Research On Intelligent Navigation Collision Avoidance Algorithm Based On Internet Of Things

With the strategy of “The Belt and Road Initiatives” put forward,the idea of “The 21 st century Maritime Silk Road” pushed the Chinese maritime to a new height.The increase of maritime volume also brings unprecedented challenges to the safety of navigation.At present,the navigation of ships mainly rely on the sailing experience and judgment of the duty driver.The navigational facilities such as Radar,Automatic Identification System(AIS)and Automatic Radar Plotter(ARPA)and so on are used as the auxiliary equipment to provide information about the vessel and its surrounding environment for the driver taking ship collision avoidance strategy.However,the ship-ship collisions still exist,resulting in a large number of property losses and casualties.How to prevent the occurrence of marine collision accidents becomes an urgent problem to be solved.In order to improve the safety of navigation,scholars have done a lot of work on intelligent collision avoidance decision-making and achieved certain results.With the gradual penetration of the Internet of Things technology in many fields,such as Intelligent Transportation,Intelligent Home,Health Monitoring and so on,making the whole society more intelligent.The paper integrated the key technologies of them into the intelligent navigation,designed an intelligent navigation algorithm,which can provide a real-time prediction of ship collision risk degree and can “predict” the collision risk degree of the place where the ship may reach in the next moment in advance.And the work done in this paper is as follows:(1)The paper presents the model of intelligent navigation system based on the basic architecture of Internet of Things.The model includes the sensing layer,the transmission layer and the application layer.The sensing layer is mainly based on various types of intelligent sensors in IOT,which is used to collect various kinds of information.The transmission layer is based on the middle-ware of IOT and Zigbee protocol,which is used to transmit the information.The last is the application layer,the intelligent collision avoidance is one of the applications and used to compute and process the prediction of ship collision risk.(2)Through the further study of intelligent collision avoidance algorithm at home and abroad,this paper designs an improved intelligent collision avoidance algorithm based on the AHP analytic hierarchy process and BP neural network algorithm,which adds the environmental factor and can vary according to the practical environment.So the algorithm has more practical application value.Firstly,the paper determines the weight of factors that affect the safety of navigation based on the AHP.And then combines the values of each influencing factor with their weights to determine the environment factor dynamically;Determine the optimal prediction time T Based on the real-time data collected by the sensing layer and the environment factor.Secondly,builds the BP neural network model to study the ships' navigation habits,and then predict the coordinates of the ship(marked as P)after T minutes based on well-trained BP neural network.Finally,according to the knowledge of nautical knowledge,build the navigation model to assess the risk of collision of P;Then build the collision avoidance priority list according to collision risk degree between two vessels.(3)The paper improves the modeling and simulation all parts of intelligent navigation collision avoidance algorithm on the MATLAB platform.The feasibility and effectiveness of the proposed algorithm are verified by a large number of experiments on the actual navigation route data of fishing vessels and cargo ships in the Bohai Sea as test cases.