The purpose of this study is to explore the potentiality of wind propulsion on semi-submersible ships. A new type of Flettner rotor (two rotating cylinders) system installed on a semi-submersible ship is proposed. The structure and installation of two cylinders with a height of 20 m and a diameter of 14 m are introduced. The numerical simulation of the cylinder is carried out in Fluent software. The influence of apparent wind angle and spin ratio on the two cylinders are analysed, when the distance between two cylinders is 3D-13D (D is cylinder diameter). When the distance between two cylinders is 3D, the performance of the system increases with an increase in spin ratio. Moreover, the apparent wind angle also has an effect on the system performance. Specifically, the thrust contribution of the system at the apparent wind angle of 120° is the largest at the spin ratio of 3.0. The maximum thrust reaches 500 kN. When the spin ratio is 2.5 and the apparent wind angle is 120°, the maximum effective power of the system is 1734 kW. In addition, the influence of the two cylinders distance on system performance cannot be ignored. When the distance between the two cylinders is 7D and the spin ratio is 2.5, the effective power of the system reaches a maximum, which is 1932 kW.

This paper proposes a text classification model based on a bi-directional LSTM network with attention mechanism and subsampling in the word vector stage. Firstly, we use the Skip-gram model in Word2Vec for feature extraction, and then combine the two-way LSTM network with subsampling to extract and classify the key semantic information in the text, and integrate the Attention mechanism to optimize the generation weights, enhance the feature transfer between layers, and focus attention on the high weight words. Experimental results on different categories of open datasets show that the proposed model improves the recognition and extraction of high-featured content compared to a single network, and can effectively improve classification accuracy.

This paper investigates a filter design method for dynamic positioning control system based on the wave peak frequency tracking algorithm. The wave peak frequency varies randomly with the sea condition, ship speed, wave direction and other factors. The performance of the filter is greatly affected by the real-time recognition of the wave peak frequency. The wave disturbance model is indicated as an autoregressive moving average (ARMA) model and the recursive extended least squares (RELS) algorithm is proposed to identify the wave peak frequency with the auxiliary model idea. A filter with the wave peak frequency tracker is constructed to evaluate the effectiveness of the proposed filter. Ultimately, simulation results show that the proposed filter can effectively track the wave peak frequency and can still effectively reduce the influence of waves on the ship control system when the peak frequency changes.

No abstract

No abstract