Echo State Network-Based Internal Model Control for Pneumatic Muscle System

Pneumatic muscle (PM) has strong time varying characteristic. The complex nonlinear dynamics of PM system poses problems in achieving accurate modeling and control. To solve these challenges, we propose an echo state network (ESN)-based internal model control (IMC) for PM system in this paper. Here, ESN is employed for identifying the plant model and constructing controller. Recursive least squares (RLS) is used for the online update of ESN. The ESN-based IMC fully embodies the virtues of ESN and IMC. It can build high accurate plant model without detailed model information, as well as attain strong robustness by online self-tuning of controller and internal model. Experiment demonstrates the effectiveness of the proposed control algorithm. The results show that ESNBIMC achieves satisfactory tracking performance.