Predictive Neural Network in Multipurpose Self-Tuning Controller

Bondar, Oleksiy

doi:10.2478/ama-2020-0017

Abstract

A very important problem in designing of controlling systems is to choose the right type of architecture of controller. And it is always a compromise between accuracy, difficulty in setting up, technical complexity and cost, expandability, flexibility and so on. In this paper, multipurpose adaptive controller with implementation of artificial neural network is offered as an answer to a wide range of tasks related to regulation. The effectiveness of the approach is demonstrated by the example of an adaptive thermostat. It also compares its capabilities with those of classic PID controller. The core of this approach is the use of an artificial neural network capable of predicting the behaviour of controlled object within its known range of parameters. Since such a network, being trained, is a model of a regulated system with arbitrary precision, it can be analysed to make optimal management decisions at the moment or in a number of steps. Network learning algorithm is backpropagation and its modified version is used to analyse an already trained network in order to find the optimal solution for the regulator. Software implementation, such as graphical user interface, routines related to neural network and many other, is done using Java programming language and Processing open-source integrated development environment.

References

1. Ayomoh M. K. O., Ajala M. T. (2012), Neural Network Modeling of a Tuned PID Controller, European Journal of Scientific Research, 71, 283–297.
Search in Google Scholar Back to article
2. Burennikov Y., Kozlov L., Pyliavets V., Piontkevich O. (2017), Mechatronic Hydraulic Drive with Regulator, Based on Artificial Neuron Network, IOP Conference Series: Materials Science and Engineering, 209(1):012071.10.1088/1757-899X/209/1/012071
Search in Google Scholar Back to article
3. Du X., Wang J., Jegatheesan V., Shi G. (2018), Dissolved Oxygen Control in Activated Sludge Process Using a Neural Network-Based Adaptive PID Algorithm, Applied Sciences, 8(2):261, DOI: 10.3390/app8020261.10.3390/app8020261
Search in Google Scholar Back to article
4. Elsisi M. (2019), Design of neural network predictive controller based on imperialist competitive algorithm for automatic voltage regulator, Neural Computing and Applications, 31, 5017–5027.10.1007/s00521-018-03995-9
Search in Google Scholar Back to article
5. Han G., Fu W., Wang W., Wu Z. (2017), The Lateral Tracking Control for the Intelligent Veicle Based on Adaptive PID Neural Network, Sensors, 17(6):1244, DOI: 10.3390/s17061244.10.3390/s17061244549236428556817
Search in Google Scholar Back to article
6. Heaton J. (2008), Introduction to Neural Networks with Java, Heaton Research Inc., St. Louis.
Search in Google Scholar Back to article
7. Hernández-Alvarado R., García-Valdovinos L.G., Salgado-Jiménez T., Gómez-Espinosa A., Fonseca-Navarro F. (2016), Neural Network-Based Self-Tuning PID Control for Underwater Vehicles, Sensors, 16(9), 1429, https://doi.org/10.3390/s16091429.10.3390/s16091429503870727608018
Search in Google Scholar Back to article
8. https://stackoverflow.com/questions/10732027/fast-sigmoid-algorithm (08.02.2018)
Search in Google Scholar Back to article
9. Liu B., Hussami N., Shrikumar A., Shimko T., Bhate S., Longwell S., Montgomery S., Kundaje A. (2019), A multi-modal neural network for learning cis and trans regulation of stress response in yeast, arXiv:1908.09426.
Search in Google Scholar Back to article
10. Ma H., Lang S., Wellßow W. (2018) Fallback Solution for a Low-Voltage Regulator Control using Artificial Neural Networks, CIRED 2018 Ljubljana WS, http://dx.doi.org/10.34890/413.
Search in Google Scholar Back to article
11. MacLean D. (2019), A convolutional neural network for predicting transcriptional regulators of genes in Arabidopsis transcriptome data reveals classification based on positive regulatory interactions, bioRxiv 618926.10.1101/618926
Search in Google Scholar Back to article
12. Pirabakaran K., Becerra V.M. (2002), PID autotuning using neural networks and model reference adaptive control, IFAC Proceedings, 35, 451–456.10.3182/20020721-6-ES-1901.00728
Search in Google Scholar Back to article
13. Wica M., Witkowsk M., Szumiec A., Ziebura T. (2019), Weather forecasting system with the use of neural network and backpropagation algorithm, Proceedings of the International Conference on Data Engineering and Communication Technology, 2468, 37–41, DOI: 10.1007/978-981-10-1675-2_62.10.1007/978-981-10-1675-2_62
Search in Google Scholar Back to article
14. Zaman M.H.M., Marzuki M.M., Hannan M.A., Hussain A. (2018), Neural Network Based Prediction of Stable Equivalent Series Resistance in Voltage Regulator Characterization, Bulletin of Electrical Engineering and Informatics, 7, 134–142, DOI: 10.11591/eei.v7i1.857.10.11591/eei.v7i1.857
Search in Google Scholar Back to article
15. Zhang Z., Ma C., Zhu R. (2016), Self-Tuning Fully-Connected PID Neural Network System for Distributed Temperature Sensing and Control of Instrument with Multi-Modules, Sensors, 16(10):1709, DOI: 10.3390/s16101709.10.3390/s16101709508749727754436
Search in Google Scholar Back to article
16. Zhao D., Yang T., Ou H., Zhou H. (2018), Autopilot Design for Unmanned Surface Vehicle based on CNN and ACO, International Journal of Computers Communications & Control, 13(3), 429–439, DOI: 10.15837/ijccc.2018.3.3236.10.15837/ijccc.2018.3.3236
Search in Google Scholar Back to article

Predictive Neural Network in Multipurpose Self-Tuning Controller

Abstract

Paradigm

My account