What question did this study set out to answer?

To develop and analyze a discrete control algorithm for the Stewart platform that effectively suppresses time-varying disturbances.

April 10, 2026InformaticsOpen Access

A Discrete-Form Double-Integration-Enhanced Recurrent Neural Network for Stewart Platform Control with Time-Varying Disturbance Suppression

View Full Paper

Ask AI

Bookmark

Authors

Algorithm improves disturbance suppression in Stewart platform control, highlighting enhanced trajectory tracking accuracy.

To develop and analyze a discrete control algorithm for the Stewart platform that effectively suppresses time-varying disturbances.
Developed a continuous-form double-integration-enhanced recurrent neural network (CF-DIE-RNN).
Discretized the CF-DIE-RNN to create a discrete-form double-integration-enhanced RNN (DF-DIE-RNN).
Applied a four-step discretization formula and one-step forward difference, using Taylor expansion.
Conducted theoretical analysis to establish convergence properties and steady-state performance.
The DF-DIE-RNN showed superior performance in suppressing discrete quadratic time-varying disturbances.
Achieved more accurate trajectory tracking compared to existing discrete-form RNN algorithms.
Numerical and simulation experiments confirmed the effectiveness of the algorithm.

Ma et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark