Multi-scale deformation combination forecast model for concrete dam based on BP-ARIMA
-
摘要: 针对大坝变形常规统计预报模型在监测信息挖掘时的优势单一性及预报精度欠佳等问题,视大坝变形观测资料为非平稳时间序列,从影响大坝变形的因素出发,将其分为周期性影响因素与随机影响因素,利用多尺度小波分析方法将大坝变形监测序列分解并重构,结合BP神经网络与自回归积分滑动平均模型(Autoregressive Integrated Moving Average Model,简记ARIMA)对其随机信号与系统信号分项训练预报,并将其预报值相叠加,据此,应用时间序列原理提出了一种基于BP-ARIMA的混凝土坝多尺度变形组合预报模型。工程实例分析表明,所建组合模型较常规模型能够有效挖掘监测信息中所蕴含的有效成分,预报精度显著提升,且计算分析过程简便,为高边坡及水工建筑物中其他监测指标的预报提供了新方法。Abstract: In conventional dam deformation monitoring models, information mining of dam prototype observation data is limited and forecast precision is not up to standard. Dam deformation prototype data can be regarded as non-stationary time series, and considering the influence factors of dam deformation, it can be decomposed into cyclical factors and random factors. Dam deformation monitoring data are decomposed and reconstructed by multi-scale wavelet analysis method in this paper, BP neural network and Autoregressive Integrated Moving Average Model (ARIMA) are separately used to analyze and forecast the random signal and system signal contained in deformation monitoring data, and the forecast values based on the two models are superimposed, and the multi-scale deformation combination forecast value for concrete dam based on BP-ARIMA is proposed according to the time series principle. Example shows that, compared with the conventional models, active components contained in the monitoring data are effectively excavated, and the forecast precision is improved obviously, meanwhile, the calculation and analysis process is simple in the proposed combination model. A new method of the deformation forecast for high slope and other hydraulic structures is presented.
-
Key words:
- concrete dam /
- deformation forecast /
- wavelet analysis /
- BP neural network /
- ARIMA model
-
表 1 3种预报模型的统计指标比较
Table 1. Statistical indexes of three forecast models
统计指标 PL2测点 PL5测点 拟合段 预报段 拟合段 预报段 BP模型 ME/mm 8.852×10-1 5.614×10-1 3.310×10-1 4.329×10-1 MSE/mm 2.025×10-1 6.742×10-1 1.878×10-1 1.575×10-1 MAPE 2.522×10-1 2.361×10-1 2.357×10-1 4.921×10-2 回归模型 ME/mm 9.149×10-1 1.005 8.925×10-1 7.304×10-1 MSE/mm 1.124×10-1 8.383×10-1 9.483×10-1 9.976×10-1 MAPE 9.836×10-1 3.235×10-1 4.267×10-1 4.310×10-1 组合模型 ME/mm 8.036×10-1 2.074×10-1 2.433×10-1 3.438×10-1 MSE/mm 2.15×10-2 1.86×10-2 2.68×10-2 6.14×10-2 MAPE 4.85×10-2 3.57×10-2 5.72×10-2 6.43×10-2 -
[1] 丛培江, 顾冲时, 谷艳昌.大坝安全监控指标拟定的最大熵法[J].武汉大学学报(信息科学版), 2008, 33(11): 1126-1129. http://kns.cnki.net/KCMS/detail/detail.aspx?filename=whch200811006&dbname=CJFD&dbcode=CJFQ CONG Peijiang, GU Chongshi, GU Yanchang. Maximum entropy method for determining dam safety monitoring indices[J]. Geomatics and Information Science of Wuhan University, 2008, 33(11): 1126-1129. (in Chinese) http://kns.cnki.net/KCMS/detail/detail.aspx?filename=whch200811006&dbname=CJFD&dbcode=CJFQ [2] 曹茂森, 邱秀梅, 夏宁.大坝安全诊断的混沌优化神经网络模型[J].岩土力学, 2006, 27(8): 1344-1348. http://www.cnki.com.cn/Article/CJFDTotal-YTLX200608024.htm CAO Maosen, QIU Xiumei, XIA Ning. A chaos-optimized neural network model for dam safety monitoring[J]. Rock and Soil Mechanics, 2006, 27(8): 1344-1348. (in Chinese) http://www.cnki.com.cn/Article/CJFDTotal-YTLX200608024.htm [3] 吴中如.水工建筑物安全监控理论及其应用[M].北京:高等教育出版社, 2003. WU Zhongru. Safety monitoring theory and its application of hydraulic structures[M]. Beijing: Higher Education Press, 2003. (in Chinese) [4] 徐伟, 何金平.基于多尺度小波分析的大坝变形自回归预测模型[J].武汉大学学报(工学版), 2012, 45(3): 285-289. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=whsldldxxb201203004 XU Wei, HE Jinping. Forecast model of dam deformation based on multi-scale wavelet analysis and autoregressive method[J]. Engineering Journal of Wuhan University, 2012, 45(3): 285-289. (in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=whsldldxxb201203004 [5] 张豪, 许四法.基于经验模态分解和遗传支持向量机的多尺度大坝变形预测[J].岩石力学与工程学报, 2011, 30(增刊2): 3681-3688. http://www.cqvip.com/QK/96026X/2011S2/1003580339.html ZHANG Hao, XU Sifa. Multi-scale dam deformation prediction based on empirical mode decomposition and genetic algorithm for support vector machines (GA-SVM)[J]. Chinese Journal of Rock Mechanics and Engineering, 2011, 30(Suppl2): 3681-3688. (in Chinese) http://www.cqvip.com/QK/96026X/2011S2/1003580339.html [6] 黎良辉, 魏博文, 徐镇凯.考虑混凝土坝位移动力突变盲点的安全监控模型[J].人民长江, 2013, 44(13): 58-62. doi: 10.3969/j.issn.1001-4179.2013.13.015 LI Lianghui, WEI Bowen, XU Zhenkai. Safety monitoring model for concrete dam considering blind spot in dynamic mutation of deformation[J]. Yangtze River, 2013, 44(13): 58-62. (in Chinese) doi: 10.3969/j.issn.1001-4179.2013.13.015 [7] ZHANG Fan, HU Wusheng. Application of neural network merging model in dam deformation analysis[J]. Journal of Southeast University(English Edition), 2013, 29(4): 441-444. http://dma.lsgi.polyu.edu.hk/JISDM-Proceeding/Proceeding/Full paper/117.pdf [8] 张俊, 殷坤龙, 王佳佳, 等.基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究[J].岩石力学与工程学报, 2015, 34(2): 382-391. http://www.cnki.com.cn/Article/CJFDTotal-YSLX201502019.htm ZHANG Jun, YIN Kunlong, WANG Jiajia, et al. Displacement prediction of Baishuihe landside based on time series and PSO-SVR model[J]. Chinese Journal of Rock Mechanics and Engineering, 2015, 34(2): 382-391. (in Chinese) http://www.cnki.com.cn/Article/CJFDTotal-YSLX201502019.htm [9] 张正虎, 袁孟科, 邓建辉, 等.基于改进灰色-时序分析时变模型的边坡位移预测[J].岩石力学与工程学报, 2014, 33(增刊2): 3791-3797. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yslxygcxb2014z2049 ZHANG Zhenghu, YUAN Mengke, DENG Jianhui, et al. Displacement prediction of slope based on improved grey-time series time-varying model[J]. Chinese Journal of Rock Mechanics and Engineering, 2014, 33(Suppl2): 3791-3797. (in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yslxygcxb2014z2049 [10] 何金平, 马传彬, 施玉群.高拱坝多效应量改进型D-S证据理论融合模型[J].武汉大学学报(信息科学版), 2012, 37(12): 1397-1400. http://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201212004.htm HE Jinping, MA Chuanbin, SHI Yuqun. Multi-effect quantity fusion model of high arch dam based on improved D-S evidence theory[J]. Geomatics and Information Science of Wuhan University, 2012, 37(12): 1397-1400. (in Chinese) http://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201212004.htm [11] 梅泽宇, 许青, 康飞.基于人工蜂群算法-逐步回归模型的大坝变形监测[J].防灾减灾工程学报, 2013, 33(6): 651-656, 670. http://www.wanfangdata.com.cn/details/detail.do?_type=degree&id=Y2415906 MEI Zeyu, XU Qing, KANG Fei. Dam deformation monitoring based on stepwise regression model with artificial bee colony algorithm[J]. Journal of Disaster Prevention and Mitigation Engineering, 2013, 33(6): 651-656, 670. (in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=degree&id=Y2415906 [12] 周伟, 花俊杰, 常晓林, 等.水布垭高面板堆石坝运行期工作性态评价及变形预测[J].岩土工程学报, 2011, 33(增刊1): 65-70. http://www.oalib.com/paper/4369918 ZHOU Wei, HUA Junjie, CHANG Xiaolin, et al. Estimation of work status and deformation prediction of Shuibuya CFRD[J]. Chinese Journal of Geotechnical Engineering, 2011, 33(Suppl1): 65-70. (in Chinese) http://www.oalib.com/paper/4369918 [13] 魏博文, 熊威, 李火坤, 等.融合混沌残差的大坝位移蛙跳式组合预报模型[J].武汉大学学报(信息科学版), 2016, 41(9): 1272-1278. http://www.cnki.com.cn/Article/CJFDTOTAL-WHYC201405004.htm WEI Bowen, XIONG Wei, LI Huokun, et al. Dam deformation forecasting of leapfrog combined model merging residual errors of chaos[J]. Geomatics and Information Science of Wuhan University, 2016, 41(9): 1272-1278. (in Chinese) http://www.cnki.com.cn/Article/CJFDTOTAL-WHYC201405004.htm [14] 魏博文, 彭圣军, 徐镇凯, 等.顾及大坝位移残差序列混沌效应的GA-BP预测模型[J].中国科学(技术科学), 2015, 45(5): 541-546. http://www.cnki.com.cn/Article/CJFDTotal-JEXK201505013.htm WEI Bowen, PENG Shengjun, XU Zhenkai, et al. The GA-BP prediction model considering chaos effect of dam displacement residual[J]. Science China (Technological Sciences), 2015, 45(5): 541-546. (in Chinese) http://www.cnki.com.cn/Article/CJFDTotal-JEXK201505013.htm [15] ZHENG K H, WANG Z Q. Application of systematical optimization GM (1, 1) model based on lifting wavelet in dam displacement forecast[J]. Applied Mechanics and Materials, 2014, 488-489(3): 759-764. https://www.scientific.net/AMM.488-489.759 [16] XI G Y, YUE J P, ZHOU B X, et al. Application of an artificial immune algorithm on a statistical model of dam displacement[J]. Computers and Mathematics with Applications, 2011, 62(10): 3980-3986. doi: 10.1016/j.camwa.2011.09.057 [17] 姜振翔, 徐镇凯, 魏博文.基于小波分解和支持向量机的大坝位移监控模型[J].长江科学院院报, 2016, 33(1): 43-47. doi: 10.11988/ckyyb.20140690 JIANG Zhenxiang, XU Zhenkai, WEI Bowen. A monitoring model of dam displacement based on wavelet decomposition and support vector machine[J]. Journal of Yangtze River Scientific Research Institute, 2016, 33(1): 43-47. (in Chinese) doi: 10.11988/ckyyb.20140690 [18] RANKOVIC ' V, GRUJOVIC ' N, DIVAC D, et al. Development of support vector regression identification model for prediction of dam structural behaviour[J]. Structural Safety, 2014, 48(48): 33-39. https://www.sciencedirect.com/science/article/pii/S0167473014000174 [19] SU H Z, CHEN Z X, WEN Z P. Performance improvement method of support vector machine-based model monitoring dam safety[J]. Structural Control and Health Monitoring, 2016, 23(2): 252-266. doi: 10.1002/stc.1767 [20] 李双平, 张斌.基于小波与谱分析的大坝变形预报模型[J].岩土工程学报, 2015, 37(2): 374-378. doi: 10.11779/CJGE201502024 LI Shuangping, ZHANG Bin. Forecast model for dam deformation based on wavelet and spectral analysis[J]. Chinese Journal of Geotechnical Engineering, 2015, 37(2): 374-378. (in Chinese) doi: 10.11779/CJGE201502024 [21] 罗德河, 郑东健.大坝变形的小波分析与ARMA预测模型[J].水利水运工程学报, 2016(3): 70-75. http://slsygcxb.cnjournals.org/ch/reader/view_abstract.aspx?file_no=201603009&flag=1 LUO Dehe, ZHENG Dongjian. Wavelet analysis and ARMA prediction model for dam deformation[J]. Hydro-Science and Engineering, 2016(3): 70-75. (in Chinese) http://slsygcxb.cnjournals.org/ch/reader/view_abstract.aspx?file_no=201603009&flag=1 [22] REN F, WU X, ZHANG K, et al. Application of wavelet analysis and a particle swarm-optimized support vector machine to predict the displacement of the Shuping landslide in the Three Gorges, China[J]. Environmental Earth Sciences, 2015, 73(8): 4791-4804. doi: 10.1007/s12665-014-3764-x [23] FAN W, QIAO P. Vibration-based damage identification methods: a review and comparative study[J]. Structural Health Monitoring, 2011, 10(1): 83-111. doi: 10.1177/1475921710365419 [24] CHENY, OYADIJI S O. Delamination detection in composite laminate plates using 2D wavelet analysis of modal frequency surface[J]. Computers and Structures, 2017, 179: 109-126. doi: 10.1016/j.compstruc.2016.10.019 [25] YAN Q, MA C. Application of integrated ARIMA and RBF network for groundwater level forecasting[J]. Environmental Earth Sciences, 2016, 75(5): 1-13. doi: 10.1007/s12665-015-5198-5 [26] SHUMWAY R H, STOFFER D S. Time series analysis and its applications: with R examples[M]. Springer Science and Business Media, 2010. -