Tracking performance control of a cable communicated underwater vehicle using adaptive neural network controllers

In this paper, design, dynamic modeling and control of the fabricated underwater remotely operated vehicle have been considered. Dynamic model of the vehicle is presented for four degrees of freedom and an accurate representation of the dynamic effects of the towed cable is used for dynamic simulation and control design. A nonlinear adaptive neural network controller is developed and simulated. Multi-layer and radial basis function neural networks are used for designing the adaptive controllers. Finally, the performance of the vehicle with neural network controllers is compared with a PD controller. The significant improvement is observed for tracking performance of the vehicle in all controllable degrees of freedom. Also, the simulation illustrated the robustness of controllers for the relative large distributions of the communication cable.