基于主成分分析与支持向量机的渠道闸前冰输移与堆积判别模型

梁乃生; 脱友才; 邓云; 贾云霄

doi:10.6052/0459-1879-20-391

基于主成分分析与支持向量机的渠道闸前冰输移与堆积判别模型

doi: 10.6052/0459-1879-20-391

四川大学水力学与山区河流开发保护国家重点实验室,成都 610065

基金项目: 1) 四川大学水力学与山区河流开发保护国家重点实验室开放课题基金(SKHL1604)

详细信息

作者简介:
2) 脱友才,副研究员,主要研究方向: 寒区水力学. E-mail: tuoyoucai@scu.edu.cn

通讯作者:
脱友才

中图分类号: TV875
计量
- 文章访问数: 467
- HTML全文浏览量: 141
- PDF下载量: 109
- 被引次数: 0
出版历程
- 收稿日期: 2020-11-20
- 刊出日期: 2021-03-10

CLASSIFICATION MODEL OF ICE TRANSPORT AND ACCUMULATION IN FRONT OF CHANNEL FLAT SLUICE BASED ON PCA-SVM

State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University,Chengdu 610065,China

摘要

摘要: 冬季渠道输水过程中浮冰容易在闸前形成堆积体,导致过水断面束窄,严重时影响渠道的输水效率和安全运行. 为判断渠道闸前浮冰的输移状态,开展了明渠水槽平板闸孔自由出流条件下的室内物理模型试验,提出了一种基于主成分分析与支持向量机(principal component analysis and support vectormachine,PCA-SVM)的闸前冰堆积与输移判别模型.通过相关性分析法确定输入特征间存在信息重叠,进而采用主成分分析法对特征向量进行降维,提取贡献率为86%的第一主成分和贡献率为7%的第二主成分作为输入特征,利用网格搜索方法确定多项式、高斯径向基和Sigmoid核函数的最优参数,通过混淆矩阵确定最优核函数为高斯径向基,最优核函数参数C为137,$\gamma$为0.37,建立PCA-SVM模型对试验数据进行监督学习.结果显示,模型在验证集上预测精确率为0.94,准确率为0.97,F1-Score为0.97,上游水流弗汝徳数($Fr_{1}$)和闸前水流弗汝徳数($Fr_{2}$)是渠道闸前冰输移与堆积的主要影响因素,闸孔相对开度($H/e$)和闸门相对淹没水深($H_{1}/H$)是次要影响因素.进一步将已建立的模型应用在倒虹吸口浮冰状态判别试验中,验证开发模型的分类性能.研究成果可为冬季输水渠道的调度管理和安全运行提供重要参考.
- 浮冰 /
- 闸孔 /
- 弗汝德数 /
- 支持向量机 /
- 渠道 /
- 物理模型试验
Abstract: Floating ice is easy to formed an ice jam in front of flat sluice of channel water delivery during the ice-affected seasons, which will affect the efficiency and safe operation of the channel in severe cases. Here, an experimental for free outflow of flat sluice in the open channel were studied based on indoor physical model test. In order to judge the condition of ice float in front of gates of the water conveyance channel. A discriminant model of ice accumulation and entrainment in front of gate based on Principal Components Analysis-Support Vector Machine(PCA-SVM) algorithm is proposed. The correlation analysis method is used to determine the information correlation between input features, and then the PCA method is used to reduce the dimension of the feature vectors. The aim is to improve the computational performance of the model. The first principal component with a contribution rate of 86% and the second principal component with a contribution rate of 7% were extracted as input features. The optimal parameters of Polynomial kernel function (POL), Gaussian Radial basis kernel function (RBF) and Sigmoid kernel function (SIG) were determined by grid search method. The optimal kernel function was determined as RBF by confusion matrix, and the optimal kernel function parameters C were 137 and $\gamma $ were 0.37. The PCA-SVM model was used for supervised learning of the experimental data. It is found that the $Fr_{1}$ and $Fr_{2}$ are the main influencing factors of ice entrainment or jam in front of gates, and the $H/e$ and $H_{1}/H$ are the secondary influencing factors. Furthermore, the established model was applied to the identify the floating ice state in front of the inverted siphon. The aim is to verify the classification performance of the developed model. The results are of the great value for the dispatching management and safe operation of water delivery channels during ice period.
- floating ice /
- flat sluice /
- Froude number /
- support vector machine /
- channel /
- physical model test

HTML全文

参考文献(34)

[1]	付辉, 杨开林, 郭永鑫, 等. 南水北调典型倒虹吸防冰塞安全运行试验. 水科学进展, 2013,24(5):736-740 (Fu Hui, Yang Kailin, Guo Yongxin, et al. An experimental study on ice jam prevention of typical inverted siphon for South-to-North Water Diversion Project. Advances in Water Science, 2013,24(5):736-740 (in Chinese))
[2]	Lindenschmidt K-E, Das A, Rokaya P, et al. Ice-jam flood risk assessment and mapping. Hydrological Processes, 2016,30(21):3754-3769
[3]	梁娜娜. 输水工程的水力过渡过程及运行控制研究. [硕士论文]. 大连:大连理工大学, 2019 (Liang Nana. Research of hydraulic transition process and hydraulic control for water diversion project. [Thesis]. Dalian: Dalian University of Technology, 2019(in Chinese))
[4]	邓淯宸. 水电站叠梁门分层取水进水口漩涡特性及临界淹没水深研究. [硕士论文]. 西安: 西安理工大学, 2019 (Deng Yuchen. Study on the characteristics and the critical submergence of vortex in multi-level stop-log gates intake of hydropower stations. [Thesis]. Xian: Xian University of Technology, 2019 (in Chinese))
[5]	陈云良. 进水口前立轴旋涡水力特性的研究. [博士论文]. 成都: 四川大学, 2006 (Chen Yunliang. Research for hydraulic characteristics of vertical vortex at hydraulic intakes. [PhD Thesis]. Chengdu: Sichuan University, 2006 (in Chinese))
[6]	孙洪亮, 刘亚坤, 刘洁洁, 等. 弧形闸门前旋涡临界淹没水深研究. 水动力学研究与进展A辑, 2017,32(3):374-379 (Sun HongLiang, Liu Yakun, Liu Jiejie, et al. Study on the critical submergence of vortex before radial gate. Chinese Journal of Hydrodynamics, 2017,32(3):374-379(in Chinese))
[7]	郑永朋, 牟献友, 冀鸿兰, 等. 闸孔出流条件下闸前冰块堆积形态研究. 人民黄河, 2020,42(6):27-31, 36 (Zheng Yongpeng, Mou Xianyou, Ji Honglan, et al. Research on Accumulation Morphology of Ice in Front of Sluice Under the Condition of Outflow from Sluice Opening. Yellow River, 2020,42(6):27-31, 36 (in Chinese))
[8]	裴少锋, 刘亚坤, 倪汉根. 闸前漩涡水力特性及形成条件的试验研究. 水利与建筑工程学报, 2012,10(5):55-60 (Pei Shaofeng, Liu Yakun, Ni Hangen. Experimental study on hydraulic characteristics and formation conditions of upstream vortex. Journal of Water Resources and Architectural Engineering, 2012,10(5):55-60 (in Chinese))
[9]	Ashton GD. Ice entrainment through sumberged gate//Martin Jasek. Proceedings the 19th IAHR International Symposium on Ice, Using new technology to understand water-ice interaction, Vancouver, 2008-7-6-11. Vancouver: St.Joseph Communications Press, 2008, 179-188
[10]	Fu H, Yang KL, Guo XL, et al. Safe operation of inverted siphon during ice period. Journal of Hydrodynamics, 2015,27(2):204-209
[11]	Mu XP, Bao J, Chen YF. Floating ice transport conditions at the cross-sections between pier columns in open ice-water two-phase flow canals. Water, 2020,12(6):1-19
[12]	吴艳, 朱明远, 穆祥鹏, 等. 渠道墩柱断面过冰能力研究. 水利水电技术, 2017,48(9):126-131 (Wu Yan, Zhu Mingyuan, Mu Xiangpeng, et al. Study on ice-passing capacity of pier-column section in channel. Water Resources and Hydropower Engineering, 2017,48(9):126-131 (in Chinese))
[13]	汪运鹏, 杨瑞鑫, 聂少军, 等. 基于深度学习技术的激波风洞智能测力系统研究. 力学学报, 2020,52(5):1304-1313 (Wang Yunpeng, Yang Ruixin, Nie Shaojun, et al. Deep-learning-based intelligent force measurement system using in a shock tunnel. Chinese Journal of Theoretical and Applied Mechanics, 2020,52(5):1304-1313 (in Chinese))
[14]	谢晨月, 袁泽龙, 王建春, 等. 基于人工神经网络的湍流大涡模拟方法. 力学学报, 2021,53(1):1-16 (Xie Chenyue, Yuan Zelong, Wang Jianchun, et al. Artificial neural network-based subgrid-scale models for large-eddy simulation of turbulence. Chinese Journal of Theoretical and Applied Mechanics, 2021,53(1):1-16 (in Chinese))
[15]	Sun W. River ice breakup timing prediction through stacking multi-type model trees. Science of the Total Environment, 2018,644:1190-1200
[16]	Sun W, Trevor B. Combining k-nearest-neighbor models for annual peak breakup flow forecasting. Cold Regions Science and Technology, 2017,143:59-69
[17]	Seidou O, Ouarda TBMJ, Bilodeau L, et al. Modeling ice growth on Canadian lakes using artificial neural networks. Water Resources Research, 2006,42(11):1-15
[18]	王涛, 杨开林, 郭永鑫. 神经网络理论在黄河宁蒙河段冰情预报中的应用. 水利学报, 2005,36(10):1204-1208 (Wang Tao, Yang Kailin, Guo Yongxin. Application of artificial neural networks to forecasting of river ice condition. Journal of Hydraulic Engineering, 2005,36(10):1204-1208 (in Chinese))
[19]	Cortes C, Vapnik V. Support-vector networks. Machine Learning, 1995,20(3):273-297
[20]	周志华. 机器学习. 北京: 清华大学出版社, 2017: 121-139 (Zhou Zhihua. Machine learning. Beijing: Tsinghua University Press, 2017: 121-139(in Chinese))
[21]	邓乃扬, 田英杰. 支持向量机-理论、算法与拓展. 北京:科学出版社, 2009: 81-111 (Deng Naiyang, Tian Yingjie. Support Vector Machine-Theory, Algorithm and Extension. Beijing: Science Press, 2009: 81-111(in Chinese))
[22]	刘彦涛. 基于支持向量机的冰塞水位预测. 合肥工业大学学报(自然科学版), 2010,33(10):1550-1552 (Liu Yantao. Forecasting of ice jam stage based on support vector machine. Journal of Hefei University of Technology(Natural Science), 2010,33(10):1550-1552 (in Chinese))
[23]	Kalke H, Loewen M. Support vector machine learning applied to digital images of river ice conditions. Cold Regions Science and Technology, 2018,155:225-236
[24]	高惠璇. 应用多元统计分析. 北京:北京大学出版社, 2017: 265-280 (Gao Huixuan. Applied multivariate statistical analysis. Beijing: Peking University Press, 2017: 265-280(in Chinese))
[25]	Ren L, Song C, Wu W, et al. Reservoir effects on the variations of the water temperature in the upper Yellow River, China, using principal component analysis. Journal of Environmental Management, 2020,262(15):110339.1-110339.10
[26]	Noori R, Karbassi AR, Moghaddamnia A, et al. Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction. Journal of Hydrology, 2011,401(3-4):177-189
[27]	徐国宾, 李大冉, 黄焱, 等. 南水北调中线输水工程若干冰力学问题试验研究. 水科学进展, 2010,21(6):808-815 (Xu Guobin, Li Daran, Huang Yan, et al. Laboratory study of problems in ice mechanics encountered in the middle route of south-to-north water transfer project. Advances in Water Science, 2010,21(6):808-815 (in Chinese))
[28]	Ashton GD. Froude criterion for ice-block stability. Journal or Glaciology, 1974,13(68):307-313
[29]	王军. 冰盖前缘处冰块稳定性研究. 人民黄河, 1997: 9-12, 28 (Wang Jun. Studies on the stability of ice at the front edge of the ice cover. Yellow River, 1997: 9-12, 28 (in Chinese))
[30]	Galelli S, Humphrey GB, Maier HR, et al. An evaluation framework for input variable selection algorithms for environmental data-driven models. Environmental Modelling & Software, 2014,62:33-51
[31]	Ma WL, Liu H . Classification method based on the deep structure and least squares support vector machine. Electronics Letters, 2020,56(11):538-541
[32]	何明辉, 毛嘉成, 范如玉, 等. 基于SVM回归的圆柱壳体抗脉冲强度预估模型. 力学学报, 2009,41(3):383-388 (He Minghui, Mao Jiacheng, Fan Ruyu, et al. The regression prediction model for the strength of cylinder shell against pulse loading based on support vector machine. Chinese Journal of Theoretical and Applied Mechanics, 2009,41(3):383-388 (in Chinese))
[33]	吴峰, 陈后金, 姚畅, 等. 基于网格搜索的PCA-SVM道路交通标志识别. 铁道学报, 2014,36(11):60-64 (Wu Feng, Chen Houjin, Yao Chang, et al. Traffic sign recognition based on PCA-SVM with grid search. Journal of the China Railway Society, 2014,36(11):60-64 (in Chinese))
[34]	Wang XH, Shu P, Cao L, et al. A ROC curve method for performance evaluation of support vector machine with optimization strategy// International Forum on Computer Science-Technology and Applications, Chongqing, 2009-12-25-27, Chongqing, IEEE, 2009: 117-1