An efficient model predictive control design for ship autopilot, which is a representative marine application, is proposed based on projection neural network in this article. Ship motion control at sea exhibits the characteristics of large inertia, strong nonlinearity, and large delay; furthermore, it is frequently influenced by the external disturbances, leading to a complex uncertain problem. In addition, the amplitude of control input—the rudder is constrained. Given the mechanism of on-line computing and the advantages of handling constraints, the model predictive control is one of the most favorable solutions for this problem. Nevertheless, the major challenge of the implementation of traditional model predictive control in application is the computation intensity. In this article, the capability of parallel computation of projection neural network is employed to optimize the objective function formulated by traditional model predictive control method, aiming to improve the computational efficiency. The overall information of ship motion is normally difficult to be obtained; therefore, a state observer should be also included. Extensive studies are conducted to illustrate the effectiveness of the proposed control design.
FossenTIPerezT. Kalman filtering for positioning and heading control of ships and offshore rigs. IEEE Contr Syst Mag2009; 29(6): 32–46.
2.
RobertsGNSuttonRZirilliA, et al. A intelligent ship autopilot—A historical perspective. Mechatronics2003; 13: 1091–1103.
3.
FangMCLuoJH. The nonlinear hydrodynamic model for simulating a ship steering in waves with autopilot system. Ocean Eng2005; 32: 1486–1502.
4.
SperryEA. Automatic steering. Trans Soc Nav Archit Mar Engrs1922; 30: 53–61.
5.
MinorskyN. Directional stability of automatic steered bodies. J Am Soc Naval Engrs1922; 34(2): 280–309.
6.
BennettS. Nicolas Minorsky and the automatic steering of ships. IEEE Contr Syst Mag1984; 4(4): 10–15.
7.
AmerongenJV. Adaptive steering of ship—a model reference approach. Automatica1984; 20(1): 3–14.
8.
DuJLGuoCYuSH, et al. Adaptive autopilot design of time-varying uncertain ships with completely unknown control coefficient. IEEE J Oceanic Eng2007; 32(2): 346–351.
9.
SuttonRJessIM. A design study of a self-organizing fuzzy autopilot for ship control. Proc IMechE Part I: J Systems and Control Engineering1991; 205: 35–47.
10.
SuttonRTaylorSRobertGN. Tuning fuzzy ship autopilot using artificial neural networks. Trans Inst Meas Control1997; 19(2): 94–106.
11.
VelagicJVukicZOmerdicE. Adaptive fuzzy ship autopilot for track-keeping. Control Eng Pract2003; 11: 433–443.
12.
ChenZQQinBBSunMW, et al. Q-learning-based parameters adaptive algorithm for active disturbance rejection control and its application to ship course control. Neurocomputing. Epub ahead of print 31October2019. DOI: 10.1016/j.neucom.2019.10.060.
13.
LiZSunJ. Disturbance compensating model predictive control with application to ship heading control. IEEE T Contr Syst T2012; 20(1): 257–265.
14.
LiuCSunJZouZJ. Integrated line of sight and model predictive control for path following and roll motion control using rudder. J Ship Res2015; 59(2): 99–112.
15.
WangLP. Model predictive control system design and implementation using MATLAB. London: Springer, 2009.
16.
OhSSunJ. Path following of underactuated marine surface vessels using line-of-sight based model predictive control. Ocean Eng2010; 37(2–3): 289–295.
17.
LiangLHWenY. Rudder roll stabilization with disturbance compensation model predictive control. J Mar Sci Tech-Japan2019; 24(1): 249–259.
18.
LiWHSunYQChenHQ, et al. Model predictive controller design for ship dynamic positioning system based on state-space equations. J Mar Sci Tech-Japan2017; 22(3): 426–431.
19.
PengZWangJ. Output-feedback path-following control of autonomous underwater vehicles based on an extended state observer and projection neural networks. IEEE T Syst Man Cy-S2018; 48(4): 535–544.
20.
XiaYSLeungHWangJ. A projection neural network and its application to constrained optimization problems. IEEE Trans Circuits Syst Fundam Theory Appl2002; 49(4): 447–458.
21.
XiaYSFengGWangJ. A novel recurrent neural network for solving nonlinear optimization problems with inequality constraints. IEEE T Neural Networ2008; 19(8): 379–386.
22.
XiaoHZLiZJYangCG. Robust stabilization of a wheeled mobile robot using model predictive control based on neurodynamics optimization. IEEE T Ind Electron2017; 61(1): 505–516.
23.
ZhangYYChenSYLiS, et al. Adaptive projection neural network for kinematic control of redundant manipulators with unknown physical parameters. IEEE T Ind Electron2018; 65(6): 4909–4920.
24.
HaganMTDemuthHBBealeMH. Neural network design. Beijing, China: China Machine Press, 2002.
25.
HopfieldJJ. Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci U S A. 1982; 79: 2554–2558.
26.
HopfieldJJ. Neurons with graded response have collective computational properties like those of two-state neurons. Proc Natl Acad Sci U S A. 1984; 81(10): 3088–3092.
27.
XiaoHZChenCLP. Incremental updating multi-robot formation using nonlinear model predictive control method with general projection neural network. IEEE T Ind Electron2019; 66(6): 4502–4512.
28.
KennedyMPChuaLO. Neural networks for nonlinear programming. IEEE T Circ Syst1988; 35(5): 554–562.
29.
Rodriguez-VazquezADominguez-CastroRRuedaA, et al. Nonlinear switched capacitor “neural” networks for optimization problems. IEEE T Circ Syst1990; 37(7): 384–398.
30.
RanaMSPotaHRPetersenR. High-speed AFM image scanning using observer-based MPC-notch control. IEEE T Nanotechnol2013; 12(2): 246–254.
31.
LauvdalTFossenTI. Robust adaptive ship autopilot with wave filter and integral action. INT J Adapt Control1998; 12: 605–622.
32.
FossenTI. Guidance and control of ocean vehicles. Hoboken: John Wiley and Sons, 1994.
33.
FossenTI. Handbook of marine craft hydrodynamics and motion control. Hoboken: John Wiley and Sons, 2011.
34.
LiZ. Path following with roll constraints for marine surface vessels in wave fields. PhD Thesis, University of Michigan, Ann Arbor, MI, 2009.
35.
PerezT. Ship motion control: course keeping and roll stabilization using rudder and fins. Berlin: Springer, 2005.
LauvdalTFossenTI. Nonlinear rudder-roll damping of non-minimum phase ships using sliding mode control. In: Proceedings of the European control conference, Brussels, 1–7 July 1997. New York: IEEE.
38.
SunJVKolmanovskyIGhaemiR, et al. A stable block model predictive control with variable implementation horizon. Automatica2007; 43: 1945–1953.
39.
LiuCChenCLPZouZJ, et al. Adaptive NN-DSC control design for path following of underactuated surface vessels with input saturation. Neurocomputing2017; 267: 466–474.
40.
DuJLHuXKrstićM, et al. Robust dynamic position of ships with disturbances under input saturation. Automatica2016; 73: 207–214.
