Abstract

Ship motion mathematical models are the foundation of ship motion control. Ship motion control requires not only applicable ship motion models, but also the accurate identification of model parameters. In control state, the navigating ship motion system in this paper has strong nonlinear characteristics. In addition, ship motion performance witnesses changes due to cargo handling, oil and water consumption possesses significant time-variant characteristics. As a result, this paper proposes an online identification algorithm of ship motion based on neural network. The research object is a separation ship maneuvering motion mathematical model (MMG) which is a set of nonlinear differential equations. The set of nonlinear differential equations and ship plane motion model under the inertial coordinate system are paralleled and transformed into a state-space equation. Through a series of free-running tests of KCS ship model, this paper takes the real-timely collected input and output variables of ship motion mathematical models as the input data and learning samples of neural network online identification algorithm and identified parameters in the state-space equation online. Experiment results show that free-running tests and neural network online identification algorithm can effectively and accurately identify the parameters of nonlinear ship motion mathematical models.

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

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.