Disturbance Rejection-Guarded Learning for Vibration Suppression of Two-Inertia Systems

Fan Zhang, Jinfeng Chen, Yu Hu, Zhiqiang Gao, Ge Lv, Qin Lin

Abstract: Model uncertainty presents significant challenges in vibration suppression of multi-inertia systems, which often rely on inaccurate nominal mathematical models due to system identification errors or unmodeled dynamics. An observer, such as an extended state observer (ESO), can estimate the discrepancy between the inaccurate nominal model and the true model, thus improving control performance via disturbance rejection. Conventional observer design is memoryless; once the estimated disturbance is obtained and sent to the controller, the data is discarded. In this paper, we propose a learning-enabled ESO (L-ESO) with seamless integration of ESO and machine learning. The machine learning model attempts to predict the disturbance, using prior information to help the observer achieve faster convergence in disturbance estimation. Additionally, any imperfections in the machine learning model can be compensated for by the ESO, providing an assurance layer. We validated the effectiveness of this novel learning-for-control paradigm through simulation and physical tests on two-inertial motion control systems used for vibration studies. Video: https://youtu.be/OUerJ4w_esk