SOSMC-Based Neural Adaptive Control for Pneumatic Artificial

This Simulink model demonstrates a second-order sliding mode controller enhanced with a neural network for precise tracking and robustness i

This project presents a Simulink implementation of a hybrid control strategy combining a Second-Order Sliding Mode Controller (SOSMC) with a Neural Network compensator to control Pneumatic Artificial Muscles (PAMs).

The controller design aims to enhance trajectory tracking performance while preserving robustness against modeling uncertainties and external disturbances. The neural network component estimates unknown dynamics online, reducing the tracking error and improving system stability.

Key Features:

- Simulink model using SOSMC for high robustness

- Online neural network adaptation for uncertainty compensation

- Designed for nonlinear PAM actuators

- Demonstrates improved tracking performance over conventional methods

This model is useful for researchers and developers working on bio-inspired actuators, robotics, and intelligent nonlinear control systems.