What does this research mean for the field?

Integrating image processing techniques with a knowledge-driven, rule-based framework enables automated, explainable defect detection in high-noise nuclear reactor inspection videos. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Develop an automated, transparent defect detection framework that combines digital image processing with domain-specific engineering rules to identify structural anomalies in high-radiation nuclear reactor inspection footage.

September 14, 2026Nuclear TechnologyOpen Access

Knowledge-Driven Explainable AI for Automated Defect Detection in Nuclear Reactor Components

View Full Paper

Ask AI

Bookmark

Authors

AYAndrew Young CMCallum Manning JZJaime Zabalza

Discussion

Member takes

Overview

Validation study demonstrates automated defect detection in nuclear reactor inspection footage, highlighting explainable anomaly filtering in high-radiation environments.

Key Points

Develop an automated, transparent defect detection framework that combines digital image processing with domain-specific engineering rules to identify structural anomalies in high-radiation nuclear reactor inspection footage.
Applied frame differencing to capture temporal variations across video frames, followed by intensity thresholding and morphological operations to reduce radiation-induced visual noise.
Integrated a knowledge-driven, rule-based filtering module incorporating anomaly size, persistence across multiple frames, and proximity to critical structural surfaces.
Evaluated the algorithmic pipeline using a real-world case study of calandria tubesheet bore inspection video data.
Successfully suppressed radiation-induced visual artifacts and isolated true surface defects within calandria tubesheet bore inspection videos.
Provided transparent, rule-based justifications for every flagged anomaly to satisfy nuclear regulatory requirements for traceable and defensible inspection records.
Generated automated defect reports with visual overlays to streamline manual reviews and assist plant engineers in structural assessments.

Cite This Study

Young et al. (2026) studied this question.

synapsesocial.com/papers/6aa7b2f70926e14a848b1891 https://doi.org/10.1080/00295450.2026.2721224

View Full Paper

Ask AI

Bookmark

September 14, 2026Nuclear TechnologyOpen Access

Knowledge-Driven Explainable AI for Automated Defect Detection in Nuclear Reactor Components

View Full Paper

Ask AI

Bookmark

Authors

AYAndrew Young CMCallum Manning JZJaime Zabalza

Discussion

Member takes

Overview

Validation study demonstrates automated defect detection in nuclear reactor inspection footage, highlighting explainable anomaly filtering in high-radiation environments.

Key Points

Develop an automated, transparent defect detection framework that combines digital image processing with domain-specific engineering rules to identify structural anomalies in high-radiation nuclear reactor inspection footage.
Applied frame differencing to capture temporal variations across video frames, followed by intensity thresholding and morphological operations to reduce radiation-induced visual noise.
Integrated a knowledge-driven, rule-based filtering module incorporating anomaly size, persistence across multiple frames, and proximity to critical structural surfaces.
Evaluated the algorithmic pipeline using a real-world case study of calandria tubesheet bore inspection video data.
Successfully suppressed radiation-induced visual artifacts and isolated true surface defects within calandria tubesheet bore inspection videos.
Provided transparent, rule-based justifications for every flagged anomaly to satisfy nuclear regulatory requirements for traceable and defensible inspection records.
Generated automated defect reports with visual overlays to streamline manual reviews and assist plant engineers in structural assessments.

Cite This Study

Young et al. (2026) studied this question.

synapsesocial.com/papers/6aa7b2f70926e14a848b1891 https://doi.org/10.1080/00295450.2026.2721224

Also Consider

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

View Full Paper

Ask AI

Bookmark