Automated gas pipeline corrosion detection with artificial intelligence
Abstract
The article presents a method to detect gas pipeline corrosion using artificial intelligence to analyse visual images with 3 steps: preprocessing of input images; segmentation and extraction of histogram features and texture features; and proposing to use the hidden Markov model trained from feature vectors capable of automatically analysing the camera images and identifying eroded areas of the gas pipeline. An initial experiment on a dataset of over 5000 published oil pipeline images shows the proposed method achieves results with over 90% accuracy.
References
Gerhardus Koch, Jeff Varney, Neil Thopson, Oliver Moghissi, Melissa Goud, and Joe Payer, “International measures of prevention, application, and economics of corrosion technologies study”, NACE International, 2016.
Duzgun Agdas, Jennifer A. Rice, Justin R. Martinez, and Ivan R. Lasa, "Comparison of visual inspection and structural-health monitoring as bridge condition assessment methods", Journal of Performance of Constructed Facilities, Vol. 30, No. 3, pp. 1 - 10, 2016. DOI: 10.1061/(ASCE)CF.1943-5509.0000802.
Marat Enikeev, Irek Gubaydullin, and Marina Maleeva, “Analysis of corrosion process development on metals by means of computer vision”, Engineering Journal, Vol. 21, No. 4, pp. 183 - 192, 2017. DOI: 10.4186/ ej.2017.21.4.183.
Flávio Felix Feliciano, Fabiana Rodrigues Leta, and Fernando Benedicto Mainier, “Texture digital analysis for corrosion monitoring”, Corrosion Science, Vol. 93, pp. 138 - 147, 2015. DOI: 10.1016/j.corsci.2015.01.017.
Po-Han Chen, Ya-Ching Yang, and Luh-Maan Chang, “Automated bridge coating defect recognition using adaptive ellipse approach”, Automation in Construction, Vol. 18, No. 5, pp. 632 - 643, 2009. DOI: 10.1016/j.autcon.2008.12.007.
Amjad Khan, Syed Saad Azhar Ali, Atif Anwer, Syed Hasan Adil, and Fabrice Mériaudeau, “Subsea pipeline corrosion estimation by restoring and enhancing degraded underwater images”, IEEE Access, Vol. 6, pp. 40585 - 40601, 2018. DOI: 10.1109/ACCESS.2018.2855725.
M. Khayatazad, L. De Pue, and W. De Waele, “Detection of corrosion on steel structures using automated image processing”, Developments in the Built Environment, Vol. 3, 2020. DOI: 10.1016/j.dibe.2020.100022.
Luca Petricca, Tomas Moss, Gonzalo Figueroa, and Stian Broen. “Corrosion detection using A.I: A comparison of standard computer vision techniques and deep learning model”, The 6th International Conference on Computer Science, Engineering and Information Technology, Vienna, Austria, 21 - 22 May 2016. DOI: 10.5121/csit.2016.60608.
Tom Gibbons, Gareth Pierce, Keith Worden, and Ifigeneia Antoniadou, "A Gaussian mixture model for automated corrosion detection in remanufacturing", 16th International Conference on Manufacturing Research ICMR, 11 - 13 September 2018. DOI: 10.3233/978-1-61499-902-7- 63.
Francisco Bonnin-Pascuala and Alberto Ortiz, “Corrosion detection for automated visual inspection”, Developments in Corrosion Protection. InTech, 2014, pp. 619 - 632. DOI: 10.5772/57209.
Kristie Seymore, Andrew McCallum, and Ronald Rosenfeld, “Learning hidden Markov model structure for information extraction”, AAAI Technical Report WS-99-11, pp. 37 - 42, 1999.
Yasuo Matsuyama, "Hidden Markov model estimation based on alpha-EM algorithm: Discrete and continuous alpha-HMMs", International Joint Conference on Neural Networks, USA, 31 July - 5 August 2011. DOI: 10.1109/IJCNN.2011.6033304.
Blossom Treesa Bastian, N. Jaspreeth, S. KumarRanjithb, and C.V. Jiji, "Visual inspection and characterization of external corrosion in pipelines using deep neural network", NTD & E International, No. 107, pp. 102 - 134, 2019. DOI: 10.1016/j.ndteint.2019.102134.
G. McLachlan and T. Krishnan, The EM algorithm and extensions, 2nd edition. John Wiley & Sons, 2008.
1. The Author assigns all copyright in and to the article (the Work) to the Petrovietnam Journal, including the right to publish, republish, transmit, sell and distribute the Work in whole or in part in electronic and print editions of the Journal, in all media of expression now known or later developed.
2. By this assignment of copyright to the Petrovietnam Journal, reproduction, posting, transmission, distribution or other use of the Work in whole or in part in any medium by the Author requires a full citation to the Journal, suitable in form and content as follows: title of article, authors’ names, journal title, volume, issue, year, copyright owner as specified in the Journal, DOI number. Links to the final article published on the website of the Journal are encouraged.