Rudder Roll Damping Autopilot Using Dual Extended Kalman Filter–Trained Neural Networks for Ships in Waves

Yuanyuan Wang , Hung Duc Nguyen

Journal of Marine Science and Application ›› 2019, Vol. 18 ›› Issue (4) : 510 -521.

PDF
Journal of Marine Science and Application ›› 2019, Vol. 18 ›› Issue (4) : 510 -521. DOI: 10.1007/s11804-019-00111-8
Research Article

Rudder Roll Damping Autopilot Using Dual Extended Kalman Filter–Trained Neural Networks for Ships in Waves

Author information +
History +
PDF

Abstract

The roll motions of ships advancing in heavy seas have severe impacts on the safety of crews, vessels, and cargoes; thus, it must be damped. This study presents the design of a rudder roll damping autopilot by utilizing the dual extended Kalman filter (DEKF)–trained radial basis function neural networks (RBFNN) for the surface vessels. The autopilot system constitutes the roll reduction controller and the yaw motion controller implemented in parallel. After analyzing the advantages of the DEKF-trained RBFNN control method theoretically, the ship’s nonlinear model with environmental disturbances was employed to verify the performance of the proposed stabilization system. Different sailing scenarios were conducted to investigate the motion responses of the ship in waves. The results demonstrate that the DEKF RBFNN–based control system is efficient and practical in reducing roll motions and following the path for the ship sailing in waves only through rudder actions.

Keywords

Rudder roll damping / Autopilot / Radial basis function / Neural networks / Dual extended Kalman filter training / Intelligent control / Path following / Advancing in waves

Cite this article

Download citation ▾
Yuanyuan Wang, Hung Duc Nguyen. Rudder Roll Damping Autopilot Using Dual Extended Kalman Filter–Trained Neural Networks for Ships in Waves. Journal of Marine Science and Application, 2019, 18(4): 510-521 DOI:10.1007/s11804-019-00111-8

登录浏览全文

4963

注册一个新账户 忘记密码

References

[1]

Alarçïn F. Internal model control using neural network for ship roll stabilization. J Mar Sci Technol, 2007, 15(2): 141-147

[2]

Broomhead DS, Lowe D (1988) Radial basis functions, multi-variable functional interpolation and adaptive networks. Royal Signals and Radar Establishment Malvern, London, 39

[3]

Choi J, Lima ACC, Haykin S. Kalman filter-trained recurrent neural equalizers for time-varying channels. IEEE Trans Commun, 2005, 53(3): 472-480

[4]

De JRJ, Yu W. Nonlinear system identification with recurrent neural networks and dead-zone Kalman filter algorithm. Neurocomputing, 2007, 70(13–15): 2460-2466

[5]

Fang MC, Luo JH. A combined control system with roll reduction and track keeping for the ship moving in waves. J Ship Res, 2006, 50(4): 344-354

[6]

Fang MC, Luo JH. On the track keeping and roll reduction of the ship in random waves using different sliding mode controllers. Ocean Eng, 2007, 34(3): 479-488

[7]

Fang MC, Zhuo YZ, Lee ZY. The application of the self-tuning neural network PID controller on the ship roll reduction in random waves. Ocean Eng, 2010, 37(7): 529-538

[8]

Fang MC, Lin YH, Wang BJ. Applying the PD controller on the roll reduction and track keeping for the ship advancing in waves. Ocean Eng, 2012, 54: 13-25

[9]

Fossen TI (1994) Guidance and control of ocean vehicles. Wiley, New York, 48, 302, 440

[10]

Fossen Thor I. Handbook of Marine Craft Hydrodynamics and Motion Control, 2011, Chichester, UK: John Wiley & Sons, Ltd

[11]

Ge SS, Hang CC, Tao Z. A direct method for robust adaptive nonlinear control with guaranteed transient performance. Syst Control Lett, 1999, 37(5): 275-284

[12]

Ge SS, Hang CC, Lee TH, Tao Z (2010) Stable adaptive neural network control. Springer, New York, 44

[13]

Goh SL, Mandic DP. An augmented extended Kalman filter algorithm for complex-valued recurrent neural networks. Neural Comput, 2007, 19(4): 1039-1055

[14]

Ko CN, Lee CM. Short-term load forecasting using SVR (support vector regression)-based radial basis function neural network with dual extended Kalman filter. Energy, 2013, 49: 413-422

[15]

Li H, Guo C, Li X (2010) Ship roll stabilization using supervision control based on inverse model wavelet neural network. Proceedings of the 8th World Congress on Intelligent Control and Automation, Jinan, China, 4829–4833. https://doi.org/10.1109/WCICA.2010.5554721

[16]

Liu J (2013) Radial basis function (RBF) neural network control for mechanical systems: design, analysis and Matlab simulation. Springer, New York, 58–60

[17]

McGookin EW, Murray-Smith DJ, Li Y, Fossen TI. Ship steering control system optimisation using genetic algorithms. Control Eng Pract, 2000, 8(4): 429-443

[18]

Medagam PV, Pourboghrat, F (2009) Optimal control of nonlinear systems using RBF neural network and adaptive extended Kalman filter. Proceedings of the American Control Conference 2009, Hyatt Regency Riverfront, USA, 355–360. https://doi.org/10.1109/ACC.2009.5160105

[19]

Nejim S (2000) Rudder roll damping system for ships using fuzzy logic control. Proceedings of the OCEANS 2000 MTS/IEEE Conference and Exhibition, Providence, USA, 1137–1143. https://doi.org/10.1109/OCEANS.2000.881755

[20]

Nouri K, Dhaouadi R, Braiek NB. Adaptive control of a nonlinear dc motor drive using recurrent neural networks. Appl Soft Comput, 2008, 8(1): 371-382

[21]

Oda H, Ohtsu K, Sato H, Kanehiro K (2008) Designing advanced rudder roll stabilization system. Proceedings of the 7th JFPS International Symposium on Fluid Power, Toyama, Japan, 169–174

[22]

Perez T, Blanke M. Ship roll damping control. Annu Rev Control, 2012, 36(1): 129-147

[23]

Sanchez Edgar N., Alanís Alma Y., Loukianov Alexander G. Discrete-Time High Order Neural Control, 2008, Berlin, Heidelberg: Springer Berlin Heidelberg

[24]

Sun B, Zhu D, Yang SX. A bioinspired filtered backstepping tracking control of 7000-m manned submarine vehicle. IEEE Trans Ind Electron, 2014, 61(7): 3682-3693

[25]

Treakle TW, Mook DT, Liapis SI, Nayfeh AH. A time-domain method to evaluate the use of moving weights to reduce the roll motion of a ship. Ocean Eng, 2000, 27(12): 1321-1343

[26]

Van AJ, Van NLH (1978) Optimum steering of ships with an adaptive autopilot. Proceedings of the Fifth Ship Control Systems Symposium, Annapolis, USA, 8–17

[27]

Wang X, Huang Y. Convergence study in extended Kalman filter-based training of recurrent neural networks. IEEE Trans Neural Netw, 2011, 22(4): 588-600

[28]

Wang Y, Chai S, Khan F, Nguyen HD (2015) Radial basis function neural network based rudder roll stabilization for ship sailing in waves. Proceedings of the 5th Australian Control Conference, Gold coast, Australia, 256–261

[29]

Wang Y, Chai S, Khan F, Nguyen HD. Unscented Kalman filter trained neural networks based rudder roll stabilization system for ship in waves. Appl Ocean Res, 2017, 68: 26-38

[30]

Wang Y, Chai S, Nguyen HD (2017b) Modelling of a surface vessel from free running test using low cost sensors. Proceedings of the 3rd International Conference on Control, Automation and Robotics, Nagoya, Japan, 299–303. https://doi.org/10.1109/ICCAR.2017.7942707

[31]

Zhang XK, Jin YC, Yang C, Zhang L (2006) A kind of robust rudder roll-damping system. Paper presented at the Systems and Control in Aerospace and Astronautics. Proceedings of the 1st International Symposium on Systems and Control in Aerospace and Astronautics, Harbin, China, 1151–1154. https://doi.org/10.1109/ISSCAA.2006.1627570

[32]

Zhao J, Zhu X, Wang W, Liu Y. Extended Kalman filter-based Elman networks for industrial time series prediction with GPU acceleration. Neurocomputing, 2013, 118: 215-224

AI Summary AI Mindmap
PDF

145

Accesses

0

Citation

Detail

Sections
Recommended

AI思维导图

/