ABSTRACT
The performance of the robotic manipulator is negatively impacted by outside disturbances and uncertain parameters. The system's variables are also highly coupled, complex, and nonlinear, indicating that it is a multi-input, multi-output system. Therefore, it is necessary to develop a controller that can control the variables in the system in order to handle these complications. This work proposes six control structures based on neural networks (NNs) with proportional integral derivative (PID) and fractional-order PID (FOPID) controllers to operate a 2-link rigid robot manipulator (2-LRRM) for trajectory tracking. These are named as set-point-weighted PID (W-PID), set-point weighted FOPID (W-FOPID), recurrent neural network (RNN)-like PID (RNNPID), RNN-like FOPID (RNN-FOPID), NN+PID, and NN+FOPID controllers. The zebra optimization algorithm (ZOA) was used to adjust the parameters of the proposed controllers while reducing the integral-time-square error (ITSE). A new objective function was proposed for tuning to generate controllers with minimal chattering in the control signal. After implementing the proposed controller designs, a comparative robustness study was conducted among these controllers by altering the initial conditions, disturbances, and model uncertainties. The simulation results demonstrate that the NN+FOPID controller has the best trajectory tracking performance with the minimum ITSE and best robustness against changes in the initial states, external disturbances, and parameter uncertainties compared to the other controllers.
ABSTRACT
Robotic manipulators are nonlinear systems, multi-input multi-output, highly coupled and complicated whose performance is negatively impacted by external disturbances and parameter un-certainties. Therefore, the controllers designed for such systems must be capable of managing their complexity. The main aim of this study is to tackle the trajectory tracking issue of the three-Link Rigid Robot Manipulator (3-LRRM) based on designing three control structures using a combi-nation Neural Network (NN) with Proportional, Integral and Derivative (PID) actions named Neural Controller Like PIPD (NN-PIPD) controller, Neural Network plus PID (NN + PID) controller NN + PID controller and Elman Neural Network Like PID (ELNN-PID) controller. The parameters of the proposed controllers are adjusted utilizing the Coot Optimization Algorithm (COOA) in order to reduce the Integral Time Square Error (ITSE). A novel objective function for tuning process to produce a controller with minimum value of the chattering in the control signal is proposed. The performance of the proposed controllers is evaluated in terms of disturbance rejection, model uncertainty, fluctuating initial conditions and reference trajectory tracking. According to the simulation results proved that the suggested NN-PIPD controller outperforms all other proposed controller structures for tracking performance, stability, and robustness. As a result of the com-parison analysis the optimal controller was considered to be an NN-PIPD controller for tracking trajectory, rejecting disturbances, and parameter variation with minimizing ITSE of 0.001777.