The fault-tolerant control problem of a hydraulic servo actuator in the presence of actuator faults is studied utilizing adaptive dynamic programming. This task is challenging because of unknown system dynamics, uncertain disturbances or unmeasurable system states of such highly nonlinear systems in real applications. The aim is to achieve asymptotic tracking and actuator faults compensation by minimizing some predefined performance index. The discrete-time algebraic Riccati equation is iteratively solved by the adaptive dynamic programming approach. For practical reasons, adaptive dynamic programming techniques and fault compensation are integrated to iteratively compute an approximated optimal fault-tolerant control using real-time input/output data without any a priori knowledge of the system dynamics and unmeasurable states. As a result, a fault-tolerant control of hydraulic servo actuator is then designed based on adaptive dynamic programming via output feedback. Also, the convergence analysis of a data-driven fault-tolerant control is theoretically shown as well. Finally, intensive simulation results are given to prove the validity and merits of the developed data-driven fault-tolerant control strategy.

In this paper, the mechanism for the fault estimation (FE) problem for a hydraulic servo actuator (HSA) with sensor faults is investigated. To deal with the design issues, we transformed the nonlinear model of HSA into a new coordinate system to estimate the sensor faults. In the new coordinate system, the Lipschitz conditions and system uncertainties are also considered. Then, we implement a sliding mode observer (SMO) approach to introduce the transformation scheme to make the system rational. The proposed fault estimation scheme essentially transforms the original system into two subsystems where the first one includes system uncertainties, but is free from sensor faults and the second one has sensor faults but without uncertainties. The effects of system uncertainties on the estimation errors of states and faults are minimized by integrating an $H_{\mathrm{\infty }}$ uncertainty attenuation level into the observer. The sufficient conditions for the state estimation error to be bounded and satisfy a prescribed $H_{\mathrm{\infty }}$ performance are derived and expressed as a linear matrix inequality (LMI) optimization problem. Finally, the numerical example with simulation results is provided to validate the practicability and efficacy of the developed control strategy.