Abstract
To represent the time-varying dynamics of nonlinear systems, a variable multidimensional fuzzy model is online constructed by the Delaunay triangulation method. Construction and adjustment of model is based on the learning of samples in a real-time updated sliding data window (SDW). The proposed fuzzy model is combined with harmonic method and the resulted modular model is implemented for real-time tidal level prediction where the harmonic method is used to represent the periodic changes of tidal level caused by celestial movement and the variable fuzzy model is used to give predictions caused by water temperature and air pressure. The measured tidal data at the port of Honolulu is implemented for the online tidal level prediction and the results demonstrate the feasibility and effectiveness of the proposed variable multidimensional fuzzy model and the modular prediction method.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
