Adaptive Neural Network Control for Full‐State Constrained Hydraulic Systems Without Feasibility Conditions

In this study, the accurate control is studied of hydraulic systems subject to full‐state constraints and complex uncertainties, including the unmeasured unmodeled dynamics, time‐varying disturbances, and parametric uncertainties. The original state‐constrained hydraulic system is transformed into an equivalent unconstrained augmented system by the system transformation technique, eliminating the dependence on feasibility conditions (FCs) in the barrier Lyapunov function (BLF)‐based state constraint control algorithm. A disturbance observer is constructed to estimate and compensate for all unmeasured time‐varying disturbances, while adaptive control and neural network (NN) are synergistically integrated to handle unmeasured parametric uncertainties and unmodeled dynamics, respectively. Subsequently, an adaptive NN controller is developed by integrating backstepping technology and command filters to avoid computational complexity caused by uncomputable items and prevent differential explosion. Through Lyapunov stability analysis, the stability of the closed‐loop system is proven. The experimental results verified the effectiveness of the proposed method, proving that this method not only has good tracking performance, but also strictly adheres to state constraints and has significant robustness against various uncertainties.