CMAC based controller for hydro-mechanical systems
Linping Chan, Samuel F. Asokanthan · 2001
A cerebellar model articulation controller (CMAC) neural network based scheme for controlling a nonlinear mechanical system that incorporates hydraulic actuator dynamics is proposed. This control scheme is shown to perform well in the presence of nonlinearities due to fluid flow, oil compressibility, leakages and static friction. Further, the algorithms developed are shown to effectively track different trajectories and reject disturbances while compensating uncertain dynamics present in the hydro-mechanical system. This control scheme also shows that it can cope with complexities associated with a highly nonlinear hydraulic system, which is more desirable than conventional control schemes that are typically designed using linearised models.