ARTIFICIAL NEURAL NETWORKS USED IN THE PROBLEMS OF OPTIMIZING THE TECHNICAL OPERATION OF THE ELECTRIC TRANSPORT MOVABLE COMPOSITION
Abstract
Optimization problems often require the use of optimization techniques, which minimize or maximize certain target functions. Sometimes the problems that need to be optimized are not linear or polynomial; they can not be precisely resolved, and they must be approximated. In these cases, it is necessary to apply a heuristic that is capable of solving such problems. Some algorithms linearize the constraints and objective functions at a certain point of space, using derivatives and partial derivatives for some cases; in other cases, evolution algorithms are used to approximate the solution. In this paper, we propose the use of artificial neural networks to approximate the objective function in optimization problems, which allows us to apply other methods of solving the problem. The target function is approximated by nonlinear regression, which can be used to solve the optimization problem. The derivative of the new target function must be polynomial so that one can calculate the solution to the optimization problem.
Recently, many methods and algorithms of automated control of the technical state of rolling stock of electric vehicles, both foreign and domestic scientists, are being developed. This is due to increasing requirements for transport companies operating in difficult circumstances of uncertainty about future factors affecting the company's performance. Fuzzy predictability of future actions determines the generation and decision making using the fuzzy logic tool.In the article the authors analyze the existing approaches to optimization of intelligent transport management systems. The urgency of the topic is due to a number of issues that exist when making the optimal solution for transport companies, while complying with the conditions of minimum use of the main resources, and ensuring the safe operation of the enterprise as a whole.The positive scientific result in this article is that the concept of constructing hierarchical intelligent control systems by complex dynamic-changing objects of transport enterprises, operating in conditions of significant uncertainty, is proposed. Among them, it is possible to define multilevel intelligent control and control systems as part of algorithmic support. In this case, it is necessary to apply management algorithms based on the use of knowledge, teaching methods, soft computing, neural networks based on fuzzy logic.
Keywords: neural networks, optimization problems, nonlinear optimization, rolling stock, electric transport.
References
References
Ríos-Mercado, R.Z & Conrado, Borraz-Sánchez (2015) Op-timization problems in natural gas transportation systems: A state-of-the-art review. Applied Energy, 147, 536–555.
Wang, Y., Ma, X., Xu, M., Liu, Yong ., Wang, Y. (2015) Two-echelon logistics distribution region partitioning problem based on a hybrid particle swarm optimization–genetic algo-rithm, 42(12), 5019–5031
Salari, M., Reihaneh, M., Sabbagh, M.S (2015) Combining ant colony optimization algorithm and dynamicprogramming technique for solving the covering salesman problem. Comput-ers & Industrial Engineering, 83, 244–251.
Zheng, X.L., Wang, L. (n.d.) A multi-agent optimization algo-rithm for resource constrained project scheduling problem. Expert Systems with Applications, In Press.
Lanza-Gutierrez, J.M., Gomez-Pulido, J.A. (2015) Assuming multiobjectivemetaheuristics to solve a three-objective optimisa-tion problem for Relay Node deployment in Wireless Sensor Networks. Applied Soft Computing, 30, 675–687.
Ploskas, N., Samaras, N. (2015) Efficient GPU-based imple-mentations of simplex type algorithms. Applied Mathematics and Computation, 250, 552–570.
Kuhn, H. W., Tucker, A. W. (1951) Nonlinear Programming. Proceedings of the Second Berkeley Symposium on Mathemati-cal Statistics and Probability, University of California Press, Berkeley, Calif., 481—492.
Wang, Y. (2014) The hybrid genetic algorithm with two local optimization strategies for traveling salesman problem. Com-puters & Industrial Engineering, 70, 124–133.
Li, L., Yu, Z., Chen, Y. (n.d.) Evacuation dynamic and exit optimization of a supermarket based on particle swarm optimi-zation. Physica A: Statistical Mechanics and its Applications, 416, 157–172.
Kolonko, M. (2009) Some new results on simulated annealing applied to the job shop scheduling problem. European Journal of Operational Research, 113(1), 123–136.
Hannah, L.A. (2015) Stochastic Optimization. International Encyclopedia of the Social & Behavioral Sciences (Second Edi-tion), 473–481.
İnkaya, T., Kayalıgil, S., Özdemirel, N.E. (2015) Ant Colo-ny Optimization based clustering methodology. Applied Soft Computing, 28, 301–311.
Yang, J., Zhuang, Y. (2010) An improved ant colony opti-mization algorithm for solving a complex combinatorial optimi-zation problem. Appl. Soft Comput., 10 (2), 653–660.
Bououden, S., Chadli, M., Karimi, H.R. (2015) An ant colony optimization-based fuzzy predictive control approach for nonlinear processes. Information Sciences, 299, 143–158.
Ñanculef, R., Frandi, E., Sartori, C., Allendea, H. (2014) A novel Frank–Wolfe algorithm. Analysis and applications to large-scale SVM training, Information Sciences, 285, 66–99.
Downloads
Published
How to Cite
Issue
Section
License
The authors who publish in this collection agree with the following terms:
• The authors reserve the right to authorship of their work and give the magazine the right to first publish this work under the terms of license CC BY-NC-ND 4.0 (with the Designation of Authorship - Non-Commercial - Without Derivatives 4.0 International), which allows others to freely distribute the published work with a mandatory reference to the authors of the original work and the first publication of the work in this magazine.
• Authors have the right to make independent extra-exclusive work agreements in the form in which they were published by this magazine (for example, posting work in an electronic repository of an institution or publishing as part of a monograph), provided that the link to the first publication of the work in this journal is maintained. .
• Journal policy allows and encourages the publication of manuscripts on the Internet (for example, in institutions' repositories or on personal websites), both before the publication of this manuscript and during its editorial work, as it contributes to the emergence of productive scientific discussion and positively affects the efficiency and dynamics of the citation of the published work (see The Effect of Open Access).