Тип публикации: статья из журнала

Год издания: 2024

Идентификатор DOI: 10.3390/s24113563

Аннотация: <jats:p>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, disПоказать полностьюtinguishing 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.</jats:p>

Журнал: Sensors

Выпуск журнала: Т. 24, № 11

Номера страниц: 3563

ISSN журнала: 14248220

Издатель: Molecular Diversity Preservation International

• Malashin Ivan (Artificial Intelligence Technology Scientific and Education Center, Department of Welding, Diagnostics and Special Robotics, Bauman Moscow State Technical University, 105005 Moscow, Russia)
• Tynchenko Vadim (Artificial Intelligence Technology Scientific and Education Center, Department of Welding, Diagnostics and Special Robotics, Bauman Moscow State Technical University, 105005 Moscow, Russia)
• Nelyub Vladimir (Scientific Department, Far Eastern Federal University, 690922 Vladivostok, Russia)
• Borodulin Aleksei (Artificial Intelligence Technology Scientific and Education Center, Department of Welding, Diagnostics and Special Robotics, Bauman Moscow State Technical University, 105005 Moscow, Russia)
• Gantimurov Andrei (Artificial Intelligence Technology Scientific and Education Center, Department of Welding, Diagnostics and Special Robotics, Bauman Moscow State Technical University, 105005 Moscow, Russia)
• Krysko Nikolay V. (Artificial Intelligence Technology Scientific and Education Center, Department of Welding, Diagnostics and Special Robotics, Bauman Moscow State Technical University, 105005 Moscow, Russia)
• Shchipakov Nikita A. (Artificial Intelligence Technology Scientific and Education Center, Department of Welding, Diagnostics and Special Robotics, Bauman Moscow State Technical University, 105005 Moscow, Russia)
• Kozlov Denis M. (Artificial Intelligence Technology Scientific and Education Center, Department of Welding, Diagnostics and Special Robotics, Bauman Moscow State Technical University, 105005 Moscow, Russia)
• Kusyy Andrey G. (Artificial Intelligence Technology Scientific and Education Center, Department of Welding, Diagnostics and Special Robotics, Bauman Moscow State Technical University, 105005 Moscow, Russia)
• Martysyuk Dmitry (Artificial Intelligence Technology Scientific and Education Center, Department of Welding, Diagnostics and Special Robotics, Bauman Moscow State Technical University, 105005 Moscow, Russia)
• Galinovsky Andrey (Artificial Intelligence Technology Scientific and Education Center, Department of Welding, Diagnostics and Special Robotics, Bauman Moscow State Technical University, 105005 Moscow, Russia)

• Ядро РИНЦ (eLIBRARY.RU)