A Comprehensive Survey on Machine Learning Driven Material Defect Detection: Challenges, Solutions, and Future Prospects

2024-06-12

ACM Computing Surveys

AI Summary

Material defects represent a critical bottleneck undermining the safety and performance of high-end equipment—particularly aerospace composite materials. This paper presents a systematic review of recent advances in machine learning for material defect detection (ML-MDD). We propose, for the first time, a unified methodological framework categorizing ML-MDD approaches into five paradigms: unsupervised, supervised, semi-supervised, reinforcement learning, and generative learning. Addressing domain-specific challenges—including imaging blur, severe data scarcity, and multi-scale defects in composites—we rigorously analyze the applicability boundaries and performance limitations of each paradigm. By integrating autoencoders, generative adversarial networks (GANs), graph neural networks (GNNs), and multimodal industrial imaging modalities, we construct the most comprehensive ML-MDD technology taxonomy to date and outline an extensible evolutionary roadmap. Our work provides both theoretical foundations and practical guidelines for algorithm selection in industrial quality inspection and for strategic planning of future research directions.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

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
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Material defects (MD) represent a primary challenge affecting product performance and giving rise to safety issues in related products. The rapid and accurate identification and localization of MD constitute crucial research endeavors in addressing contemporary challenges associated with MD. In recent years, propelled by the swift advancement of machine learning (ML) technologies, particularly exemplified by deep learning, ML has swiftly emerged as the core technology and a prominent research direction for material defect detection (MDD). Through a comprehensive review of the latest literature, we systematically survey the ML techniques applied in MDD into five categories: unsupervised learning, supervised learning, semi-supervised learning, reinforcement learning, and generative learning. We provide a detailed analysis of the main principles and techniques used, together with the advantages and potential challenges associated with these techniques. Furthermore, the survey focuses on the techniques for defect detection in composite materials, which are important types of materials enjoying increasingly wide application in various industries such as aerospace, automotive, construction, and renewable energy. Finally, the survey explores potential future directions in MDD utilizing ML technologies. This survey consolidates ML-based MDD literature and provides a foundation for future research and practice.

Problem

• Identifying and localizing material defects rapidly and accurately
• Surveying ML techniques for material defect detection in five categories
• Focusing on defect detection in widely used composite materials

Innovation

• Machine learning for material defect detection
• Five ML categories for defect analysis
• Focus on composite materials detection