Implementation of a Neuro-Fuzzy PD Controller for Position Control


Neural network simulations appear to be a recent development. However, this field was established before the advent of computers, and has survived at least one major setback and several eras. The history of neural networks can be traced back to the work of trying to model the neuron. Neural networks have the natural ability of learning like that of a human brain. This paper focuses on the implementation of Neural network based fuzzy PD controller for position control of a DC motor. Firstly, we have used the fuzzy logic controller of Mamdani type inferencing. The training data is fed to the Neural network based structure (connectionist structure or ANFIS structure). That training data is considered as the expert data. The proposed ANFIS structure uses the Sugeno type inferencing. In both of the fuzzy and Neuro-fuzzy PD controller has the rule base. It is verified that the DC motor characteristics is better using the ANFIS controller with lesser number of rules than that of the fuzzy logic controller. Keyword: ANFIS controller, connectionist model, fuzzy PD controller, neuro-fuzzy PD controller, DC motor position control.

8 Figures and Tables

Cite this paper

@inproceedings{Chakraborty2014ImplementationOA, title={Implementation of a Neuro-Fuzzy PD Controller for Position Control}, author={Sudipta Chakraborty and Saunak Bhattacharya and Debabrata Raha}, year={2014} }