Physics-Informed Disturbance Estimation and Nonlinear Controller Design for a Multi-Axis Gimbal System

The increasing demand for target tracking, environmental surveys, surveillance and mapping requires multi-axis gimbal systems with high tracking stabilization performance. In this study, a new torque estimation structure is proposed to compute the complex disturbances negatively affecting performance of system. Two different control strategies based on Active Disturbance Rejection Control (ADRC) Estimated Torque Model are implemented two-axis first strategy, purpose improve robustness, adaptability accuracy tuning effort ADRC reduced by integrating Neural Network (NN) disturbance compensator (NN assisted ADRC). second NN replaced an (ETM ADRC), whose inputs come from plant outputs. simulation results show that, both ETM structures decrease errors. However, improvements achieved physics-informed neural network-based estimator more significant.