Nonlinear innovation identification of ship response model via the hyperbolic tangent function

This research is concerned with the problem of parameter identification for ship response model. A novel nonlinear innovation–based algorithm is proposed by use of the hyperbolic tangent function and the stochastic gradient algorithm. In order to demonstrate the validity of the algorithm, two identification experiments are adopted by the “Galaxy” ship and the “Yupeng” ship. Furthermore, the comparison experiment is illustrated to verify the effectiveness of the proposed algorithm, including the least square algorithm, the traditional stochastic gradient algorithm and the improved nonlinear innovation–based stochastic gradient algorithm. The identification results indicate that the improved stochastic gradient algorithm is with higher accuracy by 95.2% than the original algorithm and 11.75% than the least square algorithm. In addition, the proposed algorithm is with advantages of fast speed and high accuracy of identification. That can be extended to other parameter identification systems with the limited test data.

[1]  Cheng Wang,et al.  A Recursive Least Squares Algorithm for Pseudo-Linear ARMA Systems Using the Auxiliary Model and the Filtering Technique , 2016, Circuits Syst. Signal Process..

[2]  Elías Revestido Herrero,et al.  Improving parameter estimation efficiency of a non linear manoeuvring model of an underwater vehicle based on model basin data , 2018, Applied Ocean Research.

[3]  Xin Yang,et al.  Parameter identification of unmanned marine vehicle manoeuvring model based on extended Kalman filter and support vector machine , 2019 .

[4]  Chris Manzie,et al.  Fast extremum seeking on Hammerstein plants: A model-based approach , 2015, Autom..

[5]  Ajit Achuthan,et al.  Recursive wind speed forecasting based on Hammerstein Auto-Regressive model , 2015 .

[6]  Tieshan Li,et al.  Multi-Innovation Gradient Iterative Locally Weighted Learning Identification for A Nonlinear Ship Maneuvering System , 2018 .

[7]  Guo-qing Zhang,et al.  Design of Ship Course-Keeping Autopilot using a Sine Function-Based Nonlinear Feedback Technique , 2015, Journal of Navigation.

[8]  Thomas B. Schön,et al.  System identification of nonlinear state-space models , 2011, Autom..

[9]  Fujimoto Kenji,et al.  System identification of nonlinear state-space models based on variational Bayes: how to cope with multimodality of variational posterior distributions , 2017 .

[10]  Alon Kuperman,et al.  Recursive-Least-Squares-Based Real-Time Estimation of Supercapacitor Parameters , 2016, IEEE Transactions on Energy Conversion.

[11]  Santosh Kumar Singh,et al.  Robust estimation of power system harmonics using a hybrid firefly based recursive least square algorithm , 2016 .

[12]  Weidong Zhang,et al.  Robust neural event-triggered control for dynamic positioning ships with actuator faults , 2020 .

[13]  Yan Peng,et al.  Adaptive Sliding Mode Fault-Tolerant Fuzzy Tracking Control With Application to Unmanned Marine Vehicles , 2021, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[14]  Qiang Zhang,et al.  Nonlinear Improved Concise Backstepping Control of Course Keeping for Ships , 2019, IEEE Access.

[15]  Yang Jiaben.  Convergence analysis of stochastic gradient algorithms , 1999 .

[16]  Qiang Zhang,et al.  Linear reduction of backstepping algorithm based on nonlinear decoration for ship course-keeping control system , 2018 .

[17]  Xianku Zhang,et al.  Improved composite learning path-following control for the underactuated cable-laying ship via the double layers logical guidance , 2020 .