Advancing Welding Defect Detection in Maritime Operations via Adapt-WeldNet and Defect Detection Interpretability Analysis

2025-08-01

AI Summary

Traditional non-destructive testing (NDT) methods for weld defect detection in offshore oil and gas pipelines suffer from insufficient sensitivity, while existing deep learning approaches exhibit arbitrary architectural choices and lack interpretability. Method: This paper proposes Adapt-WeldNet, an adaptive detection framework, and DDIA, a dedicated explainability analysis system. The methodology integrates transfer learning, adaptive optimization, and eXplainable AI (XAI) techniques—including Grad-CAM and LIME—and incorporates a Human-in-the-Loop validation mechanism guided by ASNT-certified domain experts to jointly optimize model performance and decision transparency. Contribution/Results: Experimental results demonstrate significant improvements in defect identification accuracy and enhanced trustworthiness of automated interpretation. The proposed solution delivers a high-precision, high-reliability intelligent inspection framework tailored for critical offshore infrastructure, bridging the gap between algorithmic performance and operational accountability.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Weld defect detection is crucial for ensuring the safety and reliability of piping systems in the oil and gas industry, especially in challenging marine and offshore environments. Traditional non-destructive testing (NDT) methods often fail to detect subtle or internal defects, leading to potential failures and costly downtime. Furthermore, existing neural network-based approaches for defect classification frequently rely on arbitrarily selected pretrained architectures and lack interpretability, raising safety concerns for deployment. To address these challenges, this paper introduces ``Adapt-WeldNet", an adaptive framework for welding defect detection that systematically evaluates various pre-trained architectures, transfer learning strategies, and adaptive optimizers to identify the best-performing model and hyperparameters, optimizing defect detection and providing actionable insights. Additionally, a novel Defect Detection Interpretability Analysis (DDIA) framework is proposed to enhance system transparency. DDIA employs Explainable AI (XAI) techniques, such as Grad-CAM and LIME, alongside domain-specific evaluations validated by certified ASNT NDE Level II professionals. Incorporating a Human-in-the-Loop (HITL) approach and aligning with the principles of Trustworthy AI, DDIA ensures the reliability, fairness, and accountability of the defect detection system, fostering confidence in automated decisions through expert validation. By improving both performance and interpretability, this work enhances trust, safety, and reliability in welding defect detection systems, supporting critical operations in offshore and marine environments.

Problem

• Detect subtle welding defects in maritime piping systems
• Improve interpretability of neural network-based defect classification
• Enhance trust and reliability in automated defect detection

Innovation

• Adapt-WeldNet optimizes defect detection via adaptive framework
• DDIA enhances transparency with XAI and expert validation
• Combines HITL and Trustworthy AI for reliable decisions