Neural Network Control Strategies Applied to a DC Motor with a Nonlinear Load
This paper investigates the use of neural networks in the design of control systems. For that, it was considered two different neural control structures, namely the stabilizing and the adaptive reference model control systems. The analysis tries to understand to which extent the introduction of neural networks improves a process control. The control systems are simulated and analyzed for several reference inputs with and without added noise in the sensor. The simulation results show the improved performance of the control systems with neural networks.
KeywordsNeural network Control Backpropagation Proportional-integral-derivative controller Stabilizing controller Reference adaptive controller
This work is supported by FEDER Funds through the “Programa Operacional Factores de Competitividade - COMPETE” program and by National Funds through FCT “Fundação para a Ciência e a Tecnologia”.
- 1.Haykin, S.: Neural Networks and Learning Machines, 3rd edn. Pearson (2009)Google Scholar
- 2.Hagan, M.T., Demuth, H.B.: Neural networks for control. In: American Control Conference, pp. 1642–1656. IEEE, San Diego (1999)Google Scholar
- 5.Gopal, M.: Digital Control and State Variable Methods: Conventional and Intelligent Control Systems, 3rd edn. McGraw-Hill, Singapore (2010)Google Scholar
- 6.Åström, K.J., Hägglund, T.: PID Controllers: Theory, Design, and Tuning. Instrument Society of America, North Carolina (1995)Google Scholar
- 7.Zhuang, M., Atherton, D.P.: Automatic tuning of optimum PID controllers. IEEE Proc D 140(3), 216–224 (1993)Google Scholar
- 8.Nguyen, D., Widrow, B.: Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN), pp. 21–26. Edward Brothers, San Diego (1990)Google Scholar