COMPUTATIONAL MODEL OF HULL STEEL POTENTIAL VALUES IN SEA WATER
Abstract
The article provides an analysis of existing neural network models. The features of constructing a neural network using several parameters that affect the output value are described. The advantages of using neural networks and computing systems based on them are revealed. The task was solved using the Python programming language. The computing model of the potential values of steel with an oxide film and the potential of steel without an oxide film has been developed for various salinity of sea water and different types of hull steels used for hulls of sea vessels and underwater structures of ocean engineering structures designed for the Black Sea basin of the Sevastopol region and operated in this region. The obtained results will improve the accuracy of predicting potentials for various hull steel grades.
References
Kramar Vadim, Neural Network Modeling the Potential of Steels with Different Chrome Content / Vadim Kramar, Veronika Dushko, Anna Rodkina, Vasiliy Alchakov // Proceedings Engineering of the 26th International DAAAM Symposium «Intelligent Manufacturing & Automation» 21-24th October 2015, Zadar, Croatia, EU, Volume 26, No.1, ISSN 1726-9679, Ed. B. Katalinic, Published by DAAAM International, Vienna, Austria, EU, 2016. – pp. 1059–1067. https://doi.org/10.2507/26th.daaam.proceedings.087
Hussein Kadhim Mohammed AL-Shareefi. Neural Network Corrosion Control by Impressed Cathodic Protiction / University of Technology – Baghdad – Iraq. 2009.
Wasserman, P.D. «Neural Computing :Theory and Practice», Van Nostrand Reinhold, New York, USA, 1989.
Jain, A.K., Mao, J.and Mohiuddin, K. «Artificial Neural Networks: A Tutorial», IEEE Computer, Vol.29, No.3, pp.31-44, 1996. https://doi.org/10.1109/2.485891
Hornik, K., Stinchcombe, M.and White, H. «Multilayer Feedforward Networks are Universal Approximators», Neural Networks, Vol.2, pp.359 -366, 1989. https://doi.org/10.1016/0893-6080(89)90020-8
Principe, J.C., Euliano, N.R.and Lefebvre, W.C. «Neural and Adaptive Systems», John Wiley and Sons, Inc., USA, 2000.
Hecht-Nielsen, R. «Neurocomputing», Addison-Wesley Publishing Company, Inc., 1990.
Shayma Mehdi Salih, «study the effect of some variables on cathodic protection current density»، MSc.Thesis, Iraq University of Technology, 2005.
V A Kramar, V V Alchakov, V R Dushko, T V Kramar Application of support vector machine for prediction and classification / IOP Conf. Series: Journal of Physics: Conf. Series 1015 (2018) 032070 doi :10.1088/1742-6596/1015/3/032070. https://doi.org/10.1088/1742-6596/1015/3/032070
Круглов В.В. Искуственные нейронные сети. Теория и практика / В.В. Круглов, В.В. Борисов ‒ М.: Горячая линия ‒ Телеком, 2002. ‒ 382 с.
Вандер Плас Дж. Python для сложных задач: наука о данных и машинное обучение / Плас Дж. Вандер. – СПб.: Питер, 2018. – 576 с.: ил.
Родькина А.В. Гибридная нейронная сеть для прогнозирования защитного потенциала подводной части океанотехнических сооружений / А.В. Родькина, В.А. Крамарь, Е.М. Грамузов, О.А. Иванова // Труды Крыловского государственного научного центра. – СПб.: ФГУП «Крыловский государственный научный центр», 2019. – Журнал_№ 20192. – Том 2. – С. 254–262. https://doi.org/10.24937/2542-2324-2019-2-s-i-254-262
Copyright (c) 2020 Russian Journal of Water Transport
This work is licensed under a Creative Commons Attribution 4.0 International License.
