Ship and static target collision risk anticipation method based on BP neural network

Abstract

The invention provides a ship and static target collision risk anticipation method based on a BP neural network. The method comprises the steps that S1, an AIS receiver acquires the static information, the dynamic information and the navigational information of the ship and stores the data; S2, the neural network model of the T moment is trained; S3, the ship position point of the T+N moment is predicted through the neural network model of the T moment, and the ship position point of the next time period is predicted in turn through iterative training of the new training data sample set; S4, the ship boundary points are acquired based on the ship position point of each moment; and S5, whether the ship passing area is intersected with the static target on the electronic channel chart is analyzed so as to judge the collision risk. According to the method, the ship is enabled to learn the historical courses and a model further meeting the actual motion process is constructed based on thedata points of the previous time period, the ship length and the ship width of the ship are considered and then the collision risk is anticipated so as to be closer to the actual situation and higherin accuracy.

Description

technical field [0001] The invention relates to the technical field of traffic management, in particular to a method for predicting the risk of collision between a ship and a static object based on a BP neural network. Background technique [0002] The collision risk prediction methods commonly used in existing navigation are to analyze the ship as a mass point, use the ship’s position point at this time as the reference point, and draw a line about 5 degrees to the left and right of the course line, and use these two straight lines and an arc The lines form a fan-shaped area, and whether there is a risk of collision is judged by whether there are obstacles in the area. This method has low precision and large errors, and it cannot meet the needs of ship pilots and VTS personnel well when the ship changes direction frequently or sails in restricted waters. Contents of the invention [0003] According to the above-mentioned technical problems, a method for predicting the ri...

AI Technical Summary

Problems solved by technology

This method has low accuracy and large errors, and it cannot meet the needs of ship drivers and VTS personnel when the ship changes direction frequently or sails in restricted waters

Images