A Water Flow Control with OnLine Neurofuzzy Controller using a Dynamic Learning Rate

• Hugo Gomes UFMG
• Carolina Ferreira UFMG
• Everthon Oliveira UFMG
• Agnaldo Reis UFOP
• Walmir Caminhas UFMG

DOI: https://doi.org/10.5753/eniac.2018.4473

Resumo

This paper describes an ONFC (OnLine Neurofuzzy Controller) application with a dynamic learning rate to control the water flow of a real plant. A revision of ONFC is presented and the ONFCDw version is used, which has an action that minimizes the increase in the difference between the controller weights. The dynamic learning rate used to update the controller weights is described and the results of experiments performed in a water flow control process are presented, comparing the results with the PID controller used in the process.

Referências

Caminhas, W., Pereira, G., Tavares, H., and Gomide, F. (1998). Identificação de sistemas dinâmicos: Abordagem baseada em neurônio nebuloso. Anais do V Simpósio Brasileiro de Redes Neurais (SBRN 98), Belo Horizonte–MG, pages 105–110.

Carvalho, M. A. (2010). Controlador neurofuzzy com aprendizado on-line: Teoria e aplicação na indústria de petróleo. Master’s thesis, Universidade Federal de Minas Gerais.

dos Santos, S. R., Amaral, J. L., and Amaral, J. F. M. (2016). Adaptive intelligent systems applied to two-wheeled robot. In Evolving and Adaptive Intelligent Systems (EAIS), 2016 IEEE Conference on, pages 146–150. IEEE.

Ferreira, C. Z. M. (2017). Controlador NeuroFuzzy Online: Estudo Comparativo com PID em Simulação e Aplicação Real. Monografia de Graduação. Universidade Federal de Minas Gerais.

Goodwin, G., Ramadge, P., and Caines, P. (1980). Discrete-time multivariable adaptive control. IEEE Transactions on Automatic Control, 25(3):449–456.

Gouvêa, M. R. (2005). Controle Neurofuzzy de Motor de Indução com Estimação de Parâmetros e Fluxo de Estator. PhD thesis, Universidade Federal de Minas Gerais.

Jang, J.-S. R., Sun, C.-T., and Mizutani, E. (1997). Neuro-Fuzzy and Soft Computing. Prentice Hall.

Ogata, K. (2003). Engenharia de Controle Moderno. Pearson Prentice Hall.

Pires, A. V. (2007). Controladores baseados em técnicas de inteligência computacional: Análise, projeto e aplicações. Master’s thesis, Universidade Federal de Minas Gerais.

Precup, R.-E. and Hellendoorn, H. (2011). A survey on industrial applications of fuzzy control. Computers in Industry, 62(3):213–226.

Yamakawa, T., Uchino, E., and Miki, T. (1992). A neo fuzzy neuron and its application to system identification and prediction of the system behaviour. Proceedings of the Second International Conference on Fuzzy Logic and Neural Networks, (2):477–483.