The hydrodynamic and control performances of a self-stable controllable underwater towed vehicle developed by South China University of Technology under different depth trajectory control operations are analyzed by means of a proposed hydrodynamic numerical model. The model is established based on LMBP algorithm of neural network theory. Training samples for the neural network model are provided from the experimental data of the vehicle prototype towing experiments conducted in a large-scale ship model towing tank under the manipulation of a depressing wing installed in the vehicle. After the LMBP model is established, a depth trajectory control system for the towed vehicle is designed in order to accomplish vehicle trajectory control. This system is mainly composed of tow parts: a neural network identifier based on genetic algorithm and a fuzzy neural network controller based on genetic algorithm simulated annealing. Hydrodynamic performances of the vehicle under various control operations can then be numerically simulated with the proposed LMBP model and the depth trajectory control system of the towed vehicle. In numerical simulation of trajectory control to the towed vehicle, deflection of the vehicle’s depressing wing is adjusted at every time step by the proposed control system to match the trajectory of the vehicle with a pre-designated one. The value of the deflection is taken as input parameter for the LMBP neural network model, trajectory and attitude behavior of the towed vehicle under the control manipulations can then be predicted by the LMBP model.

This content is only available via PDF.
You do not currently have access to this content.