Online self-constructing fuzzy neural identification for ship motion dynamics based on MMG model

In this paper, an online self-constructing fuzzy neural identification for MMG ship motion model is clearly identified by using the promising Generalized Ellipsoidal Function Based Fuzzy Neural Network (GEBF-FNN) method. Nonlinear differential equations of MMG-type ship motion dynamics are used to establish the reference model implicating essential nonlinearities for GEBF-FNN based ship motion model (GEBF-FNN-SMM) identification. The GEBF-FNN-SMM starts without fuzzy rules and online recruits efficient fuzzy rules via rule node generation criteria and parameter estimation. The resultant GEBF-FNN-SMM reasonably captures essential dynamics since the checking process validates the prediction performance with high accuracy. Finally, in order to demonstrate that the GEBF-FNN-SMM scheme is effective, simulation studies are conducted on zig-zag maneuvers. Moreover, comprehensive comparisons are carefully presented. Simulation results indicate that the GEBF-FNN-SMM achieves promising performance in terms of approximation and prediction.