Method for constructing an adaptive suboptimal stationary train traffic controller based on artificial neural networks

The article discusses the modern methodology for performing the synthesis of a suboptimal train controller for the purpose of energy saving. The existing methods of optimal traction control have a number of disadvantages, the main one of which is the lack of direct use in the control program of the...

Full description

Saved in:
Bibliographic Details
Main Authors: S. V. Malakhov, M. Yu. Kapustin
Format: Article
Language:Russian
Published: Joint Stock Company «Railway Scientific and Research Institute» 2021-04-01
Series:Вестник Научно-исследовательского института железнодорожного транспорта
Subjects:
Online Access:https://www.journal-vniizht.ru/jour/article/view/494
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849244540613951488
author S. V. Malakhov
M. Yu. Kapustin
author_facet S. V. Malakhov
M. Yu. Kapustin
author_sort S. V. Malakhov
collection DOAJ
description The article discusses the modern methodology for performing the synthesis of a suboptimal train controller for the purpose of energy saving. The existing methods of optimal traction control have a number of disadvantages, the main one of which is the lack of direct use in the control program of the data obtained during train operation. Mathematical models used to solve the op- timal problem can be used correctly only in the case of sufficient adequacy. Adequacy check is not part of the known methods of optimal control theory. To eliminate this drawback, it is proposed to use the method of optimal (suboptimal) traction calculations based on artificial neural networks. It improves the accuracy of traction calculations, which is especially important in the aspect of considering energy savings, while reducing the need for computing power. When using this method, it is possible not only to achieve results close to the classical Bellman method, but also to train or verify the network using the recorded data. The article discusses the process of creating and training an artificial neural network based on model data to solve the problem of suboptimal control. The train motion modes obtained by Bellman's method were used as reference data for training the neural network. The presented comparative results of the two methods show the applicability of artificial neural networks for solving applied problems of train traction with the possibility of continuous learning, including the use of trip data, which can be directly included in the training or testing set.
format Article
id doaj-art-53e7e84070b748e98caf7a0dbbba483e
institution Kabale University
issn 2223-9731
2713-2560
language Russian
publishDate 2021-04-01
publisher Joint Stock Company «Railway Scientific and Research Institute»
record_format Article
series Вестник Научно-исследовательского института железнодорожного транспорта
spelling doaj-art-53e7e84070b748e98caf7a0dbbba483e2025-08-20T03:59:08ZrusJoint Stock Company «Railway Scientific and Research Institute»Вестник Научно-исследовательского института железнодорожного транспорта2223-97312713-25602021-04-01801131910.21780/2223-9731-2021-80-1-13-19321Method for constructing an adaptive suboptimal stationary train traffic controller based on artificial neural networksS. V. Malakhov0M. Yu. Kapustin1Federal State Autonomous Educational Institution of Higher Education “Russian University of Transport” (FGAOU VO “RUT” (MIIT))Federal State Autonomous Educational Institution of Higher Education “Russian University of Transport” (FGAOU VO “RUT” (MIIT))The article discusses the modern methodology for performing the synthesis of a suboptimal train controller for the purpose of energy saving. The existing methods of optimal traction control have a number of disadvantages, the main one of which is the lack of direct use in the control program of the data obtained during train operation. Mathematical models used to solve the op- timal problem can be used correctly only in the case of sufficient adequacy. Adequacy check is not part of the known methods of optimal control theory. To eliminate this drawback, it is proposed to use the method of optimal (suboptimal) traction calculations based on artificial neural networks. It improves the accuracy of traction calculations, which is especially important in the aspect of considering energy savings, while reducing the need for computing power. When using this method, it is possible not only to achieve results close to the classical Bellman method, but also to train or verify the network using the recorded data. The article discusses the process of creating and training an artificial neural network based on model data to solve the problem of suboptimal control. The train motion modes obtained by Bellman's method were used as reference data for training the neural network. The presented comparative results of the two methods show the applicability of artificial neural networks for solving applied problems of train traction with the possibility of continuous learning, including the use of trip data, which can be directly included in the training or testing set.https://www.journal-vniizht.ru/jour/article/view/494traction calculationsoptimization of traction calculationsrationing of energy consumption for train tractionarti- ficial neural networksautomatic vehicle control systemstraction properties of the locomotiveregulation of traction and braking forces
spellingShingle S. V. Malakhov
M. Yu. Kapustin
Method for constructing an adaptive suboptimal stationary train traffic controller based on artificial neural networks
Вестник Научно-исследовательского института железнодорожного транспорта
traction calculations
optimization of traction calculations
rationing of energy consumption for train traction
arti- ficial neural networks
automatic vehicle control systems
traction properties of the locomotive
regulation of traction and braking forces
title Method for constructing an adaptive suboptimal stationary train traffic controller based on artificial neural networks
title_full Method for constructing an adaptive suboptimal stationary train traffic controller based on artificial neural networks
title_fullStr Method for constructing an adaptive suboptimal stationary train traffic controller based on artificial neural networks
title_full_unstemmed Method for constructing an adaptive suboptimal stationary train traffic controller based on artificial neural networks
title_short Method for constructing an adaptive suboptimal stationary train traffic controller based on artificial neural networks
title_sort method for constructing an adaptive suboptimal stationary train traffic controller based on artificial neural networks
topic traction calculations
optimization of traction calculations
rationing of energy consumption for train traction
arti- ficial neural networks
automatic vehicle control systems
traction properties of the locomotive
regulation of traction and braking forces
url https://www.journal-vniizht.ru/jour/article/view/494
work_keys_str_mv AT svmalakhov methodforconstructinganadaptivesuboptimalstationarytraintrafficcontrollerbasedonartificialneuralnetworks
AT myukapustin methodforconstructinganadaptivesuboptimalstationarytraintrafficcontrollerbasedonartificialneuralnetworks