International Journal of Naval Architecture and Ocean Engineering

The Society of Naval Architects of Korea (대한조선학회)
권호 표지
DOI QR코드

DOI QR Code

Experimental and numerical study of autopilot using Extended Kalman Filter trained neural networks for surface vessels

  • Wang, Yuanyuan (National Centre for Maritime Engineering and Hydrodynamics, Australian Maritime College, University of Tasmania) ;
  • Chai, Shuhong (National Centre for Maritime Engineering and Hydrodynamics, Australian Maritime College, University of Tasmania) ;
  • Nguyen, Hung Duc (National Centre for Maritime Engineering and Hydrodynamics, Australian Maritime College, University of Tasmania)
  • Received : 2018.03.09
  • Accepted : 2019.11.11
  • Published : 2020.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Due to the nonlinearity and environmental uncertainties, the design of the ship's steering controller is a long-term challenge. The purpose of this study is to design an intelligent autopilot based on Extended Kalman Filter (EKF) trained Radial Basis Function Neural Network (RBFNN) control algorithm. The newly developed free running model scaled surface vessel was employed to execute the motion control experiments. After describing the design of the EKF trained RBFNN autopilot, the performances of the proposed control system were investigated by conducting experiments using the physical model on lake and simulations using the corresponding mathematical model. The results demonstrate that the developed control system is feasible to be used for the ship's motion control in the presences of environmental disturbances. Moreover, in comparison with the Back-Propagation (BP) neural networks and Proportional-Derivative (PD) based control methods, the EKF RBFNN based control method shows better performance regarding course keeping and trajectory tracking.

Keywords

Acknowledgement

This research is funded by the Tasmanian Institutional Grants Scheme (IGS) and the Guangdong MEPP Fund (Grant No. GDOE 2019A18). The authors would like to appreciate Michael Underhill and Yufei Wang for the technical supply during the experiments.

References

  1. Burns, R., 1995. The use of artificial neural networks for the intelligent optimal control of surface ships. IEEE J. Ocean. Eng. 20, 65-72. https://doi.org/10.1109/48.380245
  2. Dai, S.-L., Wang, C., Luo, F., 2012. Identification and learning control of ocean surface ship using neural networks. IEEE Trans. Ind. Inform. 8, 801-810. https://doi.org/10.1109/TII.2012.2205584
  3. Dong, Z., Wan, L., Li, Y., Liu, T., Zhang, G., 2015. Trajectory tracking control of underactuated USV based on modified backstepping approach. Int. J. Naval Arch. Ocean Eng. 7, 817-832. https://doi.org/10.1515/ijnaoe-2015-0058
  4. Fang, M.-C., Lee, Z.-Y., 2016. Application of neuro-fuzzy algorithm to portable dynamic positioning control system for ships. Int. J. Naval Arch. Ocean Eng. 8, 38-52. https://doi.org/10.1016/j.ijnaoe.2015.09.003
  5. Fang, M.C., Zhuo, Y.Z., Lee, Z.Y., 2010. The application of the self-tuning neural network PID controller on the ship roll reduction in random waves. Ocean Eng. 37, 529-538. https://doi.org/10.1016/j.oceaneng.2010.02.013
  6. Fossen, T., 2011. Hydrostatics. Handbook of Marine Craft Hydrodynamics and Motion Control.
  7. Fossen, T.I., 1994. Guidance and Control of Ocean Vehicles. John Wiley & Sons Inc.
  8. Ge, S.S., Hang, C.C., Lee, T.H., Zhang, T., 2013. Stable Adaptive Neural Network Control. Springer Science & Business Media.
  9. Liu, J., 2013. Radial Basis Function (RBF) Neural Network Control for Mechanical Systems: Design, Analysis and Matlab Simulation. Springer Berlin Heidelberg.
  10. Morawski, L., Pomirski, J., 1998. Ship track-keeping: experiments with a physical tanker model. Contr. Eng. Pract. 6, 763-769. https://doi.org/10.1016/S0967-0661(98)00082-3
  11. Naeem, W., Sutton*, R., Chudley, J., Dalgleish, F., Tetlow, S., 2005. An online genetic algorithm based model predictive control autopilot design with experimental verification. Int. J. Contr. 78, 1076-1090. https://doi.org/10.1080/00207170500228483
  12. Park, J., Sandberg, I.W., 1991. Universal approximation using radial-basis-function networks. Neural Comput. 3, 246-257. https://doi.org/10.1162/neco.1991.3.2.246
  13. Purushothaman, S., 2010. Tool wear monitoring using artificial neural network based on extended Kalman filter weight updation with transformed input patterns. J. Intell. Manuf. 21, 717-730. https://doi.org/10.1007/s10845-009-0249-y
  14. Rigatos, G., Tzafestas, S., 2006. Adaptive fuzzy control for the ship steering problem. Mechatronics 16, 479-489. https://doi.org/10.1016/j.mechatronics.2006.01.003
  15. Ruck, D.W., 1990. Characterization of Multilayer Perceptrons and Their Application to Multisensor Automatic Target Detection. AIR FORCE INST OF TECH WRIGHTPATTERSON AFB OH SCHOOL OF ENGINEERING.
  16. Sanchez, E.N., Alan S, A.Y., Loukianov, A.G., 2008. Discrete-time High Order Neural Control: Trained with Kalman Filtering. Springer Science & Business Media.
  17. Sgobbo, J.N., Parsons, M.G., 1999. Rudder/fin roll stabilization of the USCG WMEC 901 class vessel. Mar. Technol. SNAME News 36, 157. https://doi.org/10.5957/mt1.1999.36.3.157
  18. Sum, J., Leung, C.-S., Young, G.H., Kan, W.-K., 1999. On the Kalman filtering method in neural network training and pruning. Neural Networks. IEEE Trans. on 10, 161-166. https://doi.org/10.1109/72.737502
  19. Sun, B., Zhu, D., Yang, S.X., 2014. A bioinspired filtered backstepping tracking control of 7000-m manned submarine vehicle. IEEE Trans. Ind. Electron. 61, 3682-3693. https://doi.org/10.1109/TIE.2013.2267698
  20. Tannuri, E., Agostinho, A., Morishita, H., Moratelli, L., 2010. Dynamic positioning systems: an experimental analysis of sliding mode control. Contr. Eng. Pract. 18, 1121-1132. https://doi.org/10.1016/j.conengprac.2010.06.007
  21. Trebatick, P., 2005. Recurrent neural network training with the extended kalman filter. In: IIT. SRC 2005: Student Research Conference, vol. 57.
  22. Wang, N., Er, M.J., 2015. Self-constructing adaptive robust fuzzy neural tracking control of surface vehicles with uncertainties and unknown disturbances. IEEE Trans. Contr. Syst. Technol. 23, 991-1002. https://doi.org/10.1109/TCST.2014.2359880
  23. Wang, N., Lv, S., Zhang, W., Liu, Z., Er, M.J., 2017a. Finite-time observer based accurate tracking control of a marine vehicle with complex unknowns. Ocean Eng. 145, 406-415. https://doi.org/10.1016/j.oceaneng.2017.09.062
  24. Wang, N., Su, S.-F., Han, M., Chen, W.-H., 2018a. Backpropagating constraints-based trajectory tracking control of a quadrotor with constrained actuator dynamics and complex unknowns. IEEE Trans. Systems, Man, and Cybernetics: Syst. 1-16.
  25. Wang, N., Su, S.-F., Pan, X., Yu, X., Xie, G., 2018. Yaw-guided trajectory tracking control of an asymmetric underactuated surface vehicle. IEEE Trans. Ind. Inform. 15 (6), 3502-3513. https://doi.org/10.1109/TII.2018.2877046
  26. Wang, N., Sun, J.-C., Han, M., Zheng, Z., Er, M.J., 2018c. Adaptive approximationbased regulation control for a class of uncertain nonlinear systems without feedback linearizability. IEEE Trans. Neural Netw. Learn. Syst. 29, 3747-3760. https://doi.org/10.1109/TNNLS.2017.2738918
  27. Wang, Y., Chai, S., Nguyen, H.D., 2017b. Modelling of a surface vessel from free running test using low cost sensors. In: Control, Automation and Robotics(ICCAR), 2017 3rd International Conference on. IEEE, pp. 299-303.
  28. Wang, Y., Nguyen, H.D., Chai, S., Khan, F., 2015. Radial basis function neural network based rudder roll stabilization for ship sailing in waves. In: Control Conference(AUCC), 2015 5th Australian. IEEE, pp. 158-163.
  29. Wang, Y., Shuhong, C., Nguyen, H.D., 2017c. Modelling of a surface vessel from free running test using low cost sensors. In: 2017 3rd International Conference on Control, Automation and Robotics (ICCAR), 24-26 April 2017, pp. 299-303.
  30. Wu, J., Peng, H., Ohtsu, K., Kitagawa, G., Itoh, T., 2012. Ship's tracking control based on nonlinear time series model. Appl. Ocean Res. 36, 1-11. https://doi.org/10.1016/j.apor.2012.01.004
  31. Yahui, L., Sheng, Q., Xianyi, Z., Okyay, K., 2004. Robust and adaptive backstepping control for nonlinear systems using RBF neural networks. IEEE Trans. Neural Network. 15, 693-701. https://doi.org/10.1109/TNN.2004.826215
  32. Yang, H., Li, J., Ding, F., 2007. A neural network learning algorithm of chemical process modeling based on the extended Kalman filter. Neurocomputing 70, 625-632. https://doi.org/10.1016/j.neucom.2006.10.033

Cited by

  1. Control system design for vessel towing system by activating rudders of the towed vessel vol.12, 2020, https://doi.org/10.1016/j.ijnaoe.2020.11.008
  2. Multi-Sensor Fusion for Underwater Vehicle Localization by Augmentation of RBF Neural Network and Error-State Kalman Filter vol.21, pp.4, 2020, https://doi.org/10.3390/s21041149