| This research work addresses the problem of position control of an inverted pendulum system. In this work an 'Adaptive Neuro-Fuzzy Inference System' is used to implement position control. Fuzzy logic and neural networks are complementary technologies. Neural networks extract information from system to be learned or controlled, while fuzzy logic techniques most often use verbal and linguistic information from experts. A promising approach to obtaining the benefits of both fuzzy system and neural networks and solving their respective problems is to combine them into an integrated system. These systems can learn and adapt. They learn new associations, new patterns, and new functional dependencies. We may characterize the efforts at merging these two technologies into the following categories: Neural fuzzy system, Fuzzy neural networks, and Fuzzy-neural hybrid systems. As a part of the research work a ANFIS controller was designed for the "Inverted Pendulum System". The simulation results and actual implementation of this Adaptive Neuro Fuzzy Controller on a real-time system are shown. A PVLQR Controller was designed and its results are also shown. These results proved to be satisfactory, and the performance of the proposed design was thus validated. |
