Learn More
According to the problem of small samples and nonlinear feature in fault diagnosis of marine diesel engine, comprehensively using the methods of grey relational analysis and kernel fuzzy c-means clustering, a method solving fault diagnosis of marine diesel engine is proposed. Firstly, kernel fuzzy c-means clustering was made on historical fault dataset.(More)
An online neural-net control system, in which learning and control are independently carried out, is proposed for the problem of ship motion control, including roll, yaw and sway stabilization at the same time. Disturbance models, including roll moment, yaw moment and sway force induced by sea wave and wind, are presented by the experimental data in tank.(More)
A method of data driven fault diagnosis for ship course control of sensor fault and steering gear fault in this paper. The offline data are used to identify the parity space and vector, and designed observer class residual generator, which can construct the residual signal, and evaluate the threshold value, so as to realize fault diagnosis of abnormal(More)
An integral nested sliding mode control (INSMC) is proposed for the ship turning control problem by employing integral sliding mode (ISM) and nested sliding mode (NSM) concepts. This controller has the robustness of NSM against matched and unmatched perturbations, and the capability of ISM to reduce the sliding functions gains. The simulation illustrates(More)
A sliding mode variable structure controller is designed in this paper for the two-stage inverted pendulum, and the parameters of controller is given by pole placement method. The simplex optimization method based on the performance index of integrated time and absolute error (ITAE) to optimize the parameters of controller is purposed for the difficulty of(More)
The single-step neural network combining prediction model and the multi-step neural network combining prediction model are researched on this paper, and those models are applied to the ship pitch motion prediction. Firstly the single-step neural network combination prediction model is proposed and the optimal combination of the conventional single-step(More)
A system, which can capture the real time image of ablative surface under strong stray light environments caused by plasma arc, has been presented. The system has been under nearly one year of service in some national key laboratory. It has been shown that the system can effectively shield the influence of plasma jet and stray light with the temperature(More)