基于文化萤火虫算法-广义回归神经网络的船舶交通流量预测

doi:10.16183/j.cnki.jsjtu.2020.04.011

摘要/Abstract

摘要： 为了给海事部门提供科学准确的船舶交通流量预测，本文提出一种基于文化萤火虫算法（CFA）来优化广义回归神经网络（GRNN）的算法(CFA-GRNN)，对船舶交通流量进行预测分析.介绍了基于自动识别系统(AIS)的航道交通流量统计方法.利用快速排斥试验和跨立试验来判断船舶轨迹是否穿过航道某一断面的观测线，并将AIS数据中的经纬度数据转换为墨卡托平面坐标系数据.研究了GRNN的实现原理，CFA以GRNN输出均方差为适应度函数，以GRNN的输入层和隐含层中的权值、隐含层和输出层中的权值、隐含层的阈值及输出层的阈值为编码进行优化，进化目标是得到最合适、最优的神经网络结构.利用AIS收集统计到并经过预处理后的数据, 应用CFA-GRNN对舟山螺头通航的船舶进行交通流量预测, 并对试验结果和误差进行了统计分析.结果表明：CFA-GRNN与GRNN和萤火虫优化广义回归神经网络相比，泛化性能好，不易陷入局部最优，预测结果精度更高.本研究对船舶交通流量进行预测分析有着十分重要的理论和实际意义.

关键词: 船舶交通流量预测；广义回归神经网络；文化算法；萤火虫算法

Abstract: In order to provide the maritime department with the scientific and accurate prediction of the essel traffic flow, this paper proposes an algorithm based on the cultural firefly algorithm (CFA) to optimize the generalized regression neural network (GRNN) to predict vessel traffic flow. This paper introduces the statistial method of fairway traffic flow based on automatic indentity system (AIS). Fast rejection test and cross stand test are used to judge whether the ship track passes through the observation line of a certain cross section of the channel. The latitude and longitude data in the AIS data is converted to the Mercator plane coordinate system. The realization principle of GRNN is studied. CFA takes the output mean square error of GRNN as fitness function. Its encoding takes the weight value in the input and hidden layers, the weight value in the hidden layer and the output layer, the threshold of the hidden layer and the threshold of the output layer. Its evolutionary goal is to get the most suitable and optimal structure of GRNN. With the statistics and pretreatment data collected from AIS, the CFA-GRNN is used to predict the vessel traffic flow, and the experimental results and errors are analyzed. The results show that CFA-GRNN has better generalization performance and higher accuracy of the prediction results than GRNN and firely algorithm-GRNN, and is not easy to fall into local optimum. This study is of theoretical and practical significance for forecasting and analyzing ship traffic flow.

Key words: vessel traffic flow prediction; general regression neural network (GRNN); cultural algorithm; firefly algorithm (CFA)

中图分类号:

U 61

薛晗，邵哲平，潘家财，张锋. 基于文化萤火虫算法-广义回归神经网络的船舶交通流量预测[J]. 上海交通大学学报, 2020, 54(4): 421-429.

XUE Han，SHAO Zheping，PAN Jiacai，ZHANG Feng. Vessel Traffic Flow Prediction Based on CFA-GRNN Algorithm[J]. Journal of Shanghai Jiaotong University, 2020, 54(4): 421-429.

参考文献

［1］WANG C B, ZHANG X Y, CHEN X, et al. Vessel traffic flow forecasting based on BP neural network and residual analysis［C］//2017 4th International Conference on Information, Cybernetics and Computational Social Systems (ICCSS). Dalian, China: IEEE, 2017: 350-354. ［2］崔翔鹏, 黄洪琼. 基于GA优化ELM的船舶交通流预测模型［J］. 微型机与应用, 2017, 36 (9): 15-17. CUI Xiangpeng, HUANG Hongqiong. Ship traffic flow prediction model based on GA-ELM algorithm［J］. Microcomputer and Its Applications, 2017, 36(9): 15-17. ［3］王林生, 蔡丽霞. 模糊控制在船舶交通流量预测中的应用研究［J］. 舰船科学技术, 2016, 38(8): 97-99. WANG Linsheng, CAI Lixia.Application of fuzzy control in ship traffic flow prediction［J］. Ship Science and Technology, 2016, 38(8): 97-99. ［4］LI X, XIAO J, LIU M. Vessel traffic flow prediction based on the SARIMA model［J］. Journal of Wuhan University of Technology, 2017, 41 (2): 329-332. ［5］LIU R W, CHEN J W, LIU Z, et al. Vessel traffic flow separation-prediction using low-rank and sparse decomposition［C］//2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). Yokohama, Japan: IEEE, 2017: 1-6. ［6］WANG H Y, WANG Y Z. Vessel traffic flow forecasting with the combined model based on support vector machine［C］//2015 International Conference on Transportation Information and Safety. Wuhan, China: IEEE, 2015: 695-698. ［7］CHEN J B, TIAN Y H, YING S J. Optimized LS-SVR method applied to vessel traffic flow prediction［C］//2010 Second International Conference on Computational Intelligence and Natural Computing (CINC). Wuhan, China: IEEE, 2010: 315-320. ［8］ZHANG H, XIAO Y J, BAI X G, et al. GA-support vector regression based ship traffic flow prediction［J］. International Journal of Control and Automation, 2016, 9(2): 219-228. ［9］张树奎, 肖英杰. 船舶交通流量预测的灰色神经网络模型［J］. 上海海事大学学报, 2015, 36(1): 46-49. ZHANG Shukui, XIAO Yingjie. Grey neural network model for ship traffic flow prediction［J］. Journal of Shanghai Maritime University, 2015, 36(1): 46-49. ［10］李俊, 徐志京, 唐贝贝. 基于GA优化的灰色神经网络船舶交通流量预测方法研究［J］. 船海工程, 2013, 42(5): 135-137. LI Jun, XU Zhijing, TANG Beibei. Prediction method of ship flow based on grey-neural network improved by GA［J］. Ship and Ocean Engineering, 2013, 42(5): 135-137. ［11］钮浩东, 黄洪琼. 基于FOA优化GRNN的船舶交通流预测模型［J］. 微型机与应用, 2016, 35(12): 81-83. NIU Haodong, HUANG Hongqiong. Ship traffic flow prediction model based on FOA-GRNN algorithm［J］. Microcomputer and Its Applications, 2016, 35(12): 81-83. ［12］ALI M Z, AWAD N H. A novel class of niche hybrid cultural algorithms for continuous engineering optimization［J］. Information Sciences, 2014, 267(2): 158-190. ［13］YANG X S. Firefly algorithm, stochastic test functions and design optimization［J］. International Journal of Bio-Inspired Computation, 2010, 2(2): 78-84. ［14］SUNDARI M G, RAJARAM M, BALARAMAN S. Application of improved firefly algorithm for programmed PWM in multilevel inverter with adjustable DC sources［J］. Applied Soft Computing, 2016, 41(4): 169-179. ［15］LIANG R H, WANG J C, CHEN Y T, et al. An enhanced firefly algorithm to multi-objective optimal active/reactive power dispatch with uncertainties consideration［J］. International Journal of Electrical Power and Energy Systems, 2015, 64(1): 1088-1097. ［16］ADIL B, FEHMI B O. Adaptive firefly algorithm with chaos for mechanical design optimization problems［J］. Applied Soft Computing, 2015, 36(C): 152-164. ［17］RIZK-ALLAH R M, ZAKI E M, EL-SAWY A A. Hybridizing ant colony optimization with firefly algorithm for unconstrained optimization problems［J］. Applied Mathematics and Computation, 2013, 224(1): 473-483. ［18］RAHMANI A, MIRHASSANI S A. A hybrid firefly-genetic algorithm for the capacitated facility location problem［J］. Information Sciences, 2014, 283(4): 70-78. ［19］KORA P, KRISHNA K S R. Hybrid firefly and particle swarm optimization algorithm for the detection of bundle branch block［J］. International Journal of the Cardiovascular Academy, 2016, 2(1): 44-48. ［20］李兴锋. 基于S-57国际标准的电子海图显示与导航系统［D］. 西安: 西安电子科技大学, 2007. LI Xingfeng. Electronic chart display and navigation system based on S-57 international standard［D］. Xi′an: Xidian University, 2007. ［21］SPECHT D F. A general regression neural network［J］. IEEE Transactions On Neural Networks, 1991, 2(6): 568-576. ［22］SOLIS F J, WETS R J. Minimization by random search techniques［J］. Mathematics of Operations Research, 1981, 6(1): 19-30.