Advances and Challenges in Deep Learning for Automated Welding Defect Detection: A Technical Survey

Достижения и проблемы глубокого обучения для автоматизированного обнаружения дефектов сварных соединений: технический обзор
Muhammad Hussain, Abdulrahim Mohammed
2025-01-01

deep learningdefect segmentationdomain adaptationexplainable AIwelding defect detection
Automated welding defect detection has emerged as a pivotal aspect of quality assurance in high-stakes industries such as aerospace, oil and gas, and construction. This paper presents a comprehensive review of state-of-the-art deep learning (DL) models tailored for welding defect detection, segmentation, and classification, emphasizing technical advancements and persistent challenges. A critical analysis of single-stage and two-stage architectures is conducted to evaluate their ability to address issues like small defect sizes, low image contrast, and diverse defect geometries. The study also highlights the integration of advanced preprocessing techniques, such as noise reduction and contrast enhancement, within DL workflows to improve feature extraction and detection accuracy. Persistent challenges, such as the scarcity of large, labeled datasets, lack of real-time applicability, and limited model interpretability, are explored in depth. To address these gaps, the survey proposes future directions, including the use of self-supervised learning, domain adaptation, generative adversarial networks (GANs), and explainable AI techniques to enhance the robustness, scalability, and transparency of welding defect detection systems. By synthesizing insights from more than a decade of research, this paper provides a detailed roadmap for advancing automated welding inspection technologies, enabling reliable deployment in real-world industrial environments.
1
Major barriers to industrial deployment include scarce large labeled datasets, insufficient real-time applicability, and limited model interpretability.
2
Noise reduction and contrast enhancement integrated into deep-learning workflows can improve feature extraction and detection accuracy.
3
Self-supervised learning, domain adaptation, GANs, and explainable AI are identified as promising directions for improving robustness, scalability, and transparency.
4
Single-stage and two-stage architectures are critically compared for handling small defects, low image contrast, and diverse defect geometries.
5
The survey synthesizes over a decade of deep-learning research on automated welding defect detection, segmentation, and classification.

automated welding defect detection systems

deep-learning-based detection, segmentation, and classification performance, robustness, scalability, real-time applicability, and interpretability under challenges such as small defects, low image contrast, diverse defect geometries, and limited labeled data

Publication Details
Publication Date
2025-01-01
Journal
Publisher
ISSN
Cited by
42
Access Type
Author Information
Authors
Muhammad Hussain
Abdulrahim Mohammed
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%