Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{171031,
        author = {Harsh Pathak and Atul Suri},
        title = {Enhancing Non-Destructive Testing through Data Mining and Machine Learning: A Transfer Learning Perspective},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {7},
        pages = {1917-1926},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=171031},
        abstract = {Non-destructive testing (NDT) is crucial for ensuring structural integrity and safety across various industries. Traditional NDT methods, while effective, are often time-consuming, subjective, and heavily reliant on human judgment. Recent advancements in machine learning (ML) and data mining (DM) techniques have shown promise in enhancing the accuracy, efficiency, and consistency of NDT processes. Approaches such as support vector machines, neural networks, and random forests have been successfully applied to critical NDT applications, including defect classification, severity rating, and localization. However, the reliance of these methods on large labelled datasets has been a significant limitation, particularly in specialized fields with restricted data access. Transfer learning (TL) has emerged as a practical solution to this challenge, enabling the adaptation of pre-trained models to specific NDT tasks with minimal additional training data. TL has demonstrated improved accuracy and reduced training time in various NDT applications, such as radiographic testing of welds and defect detection in composite materials. Despite these advancements, challenges remain in developing more robust and interpretable models, as well as addressing ethical considerations, including data privacy and bias. This review provides an overview of the state-of-the-art integration of NDT with ML, DM, and TL, discussing the key benefits, limitations, and future research directions in this rapidly evolving field.},
        keywords = {Data mining, Machine learning, Non-destructive testing, Safety, Structural integrity, Transfer learning},
        month = {December},
        }