Deep Learning Approach for Pitting Corrosion Detection in Gas Pipelines

Autor: Ivan Malashin, Vadim Tynchenko, Vladimir Nelyub, Aleksei Borodulin, Andrei Gantimurov, Nikolay V. Krysko, Nikita A. Shchipakov, Denis M. Kozlov, Andrey G. Kusyy, Dmitry Martysyuk, Andrey Galinovsky
Jazyk: angličtina
Rok vydání: 2024
Předmět:
Zdroj: Sensors, Vol 24, Iss 11, p 3563 (2024)
Druh dokumentu: article
ISSN: 1424-8220
DOI: 10.3390/s24113563
Popis: The paper introduces a computer vision methodology for detecting pitting corrosion in gas pipelines. To achieve this, a dataset comprising 576,000 images of pipelines with and without pitting corrosion was curated. A custom-designed and optimized convolutional neural network (CNN) was employed for binary classification, distinguishing between corroded and non-corroded images. This CNN architecture, despite having relatively few parameters compared to existing CNN classifiers, achieved a notably high classification accuracy of 98.44%. The proposed CNN outperformed many contemporary classifiers in its efficacy. By leveraging deep learning, this approach effectively eliminates the need for manual inspection of pipelines for pitting corrosion, thus streamlining what was previously a time-consuming and cost-ineffective process.
Databáze: Directory of Open Access Journals
Nepřihlášeným uživatelům se plný text nezobrazuje