A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Robust adaptive neural networks control for dynamic positioning of ships with unknown saturation and time-delay
https://orcid.org/0000-0001-7288-5053
Highlights To the best knowledge of authors, it is the first time in the literature that the unknown input saturation, time delay, unknown time-varying disturbances and dynamic uncertainties are considered simultaneously in dynamic positioning controller design. The minimal-parameters-learning (MLP) technology is introduced to reduce the computational burden while only one parameter need to be update by an adaptive law so the problems of “explosion of complexity” in the conventional backstepping method and “curse of dimensionality” in the traditional neural networks control are avoided which will make it easy to apply the controller in practical engineering. A robust adaptive compensation is introduced to handle the unknown input saturation, unknown time-varying disturbances and approximation error of RBFNN. The robustness of RBFNN with MLP is improved while the prior knowledge of input saturation is not required.
Abstract In this paper, a robust adaptive neural networks control based on minimal–parameter-learning (MLP) is proposed for dynamic positioning (DP) of ships with unknown saturation, time delay, external disturbance and dynamic uncertainties. Through the velocities backstepping method, radial basis function (RBF) neural networks and robust adaptive control are incorporated to design a novel controller of which an appropriate Lyapunov-Krasovskii Function (LKF) is constructed to overcome the effect caused by time-delay. Meanwhile, the MLP technology is applied to reduce the computational burden while only one parameter need to be update by an adaptive law. In additional, a robust adaptive compensate term is introduced to estimate the bound of the lumped disturbance including the unknown saturation, unknown external disturbance and the approximate error of neural networks control while the robustness of MLP is improved and the unknown saturation is compensated. The developed control law makes the DP closed-loop system be uniformly ultimately stable which can be proved strictly through Lyapunov theory. Finally, simulations with a guidance law are proposed to demonstrate the validity of controller we developed.
Robust adaptive neural networks control for dynamic positioning of ships with unknown saturation and time-delay
https://orcid.org/0000-0001-7288-5053
Highlights To the best knowledge of authors, it is the first time in the literature that the unknown input saturation, time delay, unknown time-varying disturbances and dynamic uncertainties are considered simultaneously in dynamic positioning controller design. The minimal-parameters-learning (MLP) technology is introduced to reduce the computational burden while only one parameter need to be update by an adaptive law so the problems of “explosion of complexity” in the conventional backstepping method and “curse of dimensionality” in the traditional neural networks control are avoided which will make it easy to apply the controller in practical engineering. A robust adaptive compensation is introduced to handle the unknown input saturation, unknown time-varying disturbances and approximation error of RBFNN. The robustness of RBFNN with MLP is improved while the prior knowledge of input saturation is not required.
Abstract In this paper, a robust adaptive neural networks control based on minimal–parameter-learning (MLP) is proposed for dynamic positioning (DP) of ships with unknown saturation, time delay, external disturbance and dynamic uncertainties. Through the velocities backstepping method, radial basis function (RBF) neural networks and robust adaptive control are incorporated to design a novel controller of which an appropriate Lyapunov-Krasovskii Function (LKF) is constructed to overcome the effect caused by time-delay. Meanwhile, the MLP technology is applied to reduce the computational burden while only one parameter need to be update by an adaptive law. In additional, a robust adaptive compensate term is introduced to estimate the bound of the lumped disturbance including the unknown saturation, unknown external disturbance and the approximate error of neural networks control while the robustness of MLP is improved and the unknown saturation is compensated. The developed control law makes the DP closed-loop system be uniformly ultimately stable which can be proved strictly through Lyapunov theory. Finally, simulations with a guidance law are proposed to demonstrate the validity of controller we developed.
Robust adaptive neural networks control for dynamic positioning of ships with unknown saturation and time-delay
https://orcid.org/0000-0001-7288-5053
Highlights To the best knowledge of authors, it is the first time in the literature that the unknown input saturation, time delay, unknown time-varying disturbances and dynamic uncertainties are considered simultaneously in dynamic positioning controller design. The minimal-parameters-learning (MLP) technology is introduced to reduce the computational burden while only one parameter need to be update by an adaptive law so the problems of “explosion of complexity” in the conventional backstepping method and “curse of dimensionality” in the traditional neural networks control are avoided which will make it easy to apply the controller in practical engineering. A robust adaptive compensation is introduced to handle the unknown input saturation, unknown time-varying disturbances and approximation error of RBFNN. The robustness of RBFNN with MLP is improved while the prior knowledge of input saturation is not required.
Abstract In this paper, a robust adaptive neural networks control based on minimal–parameter-learning (MLP) is proposed for dynamic positioning (DP) of ships with unknown saturation, time delay, external disturbance and dynamic uncertainties. Through the velocities backstepping method, radial basis function (RBF) neural networks and robust adaptive control are incorporated to design a novel controller of which an appropriate Lyapunov-Krasovskii Function (LKF) is constructed to overcome the effect caused by time-delay. Meanwhile, the MLP technology is applied to reduce the computational burden while only one parameter need to be update by an adaptive law. In additional, a robust adaptive compensate term is introduced to estimate the bound of the lumped disturbance including the unknown saturation, unknown external disturbance and the approximate error of neural networks control while the robustness of MLP is improved and the unknown saturation is compensated. The developed control law makes the DP closed-loop system be uniformly ultimately stable which can be proved strictly through Lyapunov theory. Finally, simulations with a guidance law are proposed to demonstrate the validity of controller we developed.
Robust adaptive neural networks control for dynamic positioning of ships with unknown saturation and time-delay
Liang, Kun (author) / Lin, Xiaogong (author) / Chen, Yu (author) / Liu, Yeye (author) / Liu, Zhaoyu (author) / Ma, Zhengxiang (author) / Zhang, Wenli (author)
Applied Ocean Research ; 110
2021-03-01
Article (Journal)
Electronic Resource
English
Robust adaptive control of dynamic positioning ship under thruster faults and unknown disturbances
| SAGE Publications | 2024
| Elsevier | 2025
Neural adaptive robust control of underactuated marine surface vehicles with input saturation
| Online Contents | 2015