Anti-swing radial basis neuro-fuzzy linear quadratic regulator control of double link rotary pendulum

In this article, a radial basis neuro-fuzzy linear quadratic regulator controller is developed for the anti-swing control of a double link rotary pendulum system. The objective of this work is to study the radial basis neuro-fuzzy linear quadratic regulator controller and to compare it with a fuzzy linear quadratic regulator and the linear quadratic regulator controllers. In the proposed radial basis neuro-fuzzy linear quadratic regulator controllers, the positions and velocities of state variables multiplied by their linear quadratic regulator gains are trained using two radial basis neural networks architecture. The output of the two radial basis neural networks is used as the input variables of the fuzzy controller. The novel architecture of the radial basis neuro-fuzzy controller is developed in order to obtain better control performance than the classical adaptive neuro-fuzzy controller. To determine the control performance of the anti-swing controllers, different control parameters are computed. According to the comparative results, the anti-swing radial basis neuro-fuzzy linear quadratic regulator controller yields improved results than fuzzy linear quadratic regulator and linear quadratic regulator. Furthermore, the performance of the three controllers developed was compared based on robustness analysis under external force disturbance. The results obtained here indicate that the anti-swing radial basis neuro-fuzzy linear quadratic regulator controller product has better performance than other controllers in terms of vibration suppression ability.

Automated summary

In this study, a radial basis neuro-fuzzy linear quadratic regulator controller was developed to control the anti-swing of a double link rotary pendulum system, showing better performance than fuzzy linear quadratic regulator and linear quadratic regulator. The controller was trained using two radial basis neural networks architecture and the outputs were used as input variables for the fuzzy controller, resulting in improved control performance.