Abstract
The goal of the work is to development of a synchronous-replicated model for the assessment of the technical state of a locomotive as a technological system. When performing the work, method of systems analysis, computer and mathematical modelling, artificial intelligence, and mathematical analysis were used. As a result of the research we have obtained a mathematical synchronous-replicated model for the assessment of the technical state of a locomotive based on multilayer neuron forecasting network. The model developed can be used in systems for monitoring, controlling and diagnosing the technical state of the locomotive fleet. This model possesses such novel specific features as low sampling period between quizzing of monitoring facilities, versatility, adaptability and operability. This suggested model resolves a range of tasks set forth in the Concept for the development of the OJSC Russian Railways connected with the implementation of an actual system for repairs and maintenance according to the current condition of locomotives as well as the digitalization of the advanced fields of the company.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Golubev, Y.F.: Neural networks in mechactronics. J. Math. Sci. 147(2), 6607–6622 (2007). https://doi.org/10.1007/s10958-007-0497-3
Andreichenko, D.K., Zhadaev, F.M.: Training or neural network regulators for stabilization of combined dynamic systems. News Saratov Univ. New Ser. Math. Mech. Inform. 18(3), 354–360 (2018). https://doi.org/10.18500/1816-9791-2018-18-3-354-360
Kominkova Oplatkova, Z., Senkerik, R., Zelinka, I., Pluhacek, M.: Analytic programming in the task of evolutionary synthesis of a controller for high order oscillations stabilization of discrete chaotic systems. Comput. Math Appl. 66(2), 177–189 (2013). https://doi.org/10.1016/j.camwa.2013.02.008
Daoud, M., Mayo, M.: A survey of neural network-based cancer prediction models from microarray data. Artif. Intell. Med. 97(5), 204–214 (2019). https://doi.org/10.1016/j.artmed.2019.01.006
Hara, K., Okada, M.: On-line learning through simple perceptron learning with a margin. Neural Netwo. 17(2), 215–223 (2004). https://doi.org/10.1016/j.neunet.2003.08.005
Uhobotov, V.I., Mihailova E.S.: On the comparison of fuzzy numbers in the decision-making problems. Bull. Udmurt Univ. Math. Mech. Comput. Sci. 26(1), 87–94 (2016). https://doi.org/10.20537/vm160108
Mohammed, M.A., Naji, T.A.H., Abdulyabbar, H.M.: The effect of the activation functions on the classification accuracy of satellite image by artificial neural network. Energy Procedia 157(2), 164–170 (2019). https://doi.org/10.1016/j.egypro.2018.11.177
Diene, O., Bhaya, A.: Conjugate gradient and steepest descent constant modulus algorithms applied to a blind adaptive array. Signal Process. 90(10), 2835–2841 (2010). https://doi.org/10.1016/j.sigpro.2010.04.002
Chen, J., Weiguo, L.: Convergence of Gauss-Newton’s method and uniqueness of the solution. Appl. Math. Comput. 170(1), 686–705 (2005). https://doi.org/10.1016/j.amc.2004.12.055
Maric, I.: Optimization of self-organizing polynomial neural networks. Expert Syst. Appl. 40(11), 4528–4538 (2013). https://doi.org/10.1016/j.eswa.2013.01.060
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Plyaskin, A., Kushniruk, A. (2020). Actual Artificial-Intelligence Based System for Assessment of the Technical State of the Rolling Stock Fleet. In: Popovic, Z., Manakov, A., Breskich, V. (eds) VIII International Scientific Siberian Transport Forum. TransSiberia 2019. Advances in Intelligent Systems and Computing, vol 1115. Springer, Cham. https://doi.org/10.1007/978-3-030-37916-2_42
Download citation
DOI: https://doi.org/10.1007/978-3-030-37916-2_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37915-5
Online ISBN: 978-3-030-37916-2
eBook Packages: EngineeringEngineering (R0)