Research on ship autonomous steering control for short-sea shipping problems

摘要

Today most ship rotation angle (steering control during movement) increase or decrease is done using an operator on deck or the auxiliary system in the ships engine room. Formal regulations suggest using manual inspection of the ship rotation and the work effectiveness of the engine during manoeuvring in ports and in the open sea regions. The accuracy of this procedure is very low and depends on the personnel of the deck. Therefore, automation and computer control systems are constantly required to assist the human eye. This problem becomes clearly visible when dealing with full ship autonomy in the open sea in the short-sea shipping regions. The trend of maritime technology development will only increase in the area of human interaction decrease with the physical operations and the shipping procedures, which will lead to the future full ship autonomy in the open sea regions around the globe. With the growing automation technologies, predictive control can prove to be a better approach than the traditionally applied visual inspection policy and linear control models. Ship full autonomy is also linked to the ship’s machinery regular repair and maintenance that has to be carried out for delivering satisfactory performance and minimizing downtime during transportation operations. In this paper, current stages of development of the intelligent transportation system concept are discussed for the ship autonomy in manoeuvring control and a robust ships’ systems integration and communication system concept is presented for several normal and abnormal situations: high-traffic, potentially dangerous situations or port approaching or ship maintenance, with the capability to solve problems with the limited human interface and with a remote control possibility. Then, simplified ship steering motor system for the main pump is analysed for rotation control using control voltage from the converters. Retrieved data from a small experimental control motor is used for the predictive control approach using two different methods: a neural network trained with Basic Levenberg– Marquardt Method and a Linear Model.