Analysis and Prediction of Water Traffic Accidents in Jingtang Port based on Improved GM(1,1) Model

Abstract

The prediction of water traffic accidents is important for port safety management. There are various influential factors for the water traffic which presents challenges for the prediction of water traffic accident. The traditional grey model (GM) gained much popularity in prediction applications, but the prediction accuracy is not satisfactory for the complex nonlinear system. In this paper, the GM is improved by tuning generation coefficients of the traditional model to better tracking the changing tendency of the system. The improved model is validated by water traffic accident prediction simulations based on the accident statistics of Jingtang Port in Tangshan in the last seven years. The results show that different prediction sequences correspond to different values of generation coefficient, which can get high -precision level predictions. The simulation results demonstrated the effectiveness and efficiency of the proposed improved GM(1,1) model.