基于GA优化BP神经网络的港口集装箱吞吐量预测

Ship Traffic Flow Prediction based on Genetic Algorithm to Optimize BP Neural Network

为了提高港口集装箱吞吐量的预测精度,在BP神经网络的基础上,结合遗传算法(GA)建立一个新的预测模型。该模型利用GA自适应搜索能力和较快的收敛速度,进而确定BP神经网络中的最优权值和阈值。以青岛港2012-2018年集装箱吞吐量统计数据为例,进行实例验证。结果表明,与传统的BP神经网络相比,该模型能显著地提高港口集装箱吞吐量的预测精度,用于预测港口集装箱吞吐量具有一定可行性。

In order to improve the prediction accuracy of port container throughput,a new prediction model was established based on BP neural network and genetic algorithm(GA).This model uses GA’s adaptive search capability and fast convergence speed to determine the optimal weights and thresholds in the BP neural network.Take the 2012-2018 container throughput statistics of Qingdao Port as an example to verify the case.The results show that compared with the traditional BP neural network,the model can significantly improve the prediction accuracy of port container throughput,and it is feasible to predict the port container throughput.