提升航道和港口资源的高效、合理利用，需精准掌握船舶交通流量情况。为此，本文提出基于支持向量机的船舶交通流量预测方法。该方法以船舶交通流量数据为基础，经预处理后将其作为采用支持向量机的输入量，通过输入量和输出量之间的高维映射，预测船舶交通流量；通过鲸鱼优化算法优化支持向量机的核参数和惩罚项参数；通过迭代寻优获取最优的参数结果，以此保证舰船交通流量预测结果的精准程度。测试结果表明：该方法能可靠完成不同航行环境下的船舶交通流量预测，均等系数均在0.019以下；中心可依据预测结果对船舶进行管理，高效、合理实现港口资源利用，减少船舶等待进港时间。
To improve the efficient and reasonable use of channel and port resources by port departments, it is necessary to accurately grasp the ship traffic flow. Therefore, a ship traffic flow prediction method based on support vector machine is proposed. This method is based on the ship traffic flow data, which is preprocessed as the input of support vector machine, and predicts the ship traffic flow through the high-dimensional mapping between the input and output; The whale optimization algorithm is used to optimize the kernel parameters and penalty parameters of the support vector machine, and the optimal parameter results are obtained through iterative optimization to ensure the accuracy of the ship traffic flow prediction results. The test results show that this method can reliably predict the ship traffic flow under different navigation environments, with the equalization coefficient below 0.019. The port dispatching center can dispatch ships according to the prediction results, efficiently and reasonably realize the utilization of port resources, reduce the waiting time for ships to enter the port, and improve the throughput of ships.
2023,45(5): 160-163 收稿日期：2022-09-11
DOI：10.3404/j.issn.1672-7649.2023.05.031
分类号：TP391
基金项目：江苏航运职业技术学院科研课题（HYKY/2020B03）
作者简介：曾晓晴(1983-),女,硕士,讲师,研究方向为物流管理及交通运输管理
