Tuning of extended state observer with neural network-based control performance assessment
This work addresses tuning challenges for control engineers in observer-based systems, offering an incremental improvement over existing methods.
The paper tackles the problem of tuning extended state observer (ESO) parameters in robust control systems by proposing a neural network-based procedure that prioritizes quality criteria like control and observation errors, delivering near-optimal gains within seconds from a single closed-loop experiment.
The extended state observer (ESO) is an inherent element of robust observer-based control systems that allows estimating the impact of disturbance on system dynamics. Proper tuning of ESO parameters is necessary to ensure a good quality of estimated quantities and impacts the overall performance of the robust control structure. In this paper, we propose a neural network (NN) based tuning procedure that allows the user to prioritize between selected quality criteria such as the control and observation errors and the specified features of the control signal. The designed NN provides an accurate assessment of the control system performance and returns a set of ESO parameters that delivers a near-optimal solution to the user-defined cost function. The proposed tuning procedure, using an estimated state from the single closed-loop experiment produces near-optimal ESO gains within seconds.