An on-line training functional-link neural network predictor/controller fordynamic positioning of water surface structures is described in this paper. The on-line trainingneural network predictor acquires the knowledg...An on-line training functional-link neural network predictor/controller fordynamic positioning of water surface structures is described in this paper. The on-line trainingneural network predictor acquires the knowledge about the system using a small number of samples ofthe latest system status measured on board of the structure. The trained function-link neuralnetwork is used with an optimal controller to control the output of the system. The accuracy androbustness of the on-line training predictor are demonstrated through the numerical simulations oftwo ship maneuvers. The on-line training neural network predictor/controller is applied to thedynamic positioning (station-keeping) of a ship in a uniform current with and without externalenvironmental disturbances. The results of the numerical simulations are very satisfactory.展开更多
文摘An on-line training functional-link neural network predictor/controller fordynamic positioning of water surface structures is described in this paper. The on-line trainingneural network predictor acquires the knowledge about the system using a small number of samples ofthe latest system status measured on board of the structure. The trained function-link neuralnetwork is used with an optimal controller to control the output of the system. The accuracy androbustness of the on-line training predictor are demonstrated through the numerical simulations oftwo ship maneuvers. The on-line training neural network predictor/controller is applied to thedynamic positioning (station-keeping) of a ship in a uniform current with and without externalenvironmental disturbances. The results of the numerical simulations are very satisfactory.
