Ship domain identification using Fast and Accurate Online Self-organizing Parsimonious Fuzzy Neural Networks

In this paper, we propose a novel ship domain model identified by the Fast and Accurate Online Self-organizing Parsimonious Fuzzy Neural Network (FAOS-PFNN), which is an effective and powerful algorithm for nonlinear system identifications. The blocking area is introduced to be the reference model of ship domains to generate testing and checking databases for online modeling based on the FAOS-PFNN. The main features of our proposed method are as follows: (1) a mass of reasonable input-output data pairs possessing the complex nonlinear dynamics of ship domains could be randomly extracted; (2) based on the dependable databases, the intelligent ship domain model could be online identified by the FAOS-PFNN while training data pairs sequentially arrives; (3) dynamic and static parameters of own and target ships encountered could be reasonably and comprehensively incorporated into the resulting fuzzy neural network model of ship domains; and, (4) the shape and size of ship domains could be implemented by three independent fuzzy neural systems based on the FAOS-PFFN. It is shown that the identified ship domain model could capture well the key nonlinear properties of ship domains over a wide range. Simulation studies demonstrate the high performance of identification and generalization in the proposed intelligent ship domain model.