Abstract
Robotics have been substituting humans increasingly and effectively to operate repeated, dangerous, heavy, complicated works in human life, production industry, and discovery missions. This work designs a Neural Integral Non-singular Fast Terminal Synchronous Sliding Mode Control (NINFTSSMC) approach for 3-DOF parallel robotic manipulators with uncertain dynamics, using synchronous nonlinear sliding surface, where this sliding surface is formed through the integration of the Synchronization Control (SC) and the Integral Non-singular Fast Terminal Sliding Mode Control (INFTSMC). Accordingly, position errors and synchronization errors quickly converge to the sliding surface at the same time. Next, a Feed-Forward Neural Network (FNN) is applied to estimate uncertain dynamics, whose novelty, compared to a classic FNN, is that they utilize a Non-singular Fast Terminal Sliding Mode (NFTSM) error filter to replace a classic error filter. Thanks to this procedure, the lumped uncertain dynamics are compensated more quickly and more accurately, thus, the malfunction in the reaching phase of state variables approaching the sliding surface is handled thoroughly. Finally, the control approach is designed for a robotic system to achieve the prescribed performance, obtaining rapid error convergence, robustness with uncertain dynamics, minimum chattering, synchronization, and high precision. The stability of the control loop is secured according to the Lyapunov theory. To test the robustness and confirm the effectiveness of the suggested controller for a 3-DOF parallel manipulator, computer simulations and performance comparisons are conducted.
Highlights
Parallel robotic manipulators have become increasingly popular and play an important role in industrial production systems, applied science fields, and the broader research community
This work proposed NINFTSSMC for 3-DOF parallel robotic manipulators with uncertain dynamics using synchronous nonlinear sliding surface, where this sliding surface is formed based on the integration of Synchronization Control (SC) and Integral Non-singular Fast Terminal Sliding Mode Control (INFTSMC)
The FeedForward Neural Network (FNN) is applied to estimate uncertain dynamics, in which the novelty of the proposed approach compared to a classic FNN is that the proposed Neural Network (NN) utilizes the Non-singular Fast Terminal Sliding Mode (NFTSM) error filter replacing for a classic error filter
Summary
Parallel robotic manipulators have become increasingly popular and play an important role in industrial production systems, applied science fields, and the broader research community. It raises a new drawback to applying in real applications, since the large size NNs has a complex structure and a large calculation requirement In another solution [64], a controller has been developed for 2-DOF parallel robotic manipulators where disturbances and uncertainties are compensated by using a combination of the FNN with an error estimator. The central motivation in our paper is to develop an enhanced path tracking controller for 3-DOF parallel robot manipulators with uncertain components, while offering the following benefits: (1) the designed method contains the benefits of the INFTSMC, SC, and FNN regarding faster error convergence, a faster transient response, approximation. The lumped uncertain dynamics are compensated more quickly and more accurately, the malfunction in the reaching phase of state variables approaching the sliding surface is handled thoroughly
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
