Adaptive Neural Network Saturated Control for MDF Continuous Hot Pressing Hydraulic System With Uncertainties

This paper presents a novel nonlinear control approach for a medium density fiberboard continuous hot pressing hydraulic system. Uncertainties, disturbances, and input saturation are explicitly taken into account. The proposed controller incorporates a smooth function by using a hyperbolic tangent function to substitute for the saturation nonlinearity in the system. Moreover, a novel backstepping-like slab thickness tracking controller is developed for a third-order cascade system within two steps. Taking advantages of radial basis function neural network (RBFNN) technique, a RBFNN-based reconstruction law is introduced to approximate the composite term consisting unknown function, disturbances, and saturation error. Lyapunov stability analysis shows that the designed control algorithm guarantees the asymptotic stability of the system with great robustness. Numerical simulation results are also exhibited to authenticate and validate the benefits of the proposed control scheme.