In order to precisely control ships, her engines and so on, it is very important to previously estimate the behaviors (output signals) of these objectives when the manipulation action (input signal) was given to the relevant objects. In other words, it is necessary to have some models which can simulate the behaviors, that is, the characteristics, of the object systems. Usual models such as a mathematical one, or others, however, seem to be unsuitable in the case of the field of ship engineering because the characteristics are complex, and sometimes have the characteristics of time-varying as well as nonlinear dynamic. New techniques such as neural network (NN) is said to be superior to simulate such complex characteristics. Therefore, the ability of NN, especially, the ability of adaptiveness for time-varying characteristics was investigated by using frequency response method. The results have shown that the ability of NN is enouth against the relatively slow time-varying object systems in the field of ship engineering.
Applications of neural network for ships
Einsatz von neuronalen Netzen auf Schiffen
1995
6 Seiten, 11 Bilder, 3 Quellen
Conference paper
English
Development of a neural network-based controller for ships
Tema Archive | 2010
|Dynamic Positioning of Ships Using a Planned Neural Network Controller
Online Contents | 1996
|System Identification for Nonlinear Maneuvering of Ships Using Neural Network
Online Contents | 2010
|A Neural Network Controller for Optimal Guidance of Surface Ships
British Library Conference Proceedings | 1993
|Neural network-based fuel consumption estimation for container ships in Korea
Taylor & Francis Verlag | 2020
|