Modeling of a neural network-based system for identification and control of technical object parameters

Authors

  • Mykhailenko Vladyslav
  • Kamienieva Alla
  • Stukalov Segii
  • Zui Oksana

DOI:

https://doi.org/10.34185/1562-9945-3-146-2023-02

Keywords:

automatic control system; neural network controller, PID-regulator; boiler; transitional process

Abstract

The article analyzes the effectiveness of a neural network control system for main-taining the pH level in the feedwater of a steam boiler. An intelligent control system im-plements the principle of reverse error propagation through a neural emulator. The sub-system model of steam boiler water tube blowing was used as the research object. The neural network controller and neural emulator were trained on a control system model with a PID controller using the expert correction methodology of tuning coefficients: proportionality, integration constant, and differentiation based on the analysis of tran-sient process quality indicators. The analysis of the transient processes obtained from simulation modeling allows us to state that the trained neural network control system successfully compensates for disturbances over a wide range of changes in the object's parameter values via control channels and disturbances (simulating changes in steam load).

References

Zhang Y. Neural network-based PID prediktivní kontrolʹ dlya neliniynykh time-delay systems / Y. Zhang, Z.Q. Chen, P. Yang, ZZ. Yuan // Proceedings of Interna-tional Conference on Machine Learning and Cybernetics.Vol. 2. 2017.

P. 1014 - 1018.

Yongquan Y.A. PID neural network controller/ Y.A.Yongquan, H.Ying, Z.Bi // Protsedury mizhnarodnoho menedzhmentu na Neural Networks.Vol. 3. 2017.

P. 1933 - 1938.

Klyuyev O.S. Nalahodzhennya system avtomatychnoho rehulyuvannya parovykh kotloahrehativ / O.S. Klyuyev, A. H. Tovarnov. M.: Enerhiya, 1970. - 270 s.

Ho S.J. Optimizing fuzzy neural networks dlya tuning PID controllers vykorystovuyuchy ortohonalʹni simulated annealing algorithm OSA/ S.J. Ho, L.S. Shu, S.Y. Ho / IEEE Transactions on Fuzzy Systems.Vol. 14. Issue 3. 2016.

P. 421 -434.

Yang P. Neural networks internal model control for water level of boiler drum in power station / P.Yang, D.G.Peng, Y.H. Yang, ZP. Wang // Proceedings of 2017 In-ternational Conference on Machine Learning and Cybernetics.Vol. 5. 2017. P. 3300 - 3303.

Mykhaylenko V.S. Syntez neyromerezhevoyi systemy avtomatychnoho rehulyuvannya rivnya vody v barabani kotla enerhobloku TES / Mykhaylenko V.S., Kharchenko R.YU. // Naukovi visti NTUU «KPI». - 2012. - №5. - S. 45 - 51.

Sen P. Adaptive Neural Controller/P.Sen, G.E. Hearn, Y. Zhang // In Neural Net-work Systems Techniques and Aplications. HRSG. Leondes C.T. 1998. - Vol.4. -

R. 274 - 343.

Boiler Operating Mistakes On Ships That Can Cost Big Time. URL: https://www.marineinsight.com/tech/boiler.

Artificial Neural Network and Machine Learning using MATLAB// https://www.udemy.com.

Yongquan, Y.A. PID neural network controller / Y.A.Yongquan, H. Ying, Z. Bi // Proceedings of International Joint Conference on Neural Networks.Vol. 3. 2017.

P. 1933 - 1938.

Mikhaylenko V.S. Analysis of Traditional and Neuro Fuzzy Adaptive System of Controlling the Primary Steam Temperature in Direct Flow Steam Generators in Thermal Power Stations / V. S. Mikhailenko, R. Yu. Kharchenko. // Automatic Con-trol and Computer Sciences - 2014. - Vol. 48 №. 6. - R. 334 -344.

Published

2023-05-11