Data-driven model identification and predictive control for path-following of underactuated ships with unknown dynamics
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
With the trends towards autonomous shipping, advanced ship motion control methods have received increased attention in recent years. The validity of ship models is crucial in designing motion controllers and directly affects their performances. However, accurate models that could reflect true ship dynamics are highly nonlinear, complex and complicated to identify, especially in situations when the experimental conditions are limited. This paper proposes a data-driven predictive control method for pathfollowing of under-actuated cargo ships with unknown dynamics, which makes use of data gathered during operation to improve the model and the path-following performance. Based on the ship navigation data set, the relations between the heading angle and the rudder angle of the ship are fitted with seven typical regression algorithms, which acts as the prediction model in the path-following controller. Simulation study is carried out to choose the most suitable regression algorithm, among which elastic net regression is selected. The Antenna Mutation Beetle Swarm Predictive (AMBS-P) algorithm is introduced to find the optimal weights in the model identification process. A Line-of-Sight (LOS) algorithm is used as the guidance law to transform reference way-points into reference heading angles, and the path-following controller is designed also based on and the AMBS-P algorithm. Simulation results show that the proposed data-driven control method performs well in the path-following task without having prior knowledge regarding the hydrodynamic coefficients and ship parameters.
Abstract
With the trends towards autonomous shipping, advanced ship motion control methods have received increased attention in recent years. The validity of ship models is crucial in designing motion controllers and directly affects their performances. However, accurate models that could reflect true ship dynamics are highly nonlinear, complex and complicated to identify, especially in situations when the experimental conditions are limited. This paper proposes a data-driven predictive control method for pathfollowing of under-actuated cargo ships with unknown dynamics, which makes use of data gathered during operation to improve the model and the path-following performance. Based on the ship navigation data set, the relations between the heading angle and the rudder angle of the ship are fitted with seven typical regression algorithms, which acts as the prediction model in the path-following controller. Simulation study is carried out to choose the most suitable regression algorithm, among which elastic net regression is selected. The Antenna Mutation Beetle Swarm Predictive (AMBS-P) algorithm is introduced to find the optimal weights in the model identification process. A Line-of-Sight (LOS) algorithm is used as the guidance law to transform reference way-points into reference heading angles, and the path-following controller is designed also based on and the AMBS-P algorithm. Simulation results show that the proposed data-driven control method performs well in the path-following task without having prior knowledge regarding the hydrodynamic coefficients and ship parameters.
참고문헌 (39)
- Carron, A., "Data-driven model predictive control for trajectory tracking with a robotic arm", IEEE Robot. Automat. Lett, 4, pp.3758~3765 (2019)
- Deng, Y., "Fuzzy logic based speed optimization and path following control for sail-assisted ships", Ocean Eng, 171, pp.300~310 (2019)
- Doris, Schadler, "Fault detection using online selected data and updated regression models", Measurement, pp.437~449 (2019)
- Fossen, T. I., "Line-of-sight path following for dubins paths with adaptive sideslip compensation of drift forces", IEEE Trans. Control Syst. Technol, 23, pp.820~827 (2015)
- Haseltalab, A., "Adaptive control for autonomous ships with uncertain model and unknown propeller dynamics", Control Eng. Pract, 91, pp.104116.1~104116.12 (2019)
- Hoerl, A., "Application of ridge analysis to regression problems", Chem. Eng. Prog, 58, pp.54~59 (1962)
- Hui, Z., "Regression shrinkage and selection via the elastic net, with applications to microarrays", J. Roy. Stat. Soc, pp.1~10 (2004)
- Jiang, X., "Bas: beetle antennae search algorithm for optimization problems", Int. J. Robot. Contr, 1, pp.1~3 (2017)
- Karagiannidis, P., "Data-driven modelling of ship propulsion and the effect of data pre-processing on the prediction of ship fuel consumption and speed loss", Ocean Eng, 222, pp.108616~ (2021)
- Koyama, T., "An application of the least square method to the ship maneuverability identification", J. Soc. Nav. Archit. Jpn, 134, pp.173~181 (1973)
- Free Sailing Manoeuvring Tests on KVLCC1 and KVLCC2, "Lee, S.", Maritime Research Institute Netherlands, ~ (2007)
- Li, S., "Automatic Docking for Underactuated Ships Based on Multi-Objective Nonlinear Model Predictive Control", IEEE Access, pp.70044~70057 (2020)
- Liu, J., "Impacts of the rudder profile on manoeuvring performance of ships", Ocean Eng, 124, pp.226~240 (2016)
- Liu, Y., "Ship trajectory tracking control system design based on sliding mode control algorithm", Pol. Marit. Res, 25, pp.26~34 (2018)
- Liu, Y., "Design for underactuated ships' trajectory tracking control", Comput. Integr. Manuf. Syst, 36, pp.6~10 (2019)
- Liu, Z., "Practical backstepping control for underactuated ship path following associated with disturbances", IET Intell. Transp. Syst, 13, pp.834~840 (2019)
- Liu, Z., "Pre-filtered backstepping control for underactuated ship path following", Pol. Marit. Res, 26, pp.68~75 (2019)
- Ma, Y., "Error-driven-based nonlinear feedback recursive design for adaptive nn trajectory tracking control of surface ships with input saturation", IEEE Intel. Trans. Syst. Mag, pp.17~28 (2019)
- Ostafew, C. J., "Learning-based nonlinear model predictive control to improve vision-based mobile robot path tracking", J. Field Robot, 33, pp.133~152 (2016)
- Sawada, R., "Path following algorithm application to automatic berthing control", J. Mar. Sci. Technol, 26, pp.541~554 (2021)
- Shen, Z., "Adaptive dynamic surface output feedback trajectory tracking control for underactuated ships with nonlinear observer", Syst. Eng. Electron, 41, pp.409~416 (2019)
- Shen, Z., "Neuron adaptive iterative sliding-mode control for path tracking of underactuated ship", J. Harbin Eng. Univ, 40, pp.60~65 (2019)
- Shen, Z., "Extended state observer based adaptive dynamic surface output feedback control for underactuated surface vessel trajectory tracking with low-frequency learning", Control Theory & Appl, 36, pp.867~876 (2019)
- Shin, J., "Adaptive path-following control for an unmanned surface vessel using an identified dynamic model", IEEE ASME Trans. Mechatron, 22, pp.1143~1153 (2017)
- Ugo, R., "Data-driven predictive control for autonomous systems", Annu. Rev. Contr. Robot. Auto. Syst, 1, pp.259~286 (2018)
- Wang, L., "Ship motion control based on ambps-pid algorithm", IEEE Access, 7, pp.183656~183671 (2019)
- Wang, X. Z, Z, "Identification of ship manoeuvring response model based on fruit fly optimization algorithm", J. Dalian Marit. Univ, 38, pp.1~4 (2012)
- Wang, X. G., "System identification modelling of ship manoeuvring motion based on support vector regression", J. Hydrodyn, 27, pp.502~512 (2015)
- Wang, Z., "Kernel-based support vector regression for nonparametric modeling of ship maneuvering motion", Ocean Eng, 216, pp.1~12 (2020)
- Wang, Z., "Identification of ship manoeuvring motion based on mi-support vector machine", Ocean Eng, 183, pp.270~281 (2019)
- Xue, Y., "System identification of ship dynamic model based on Gaussian process regression with input noise", Ocean Eng, 216, pp.107862~ (2020)
- Yasukawa, H., "Introduction of mmg standard method for ship maneuvering predictions", J. Mar. Sci. Technol, 20, pp.37~52 (2015)
- Yu, Y., "Ship trajectory tracking using improved simulated annealing and reinforcement learning", IEEE, 1, pp.1384~1389 (2018)
- Zhang, G., "Multi-innovation auto-constructed least squares identification for 4 dof ship manoeuvring modelling with full-scale trial data", ISA(Instrum. Soc. Am. )Trans, 58, pp.186~195 (2015)
- Zhang, X. G., "Identification of abkowitz model for ship manoeuvring motion using ε-support vector regression", J. Hydrodyn, 23, pp.353~360 (2011)
- Zhao, Y., "Broken lines path following algorithm for a water-jet propulsion usv with disturbance uncertainties", Ocean Eng, 201, pp.1~9 (2020)
- Zhu, G., "Global robust adaptive trajectory tracking control for surface ships under input saturation", IEEE J. Ocean. Eng, 45, pp.442~450 (2020)
- Zhu, M., "Identification-based controller design using cloud model for course-keeping of ships in waves", Eng. Appl. Artif. Intell, 75, pp.22~35 (2018)
- Zhu, M., "Identification-based simplified model of large container ships using support vector machines and artificial bee colony algorithm", Appl. Ocean Res, 68, pp.249~261 (2017)