Adaptive Neuro-fuzzy Inference System Design of Inverted Pendulum System on an Inclined Rail

The basic aim of our work was to design appropriate controller to control the angle of the pendulum and the position of the cart in order to stabilize the conventional inverted pendulum system on an inclined rail. We improved the adaptive neuro-fuzzy inference system (ANFIS) on the basis of conventional fuzzy controller. A neuro-fuzzy hybrid approach was used to design the fuzzy rule base on a basis of building a Sugeno fuzzy model in order to swing a pendulum attached to a cart from an initial downwards position to an upright position and maintain that state. The adaptive neuro-fuzzy logic controller was designed in the Matlab-Simulink environment. By training and checking of effective data, the results proved that the adaptive neuro-fuzzy controller had good performance about stability in the real-time control of the inverted pendulum on an inclined rail.