As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Time delays in network transmission have been a concern in teleoperation robot. In order to solve the problem, this paper proposes a delay prediction compensation scheme based on Wolf Pack Algorithm (WPA)-Back Propagation (BP) neural network model combined with generalized predictive control algorithm. The WPA has optimized the initial weights and threshold of the BP neural network and has improved the convergence speed and prediction accuracy of the BP neural network so that the WPA-BP model can accurately predict the time delay of a network. The time delay obtained by the model was combined with the improved generalized predictive control algorithm to calculate control increments for the design of a controller. The improved generalized predictive control algorithm can directly identify controller parameters without having to solve the Diophantine equation, saving time on online computation. The simulation results show that the solution can well compensate the time delay of network transmission ensuring a real-time and stable system.