{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T07:45:00Z","timestamp":1786088700840,"version":"3.56.0"},"reference-count":50,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2019,5,18]],"date-time":"2019-05-18T00:00:00Z","timestamp":1558137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Understanding the corrosion risk of a pipeline is vital for maintaining health, safety and the environment. This study implemented a data-driven machine learning approach that relied on Principal Component Analysis (PCA), Particle Swarm Optimization (PSO), Feed-Forward Artificial Neural Network (FFANN), Gradient Boosting Machine (GBM), Random Forest (RF) and Deep Neural Network (DNN) to estimate the corrosion defect depth growth of aged pipelines. By modifying the hyperparameters of the FFANN algorithm with PSO and using PCA to transform the operating variables of the pipelines, different Machine Learning (ML) models were developed and tested for the X52 grade of pipeline. A comparative analysis of the computational accuracy of the corrosion defect growth was estimated for the PCA transformed and non-transformed parametric values of the training data to know the influence of the PCA transformation on the accuracy of the models. The result of the analysis showed that the ML modelling with PCA transformed data has an accuracy that is 3.52 to 5.32 times better than those carried out without PCA transformation. Again, the PCA transformed GBM model was found to have the best modeling accuracy amongst the tested algorithms; hence, it was used for computing the future corrosion defect depth growth of the pipelines. This helped to compute the corrosion risks using the failure probabilities at different lifecycle phases of the asset. The excerpts from the results of this study indicate that my technique is vital for the prognostic health monitoring of pipelines because it will provide information for maintenance and inspection planning.<\/jats:p>","DOI":"10.3390\/bdcc3020028","type":"journal-article","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T11:05:07Z","timestamp":1558350307000},"page":"28","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":104,"title":["A Data-Driven Machine Learning Approach for Corrosion Risk Assessment\u2014A Comparative Study"],"prefix":"10.3390","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9749-3256","authenticated-orcid":false,"given":"Chinedu I.","family":"Ossai","sequence":"first","affiliation":[{"name":"School of Information Technology &amp; Mathematical Sciences, University of South Australia, Mawson Lakes Campus, GPO Box 2471 Adelaide, SA 5001, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,5,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.engfailanal.2015.03.004","article-title":"Pipeline failures in corrosive environments\u2013A conceptual analysis of trends and effects","volume":"53","author":"Ossai","year":"2015","journal-title":"Eng. Fail. Anal."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"663","DOI":"10.5006\/1.3319093","article-title":"Effect of surface layers on the initiation of internal pitting corrosion in oil and gas pipelines","volume":"65","author":"Papavinasam","year":"2009","journal-title":"Corrosion"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"443","DOI":"10.5006\/1.3277576","article-title":"A mechanistic model for carbon dioxide corrosion of mild steel in the presence of protective iron carbonate films-Part 1: Theory and verification","volume":"59","author":"Nordsveen","year":"2003","journal-title":"Corrosion"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"4308","DOI":"10.1016\/j.corsci.2007.06.006","article-title":"Key issues related to modelling of internal corrosion of oil and gas pipelines\u2013A review","volume":"49","year":"2007","journal-title":"Corros. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.corsci.2013.04.011","article-title":"Stochastic process corrosion growth models for pipeline reliability","volume":"74","author":"Bazan","year":"2013","journal-title":"Corros. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1179\/147842209X12489567719581","article-title":"Estimating uncertainty in maximum pit depth from limited observational data","volume":"45","author":"Melchers","year":"2010","journal-title":"Corros. Eng. Sci. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1016\/j.corsci.2004.08.006","article-title":"Early corrosion of mild steel in seawater","volume":"47","author":"Melchers","year":"2005","journal-title":"Corros. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"874","DOI":"10.5006\/1.3580852","article-title":"Relationship between the structure of disturbed flow and erosion-corrosion","volume":"46","author":"Nesic","year":"1990","journal-title":"Corrosion"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2027","DOI":"10.1016\/j.wear.2009.07.023","article-title":"CO2 erosion\u2013corrosion of pipeline steel (API X65) in oil and gas conditions\u2014A systematic approach","volume":"267","author":"Hu","year":"2009","journal-title":"Wear"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"190","DOI":"10.5006\/1.3585090","article-title":"Statistical modeling of pitting corrosion and pipeline reliability","volume":"46","author":"Sheikh","year":"1990","journal-title":"Corrosion"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1016\/j.corsci.2009.06.014","article-title":"Markov chain modelling of pitting corrosion in underground pipelines","volume":"51","author":"Caleyo","year":"2009","journal-title":"Corros. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.engfailanal.2015.11.052","article-title":"Markov chain modelling for time evolution of internal pitting corrosion distribution of oil and gas pipelines","volume":"60","author":"Ossai","year":"2016","journal-title":"Eng. Fail. Anal."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2001","DOI":"10.1016\/S0010-938X(99)00024-4","article-title":"Phenomenological modelling of atmospheric corrosion using an artificial neural network","volume":"41","author":"Cai","year":"1999","journal-title":"Corros. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.psep.2018.07.006","article-title":"Neural network modelling of high-pressure CO2 corrosion in pipeline steels","volume":"119","author":"Abbas","year":"2018","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/j.oceaneng.2017.12.014","article-title":"Developing a dynamic model for pitting and corrosion-fatigue damage of subsea pipelines","volume":"150","author":"Arzaghi","year":"2018","journal-title":"Ocean Eng."},{"key":"ref_16","unstructured":"De Masi, G., Vichi, R., Gentile, M., Bruschi, R., and Gabetta, G. (May, January 29). A Neural Network Predictive Model of Pipeline Internal Corrosion Profile. Proceedings of the IEEE SIMS, Washington, DC, USA."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.jngse.2018.07.025","article-title":"Film former corrosion inhibitors for oil and gas pipelines\u2014A technical review","volume":"58","author":"Askari","year":"2018","journal-title":"J. Nat. Gas Sci. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.oceaneng.2017.06.057","article-title":"Corrosion fatigue crack growth modelling for subsea pipeline steels","volume":"142","author":"Cheng","year":"2017","journal-title":"Ocean Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.ress.2018.07.012","article-title":"Stochastic corrosion growth modeling for pipelines using mass inspection data","volume":"180","author":"Dann","year":"2018","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1016\/j.engfailanal.2017.04.027","article-title":"Modeling localized corrosion of pipeline steels in oilfield produced water environments","volume":"79","author":"Valor","year":"2017","journal-title":"Eng. Fail. Anal."},{"key":"ref_21","first-page":"379","article-title":"Prediction of metal corrosion by neural networks","volume":"52","year":"2013","journal-title":"Metalurgija"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2266","DOI":"10.1016\/j.corsci.2009.06.004","article-title":"Artificial neural network corrosion modeling for metals in an equatorial climate","volume":"51","author":"Kenny","year":"2009","journal-title":"Corros. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/S0308-0161(98)00136-7","article-title":"Artificial neural network technology for the data processing of on-line corrosion fatigue crack growth monitoring","volume":"76","author":"Cheng","year":"1999","journal-title":"Int. J. Press. Vessel. Pip."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Singer, M. (2017). Top-of-the-line corrosion. Trends in Oil and Gas Corrosion Research and Technologies, Woodhead Publishing.","DOI":"10.1016\/B978-0-08-101105-8.00016-4"},{"key":"ref_25","unstructured":"Boyun, G., Xinghui, L., and Xuehao, T. (2017). Chapter 22\u2014Pipeline Pigging. Petroleum Production Engineering, Gulf Professional Publishing. [2nd ed.]."},{"key":"ref_26","first-page":"116","article-title":"Intelligent Pigging Technology and Application for Gas Pipelines","volume":"25","author":"Nianzhong","year":"2005","journal-title":"Nat. Gas Ind."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1609","DOI":"10.1016\/j.wear.2013.01.044","article-title":"Effects of the dissolved oxygen and slurry velocity on erosion\u2013corrosion of carbon steel in aqueous slurries with carbon dioxide and silica sand","volume":"302","author":"Yu","year":"2013","journal-title":"Wear"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"5354","DOI":"10.1128\/AEM.69.9.5354-5363.2003","article-title":"Characterization of microbial communities in gas industry pipelines","volume":"69","author":"Zhu","year":"2003","journal-title":"Appl. Environ. Microbiol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/wics.101","article-title":"Principal component analysis","volume":"2","author":"Abdi","year":"2010","journal-title":"Wiley interdisciplinary reviews: Comput. Stat."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/j.jhydrol.2004.10.008","article-title":"Nonstationary Hydrological Time Series Forecasting Using Nonlinear Dynamic Methods","volume":"307","author":"Coulibaly","year":"2005","journal-title":"J. Hydrol."},{"key":"ref_31","unstructured":"Shi, Y., and Eberhart, R.C. (1988, January 4\u20139). A Modified Particle Swarm Optimizer. Proceedings of the IEEE International Conference on Evolutionary Computation, Anchorage, AK, USA."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wall, M.E., Rechtsteiner, A., and Rocha, L.M. (2003). Singular value decomposition and principal component analysis. A Practical Approach to Microarray Data Analysis, Springer.","DOI":"10.1007\/0-306-47815-3_5"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1097\/00004691-199701000-00007","article-title":"Spatial filtering of multichannel electroencephalographic recordings through principal component analysis by singular value decomposition","volume":"14","author":"Lagerlund","year":"1997","journal-title":"J. Clin. Neurophysiol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"21","DOI":"10.3389\/fnbot.2013.00021","article-title":"Gradient Boosting Machines, a Tutorial","volume":"7","author":"Natekin","year":"2013","journal-title":"Front. Neurorobotics"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy Function Approximation: A Gradient Boosting Machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_36","unstructured":"Ridgeway, G. (2019, December 15). Generalized Boosted Models: A Guide to the gbm Package. Available online: http:\/\/btr0x2.rz.uni-bayreuth.de\/math\/statlib\/R\/CRAN\/doc\/vignettes\/gbm\/gbm.pdf."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"318","DOI":"10.3923\/jse.2016.318.327","article-title":"Classification of High-resolution Remotely Sensed Images Based on Random Forests","volume":"10","author":"Chen","year":"2016","journal-title":"J. Softw. Eng."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_40","unstructured":"Segal, M.R. (2004). Machine Learning Benchmarks and Random Forest Regression, Center for Bioinformatics and Molecular Biostatistics. Available online: https:\/\/escholarship.org\/uc\/item\/35x3v9t4."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.compag.2015.07.017","article-title":"Investigating the use of gradient boosting machine, random forest and their ensemble to predict skin flavonoid content from berry physical\u2013mechanical characteristics in wine grapes","volume":"117","author":"Brillante","year":"2015","journal-title":"Comput. Electron. Agric."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/S0308-0161(98)00006-4","article-title":"Probabilistic estimation of remaining life of a pipeline in the presence of active corrosion defects","volume":"75","author":"Ahammed","year":"1998","journal-title":"Int. J. Press. Vessel. Pip."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/S0308-0161(01)00124-7","article-title":"A study on the reliability assessment methodology for pipelines with active corrosion defects","volume":"79","author":"Caleyo","year":"2002","journal-title":"Int. J. Press. Vessel. Pip."},{"key":"ref_44","unstructured":"Rausand, M., and H\u00f8yland, A. (2004). System Reliability Theory: Models, Statistical Methods, and Applications, John Wiley & Sons."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/S0951-8339(01)00030-2","article-title":"Risk assessment of aging ship hull structures in the presence of corrosion and fatigue","volume":"15","author":"Akpan","year":"2002","journal-title":"Mar. Struct."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"C251","DOI":"10.1149\/2.0701506jes","article-title":"Predictive modelling of internal pitting corrosion of aged non-piggable pipelines","volume":"162","author":"Ossai","year":"2015","journal-title":"J. Electrochem. Soc."},{"key":"ref_47","unstructured":"Nesic, S., Lee, K.L.J., and Ruzic, V. (2002). A Mechanistic Model of Iron Carbonate Film Growth and the Effect on Co2 Corrosion of Mild Steel, NACE International. CORROSION\/2002, paper; 02237."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1016\/S0010-938X(01)00141-X","article-title":"Fe3C influence on the corrosion rate of mild steel in aqueous CO2 systems under turbulent flow conditions","volume":"44","author":"Turgoose","year":"2002","journal-title":"Corros. Sci."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1016\/j.apsusc.2015.05.053","article-title":"Effect of pH and chloride on the micro-mechanism of pitting corrosion for high strength pipeline steel in aerated NaCl solutions","volume":"349","author":"Wang","year":"2015","journal-title":"Appl. Surf. Sci."},{"key":"ref_50","unstructured":"(2005). NACE Standard RP0775, Preparation, Installation, Analysis and Interpretation of Corrosion Coupons in Oilfield Operations, NACE International."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/3\/2\/28\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:53:20Z","timestamp":1760187200000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/3\/2\/28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,18]]},"references-count":50,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2019,6]]}},"alternative-id":["bdcc3020028"],"URL":"https:\/\/doi.org\/10.3390\/bdcc3020028","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,18]]}}}