Control of submarine operating in shallow waters: a neuro-adaptive based approach

Neuro-adaptive control algorithms for depth and pitch control of submarine operating in shallow waters are presented in this paper. The control scheme is based on two neural-network (NN) units which are shown to be effective in attenuating the reconstruction error and other lumped system uncertainties. Stable on-line weight-tuning algorithms are derived based on Lyapunov's stability theory. Variable heading speed and changing center of gravity are taken into consideration in control design. Analyses and simulations show that the proposed control is effective in dealing with external disturbances, system nonlinearities, uncertainties and parameter variations.