{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T12:51:25Z","timestamp":1770814285355,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T00:00:00Z","timestamp":1605657600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T00:00:00Z","timestamp":1605657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004955","name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004955","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Adv. Model. and Simul. in Eng. Sci."],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In industrial electro galvanizing lines aged anodes deteriorate zinc coating distribution over the strip width, leading to an increase in electricity and zinc cost. We introduce a data-driven approach in predictive maintenance of anodes to replace the cost- and labor-intensive manual inspection, which is still common for this task. The approach is based on parasitic resistance as an indicator of anode condition which might be aged or mis-installed. The parasitic resistance is indirectly observable via the voltage difference between the measured and baseline (theoretical) voltage for healthy anode. Here we calculate the baseline voltage by means of two approaches: (1) a physical model based on electrical and electrochemical laws, and (2) advanced machine learning techniques including boosting and bagging regression. The data was collected on one exemplary rectifier unit equipped with two anodes being studied for a total period of two years. The dataset consists of one target variable (rectifier voltage) and nine predictive variables used in the models, observing electrical current, electrolyte, and steel strip characteristics. For predictive modelling, we used Random Forest, Partial Least Squares and AdaBoost Regression. The model training was conducted on intervals where the anodes were in good condition and validated on other segments which served as a proof of concept that bad anode conditions can be identified using the parasitic resistance predicted by our models. Our results show a RMSE of 0.24\u00a0V for baseline rectifier voltage with a mean\u2009\u00b1\u2009standard deviation of 11.32\u2009\u00b1\u20092.53\u00a0V for the best model on the validation set. The best-performing model is a hybrid version of a Random Forest which incorporates meta-variables computed from the physical model. We found that a large predicted parasitic resistance coincides well with the results of the manual inspection. The results of this work will be implemented in online monitoring of anode conditions to reduce operational cost at a production site.<\/jats:p>","DOI":"10.1186\/s40323-020-00184-z","type":"journal-article","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T13:03:31Z","timestamp":1605704611000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Parasitic resistance as a predictor of faulty anodes in electro galvanizing: a comparison of machine learning, physical and hybrid models"],"prefix":"10.1186","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3541-9624","authenticated-orcid":false,"given":"Mario","family":"Lovri\u0107","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Meister","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Steck","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leon","family":"Fadljevi\u0107","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johann","family":"Gerdenitsch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Schuster","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lukas","family":"Schieferm\u00fcller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefanie","family":"Lindstaedt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roman","family":"Kern","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,18]]},"reference":[{"key":"184_CR1","first-page":"44","volume":"17","author":"W Karner","year":"1992","unstructured":"Karner W, Maresch G. Gravitel process for electrogalvanising steel strip. Steel Time Int. 1992;17:44\u20135.","journal-title":"Steel Time Int"},{"key":"184_CR2","unstructured":"Karner W, Lavric T, Gerdenitsch J, Faderl J, Wiesinger S. Electro Galvanizing - There Is Life in the Old Dog Yet. Galvatech 11. Genua; 2011."},{"key":"184_CR3","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.1109\/TCST.2016.2631124","volume":"25","author":"P Zhou","year":"2017","unstructured":"Zhou P, Song H, Wang H, Chai T. Data-driven nonlinear subspace modeling for prediction and control of molten iron quality indices in blast furnace ironmaking. IEEE Trans Control Syst Technol. 2017;25:1761\u201374.","journal-title":"IEEE Trans Control Syst Technol."},{"key":"184_CR4","first-page":"1","volume":"19","author":"X Liu","year":"2019","unstructured":"Liu X, Liu Y, Zhang M, Chen X, Li J. Improving stockline detection of radar sensor array systems in blast furnaces using a novel encoder\u2013decoder architecture. Sensors (Switzerland). 2019;19:1.","journal-title":"Sensors (Switzerland)."},{"key":"184_CR5","doi-asserted-by":"crossref","unstructured":"Faizullin A, Zymbler M, Lieftucht D, Fanghanel F. Use of Deep Learning for Sticker Detection during Continuous Casting. Proc - 2018 Glob Smart Ind Conf GloSIC 2018. Institute of Electrical and Electronics Engineers Inc.; 2018.","DOI":"10.1109\/GloSIC.2018.8570155"},{"key":"184_CR6","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1631\/FITEE.1601397","volume":"19","author":"ZS Pan","year":"2018","unstructured":"Pan ZS, Zhou XH, Chen P. Development and application of a neural network based coating weight control system for a hot-dip galvanizing line. Front Inf Technol Electron Eng. 2018;19:834\u201346.","journal-title":"Front Inf Technol Electron Eng."},{"key":"184_CR7","first-page":"389","volume":"3","author":"A Gonzalez-Marcos","year":"2011","unstructured":"Gonzalez-Marcos A, Alba-Elias F, Castejon-Limas M, Ordieres-Mere J. Development of neural network-based models to predict mechanical properties of hot dip galvanised steel coils. Int J Data Mining, Model Manag. 2011;3:389\u2013405.","journal-title":"Int J Data Mining, Model Manag."},{"key":"184_CR8","doi-asserted-by":"publisher","DOI":"10.1186\/s40323-020-00163-4","author":"T Groensfelder","year":"2020","unstructured":"Groensfelder T, Giebeler F, Geupel M, Schneider D, Jaeger R. Application of machine learning procedures for mechanical system modelling: capabilities and caveats to prediction-accuracy. Adv Model Simul Eng Sci. 2020. https:\/\/doi.org\/10.1186\/s40323-020-00163-4.","journal-title":"Adv Model Simul Eng Sci."},{"key":"184_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40323-019-0138-7","volume":"7","author":"M Fern\u00e1ndez","year":"2020","unstructured":"Fern\u00e1ndez M, Rezaei S, Rezaei Mianroodi J, Fritzen F, Reese S. Application of artificial neural networks for the prediction of interface mechanics: a study on grain boundary constitutive behavior. Adv Model Simul Eng Sci. 2020;7:1\u201327. https:\/\/doi.org\/10.1186\/s40323-019-0138-7.","journal-title":"Adv Model Simul Eng Sci."},{"key":"184_CR10","doi-asserted-by":"crossref","unstructured":"Chen J, Randall R, Peeters B, Desmet W, Van Der Auweraer H. Artificial neural network based fault diagnosis of IC engines. Key Eng Mater. 2012. p. 47\u201356.","DOI":"10.4028\/www.scientific.net\/KEM.518.47"},{"key":"184_CR11","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1109\/TMECH.2006.875568","volume":"11","author":"YL Murphey","year":"2006","unstructured":"Murphey YL, Masrur MA, Chen ZH, Zhang B. Model-based fault diagnosis in electric drives using machine learning. IEEE\/ASME Trans Mechatronics. 2006;11:290\u2013303.","journal-title":"IEEE\/ASME Trans Mechatronics"},{"key":"184_CR12","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/s00449-004-0385-x","volume":"26","author":"V Galvanauskas","year":"2004","unstructured":"Galvanauskas V, Simutis R, L\u00fcbbert A. Hybrid process models for process optimisation, monitoring and control. Bioprocess Biosyst Eng. 2004;26:393\u2013400.","journal-title":"Bioprocess Biosyst Eng"},{"key":"184_CR13","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1016\/S0009-2509(00)00261-X","volume":"56","author":"HC Aguiar","year":"2001","unstructured":"Aguiar HC, Filho RM. Neural network and hybrid model: A discussion about different modeling techniques to predict pulping degree with industrial data. Chem Eng Sci. 2001;56:565\u201370.","journal-title":"Chem Eng Sci"},{"key":"184_CR14","first-page":"7","volume-title":"Paterson E","author":"JL Wu","year":"2018","unstructured":"Wu JL, Xiao H. Paterson E. Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework. Phys Rev Fluids. American Physical Society; 2018. p. 7."},{"key":"184_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41524-018-0138-z","volume":"5","author":"S Wu","year":"2019","unstructured":"Wu S, Kondo Y, Kakimoto M, Yang B, Yamada H, Kuwajima I, et al. Machine-learning-assisted discovery of polymers with high thermal conductivity using a molecular design algorithm. NPJ Comput Mater. 2019;5:1.","journal-title":"NPJ Comput Mater."},{"key":"184_CR16","doi-asserted-by":"publisher","first-page":"2233","DOI":"10.1039\/C9EE01371G","volume":"12","author":"Y Li","year":"2019","unstructured":"Li Y, Yang K. High-throughput computational design of organic-inorganic hybrid halide semiconductors beyond perovskites for optoelectronics. Energy Environ Sci. 2019;12:2233\u201343.","journal-title":"Energy Environ Sci."},{"key":"184_CR17","doi-asserted-by":"crossref","unstructured":"Sadoughi M, Hu C. A physics-based deep learning approach for fault diagnosis of rotating machinery. In: Proc IECON 2018 - 44th Annu Conf IEEE Ind Electron Soc. Institute of Electrical and Electronics Engineers Inc.; 2018. p. 5919\u201323.","DOI":"10.1109\/IECON.2018.8591073"},{"key":"184_CR18","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1088\/0951-7715\/26\/1\/201","volume":"26","author":"AJ Majda","year":"2013","unstructured":"Majda AJ, Harlim J. Physics constrained nonlinear regression models for time series. Nonlinearity. 2013;26:201\u201317.","journal-title":"Nonlinearity"},{"key":"184_CR19","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s40323-016-0057-9","volume":"3","author":"BT Cao","year":"2016","unstructured":"Cao BT, Freitag S, Meschke G. A hybrid RNN-GPOD surrogate model for real-time settlement predictions in mechanised tunnelling. Adv Model Simul Eng Sci. 2016;3:5.","journal-title":"Adv Model Simul Eng Sci."},{"key":"184_CR20","unstructured":"Stewart R, Ermon S. Label-Free Supervision of Neural Networks with Physics and Domain Knowledge. 2016. https:\/\/arxiv.org\/abs\/1609.05566. Accessed 27 Jan 2020."},{"key":"184_CR21","doi-asserted-by":"publisher","first-page":"2318","DOI":"10.1109\/TKDE.2017.2720168","volume":"29","author":"A Karpatne","year":"2017","unstructured":"Karpatne A, Atluri G, Faghmous JH, Steinbach M, Banerjee A, Ganguly A, et al. Theory-guided data science: A new paradigm for scientific discovery from data. IEEE Trans Knowl Data Eng. 2017;29:2318\u201331.","journal-title":"IEEE Trans Knowl Data Eng."},{"key":"184_CR22","unstructured":"Karpatne A, Watkins W, Read J, Kumar V. How Can Physics Inform Deep Learning Methods in Scientific Problems?: Recent Progress and Future Prospects. Talk. 2017;1\u201322. https:\/\/dl4physicalsciences.github.io\/files\/nips_dlps_2017_19.pdf"},{"key":"184_CR23","unstructured":"Lei D, Chen X, Zhao J. Opening the black box of deep learning. 2018. https:\/\/arxiv.org\/abs\/1805.08355. Accessed 27 Jan 2020."},{"key":"184_CR24","unstructured":"Lovri\u0107 M, Fadljevi\u0107 L, Kern R, Steck T, Gerdenitsch J, Peche E. Prediction of anode lifetime in electro galvanizing lines by big data analysis. GALVATECH 2020. Vienna; 2020\/ https:\/\/www.researchgate.net\/publication\/340816111_PREDICTION_OF_ANODE_LIFE_TIME_IN_ELECTRO_GALVANIZING_LINES_BY_BIG_DATA_ANALYSIS. Accessed 21 Apr 2020."},{"key":"184_CR25","unstructured":"Maresch G, Ulrich K. US5637205A - Process for the electrolytical coating of an object of steel on one or both sides - Google Patents. 1992."},{"key":"184_CR26","unstructured":"Eisenkoeck P, Lavric T. The GRAVITEL process for electro-galvanising of steel strip. Millenium Steel. 2009;141\u20134."},{"key":"184_CR27","doi-asserted-by":"publisher","first-page":"114587","DOI":"10.1016\/j.envpol.2020.114587","volume":"263","author":"I \u0160imi\u0107","year":"2020","unstructured":"\u0160imi\u0107 I, Lovri\u0107 M, Godec R, Kr\u00f6ll M, Be\u0161li\u0107 I. Applying machine learning methods to better understand, model and estimate mass concentrations of traffic-related pollutants at a typical street canyon. Environ Pollut. 2020;263:114587.","journal-title":"Environ Pollut"},{"key":"184_CR28","unstructured":"Haynes WM, editor. CRC handbook of chemistry and physics, 93rd edition. CRC Press. 2012"},{"key":"184_CR29","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1080\/00202967.1992.11870941","volume":"70","author":"FC Walsh","year":"1992","unstructured":"Walsh FC. Kinetics of electrode reactions: part I - general considerations and electron transfer control. Trans Inst Met Finish. 1992;70:50\u20134.","journal-title":"Trans Inst Met Finish"},{"key":"184_CR30","unstructured":"B\u00e1n A, Buttler A, Gerdenitsch J, Debeaux M, Koll T, Lavric T, et al. Energie- und ressourceneffiziente galvanische Bandverzinkung. ZVO Oberfl\u00e4chentage 2017 [Internet]. Berlin, Germany; 2017. Available from: http:\/\/www.bfi.de\/en\/lectures\/energie-und-ressourceneffiziente-galvanische-bandverzinkung\/"},{"key":"184_CR31","doi-asserted-by":"publisher","first-page":"4636","DOI":"10.1021\/acs.iecr.9b05766","volume":"59","author":"P \u017duvela","year":"2020","unstructured":"\u017duvela P, Lovric M, Yousefian-Jazi A, Liu JJ. Ensemble Learning Approaches to Data Imbalance and Competing Objectives in Design of an Industrial Machine Vision System. Ind Eng Chem Res. 2020;59:4636\u201345. https:\/\/doi.org\/10.1021\/acs.iecr.9b05766.","journal-title":"Ind Eng Chem Res"},{"key":"184_CR32","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1007\/s00170-011-3300-z","volume":"57","author":"A Bustillo","year":"2011","unstructured":"Bustillo A, D\u00edez-Pastor JF, Quintana G, Garc\u00eda-Osorio C. Avoiding neural network fine tuning by using ensemble learning: Application to ball-end milling operations. Int J Adv Manuf Technol. 2011;57:521\u201332.","journal-title":"Int J Adv Manuf Technol"},{"key":"184_CR33","doi-asserted-by":"crossref","unstructured":"De Abril IM, Sugiyama M. Winning the Kaggle Algorithmic Trading Challenge with the composition of many models and feature engineering. IEICE Trans Inf Syst. Institute of Electronics, Information and Communication, Engineers, IEICE; 2013;E96-D:742\u20135.","DOI":"10.1587\/transinf.E96.D.742"},{"key":"184_CR34","unstructured":"Niculescu-Mizil A, Perlich C, Swirszcz G, Sindhwani V, Liu Y, Melville P, et al. Winning the KDD cup orange challenge with ensemble selection. 2009 Knowl Discov Data Compet (KDD Cup 2009) Challenges Mach Learn. 2009;7:21. https:\/\/eprints.pascal-network.org\/archive\/00009182\/01\/CiML-v3-book.pdf#page=33%5Cnpapers2:\/\/publication\/uuid\/CB992E55-3BD1-40A7-B8E9-FF8922400991"},{"key":"184_CR35","first-page":"109","volume-title":"Eriksson L","author":"S Wold","year":"2001","unstructured":"Wold S, Sj\u00f6str\u00f6m M. Eriksson L. PLS-regression: A basic tool of chemometrics. Chemom Intell Lab Syst. Elsevier; 2001. p. 109\u201330."},{"key":"184_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-019-01483-y","author":"M Said","year":"2019","unstructured":"Said M, Abdellafou K, Taouali O. Machine learning technique for data-driven fault detection of nonlinear processes. J Intell Manuf. 2019. https:\/\/doi.org\/10.1007\/s10845-019-01483-y.","journal-title":"J Intell Manuf."},{"key":"184_CR37","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L. Random forests. Mach Learn. 2001;45:5\u201332.","journal-title":"Mach Learn"},{"key":"184_CR38","unstructured":"Freund Y, Schapire RE. Experiments with a New Boosting Algorithm. Mach Learn Proc Thirteen Int Conf. 1996. p. 148\u201356."},{"key":"184_CR39","unstructured":"Pedregosa F, Michel V, Grisel O, Blondel M, Prettenhofer P, Weiss R, et al. Scikit-learn: Machine Learning in Python. J Mach Learn Res. 2011;12:2825\u201330. https:\/\/scikit-learn.sourceforge.net."},{"key":"184_CR40","first-page":"38","volume-title":"Kern R","author":"M Lovri\u0107","year":"2019","unstructured":"Lovri\u0107 M, Molero JM. Kern R. PySpark and RDKit: Moving towards Big Data in Cheminformatics. Mol Inform. Wiley-VCH Verlag; 2019. p. 38."},{"key":"184_CR41","doi-asserted-by":"publisher","first-page":"77","DOI":"10.2307\/2346413?origin=crossref","volume":"29","author":"PM Lerman","year":"1980","unstructured":"Lerman PM. Fitting segmented regression models by grid search. Appl Stat. 1980;29:77. https:\/\/doi.org\/10.2307\/2346413?origin=crossref.","journal-title":"Appl Stat."},{"key":"184_CR42","doi-asserted-by":"crossref","unstructured":"Lovri\u0107 M, Pavlovi\u0107 K, \u017duvela P, Spataru A, Lu\u010di\u0107 B, Kern R, et al. Machine learning in prediction of intrinsic aqueous solubility of drug-like compounds: generalization, complexity or predictive ability? ChemRxiv; 2020.","DOI":"10.26434\/chemrxiv.12746948"}],"container-title":["Advanced Modeling and Simulation in Engineering Sciences"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40323-020-00184-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40323-020-00184-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40323-020-00184-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T13:06:32Z","timestamp":1605704792000},"score":1,"resource":{"primary":{"URL":"https:\/\/amses-journal.springeropen.com\/articles\/10.1186\/s40323-020-00184-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,18]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["184"],"URL":"https:\/\/doi.org\/10.1186\/s40323-020-00184-z","relation":{},"ISSN":["2213-7467"],"issn-type":[{"value":"2213-7467","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,18]]},"assertion":[{"value":"8 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"46"}}