Identification and control of marine vehicles using artificial intelligence techniques

In this thesis a novel approach to the identification of marine craft dynamics using neural networks is described. From a literature review it emerged that augmented controllers, in which a conventional controller is augmenter with neural network, which accounts for unmodelled phenomena and/or unmodelled operation regions, are most likely to be used for future neural controller architectures. Such controllers are appealing, as neural networks can be used to identify the unknown phenomena with a high accuracy. However, at th ecurrent time, neural networks are predominantlz used to identify unknown phenomena in a lumped way. As a result, it is difficult, or even impossible, to use these neural networks in a conventional controller. A novel approach, involving the use of several neural networks for the identification of individual model parameters, is presented. The new approach is tested, first in simulations and consecutively in an experiment, and found to offer increased accuracy compared to a benchmark least squares identification method. Additionally, it is demonstrated that the obtained model can easily be reformulated in order to be used in a control scheme. In this control scheme, the learning capabilities of neural networks and the robustness and guaranteed stability of more conventional control schemes, can be combined, thus obtaining the advantages of both approaches.