Skip to Main Content
This paper presents the design, development and implementation of an adaptive Takagi-Sugeno fuzzy neural networks (A-FNN) controller suitable for real-time manipulator control applications. The unique feature of the A-FNN controller is that it has dynamic self-organizing structure, fast learning speed, good generalization and flexibility in learning. The proposed adaptive algorithm focuses on fast and efficiently optimizing weighting parameters of A-FNN controller. This approach of rapid prototyping is employed to implement the A-FNN controller with a view of controlling the prototype 2-axes pneumatic artificial muscle (PAM) manipulator in real time. The A-FNN controller was implemented through real-time Windows target run in real-time Matlab Simulinkreg. The performance of this novel proposed controller was found to be outperforming and it matches favorably with the simulation results. Keywords: pneumatic artificial muscle (PAM), highly nonlinear 2-axes PAM manipulator, adaptive fuzzy neural networks controller (A-FNN), real-time position control, trajectory tracking, rehabilitation device.