«Automation and Informatization of the fuel and energy complex»

Using neural networks to identify an approximate model of a boiler unit in different operational modes

UDC: 681.5.015
DOI: -

Authors:

¹ Samara State Technical University, Samara, Russia

Keywords: identification by frequency characteristics, identification of an approximate model, modeling of heat transfer processes, waste heat boiler, neural networks

Annotation:

The identification object is a waste heat boiler operating in several modes. The waste heat boiler is a multidimensional thermodynamic system with nonlinear characteristics. An approach is described that combines traditional methods of approximate models identification based on frequency characteristics and neural networks. The waste heat boiler is a multidimensional thermodynamic system with nonlinear characteristics. An autoregressive network with an external input is used to create a multidimensional dynamic model of the waste heat boiler. The neural network model was trained and tested on the data obtained during the operation of a real installation and takes into account changes of the main technological parameters in all acceptable ranges. To model the dynamic characteristics of the waste heat boiler, an autoregressive network with an external input is used. As a result of a computational experiment, the frequency characteristics of the neural network model were obtained in several operational modes. Based on the frequency characteristics of the neural model, the structure and parameters of the approximate models were identified. The authors of the article describe a neural network model of a waste heat boiler, a procedure of identifying approximate models based on the frequency characteristics of the neural network model and the results of approximate models identification for different operational modes.

Bibliography:

1. O'Dwye A. PID compensation of time delayed processes 1998–2002: a survey // Proceedings of the 2003 American Control Conf., Denver, CO, USA, June 4–6, 2003. Vol. 2. – P. 1494–1499. – DOI: 10.1109/ACC.2003.1239802
2. Glushchenko A.I. Neyrosetevaya adaptivnaya nastroyka regulyatorov dlya upravleniya nestatsionarnymi tekhnologicheskimi ob"ektami v metallurgii: dis. … d-ra tekhn. nauk: 05.13.06. – Voronezh, 2021. – 304 s.
3. Telichenko D.A., Nikol'skiy D.I. Matematicheskie modeli dlya odnogo klassa slozhnykh inertsionnykh ob"ektov s izmenyayushcheysya dinamikoy i zapazdyvaniem // Uchenye zametki TOGU. – 2016. – T. 7, № 3-1. – S. 142–151.
4. Pikina G.A., Pashchenko F.F. Identifikatsiya perekhodnykh kharakteristik ob"ektov v cheloveko-mashinnykh sistemakh // Informatika i sistemy upravleniya. – 2013. – № 3(37). – S. 53–59.
5. Shumikhin A.G., Boyarshinova A.S. Primenenie neyrosetevykh dinamicheskikh modeley v zadachakh parametricheskoy identifikatsii tekhnologicheskogo ob"ekta v sostave sistemy upravleniya // Vestn. PNIPU. Khimicheskaya tekhnologiya i biotekhnologiya. – 2015. – № 3. – S. 21–38.
6. Shumikhin A.G., Aleksandrova A.S., Mustafin A.I. Parametricheskaya identifikatsiya tekhnologicheskogo ob"ekta v rezhime ego ekspluatatsii s primeneniem tekhnologii neyronnykh setey // Vestn. PNIPU. Elektrotekhnika, inform. tekhnologii, sistemy upravleniya. – 2018. – № 26. – S. 29–41.
7. Identifikatsiya postoyannykh parametrov dinamicheskikh sistem chastotno-vremennym metodom / V.N. Ovcharenko, E.V. Danilevich, N.I. Kukharenko [i dr.] // Izv. RAN. Teoriya i sistemy upravleniya. – 2018. – № 4. – S. 3–12. – DOI: 10.31857/S000233880002509-8
8. Aleksandrov A.G., Palenov M.V. Sostoyanie i perspektivy razvitiya adaptivnykh PID-regulyatorov // Avtomatika i telemekhanika. – 2014. – № 2. – S. 16–30.
9. Danilushkin I.A., Kolpashchikov S.A., Lysenko D.S. Dinamicheskaya model' vodogreynogo kotla utilizatora // Vestn. Samar. gos. tekhn. un-ta. Seriya: Tekhnicheskie nauki. – 2023. – T. 31, № 2(78). – S. 31–42. – DOI: 10.14498/tech.2023.2.3
10. Danilushkin A.I., Danilushkin I.A. Chislenno-analiticheskaya model' transportirovki gaza po lineynomu uchastku gazoprovoda // Izv. Tomskogo politekhn. un-ta. Inzhiniring georesursov. – 2015. – T. 326, № 12. – S. 96–103.
11. Golovko N.A., Logunova O.S. Otsenka arkhitektury iskusstvennykh neyronnykh setey dlya modelirovaniya protsessov nagreva stal'noy polosy na agregate nepreryvnogo goryachego tsinkovaniya // Vestn. NTU "KhPI". – 2012. – № 62(968). – S. 33–39.
12. Mishulina O.A., Trofimov A.G. Neyrosetevoe modelirovanie raspredelennykh protsessov energovydeleniya v aktivnoy zone reaktornoy ustanovki // Neyrokomp'yutery: razrabotka, primenenie. – 2007. – № 9. – S. 57–70.
13. Gorbachenko V.I., Alkezuini M.M. Modelirovanie ob"ektov s raspredelennymi parametrami na neyronnykh setyakh // Modeli, sistemy, seti v ekonomike, tekhnike, prirode i obshchestve. – 2019. – № 4(32). – S. 50–64.
14. Gorbachenko V.I., Katkov S.N. Ispol'zovanie memristornykh setey dlya resheniya differentsial'nykh uravneniy v chastnykh proizvodnykh // Modeli, sistemy, seti v ekonomike, tekhnike, prirode i obshchestve. – 2016. – № 4(20). – S. 97–107.
15. Prakticheskaya realizatsiya primeneniya neyrosetevykh modeley dlya modelirovaniya slozhnykh gazotransportnykh sistem bol'shoy razmernosti / N.A Kislenko, S.N. Pankratov, V.V. Dedkova [i dr.] // Avtomatizatsiya i informatizatsiya TEK. – 2024. – № 9(614). – S. 33–41.
16. O vozmozhnosti ispol'zovaniya tekhnologii mashinnogo obucheniya dlya modelirovaniya kompressornoy stantsii magistral'nogo gazoprovoda / A.V. Oleynikov, V.A. Shevchenko, A.V. Belinskiy, A.V. Maletin // Avtomatizatsiya i informatizatsiya TEK. – 2024. – № 6(611). – S. 35–45.