智能水位预测服务系统研究

潘明阳; 周海南; 李增辉; 刘乙赛; 李超; 李昱

doi:10.16411/j.cnki.issn1006-7736.2020.03.004

大连海事大学学报 >

2020 , Vol. 46 >Issue 3: 31 - 37

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2020.03.004

船舶与海洋工程

智能水位预测服务系统研究

潘明阳 ,
周海南 ,
李增辉 ,
刘乙赛 ,
李超 ,
李昱

展开

(1. 大连海事大学航海学院，辽宁大连 116026;2. 长江南京航道局，南京 210011)

潘明阳（1975 — ），男，博士，副教授，E-mail：panmingyang@dlmu.edu. cn.

收稿日期: 2020-01-31

修回日期: 2020-03-25

网络出版日期: 2020-03-25

基金资助

中央高校基本科研业务费专项资金资助项目（3132019400）.

收起

Research on intelligent water level prediction service system

PAN Ming-yang ,
ZHOU Hai-nan ,
LI Zeng-hui ,
LIU Yi-sai ,
LI Chao ,
LI Yu

Expand

（1. Navigation College, Dalian Maritime University, Dalian 116026，China;2. Yangtze River Nanjing Waterway Bureau，Nanjing 210011，China）

Received date: 2020-01-31

Revised date: 2020-03-25

Online published: 2020-03-25

Fold

摘要

为提高内河航道水位预测精度，利用深度神经网络深入研究内河水位的智能预测，提出基于GRU循环神经网络的多站联动水位预测模型.在长江下游多个水位站30年8时水位观测数据集上的实验结果表明，该模型能够综合利用上下游水位站间的水位值关联性，从而减小了单水位站数据随机性的影响，具有较高的预测精确度，其5日预测的最大平均相对误差值MRE优于经典ARIMA模型，也优于单水位站的GRU模型.利用Tensor Flow Serving对预测模型进行部署，并通过基于Spring Boot及Vue.js等技术的前后端分离框架开发智能水位预测服务系统，系统的各个部分独立部署，通过RESTful API接口对接，具有很好的松耦合性和灵活性.系统的预测结果可通过Web页面、APP和微信公众号等多种形式展示，为内河航运用户提供了便利的智能服务.

关键词： 内河航道; 水位预测; 门控循环单元(GRU); Tensor Flow Serving; 智能服务

本文引用格式

潘明阳 , 周海南 , 李增辉 , 刘乙赛 , 李超 , 李昱 . 智能水位预测服务系统研究[J]. 大连海事大学学报, 2020 , 46(3) : 31 -37 . DOI: 10.16411/j.cnki.issn1006-7736.2020.03.004

Abstract

In order to improve the accuracy of water level prediction in inland waterway, the intelligent prediction of water level in inland waterway was studied by using depth neural network. A multi station linkage water level prediction model based on GRU cycle neural network was proposed. The experimental results on the water level observation data sets of several water level stations in the lower reaches of the Yangtze River at 8:00 in 30 years show that the model can make full use of the correlation of water level values between the upstream and downstream water level stations, reduce the impact of the randomness of single water level station data, and with a high prediction accuracy. The maximum average relative error value MRE of 5-day prediction is better than the classic ARIMA model, and also better than the GRU model of single water level station type. The prediction model is deployed by using TensorFlow Serving, and the intelligent water level prediction service system is developed by the front-end and back-end separation framework based on Spring Boot, Vue.js and other technologies. Each part of the system is deployed independently and connected through the RESTful API interface, which has good loose coupling and flexibility. The prediction results can be displayed in various forms, such as Web pages, APP and WeChat official account, which provides convenient intelligent services for inland river users.

Key words： inland waterway; water level prediction; Gated Recurrent Unit(GRU); Tensor Flow Serving; intelligent service

参考文献

[1]Alsova O C. An Adaptive Algorithm for Hydrological Time Series Forecasting Based on the Selection of an Analogue-Period[J]. Trudy SPIIRAN, 2016, 3(46):27-39.
[2]张展羽,梁振华,冯宝平等. 基于主成分-时间序列模型的地下水位预测[J]. 水科学进展,2017,28(3):415-420. Zhang Z Y, Liang Z H, et al. Groundwater level forecast based on principal component analysis and multivariate time series model[J]. Advances in Water Science, 2017, 28(3): 415-420. (in Chinese)
[3]Liu Z, Tan M , Zha X, et al. Hydrological time series forecasting based on WD-RSPA model——A case study of Makou Station and Shenzhen Station[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2017, 56(5): 119-126 and 138.
[4]Yang Jun-He,Cheng Ching-Hsue,Chan Chia-Pan. A Time-Series Water Level Forecasting Model Based on Imputation and Variable Selection Method[J]. Computational intelligence and neuroscience, 2017(3): 1-11.
[5]要震,许继平,孔建磊,刘松波. 基于GA-Elman的河流水位预测方法研究[J]. 长江科学院院报, 2018, 35(9): 34-37.
Yao Z, Xu J P, et al. Prediction of River Water Level by GA-Elman Model[J]. Journal of Yangtze River Scientific Research Institute, 2018, 35(9): 34-37. (in Chinese)
[6]Guo T, He W, Jiang Z, et al. An improved LSSVM model for intelligent prediction of the daily water level[J]. Energies, 2019, 12(1): 112.
[7]Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8) : 1735-1780.
[8]Cho K, Van Merri?nboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. arXiv preprint arXiv:1406.1078, 2014.
[9]Chung J, Gulcehre C, Cho K H, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[C]. in NIPS 2014 Workshop on Deep Learning, December 2014.
[10]王体迎, 时鹏超, 刘蒋琼等. 基于门限递归单元循环神经网络的交通流预测方法研究[J]. 重庆交通大学学报(自然科学版), 2018, 37(11): 76-82.
Wang T Y, Shi P C, et al. Research on Traffic Flow Prediction Method Based on Gated Recurrent Unit Recurrent Neural Network[J]. Journal of Chongqing Jiaotong University(Natural Science), 2018, 37(11): 76-82. (in Chinese)
[11]卢升荣,刘瑶. 极端水位对长江中游船舶交通流特征的影响[J]. 重庆交通大学学报(自然科学版), 2017, 36(03): 103-107.
Lu S R, Liu Y. Impact of Extreme Water Levels on Characteristics of Vessel Traffic Flow in the Middle Reaches of Yangtze River[J]. Journal of Chongqing Jiaotong University(Natural Science), 2017, 36(03): 103-107. (in Chinese)
[12]郜宁健. 基于Spring Boot的高校海洋数据共享平台的开发[D]. 浙江海洋大学, 2019.
Gao L J. Development of University Ocean Data Sharing Platform Based on Spring Boot[D]. Zhejiang Ocean University, 2019. (in Chinese)
[13]王璐, 崔保磊, 潘红霞, 赵莉, 田宇. 基于Vue.js的在线设计开放平台研究与实现[J]. 信息技术与信息化, 2019(11): 168-170.
Wang L, Cui B L, et al. Research and implementation of online design open platform based on vue.js[J]. Information Technology and Informatization, 2019(11): 168-170. (in Chinese)
[14]TensorFlow. (2020). [online] Availabe at: https://www.tensorflow.org/tfx/serving/architecture [Accessed 2020-01-29].

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献