Abstract
We solve the identification problem for “input-output” transmission channels of complex control objects that represent technological systems with continuous production in chemical, metal processing, mining, paper, and other industries, with neural networks. The resulting model represented with a dynamical neural network models the behavior of the technological object and lets us find the object’s output, including outputs for periodic test influences. By the resulting complex frequency response, with the method of least squares we find the parameters of the channel’s transfer function. We show an example of identification for “input-output” channels with a delay of the imitational object under random noise at the input.
Similar content being viewed by others
References
Eykhoff, P., System Identification: Parameter and State Estimation, Chichester: Wiley, 1974. Translated under the title Osnovy identifikatsii sistem upravleniya: otsenivanie parametrov i sostoyaniya, Moscow: Mir, 1975.
Boyarinov, A.I. and Kafarov, V.V., Metody optimizatsii v khimicheskoi tekhnologii (Optimization Methods in Chemical Technology), Moscow: Khimiya, 1975.
Gartman, T.N. and Klushin, D.V., Osnovy komp’yuternogo modelirovaniya khimiko-tekhnologicheskikh protsessov (Fundamentals of Computer Modeling for Chemical Technology Processes), Moscow: Akademkniga, 2006.
Kafarov, V.V. and Dorokhov, I.N., Sistemnyi analiz protsessov khimicheskoi tekhnologii (System Analysis for Chemical Technology Processes), Moscow: Nauka, 1976.
Saraev, P.V., Numerical Methods of Interval Analysis in Learning Neural Networks, Autom. Remote Control, 2012, vol. 73, no. 11, pp. 1865–1876.
Gabitov, R.F., Multidimensional Model-Predictive Control for Heating of Cracking Catalysts Based on an Algorithm with Interval Uncertainty, Cand. Sci. Dissertation, Ufa, 2012.
Shumikhin, A.G., Boyarshinova, A.S., and Orekhov, M.S., Applying Neural Network Models for Automated Control over Complex Chemical-Technological Systems, Polzunovskii Vestn., 2012, no. 3/2, pp. 9–12.
Idrisov, I.I., Adaptation and Fault-Tolerance Algorithms for Control Systems over Gas-Turbine Engines Based on Neural Networks, Cand. Sci. Dissertation, Ufa, 2009.
Aved’yan, E.D., Learning Algorithms for Multilayer Neural Networks, Autom. Remote Control, 1995, vol. 56, no. 4, part 2, pp. 541–551.
Makarov, I.M., Lokhin, V.M., Man’ko, S.V., et al., Avtomatizatsiya sinteza i obuchenie intellektual’nykh sistem upravleniya (Automating Synthesis and Training of Intelligent Control Systems), Makarov, I.M. and Lokhin, V.M., Eds., Moscow: Nauka, 2009.
Zhdanov, A.I., Direct Recurrent Algorithms for Solving Linear Problems in the Least Squares Method, Zh. Vychisl. Mat. Mat. Fiz., 1994, vol. 34, no. 6, pp. 805–814.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © A.G. Shumikhin, A.S. Boyarshinova, 2015, published in Avtomatika i Telemekhanika, 2015, No. 4, pp. 125–134.
Rights and permissions
About this article
Cite this article
Shumikhin, A.G., Boyarshinova, A.S. Identification of a complex control object with frequency characteristics obtained experimentally with its dynamic neural network model. Autom Remote Control 76, 650–657 (2015). https://doi.org/10.1134/S0005117915040098
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0005117915040098