In this paper a neurofuzzy control structure is presented and used for controlling the two-link robot manipulator. A neurofuzzy networks are constructed for both the controller and for identification model of robot manipulator. The performance of the proposed structure is studied by simulation. Different operating conditions are considered. Results of simulation show good performance for the proposed control structure.
This article emphasizes on a strategy to design a Super Twisting Sliding Mode Control (STSMC) method. The proposed controller depends on the device of Field Programmable Gate Array (FPGA) for controlling the trajectory of robot manipulator. The gains of the suggested controller are optimized using Chaotic Particle Swarm Optimization (PSO) in MATLAB toolbox software and Simulink environment. Since the control systems speed has an influence on their stability requirements and performance, (FPGA) device is taken in consideration. The proposed control method based on FPGA is implemented using Xilinx block sets in the Simulink. Integrated Software Environment (ISE 14.7) and System Generator are employed to create the file of Bitstream which can be downloaded in the device of FPGA. The results show that the designed controller based of on the FPGA by using System Generator is completely verified the effectiveness of controlling the path tracking of the manipulator and high speed. Simulation results explain that the percentage improvement in the Means Square Error (MSEs) of using the STSMC based FPGA and tuned via Chaotic PSO when compared with the same proposed controller tuned with classical PSO are 17.32 % and 13.98 % for two different cases of trajectories respectively.
In this paper, high tracking performance control structure for rigid robot manipulator is proposed. PD-like Sugano type fuzzy system is used as a main controller, while fuzzy-neural network (FNN) is used as a compensator for uncertainties by minimizing suitable function. The output of FNN is added to the reference trajectories to modify input error space, so that the system robust to any change in system parameters. The proposed structure is simulated and compared with computed torque controller. The simulation study has showed the validity of our structure, also showed its superiority to computed torque controller.
A composite PD and sliding mode neural network (NN)-based adaptive controller, for robotic manipulator trajectory tracking, is presented in this paper. The designed neural networks are exploited to approximate the robotics dynamics nonlinearities, and compensate its effect and this will enhance the performance of the filtered error based PD and sliding mode controller. Lyapunov theorem has been used to prove the stability of the system and the tracking error boundedness. The augmented Lyapunov function is used to derive the NN weights learning law. To reduce the effect of breaching the NN learning law excitation condition due to external disturbances and measurement noise; a modified learning law is suggested based on e-modification algorithm. The controller effectiveness is demonstrated through computer simulation of cylindrical robot manipulator.