Abstract
The evaluation of the hull condition of naval vessels is a crucial part for corrosion protection systems due to the direct linkage between the electrochemical process at the hull/water interface leading to corrosion and the overall coating of the hull to prevent the corrosion process. In the case of the latter, the condition is unknown while the vessel is on a mission and either has to be evaluated by divers (in open water) or on dry docks which is a time consuming process, respectively. In our work, we present a methodology to localize coating damages without the need of divers or dry docks using an artificial neural network (ANN) combined with the information provided by the onboard impressed current cathodic protection (ICCP) system to predict said damages in a specific sector of a generic ship model. Using only the ICCP currents as highly aggregated input variables for the ANN, approximately 86 % of randomly sized and positioned coating damages are correctly predicted.
Zusammenfassung
Die Bewertung des Rumpfzustands von Wasserfahrzeugen ist von besonderer Bedeutung für Korrosionsschutzsysteme, da ein direkter Zusammenhang zwischen dem elektrochemischen Korrosionsprozess an der Rumpf/Wasser Grenzschicht und dem Beschichtungszustand des Rumpfes herrscht. Der Beschichtungszustand ist dabei bei Einsätzen des Fahrzeugs nicht bekannt und muss entweder durch Taucher (im freien Wasser) oder in Trockendocks evaluiert werden, welches in beiden Fällen sehr zeitaufwändig ist. In der hiesigen Arbeit wird daher eine Methodik zur Lokalisierung von Beschädigungen der Rumpfbeschichtung mit Hilfe künstlicher neuronaler Netze (KNN) (engl.: artificial neural networks) vorgestellt, wobei weder Taucher, noch ein Trockendock benötigt würden. Dabei werden die Informationen des an Bord befindlichen elektrischen Korrosionsschutzsystems (EKS) (engl.: impressed current cathodic protection) in Kombination mit dem KNN verwendet, um die Beschädigungen der Rumpfbeschichtung in verschiedenen Sektoren des in dieser Arbeit verwendeten, generischen Wasserfahrzeugs zu lokalisieren. Damit gelingt eine korrekte Vorhersage des Sektors, in welchem eine Beschädigung vorliegt, bei näherungsweise 86 %, wenn einzig die EKS Ströme als Eingangsvariablen für das KNN dienen.
About the authors
Christian Thiel received his B.Sc. and M.Sc. in Business Administration and Engineering with a main focus on Power Engineering from the University of Duisburg-Essen in 2013 and 2015, respectively. Since 2015 he is a research associate and Ph.D. student on a collaborative project between the Lab of General and Theoretical Electrical Engineering (ATE) at the University of Duisburg-Essen and the Bundeswehr, Technical Center for Ships and Naval Weapons (WTD71), Federal Office of Defense Technology and Procurement (BAAINBW), Eckernförde. His main research focus lies within the numerical simulation, reduction and prediction of electric and magnetic naval vessel signatures. Furthermore. He has advanced experiences in antenna design and simulations for high-field 7T MRI and worked on several projects regarding the SERS brightness of gold and gold/silver nanoparticles.
Kevin Neumann received his B.Sc. in Nanoengineering in 2015 and his M.Sc. in Power Engineering in 2017, both at the University of Duisburg-Essen. Since 2017, he is working at the DFG project “Flexible Radio Frequency Identification Tags and System (FlexID)” as a Ph.D. student at the Laboratory of General and Theoretical Electrical Engineering (ATE) in Duisburg, Germany. His main research focus lies on the full system development of the tag, which contains semiconductor modeling as well as electromagnetic wave simulations. Furthermore, he investigates the performance of numerical crumpled antenna structures using a combination of finite element and boundary element method modeling. He also follows recent advancements in computer sciences, especially artificial intelligence.
Claas Bröcheler received his B. Eng in electrical engineering with the main focus on communication in 2013 from the University of applied Sience in Bochum. Building upon this he received his M.Sc. in electrical enigneering focused on micro- and optoelectronics from the University of Duisburg-Essen in 2016. Since 2016 he is a research associate and Ph.D. student on a collaborative project between the Lab of General and Theoretical Electrical Enigneering (ATE) at the University of Duisburg-Essen and the Bundeswehr, Technical Center for Ships and Naval Weapons (WTD71), Federal Office of Defense Technology and Procurement (BAAINBW), Eckernförde. His research focus lies with the numerical simulation on the prediction of electric naval vessel signatures in its environmental surrounding area. He has experiences in antenna design and simulations for substrate integrated waveguide antennas (SIW) and experiences by electromagnetic wave behaviour in different areas with higher electrical conductivities and permittivity. In addition, he is interested in the field of electroacoustics and has developed a speaker system in his bachelor thesis.
Since 1994 working for the Bundeswehr. Engineering Diploma in electronics in the field of cordless telephones and a Master Degree in the area of communication and networks in particular electromagnetic wave propagation in sea water and the usage of robust adaptive communication protocols. Since 1997 working at different positions for the WTD71 of the German Navy in Eckernförde. Head of Magnetic Range and Treatment Facility in Kiel-Friedrichsort and later head of the Earth Field Simulator at Bünsdorf and responsible for its renewal to the current state. Attendee of the US GER Exchange Program for Scientists and Engineers at Naval Surface Warfare Center, Carderock Division in Bethesda, Maryland. Since 2011 working for different scientific projects in the field of EM underwater signatures for instance torpedo counter measures and under water communication using VLF. Between 2014 and 2018 working in the area of electric and magnetic signature mitigation and organic ranging capability technologies using AUV.
Andreas Rennings studied electrical engineering at the University of Duisburg-Essen, Germany. He carried out his diploma work during a stay at the University of California in Los Angeles. He received his Dipl.-Ing. and Dr.-Ing. degrees from the University of Duisburg-Essen in 2000 and 2008, respectively. From 2006 to 2008 he was with IMST GmbH in Kamp-Lintfort, Germany, where he worked as an RF engineer. Since then, he is a senior scientist and principal investigator at the Laboratory for General and Theoretical Electrical Engineering of the University of Duisburg-Essen. His general research interests include all aspects of theoretical and applied electromagnetics, currently with a focus on medical applications and on-chip millimeter-wave/THz antennas. He received several awards, including a student paper price at the 2005 IEEE Antennas and Propagation Society International Symposium and the VDE-Promotionspreis 2009 for the dissertation.
Jens Doose was born in Rendsburg, Germany, in 1956. He studied Chemistry at the Christian Albrecht University Kiel and received his Dipl. Chem. (1983) and Dr. rer. nat. at the Institut for Physical Chemistry (1990). Subject of his work was Molecular Spectroscopy in the mmwave and submmwave region. Until 1997 he continued work on Molecular Spectroscopy and developed a submmwave FFT-Spectrometer. From 1997 to 2002 he taught sciences at the Technical Navy College in Kiel. 2002 he started working at the Technical Center for Ships and Naval Weapons - WTD71 - at Kiel with focus on interfacial chemistry, corrosion- and fouling protection of German Navy ships. After different projects he joined the Centre for electric and magnetic Underwater Signatures of the WTD71 in 2009. Since 2010 he has been head of the department.
Daniel Erni is a full professor for General and Theoretical Electrical Engineering at the University of Duisburg-Essen, Germany, After an apprenticeship as an electrician and mechanic he received his two degrees in electrical engineering form HSR Rapperswil and ETH Zürich in 1986 and 1990, respectively, and a PhD degree in laser physics from ETH Zürich in 1996. He has co-authored and authored over 400 scientific publications. His current research interests include optical interconnects, nanophotonics, plasmonics, optical and electromagnetic metamaterials, RF, mm-wave and THz engineering, biomedical engineer, marine electromagnetics, computational electromagnetics, multiscale and multiphysics modeling, numerical structural optimization, and science and technology studies (STS).
References
1. C. Thiel, K. Neumann, C. Broecheler, F. Ludwar, A. Rennings, J. Doose, and D. Erni, “Iterative Electric Potential Adjustment of Damaged Naval Vessels using the Onboard ICCP System,” in COMSOL Conference, Swisstech Convention Center, EPFL Lausanne, Lausanne, Switzerland, 2018.Search in Google Scholar
2. COMSOL. (2019, August) COMSOL Multiphysics. [Online]. Available: https://www.comsol.de/.Search in Google Scholar
3. H. P. Hack, “Atlas of polarization diagrams for naval materials in seawater,” Carderock Division Naval Surface Warfare Center, Tech. Rep., 1995.10.21236/ADA294683Search in Google Scholar
4. COMSOL. (2019, 8) COMSOL Multiphysics Tutorial Section. [Online]. Available: https://www.comsol.de/model/ship-hull-iccp-14565.Search in Google Scholar
5. BWB, VG 81 259 Teil 1-3. Kathodischer Korrosionsschutz von Schiffen. Außenschutzdurch Fremdstrom, BWB Std., 2004.Search in Google Scholar
6. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015.10.1038/nature14539Search in Google Scholar PubMed
7. Z. Raida, “Modeling EM Structures in the Neural Network Toolbox of MATLAB,” IEEE Antennas and Propagation Magazine, vol. 44, no. 6, pp. 46–67, Dec. 2002.10.1109/MAP.2002.1167264Search in Google Scholar
8. S. Amari, “Backpropagation and stochastic gradient descent method,” Neurocomputing, vol. 5, no. 4-5, pp. 185–196, Jun. 1993.10.1016/0925-2312(93)90006-OSearch in Google Scholar
9. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, May 2017.10.1145/3065386Search in Google Scholar
10. D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization, ” arXiv Prepr. arXiv1412.6980, Jan. 2015.Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
