AI

Bookmark

August 28, 2026Journal of Intelligent ManufacturingOpen Access

Artificial intelligence for quality control and monitoring in directed energy deposition metal additive manufacturing: applications, challenges, and opportunities

View Full Paper

Ask AI

Bookmark

Authors

BDBinoy Debnath TZTasbirul Alam Zihan CRCesar Ruiz

Discussion

Member takes

Overview

Systematic review reveals AI enhances defect detection and real-time monitoring in directed energy deposition additive manufacturing, indicating potential for automated closed-loop quality control.

Key Points

To systematically evaluate artificial intelligence methodologies for quality control, defect detection, and real-time process monitoring in directed energy deposition metal additive manufacturing.
Conducted a systematic literature review following PRISMA guidelines across 145 peer-reviewed articles published between 2015 and 2026.
Categorized quality defects into geometrical, morphological, and microstructural groups, comparing machine learning and deep learning models with conventional non-destructive evaluation methods.
Convolutional neural networks, random forests, and autoencoders successfully process thermal and optical signals to monitor melt pools and detect defects in real time.
Conventional inspection remains necessary for final part qualification, while artificial intelligence models primarily provide in-situ anomaly detection, process-state screening, and closed-loop control capabilities.
Major implementation hurdles include sensor reliability under harsh thermal gradients, limited training data, poor model interpretability, and weak generalization across diverse materials and geometries.

Cite This Study

Debnath et al. (2026) studied this question.

synapsesocial.com/papers/6a914602d15324a1df3a94d1 https://doi.org/10.1007/s10845-026-02931-2

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark