Pitting Detection and Characterization From Ultrasound Timelapse Images Using Convolutional Neural Networks
Pitting corrosion, a localized form of corrosion leading to cavities and structural failure in metallic materials, requires early detection for effective mitigation. While ultrasonic inspection techniques can readily detect uniform wall thinning, they often struggle to identify pitting corrosion. Th...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Instrumentation and Measurement |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10520720/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536191559630848 |
|---|---|
| author | Magnus Wangensteen Tonni Franke Johansen Ali Fatemi Erlend Magnus Viggen Lars Eidissen Haugan |
| author_facet | Magnus Wangensteen Tonni Franke Johansen Ali Fatemi Erlend Magnus Viggen Lars Eidissen Haugan |
| author_sort | Magnus Wangensteen |
| collection | DOAJ |
| description | Pitting corrosion, a localized form of corrosion leading to cavities and structural failure in metallic materials, requires early detection for effective mitigation. While ultrasonic inspection techniques can readily detect uniform wall thinning, they often struggle to identify pitting corrosion. This study proposes a time-lapse ultrasound inspection method to detect early-stage pitting using pulse-echo sensors. By recording multiple ultrasonic traces over time, 2-D timelapse images of ultrasonic reflectivity can be generated and fed into a trained neural network for pitting diagnostics. In general, training a machine-learning model requires a large training dataset. This work used data from a drilling experiment to generate a suitable dataset. Dataset construction by random time-ordered combinations of ultrasonic measurements was conducted to create a diverse set of time-lapse image samples to generalize the resulting machine-learning model adequately. A classification neural network was trained to detect the presence of drilled holes, and a separate regression network was trained to estimate the hole depth. Based on drilling data from an independently acquired test dataset, results demonstrate a mean absolute error of 0.163 mm for hole depth estimations. All holes are successfully detected when 0.1 mm deeper than the defined pitting threshold of 0.5 mm. This suggests that the proposed method generalizes well and can be deployed to any similar acquisition system. |
| format | Article |
| id | doaj-art-90d3bff9fab74a6eb4ec88a19d151009 |
| institution | Kabale University |
| issn | 2768-7236 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Instrumentation and Measurement |
| spelling | doaj-art-90d3bff9fab74a6eb4ec88a19d1510092025-01-15T00:04:24ZengIEEEIEEE Open Journal of Instrumentation and Measurement2768-72362024-01-01311210.1109/OJIM.2024.339682910520720Pitting Detection and Characterization From Ultrasound Timelapse Images Using Convolutional Neural NetworksMagnus Wangensteen0https://orcid.org/0000-0002-2613-7270Tonni Franke Johansen1https://orcid.org/0000-0002-7938-5243Ali Fatemi2https://orcid.org/0000-0003-2615-2507Erlend Magnus Viggen3https://orcid.org/0000-0001-8946-5741Lars Eidissen Haugan4https://orcid.org/0009-0007-6687-6629Department of Circulation and Medical Imaging, Norwegian University of Science and Technology, Trondheim, NorwayDepartment of Circulation and Medical Imaging, Norwegian University of Science and Technology, Trondheim, NorwaySensorlink AS, Trondheim, NorwayDepartment of Circulation and Medical Imaging, Norwegian University of Science and Technology, Trondheim, NorwayDepartment of Mechanical and Industrial Engineering, Norwegian University of Science and Technology, Trondheim, NorwayPitting corrosion, a localized form of corrosion leading to cavities and structural failure in metallic materials, requires early detection for effective mitigation. While ultrasonic inspection techniques can readily detect uniform wall thinning, they often struggle to identify pitting corrosion. This study proposes a time-lapse ultrasound inspection method to detect early-stage pitting using pulse-echo sensors. By recording multiple ultrasonic traces over time, 2-D timelapse images of ultrasonic reflectivity can be generated and fed into a trained neural network for pitting diagnostics. In general, training a machine-learning model requires a large training dataset. This work used data from a drilling experiment to generate a suitable dataset. Dataset construction by random time-ordered combinations of ultrasonic measurements was conducted to create a diverse set of time-lapse image samples to generalize the resulting machine-learning model adequately. A classification neural network was trained to detect the presence of drilled holes, and a separate regression network was trained to estimate the hole depth. Based on drilling data from an independently acquired test dataset, results demonstrate a mean absolute error of 0.163 mm for hole depth estimations. All holes are successfully detected when 0.1 mm deeper than the defined pitting threshold of 0.5 mm. This suggests that the proposed method generalizes well and can be deployed to any similar acquisition system.https://ieeexplore.ieee.org/document/10520720/2-D timelapse imagemachine learningnondestructive testing (NDT)pitting corrosionultrasound |
| spellingShingle | Magnus Wangensteen Tonni Franke Johansen Ali Fatemi Erlend Magnus Viggen Lars Eidissen Haugan Pitting Detection and Characterization From Ultrasound Timelapse Images Using Convolutional Neural Networks IEEE Open Journal of Instrumentation and Measurement 2-D timelapse image machine learning nondestructive testing (NDT) pitting corrosion ultrasound |
| title | Pitting Detection and Characterization From Ultrasound Timelapse Images Using Convolutional Neural Networks |
| title_full | Pitting Detection and Characterization From Ultrasound Timelapse Images Using Convolutional Neural Networks |
| title_fullStr | Pitting Detection and Characterization From Ultrasound Timelapse Images Using Convolutional Neural Networks |
| title_full_unstemmed | Pitting Detection and Characterization From Ultrasound Timelapse Images Using Convolutional Neural Networks |
| title_short | Pitting Detection and Characterization From Ultrasound Timelapse Images Using Convolutional Neural Networks |
| title_sort | pitting detection and characterization from ultrasound timelapse images using convolutional neural networks |
| topic | 2-D timelapse image machine learning nondestructive testing (NDT) pitting corrosion ultrasound |
| url | https://ieeexplore.ieee.org/document/10520720/ |
| work_keys_str_mv | AT magnuswangensteen pittingdetectionandcharacterizationfromultrasoundtimelapseimagesusingconvolutionalneuralnetworks AT tonnifrankejohansen pittingdetectionandcharacterizationfromultrasoundtimelapseimagesusingconvolutionalneuralnetworks AT alifatemi pittingdetectionandcharacterizationfromultrasoundtimelapseimagesusingconvolutionalneuralnetworks AT erlendmagnusviggen pittingdetectionandcharacterizationfromultrasoundtimelapseimagesusingconvolutionalneuralnetworks AT larseidissenhaugan pittingdetectionandcharacterizationfromultrasoundtimelapseimagesusingconvolutionalneuralnetworks |