{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:37:16Z","timestamp":1774431436347,"version":"3.50.1"},"reference-count":48,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T00:00:00Z","timestamp":1723075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Sciences and Engineering Research Council of Canada (NSERC)","award":["RGPIN-2019\u201305160"],"award-info":[{"award-number":["RGPIN-2019\u201305160"]}]},{"name":"Faculty of Engineering of the University of Western Ontario","award":["RGPIN-2019\u201305160"],"award-info":[{"award-number":["RGPIN-2019\u201305160"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Pinhole corrosions on oil and gas pipelines are difficult to detect and size and, therefore, pose a significant challenge to the pipeline integrity management practice. This study develops two convolutional neural network (CNN) models to identify pinholes and predict the sizes and location of the pinhole corrosions according to the magnetic flux leakage signals generated using the magneto-static finite element analysis. Extensive three-dimensional parametric finite element analysis cases are generated to train and validate the two CNN models. Additionally, comprehensive algorithm analysis evaluates the model performance, providing insights into the practical application of CNN models in pipeline integrity management. The proposed classification CNN model is shown to be highly accurate in classifying pinholes and pinhole-in-general corrosion defects. The proposed regression CNN model is shown to be highly accurate in predicting the location of the pinhole and obtain a reasonably high accuracy in estimating the depth and diameter of the pinhole, even in the presence of measurement noises. This study indicates the effectiveness of employing deep learning algorithms to enhance the integrity management practice of corroded pipelines.<\/jats:p>","DOI":"10.3390\/a17080347","type":"journal-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T07:01:25Z","timestamp":1723100485000},"page":"347","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Classification and Regression of Pinhole Corrosions on Pipelines Based on Magnetic Flux Leakage Signals Using Convolutional Neural Networks"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2859-6937","authenticated-orcid":false,"given":"Yufei","family":"Shen","sequence":"first","affiliation":[{"name":"Department of Civil & Environmental Engineering, The University of Western Ontario, London, ON N6A 5B9, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5932-4304","authenticated-orcid":false,"given":"Wenxing","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Civil & Environmental Engineering, The University of Western Ontario, London, ON N6A 5B9, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2024,8,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.engfailanal.2016.07.014","article-title":"Estimation of corrosion failure likelihood of oil and gas pipeline based on fuzzy logic approach","volume":"70","author":"Zhou","year":"2016","journal-title":"Eng. Fail. Anal."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1002\/prs.11744","article-title":"Nightmare pipeline failures, fantasy planning, black swans, and integrity management\u2014A review","volume":"34","author":"Murphy","year":"2015","journal-title":"Process Saf. Prog."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"100679","DOI":"10.1016\/j.ijcip.2024.100679","article-title":"A comparison of onshore oil and gas transmission pipeline incident statistics in Canada and the United States","volume":"45","author":"Shen","year":"2024","journal-title":"Int. J. Crit. Infrastruct. Prot."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.ijpvp.2016.11.007","article-title":"A review on pipeline corrosion, in-line inspection (ILI), and corrosion growth rate models","volume":"149","author":"Vanaei","year":"2017","journal-title":"Int. J. Press. Vessels Pip."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"032021","DOI":"10.1088\/1757-899X\/382\/3\/032021","article-title":"Comparative analysis of in-line inspection equipments and technologies","volume":"382","author":"Song","year":"2018","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_6","unstructured":"Pipeline Operators Forum (2022, May 18). Specifications and Requirements for In-Line Inspection of Pipelines. Version 2021. Available online: https:\/\/pipelineoperators.org\/documents."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sutherland, J., Bluck, M., Pearce, J., and Quick, E. (October, January 27). Validation of latest generation MFL in-line inspection technology leads to improved detection and sizing specification for pinholes, pitting, axial grooving and axial slotting. Proceedings of the ASME 2010 8th International Pipeline Conference, Calgary, AB, Canada.","DOI":"10.1115\/IPC2010-31124"},{"key":"ref_8","first-page":"1","article-title":"Analysis of magnetic-flux leakage (MFL) data for pipeline corrosion assessment","volume":"56","author":"Peng","year":"2020","journal-title":"IEEE Trans. Magn."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1007\/s12204-009-0168-2","article-title":"Magnetic flux leakage signal inversion of corrosive flaws based on modified genetic local search algorithm","volume":"14","author":"Han","year":"2009","journal-title":"J. Shanghai Jiaotong Univ. (Sci.)"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1109\/TMAG.2012.2208119","article-title":"Fast magnetic flux leakage signal inversion for the reconstruction of arbitrary defect profiles in steel using finite elements","volume":"49","author":"Priewald","year":"2012","journal-title":"IEEE Trans. Magn."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1016\/S0963-8695(00)00008-6","article-title":"Characterization of gas pipeline inspection signals using wavelet basis function neural networks","volume":"33","author":"Hwang","year":"2000","journal-title":"NDT E Int."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"82748276","DOI":"10.1063\/1.1558693","article-title":"Neural network based inversion algorithms in magnetic flux leakage nondestructive evaluation","volume":"93","author":"Ramuhalli","year":"2003","journal-title":"J. Appl. Phys."},{"key":"ref_13","unstructured":"Han, W.H., and Que, P.W. (2005, January 14\u201317). 2-D defect reconstruction from MFL signals based on genetic optimization algorithm. Proceedings of the IEEE 2005 International Conference on Industrial Technology, Hong Kong, China."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TMAG.2016.2631525","article-title":"Estimation of depth and length of defects from magnetic flux leakage measurements: Verification with simulations, experiments, and pigging data","volume":"53","author":"Kandroodi","year":"2016","journal-title":"IEEE Trans. Magn."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1049\/iet-smt.2016.0279","article-title":"Fast reconstruction of defect profiles from magnetic flux leakage measurements using a RBFNN based error adjustment methodology","volume":"11","author":"Feng","year":"2017","journal-title":"IET Sci. Meas. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.patrec.2018.05.018","article-title":"A review of convolutional-neural-network-based action recognition","volume":"118","author":"Yao","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Taye, M.M. (2023). Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions. Computation, 11.","DOI":"10.3390\/computation11030052"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1109\/TII.2018.2828811","article-title":"An estimation method of defect size from MFL image using visual transformation convolutional neural network","volume":"15","author":"Lu","year":"2018","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_19","first-page":"105","article-title":"Development of a convolutional neural network model to predict the size and location of corrosion defects on pipelines based on magnetic flux leakage signals","volume":"207","author":"Shen","year":"2023","journal-title":"Int. J. Press. Vessels Pip."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1784\/insi.2020.62.2.86","article-title":"Defect size estimation method for magnetic flux leakage signals using convolutional neural networks","volume":"62","author":"Wang","year":"2020","journal-title":"Insight"},{"key":"ref_21","unstructured":"EGIG (2018). 10th Report of the European Gas Pipeline Incident Data Group (Period 1970\u20132016), EGIG. Doc. number VA 17.R.0395."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"022053","DOI":"10.1088\/1757-899X\/1043\/2\/022053","article-title":"Feasibility study of pinhole inspection via magnetic flux leakage and hydrostatic testing in oil & gas pipelines","volume":"1043","author":"Zhang","year":"2021","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.engfailanal.2019.104177","article-title":"Failure analysis and simulation model of pinhole corrosion of the refined oil pipeline","volume":"106","author":"Feng","year":"2019","journal-title":"Eng. Fail. Anal."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.engfailanal.2018.06.008","article-title":"Localized pitting corrosion of API 5L grade A pipe used in industrial fire water piping applications","volume":"92","author":"Subramanian","year":"2018","journal-title":"Eng. Fail. Anal."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"102971","DOI":"10.1016\/j.jngse.2019.102971","article-title":"A comprehensive review on internal corrosion and cracking of oil and gas pipelines","volume":"71","author":"Askari","year":"2019","journal-title":"J. Nat. Gas Sci. Eng."},{"key":"ref_26","first-page":"140","article-title":"The effects of uniform transverse magnetic field on local flow and velocity profile","volume":"7","author":"Kadhim","year":"2016","journal-title":"Int. J. Civ. Eng. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1784\/insi.2009.51.1.32","article-title":"Application of 3-D FEM in the simulation analysis for MFL signals","volume":"51","author":"Ji","year":"2009","journal-title":"Insight"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Bubenik, T. (2014). Electromagnetic Methods for Detecting Corrosion in Underground Pipelines: Magnetic Flux Leakage (MFL), Woodhead Publishing. Underground Pipeline Corrosion.","DOI":"10.1533\/9780857099266.2.215"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"31036","DOI":"10.3390\/s151229845","article-title":"Theory and application of magnetic flux leakage pipeline detection","volume":"15","author":"Shi","year":"2015","journal-title":"Sensors"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1016\/j.ndteint.2009.01.006","article-title":"A fast method for rectangular crack sizes reconstruction in magnetic flux leakage testing","volume":"42","author":"Zhang","year":"2009","journal-title":"NDT E Int."},{"key":"ref_31","unstructured":"Walker, J. (2010). In-Line Inspection of Pipelines: Advanced Technologies for Economic and Safe Operation of Oil and Gas Pipelines, Verlag Moderne Industrie."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2707","DOI":"10.1007\/s12206-014-0627-z","article-title":"Sensitive parameters\u2019 optimization of the permanent magnet supporting mechanism","volume":"28","author":"Liu","year":"2014","journal-title":"J. Mech. Sci. Technol."},{"key":"ref_33","unstructured":"Yang, L., Zhang, G., Liu, G., and Gao, S. (2008, January 25\u201328). Effect of lift-off on pipeline magnetic flux leakage inspection. Proceedings of the 2008 17th World Conference on Nondestructive Testing, Shanghai, China."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.sna.2005.11.066","article-title":"Finite element modelling of a circumferential magnetizer","volume":"129","author":"Ireland","year":"2006","journal-title":"Sens. Actuators A Phys."},{"key":"ref_35","unstructured":"Azizzadeh, T., and Safizadeh, M.S. (2017, January 21\u201322). Three-dimensional finite element and experimental simulation of magnetic flux leakage-type NDT for detection of pitting corrosions. Proceedings of the 2017 4th Iranian International NDT Conference (IRNDT), Tehran, Iran."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1134\/S1061830908120097","article-title":"Signal processing of magnetic flux leakage surface flaw inspect in pipeline steel","volume":"44","author":"Chen","year":"2008","journal-title":"Russ. J. Nondestruct. Test."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1080\/09349847.2019.1595987","article-title":"The effect of motion-induced eddy current on high-speed magnetic flux leakage (MFL) inspection for thick-wall steel pipe","volume":"31","author":"Piao","year":"2020","journal-title":"Res. Nondestruct. Eval."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1109\/TIM.2018.2813839","article-title":"Quick reconstruction of arbitrary pipeline defect profiles from MFL measurements employing modified harmony search algorithm","volume":"67","author":"Li","year":"2018","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"425","DOI":"10.26599\/TST.2019.9010029","article-title":"Effect of image noise on the classification of skin lesions using deep convolutional neural networks","volume":"25","author":"Fan","year":"2019","journal-title":"Tsinghua Sci. Technol."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/j.compbiomed.2017.08.022","article-title":"A deep convolutional neural network model to classify heartbeats","volume":"89","author":"Acharya","year":"2017","journal-title":"Comput. Boil. Med."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"111842","DOI":"10.1109\/ACCESS.2022.3215665","article-title":"Lightweight shufflenet based cnn for arrhythmia classification","volume":"10","author":"Tesfai","year":"2022","journal-title":"IEEE Access."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"West, N.E., and O\u2019shea, T. (2017, January 6\u20139). Deep architectures for modulation recognition. Proceedings of the 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), Baltimore, MD, USA.","DOI":"10.1109\/DySPAN.2017.7920754"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Baranwal, S., Khandelwal, S., and Arora, A. (2019, January 26\u201328). Deep learning convolutional neural network for apple leaves disease detection. Proceedings of the 2019 International Conference on Sustainable Computing in Science, Technology and Management (SUSCOM), Amity University Rajasthan, Jaipur, India.","DOI":"10.2139\/ssrn.3351641"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Virupakshappa, K., Marino, M., and Oruklu, E. (2018, January 22\u201325). A multi-resolution convolutional neural network architecture for ultrasonic flaw detection. Proceedings of the 2018 IEEE International Ultrasonics Symposium (IUS), Kobe, Japan.","DOI":"10.1109\/ULTSYM.2018.8579888"},{"key":"ref_45","unstructured":"Bilmes, J. (2023, March 20). Underfitting and Overfitting in Machine Learning. UW ECE Course Notes. Available online: https:\/\/people.ece.uw.edu\/bilmes\/classes\/ee511\/ee511_spring_2020\/overfitting_underfitting.pdf."},{"key":"ref_46","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 2015 International Conference on Machine Learning, Lille, France."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Thakkar, V., Tewary, S., and Chakraborty, C. (2018, January 12\u201313). Batch normalization in convolutional neural networks\u2014A comparative study with CIFAR-10 data. Proceedings of the IEEE 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT), IIEST Shibpur, West Bengal, India.","DOI":"10.1109\/EAIT.2018.8470438"},{"key":"ref_48","first-page":"1","article-title":"Understanding batch normalization","volume":"31","author":"Bjorck","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/8\/347\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:31:59Z","timestamp":1760110319000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/8\/347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,8]]},"references-count":48,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["a17080347"],"URL":"https:\/\/doi.org\/10.3390\/a17080347","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,8]]}}}