基于EEMD-PE-LSTM的短时船舶交通流量预测与航道交通状态可视化

周翔宇, 吉哲, 王凤武

doi:10.16411/j.cnki.issn1006-7736.2023.02.007

大连海事大学学报 >

2023 , Vol. 49 >Issue 2: 58 - 68

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2023.02.007

交通运输工程

基于EEMD-PE-LSTM的短时船舶交通流量预测与航道交通状态可视化

展开

(1. 大连海事大学航海学院, 辽宁大连 116026; 2. 大连市自主航运安全技术重点实验室, 辽宁大连 116026）

周翔宇*（1992 — ），男，博士，讲师，E-mail：zhou.x.y@outlook.com

网络出版日期: 2022-12-16

基金资助

国家重点研发计划项目（2021YFC2801005）；国家自然科学基金青年项目（52201408）;中央高校基本科研业务费专项资金资助项目（3132022132；3132022154）

收起

Short-term ship traffic flow prediction based on EEMD-PE-LSTM and visualization of channel traffic state

Expand

(1. Navigation College, Dalian Maritime University, Dalian 116026, China; 2. Dalian Key Laboratory of Safety & Security Technology for Autonomous Shipping, Dalian 116026, China)

Online published: 2022-12-16

Fold

摘要

为满足准确、快速预测短时船舶交通流量的需求，提出一种基于集合经验模态分解（EEMD）和排列熵（PE）优化长短时记忆（LSTM）神经网络的短时船舶交通流量预测模型。预测过程分为三个阶段：首先，利用EEMD算法降低短时船舶交通流量的非平稳性影响；然后，利用PE算法对EEMD分解的时间序列分量进行相空间重构，大幅缩短预测模型的运算时间；最后，将重构后的高低频分量和残差导入LSTM模型进行预测，预测值叠加后即可得到最终预测结果。通过采集的青岛港主航道连续366天共4392组船舶交通流量数据验证了模型的有效性。结果表明，本文EEMD-PE-LSTM模型的综合评价值最高，相比LSTM模型及EEMD-LSTM模型分别提升了167%和226%，能够更为精准迅速地反映未来短时船舶交通流量的变化情况。此外，为更直观地呈现船舶交通状态的动态转换过程，简化人工识别难度，利用K均值聚类算法对预测结果进行聚类，实现了航道交通状态的可视化，有效降低了一线船舶交通管理人员的工作负荷。

关键词： 短时船舶交通流量预测; 集合经验模态分解（EEMD); 排列熵(PE); 长短时记忆神经网络(LSTM); 航道交通状态可视化

本文引用格式

周翔宇, 吉哲, 王凤武 . 基于EEMD-PE-LSTM的短时船舶交通流量预测与航道交通状态可视化[J]. 大连海事大学学报, 2023 , 49(2) : 58 -68 . DOI: 10.16411/j.cnki.issn1006-7736.2023.02.007

Abstract

A novel short-time ship traffic flow prediction model was proposed to meet the needs of accurate and rapid prediction of short-time ship traffic flow. The proposed model optimizes Long Short Term Memory (LSTM) neural network based on Ensemble Empirical Mode Decomposition (EEMD) and Permutation Entropy (PE). The prediction process was divided into three stages. Firstly, EEMD was used to reduce the non-stationarity effect of short-term ship traffic flow. Secondly, PE was used to reconstruct the phase space of the time series components decomposed by EEMD to greatly shorten the operation time of the prediction model. Finally, the reconstructed high and low frequency components and residuals are imported into the LSTM model for prediction, and the final prediction result can be obtained after the predicted values are superimposed. The effectiveness of the model is verified by collecting 4392 sets of ship traffic flow data from the main channel of Qingdao Port for 366 consecutive days. The results show that the prediction performance of the proposed EEMD-PE-LSTM model is the best, which is improved by 167% and 226% re-spectively. The proposed model was proved that can reflect the changes of the future short-term ship traffic flow more accurately and quickly. Furthermore, the K-means clustering algorithm was used to cluster the prediction results, which can present the dy-namic transformation process of the ship traffic state more intuitively and simplify the difficulty of manual identification. The visu-alization of the channel traffic state is realized and the workload of front-line ship traffic management personnel is effectively re-duced using the clustering process.

Key words： shore-time ship traffic flow prediction; ensemble empirical mode decomposition(EEMD); permutation entropy(PE); long short term memory(LSTM); visualization of channel traffic state

参考文献

[1]张新宇,李瑞杰,林俊,等. Y 形分叉复式航道船舶交通调度优化建模[J]. 大连海事大学学报, 2018, 44(2): 1-8+14.

ZHANG X Y, LI R J, LIN J, et al. Optimization modeling of vessel traffic scheduling for Y shaped bifurcated compound waterway[J]. Journal of Dalian Maritime University,2018, 44(2): 1-8+14. (in Chinese)

[2]杨凯,唐卫东,刘诚,等. 基于LSTM 循环神经网络的大地电磁方波噪声抑制[J]. 物探与化探, 2022, 46(4): 925-933.

YANG K, TANG W D, LIU C, et al. Geomagnetic square wave noise suppression based on LSTM recurrent neural network[J]. Physical and Chemical Exploration,2022, 46(4): 925-933. (in Chinese)

[3]徐开心,戴宁,汝欣,等. 基于LSTM 循环神经网络的织机了机预测[J]. 现代纺织技术, 2023,31(3): 70-80.

XU K X, DAI N, RU X, et al. Loom off-machine prediction based on LSTM recurrent neural network[J]. Advanced Textile Technology, 2023,31(3): 70-80. (in Chinese)

[4]倪扬帆,杨媛媛,谢哲,等. 基于LSTM 与注意力结构的肺结节多特征抽取方法[J]. 上海交通大学学报,2022, 56(8): 1078-1088.

NI Y F, YANG Y Y, XIE Z, et al. A multi-feature extraction method for lung nodules based on LSTM and attention structure[J]. Journal of Shanghai Jiaotong University, 2022, 56(8): 1078-1088. (in Chinese)

[5]刘佳欣. 基于深度学习的港口船舶流量预测研究[D]. 济南:山东大学, 2021.

LIU J X. Research on port ship traffic prediction based on deep learning [ D]. Jinan: Shandong University,2021. (in Chinese)

[6] 苏伟杰,刘明俊. 基于鲸鱼算法优化Attention-BiLSTM 模型的短期船舶流量预测[J]. 武汉理工大学学报, 2022, 44(5): 34-39.

SU W J, LIU M J. Optimized Attention-Bi LSTM model based on whale algorithm for short-term ship traffic prediction[J]. Journal of Wuhan University of Technology,2022, 44(5): 34-39. (in Chinese)

[7]ZHOU X Y, LIU Z J, WANG F W, et al. Using deep learning to forecast maritime vessel flows[J]. Sensors, 2020, 20(6): 1761.

[8]王凯,刘文,陈进维,等. 基于VMD 和LSTM 的船舶交通流量预测方法研究[J]. 武汉理工大学学报(交通科学与工程版), 2022, 46(1): 177-182.

WANG K, LIU W, CHEN J W, et al. Research on ship traffic flow prediction method based on VMD and LSTM[J]. Journal of Wuhan University of Technology (Transportation Science and Engineering Edition), 2022, 46(1): 177-182. (in Chinese)

[9]刘敬贤,高广旭,刘奕,等. 基于卷积神经网络及长短时记忆网络的短时船舶交通流量预测[J]. 中国航海, 2022, 45(2): 56-61.

LIU J X, GAO G X, LIU Y, et al. Short-time ship traffic flow prediction based on convolutional neural network and long-short term memory network[J]. China Navigation,2022, 45(2): 56-61. (in Chinese)

[10]张矢宇,杨宇昊,陈尘,等. 基于回归-卡尔曼滤波组合模型的航道整治区域船舶交通流时空预测[J].大连海事大学学报, 2021, 47(1): 37-44.

ZHANG S Y, YANG Y H, CHEN C, et al. Spatio-temporal prediction of ship traffic flow in waterway regulation area based on regression Kalman filter combination model [ J]. Journal of Dalian Maritime University, 2021, 47(1): 37-44. (in Chinese)

[11]肖进丽,刘明俊,李晓磊. 基于集合经验模态分解和灰色神经网络的船舶交通流预测[J]. 武汉理工大学学报(交通科学与工程版), 2017, 41(6): 938-942.

XIAO J L, LIU M J, LI X L. Ship traffic flow prediction based on ensemble empirical modal decomposition and grey neural network[J]. Journal of Wuhan University of Technology (Transportation Science and Engineering Edition), 2017, 41(6): 938-942. (in Chinese)

[12]张瑞成,曹志新. 基于EEMD-LSTM 的冷连轧机振动预测研究[J]. 锻压技术, 2022, 47(9): 174-181.

ZHANG R C, CAO Z X. Research on vibration prediction of cold rolling mills based on EEMD-LSTM[J].Forging and Pressing Technology, 2022, 47(9): 174-181. (in Chinese)

[13]BANDT C, POMPE B. Permutation entropy: a natural complexity measure for time series[J]. Physical Review Letters, 2002, 88(17): 174102.

[14]郑诗禹. 青岛港集装箱海铁联运研究[J]. 中国储运, 2021(3): 82-83.

ZHENG S Y. Study on sea-rail intermodal transport of containers in Qingdao port [ J]. China Storage and Transportation, 2021(3): 82-83. (in Chinese)

[15]侯松虎. 青岛港通航环境安全分析研究[D]. 大连:大连海事大学, 2011.

HOU S H. Study on the safety analysis of navigational environment in Qingdao port[D]. Dalian : Dalian Maritime University, 2011. (in Chinese)

[16]周世波,熊振南. 基于局部密度的成山角船舶交通流特征分析[J]. 大连海事大学学报. 2019, 45(3):100-105.

ZHOU S B, XIONG Z N. Characteristic analysis of ship traffic flow at Chengshanjiao based on local density[J].Journal of Dalian Maritime University, 2019, 45(3):100-105. (in Chinese)

[17] SUN Y, LENG B, GUAN W. A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system[J]. Neurocomputing, 2015, 166: 109-121.

[18]冯辅周,饶国强,司爱威,等. 排列熵算法研究及其在振动信号突变检测中的应用[J]. 振动工程学报,2012, 25(2): 221-224.

FENG F Z, RAO G Q, SI A W, et al. Research on ranked entropy algorithm and its application in vibration signal mutation detection[J]. Journal of Vibration Engineering,2012, 25(2): 221-224. (in Chinese)

[19]李秉晨,于惠钧,刘靖宇. 基于K-means 和CEEMDPE-LSTM 的短期光伏发电功率预测[J]. 水电能源科学, 2021, 39(4): 204-208.

LI B C, YU H J, LIU J Y. Short-term photovoltaic power prediction based on K-means and CEEMD-PELSTM[J]. Hydropower Energy Science, 2021, 39(4):204-208. (in Chinese)

[20]肖进丽,李晓磊. 基于集合经验模态分解和差分进化算法优化BP 神经网络的船舶交通流预测[J]. 大连海事大学学报, 2018, 44(2): 9-14.

XIAO J L, LI X L. Optimized BP neural network for ship traffic flow prediction based on ensemble empirical modal decomposition and differential evolutionary algorithm[J]. Journal of Dalian Maritime University,2018, 44(2): 9-14. (in Chinese)

[21]赵阳阳,夏亮,江欣国. 基于经验模态分解与长短时记忆神经网络的短时地铁客流预测模型[J]. 交通运输工程学报, 2020, 20(4): 194-204.

ZHAO Y Y, XIA L, JIANG X G. Short-term metro passenger flow prediction based on EMD-LSTM [J].Journal of Traffic and Transportation Engineering,2020, 20(4): 194-204. (in Chinese)

[22]王知昊,元海文,李维娜,等. 交汇水域船舶轨迹预测与航行意图识别[J]. 交通信息与安全, 2022, 40(4): 101-109.

WANG Z H, YUAN H W, LI W N, et al. Trajectory prediction and intention identification of ships in confluence waters[J]. Journal of Transport Information and Safety, 2022, 40(4): 101-109. (in Chinese)

[23]何振欢,肖建华. 基于EEMD-LSTM 模型的禽霍乱预测研究[J]. 动物医学进展, 2022, 43(11): 34-38.

HEN Z H, XIAO J H. Research on prediction of fowl cholera based on EEMD-LSTM model[J]. Progress in Veterinary Medicine, 2022, 43(11): 34-38. (in Chinese)

[24]张博中. 基于船舶大数据的交通状态识别及可视化技术研究[D]. 大连: 大连海事大学, 2020.

ZHANG B Z. Research on traffic status identification and visualization technology based on ship big data[D]. Dalian : Dalian Maritime University, 2020. (in Chinese)

[25]王全民,胡德程. 基于Spark 的K-means 快速聚类算法的优化[J]. 计算机仿真, 2022, 39(3): 344-349.

WANG Q M, HU D C. Optimization of K-means fast clustering algorithm based on Spark[J]. Computer Simulation,2022, 39(3): 344-349. (in Chinese)

[26]张树奎,肖英杰. 考虑周期性波动因素的船舶交通流量预测模型[J]. 大连海事大学学报, 2016, 42(4):41-46.

ZHANG S K, XIAO Y J. Prediction model of ship traffic flow based on periodic fluctuation factors[J]. Journal of Dalian Maritime University[J], 2016, 42(4):41-46. (in Chinese)

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献