Abstract
The paper presents a comparative analysis of the current instrumental software for studying models of controlled dynamic systems using artificial intelligence. We pay special attention to the open and free software use, as well as some aspects of this software use in the development of the author’s software package for modeling of controlled dynamic systems. The results of computational experiments based on the specified software package are presented. We propose a formalized description of a generalized model of a nonlinear dynamic switchable system. Based on the implementation of the neural network switching generation algorithm and the neural network training algorithm, we present a graphical interpretation of the trajectories in a model example. During the experiments, the correctness of the algorithms was checked, taking into account the relevant requirements. The obtained results can be used in the problems of synthesis and analysis of controlled dynamic transport systems models, in the problems of computer modeling using scientific software, as well as in the development of algorithms and programs based on artificial intelligence methods #CSOC1120.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Fuhrer, C., Solem, J.E., Verdier, O.: Scientific Computing with Python 3. Packt Publishing, Birmingham (2016)
Lamy, R.: Instant SymPy Starter. Packt Publishing, Birmingham (2013)
Oliphant, T.E.: Guide to NumPy, 2nd edn. CreateSpace Independet Publishing Platform, USA (2015)
Numba User Manual. https://numba.readthedocs.io/en/stable/user/
SciPy Tutotial. https://docs.scipy.org/doc/scipy/reference/tutorial/
Hansen, Jesper Schmidt: GNU Octave. Beginner’s Guide. Packt Publishing, Birmingham (2011)
Alekseev, E.R., Chesnokova, O.V.: Introduction to Octave for Engineers and Mathematicians. ALT Linux, Moscow (2012)
Kozhin, A.S., Neiman-zade, M.I., Tikhorsky, V.V.: Influence of the memory subsystem of the eight-core microprocessor “Elbrus-8C” on its performance. Probl. Radio Electron. (3), 13–21 (2017)
Druzhinina, O.V., Korepanov, E.R., Belousov, V.V., Masina, O.N., Petrov, A.A.: Experience in developing methods and tools for neural network modeling of nonlinear systems based on the Russian computing platform “Elbrus 801-RS”. Nonlinear World 18(2), 5–18 (2020)
Petrov, A.A.: The structure of the software package for modeling technical systems in the conditions of switching operating modes. Electromagn. Waves Electron. Syst. 23(4), 61–64 (2018)
Druzhinina, O.V., Masina, O.N., Petrov, A.A.: The synthesis of the switching systems optimal parameters search algorithms. Commun. Comput. Inf. Sci. (CCIS) 974, 306–320 (2019)
Liberzon, D., Morse, A.S.: Basic problems in stability and design of switched systems. IEEE Control syst. 19(5), 59–70 (1999)
Shpilevaya, O.Ya., Kotov, K.Yu.: Switched systems: stability and design (review). Auto-measurement (5), 71–87 (2008)
Vasiliev, S.N., Malikov, A.I.: On some results on the stability of switchable and hybrid systems. In: Actual Problems of Continuum Mechanics, Foliant, Kazan, vol. 1, pp. 23–81 (2011)
Druzhinina, O.V., Masina, O.N., Petrov, A.A.: Models for control of technical systems motion taking into account optimality conditions. In: Proceedings of the VIII International Conference on optimization methods and applications “Optimization and application” (OPTIMA2017), Petrovac, Montenegro, vol. 1987, pp. 386–391. (2017)
Druzhinina, O.V., Masina, O.N., Petrov, A.A., Lisovsky, E.V., Lyudagovskaya, M.A.: Neural network optimization algorithms for controlled switching systems. Adv. Int. Syst. Comput. (AISC) 1225, 470–483 (2020)
Fletcher, R.: Practical Methods of Optimization. Wiley, New York (2000)
Karpenko, A.P.: Modern Search Engine Optimization Algorithms. Bauman Moscow State Technical University, Moscow (2017)
Haykin, S.: Neural Networks. Vilyams, Moscow (2006)
Nielsen, M.: Neural Networks and Deep Learning. Determination Press, San Francisco (2015)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Li, Y.: Deep Reinforcment Learning: An Overview. Preprint. arXiv:1701.07274 [cs.LG] (2017)
Kashirina, I.A., Demchenko, M.V.: Research and comparative analysis of optimization methods used in training neural networks. Bull. Voronezh State Univ. Ser. Syst. Anal. Inf. Technol. (4), 123–132 (2018)
Alesca, C.D., Pinta, T., Boros, I.: New optimization algorithms for neural networktraining using operator splitting techniques. Preprint. ArXiv: 1904.12952v5 [cs. LG] (2020)
Yalamanchili, P., et al.: ArrayFire - A High Performance Software Library for Parallel Computing with An Easy-to-Use API. AccelerEyes, Atlanta (2015)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Druzhinina, O.V., Masina, O.N., Petrov, A.A. (2021). Up-to-date Software and Methodological Support for Studying Models of Controlled Dynamic Systems Using Artificial Intelligence. In: Silhavy, R. (eds) Informatics and Cybernetics in Intelligent Systems. CSOC 2021. Lecture Notes in Networks and Systems, vol 228. Springer, Cham. https://doi.org/10.1007/978-3-030-77448-6_65
Download citation
DOI: https://doi.org/10.1007/978-3-030-77448-6_65
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77447-9
Online ISBN: 978-3-030-77448-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)