Zhengjiang Liu

NARMAX model based on wavelet network with application in ship control

A wavelet neural network (WNN) is introduced to realize the system identification with nonlinear auto-regressive moving average with exogenous inputs (NARMAX) model. The method takes both advantages of the wavelet network and NARMAX model, and the multi-objective optimization method is used to real-time estimate the network coefficient. The wavelet-network-based NARMAX identification model is used as online system identifier, and the experimental result of ship course control proves the efficiency of the proposed neural identification model.

Nonlinear Sliding Mode Berthing Control of Underactuated Surface Ships

A novel output feedback strategy is presented for the berthing control of underactuated surface ships with nonintegrable acceleration constraint. Saturations on actuators, systemic uncertainties and drift caused by current or wind are considered. The problems of trajectory planning and tracking are circumvented by means of iterative nonlinear sliding mode control (INSMC) method. The sliding modes are decentralized and recursively designed on phase planes in the augmented states space. Increment feedback control law is developed based on the INSMC to (locally) stabilize the ships motion without estimation of uncertainties and disturbances. Numerical simulation results on a full nonlinear hydrodynamic model of a training ship are presented to validate the invariability and excellent performance of the proposed algorithm.

Path following and stabilization of underactuated surface ships

To solve the path following and stabilization problems for underactuated surface ships with nonintegrable acceleration constraint, a nonlinear feedback algorithm is presented using decoupling control method and iterative nonlinear sliding mode designing approach. The saturations on actuators and unknown environmental disturbances are also explicitly considered. Integrating with simple increment feedback control laws, a dynamic control strategy is developed to fulfill the underactuated following and stabilization objectives with only surge force and yaw movement available. Numerical simulation results on a full nonlinear hydrodynamic model of a training ship are presented to validate the effectiveness and robustness of the proposed controller.

Path following of underactuated surface ships

The path following problem is concerned for conventional surface ships with second order nonholonomic constraints. A nonlinear feedback algorithm is presented using decoupling control method. The cross track error and heading error are stabilized by means of the rudder alone and the thruster is left to adjust the forward speed. The underactuated following control objective is achieved without a reference orientation generated by a ship model. The estimation of systemic uncertainties and disturbances and the yaw velocity PE (persistent excitation) conditions are not required. Computer simulation results on a full nonlinear hydrodynamic ship model of M.V. YULONG are provided to validate the effectiveness and robustness of the proposed controller.

A nonlinearity-based genetic algorithm for ship path planning

In this thesis, a nonlinearity-based genetic algorithm for ship path planning was proposed. This novel algorithm applied the nonlinear programming to compensate the inherent deficiency of genetic algorithm in local optimization. Meanwhile, problem-specific knowledge and heuristic knowledge were incorporated into encoding, evaluation and genetic operators of genetic algorithm. Furthermore, the application of minimum generation kept of the optimal fitness as the criterion of the termination condition reflected the knowledge accumulation in the optimal process which perfectly suited this nonlinearity-based genetic algorithm. Finally, the feasibility and effectiveness of this algorithm were evaluated with a set of test cases simulating various traffic scenarios.

Ship-track Control Based Traffic Safety Assessment of Ships in the Constrained Waters

In this paper, a novel assessment technique for ship traffic safety in the constrained waters was proposed based on ship’s track automatic control technique. The ship-track controller is developed based on adaptive fuzzy control technique, and can force a ship to steer on the prescribed path automatically. Consequently, an impersonal and advising strategy of ship steering/maneuvering action on the investigated constrained waters can be achieved. The simulation results provide a comparison of the advising policies between the experts’ maneuvering and the automatic control maneuvering on the marine simulators. Thus, the evaluation of ship traffic safety is conducted and performed by this mode. The results in this paper will provide a safe, reasonable and scientific reference policy on ship handling and the traffic safety assessment in the constrained waters.