NEURAL NETWORK CONTROL SYSTEM OF VD-400 VACUUM DEAERATOR
Abstract
The article considers the algorithms, applied in program realization of a neural network control system of concentration of oxygen of deaerated water. The analysis of the VD-400vacuum deaerator as the object of control is carried out. Control and perturbation actions, as well as adjustable parameters of VD-400 are revealed. The special attention is paid to the software, creating models of the feedforward multilayered neural networks with live training. Interfaces of training and modeling are shown. The general scheme of control of the VD-400 vacuum deaerator is presented.
About the Authors
P. P. Alekseev
Astrakhan State Technical University
Russian Federation
Alekseev Pavel P., undergraduate
Russian Federation
Alekseev Pavel P., undergraduate
I. A. Sherbatov
Astrakhan State Technical University
Russian Federation
Sherbatov Ivan A., Candidate of Technical Sciences, Associate Professor
Russian Federation
Sherbatov Ivan A., Candidate of Technical Sciences, Associate Professor
References
1. Bobyr’ M.V., Titov V.S. Intellektual’naja sistema upravlenija temperaturnymi deformacijami pri rezanii // Avtomatizacija. Sovremennye tehnologii. 2011. № 5. P. 3–7.
2. Bobyr’ M.V. Diagnostika oborudovanija s ChPU metodami nechetkoj logiki // Promyshlennye ASU i kontrollery. 2010. № 1. P. 18–20.
3. Glazkov V.P., Bol’shakov A.A., Kulik A.A. Ispol’zovanie nejrosetevogo kompensatora dlja stabilizacii dvizhenija poluavtomaticheskih proteziruemyh sistem // Mehatronika, avtomatizacija, upravlenie. 2014. № 1. P. 13–17.
4. Nemchinov D.V., Protalinskij O.M. Snizhenie riska avarijnoj situacii na proizvodstvennom ob#ekte // Vestnik Astrahanskogo gosudarstvennogo tehnicheskogo universiteta. Serija: Upravlenie, vychislitel’naja tehnika i informatika. 2009. № 1. P. 111–116.
5. Osovskij S. Nejronnye seti dlja obrabotki informacii / per. s pol. M.: Finansy i statistika, 2002. 344 p.
6. Protalinskij O.M. Proverka dostovernosti pervichnoj informacii v ASU TP s ispol’zovaniem nechetkih mnozhestv // Izvestija vysshih uchebnyh zavedenij. SeveroKavkazskij region. Serija: Tehnicheskie nauki. 2003. № 3. P. 60.
7. Protalinskij O.M., Dianov R.S. Avtomatizirovannaja sistema upravlenija razrabotkoj gazovogo mestorozhdenija s primeneniem nejronnoj seti // Promyshlennye ASU i kontrollery. 2003. № 12. P. 30.
8. Skobcov Ju.A., Tkachenko A.V. Programmnaja realizacija nejronnyh setej dlja obuchenija v sistemah real’nogo vremeni // Naukovі pracі Donec’kogo derzhavnogo tehnіchnogo unіversitetu. Ser. obchisljuval’na tehnіka ta avtomatizacіja, vipusk 66. Donec’k: DonNTU. 2005.
9. Moller M.F. ‘A scaled conjugate gradient algorithm for fast supervised learning’, Neural Networks. 1993. Vol. 6. P. 525–533.
10. Nguyen D., Widrow B. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. Proceedings of the International Joint Conference on Neural Networks. 1990. Vol. 3. P. 21–26.
11. Riedmiller M. A direct method for faster backpropagation learning. Proceedings of the 1993 IEEE International Conference on Neural Networks (ICNN ’93). San Francisco. Vol. 1. P. 586–591.
12. Rumelhart D.E., Hinton G.E., Williams R.J. Learning internal representations by error propagation // Parallel Distributed Processing: Exploration in the Microstructure of Cognition, D.E. Rumelhart and J.L. McClelland (Eds.). Cambridge, MA: MIT Press, 1986. Vol. 1. P. 318–362.
Review
For citations:
Alekseev P.P., Sherbatov I.A. NEURAL NETWORK CONTROL SYSTEM OF VD-400 VACUUM DEAERATOR. Vestnik NSUEM. 2016;(2):263-275. (In Russ.)
Email this article 
