基于DE-SVM的船舶航迹预测模型

Ship trajectory prediction model based on DE-SVM

为提高船舶航迹预测精度,解决准确建模难度大和神经网络易陷入局部最优的问题,考虑实时获取目标船AIS数据较少的特点,提出一种基于支持向量机(support vector machine,SVM)的航迹预测模型。选择AIS数据中的航速、航向和船舶经纬度作为样本特征变量;采用小波阈值去噪的方法处理训练数据;采用差分进化(differential evolution,DE)算法对模型内部参数寻优以提高模型收敛速度和预测精度。选取天津港实船某段航迹的AIS数据,比较基于DE-SVM与基于BP神经网络的航迹预测模型的仿真结果。结果表明,基于DE-SVM的航迹预测模型具有更高的预测精度,简单、可行、高效,且耗时少。

In order to improve the accuracy of ship trajectory prediction,and solve the problem that accurate modeling is difficult and the neural network is prone to fall into local optimum,considering the fact that the target ship AIS data acquired in real time are less,a ship trajectory prediction model based on support vector machine(SVM)is proposed.The ship speed,course,longitude and latitude in AIS data are selected as sample feature variables,and the wavelet threshold denoising method is adopted to process the training data.The differential evolution(DE)algorithm is used to optimize the internal parameters of the model to improve the convergence speed and prediction accuracy of the model.The AIS data of a certain section of ship trajectory in Tianjin Port is selected,and the simulation results using the ship trajectory prediction models based on DE-SVM and BP neural network are compared.The results show that the ship trajectory prediction model based on DE-SVM is of higher prediction accuracy,it is simple,feasible and efficient,and it takes less time.