A feed-forward network with seven layers was designed and trained to acquire an open loop controller of course-keeping for ships. The NNC controller with five inputs and one output could follow the tacks of typical co...
详细信息
In the formulation of H∞ weighted mixed sensitivity problem, any unstable poles of the plant inside the specified control bandwidth will be shifted approximately to its jω-axis mirror image once the feedback loop is...
详细信息
The nonlinear mathematical model was linearized through exact feedback linearization, then a robust exact feedback linearizing controller was designed using closed-loop gain shaping algorithm, and applied to course-ke...
详细信息
The nonlinear mathematical model was linearized through exact feedback linearization, then a robust exact feedback linearizing controller was designed using closed-loop gain shaping algorithm, and applied to course-keeping of autopilot for ships. simulation research was carried out using Simulink of Matlab under different situations such as nominal model, perturbed model and various sea states. Finally, the simulation results were compared to that of exact feedback linearizing controller based on linear-quadratic regulator (LQR). simulation results show that the design is simple with clear physical meanings and the controller has strong robustness.
A kind of transfigured loop shaping controller is presented in this paper. A transfigured loop shaping system puts a controller K in a feedback loop, while putting the dc gain of the controller K on the reference sign...
详细信息
A kind of transfigured loop shaping controller is presented in this paper. A transfigured loop shaping system puts a controller K in a feedback loop, while putting the dc gain of the controller K on the reference signal line. It is shown through frequency domain analysis and simulation that a transfigured controller can improve the dynamic behavior of a system. The transfigured loop shaping controller method is simple and effective and corresponds to the mixed sensitivity method of robust control theory, which improves the behavior of a system by iterative tuning of weighting functions. Satisfactory control results are obtained when it is applied to the design of an underwater vehicle.
Keywords Loop shaping controller - underwater vehicle - transfiguration
Zhang Xianku graduated from Beijing Institute of Clothing Technology, China, in 1990. He received the M. S. degree from Dalian Maritime University (DMU), China, in 1993 and the Ph.D. degree from DMU, in 1998. He is currently a professor at the laboratory of simulation and control of navigationsystems, Dalian Maritime University. His research interests include ship motion control and robust control.
Jin Yicheng graduated from Zhejiang University, China, in 1967. He is currently a professor at the laboratory of simulation and control of navigationsystems, Dalian Maritime University. His research interests include simulating system of ship steering and visual control.
Recursive least-squares temporal difference algorithm (RLS-TD) is deduced, which can use data more efficiently with fast convergence and less computational burden. Reinforcement learning based on recursive least-squar...
详细信息
Recursive least-squares temporal difference algorithm (RLS-TD) is deduced, which can use data more efficiently with fast convergence and less computational burden. Reinforcement learning based on recursive least-squar...
详细信息
Recursive least-squares temporal difference algorithm (RLS-TD) is deduced, which can use data more efficiently with fast convergence and less computational burden. Reinforcement learning based on recursive least-squares methods is applied to ship steering control, as provides an efficient way for the improvement of ship steering control performance. It removes the defect that the conventional intelligent algorithm learning must be provided with some sample data. The parameters of controller are on-line learned and adjusted. simulation results show that the ship course can be properly controlled in case of the disturbances of wave, wind, current. It is demonstrated that the proposed algorithm is a promising alternative to conventional autopilots.
A fuzzy CMAC controller with eligibility (FCE) is proposed. The eligibility can forecast the controlled system, and improve the system stability. The structure of FCE system is presented, and its learning algorithm is...
详细信息
ISBN:
(纸本)0780382730
A fuzzy CMAC controller with eligibility (FCE) is proposed. The eligibility can forecast the controlled system, and improve the system stability. The structure of FCE system is presented, and its learning algorithm is deduced. To make the algorithm fit to on-line control, the efficient implementation of FCE method is also given. Applying the FCE controller in a ship steering control system, the simulation results show that the ship course can be properly controlled in case of the disturbances of wave, wind, current and error in measure apparatus exist. It is demonstrated that the proposed algorithm is a promising alternative to conventional autopilots.
In this paper, we present an Adaptive Network-based Fuzzy Inference System (ANFIS), based on a neuro-fuzzy controller, as a possible control mechanism for a ship stabilizing fin system. simulation results show that AN...
详细信息
In this paper, we present an Adaptive Network-based Fuzzy Inference System (ANFIS), based on a neuro-fuzzy controller, as a possible control mechanism for a ship stabilizing fin system. simulation results show that ANFIS can effectively improve the ship stabilizing performance against roll motion in cases of rough sea conditions. it is a promising alternative to conventional PID controllers.
暂无评论