摘要
大坝变形的时空演变预测分析有助于大坝管理人员及时掌握大坝空间的整体变形状态。目前,大坝变形预测研究分为两个方面:1)通过仅对分布变形仪器部位进行时间序列预测,得出下一时刻的变形值(如BP神经网络);2)利用周围变形数据进行空间插值,得到当前时刻未分布仪器点的变形值。单独使用上述任何一种方法都无法利用历史变形数据预测下一时刻未分布仪器部位的变形状况。针对该问题,结合空间预测模型时空克里金方法(STKriging,STK)与神经网络模型即BP神经网络及门限循环神经网络(Gated Recurrent Unit,GRU)各自的优势,构造了一种新型时空序列预测算法(BP-STK-GRU),实现了对未分布监测仪器部位的变形值预测。主要步骤包括:1)GRU优化单个测点的历史时间序列变形值;2)BP拟合测点下一时刻数据的整体趋势;3)利用STK拟合BP预测结果的稳定部分;4)结合空间插值及BP空间整体预测值,得出未分布仪器点的变形值。实验结果表明,所提方法是有效的,并且在对未知点的变形预测稳定性及精确度方面都有很好的表现。
The analysis of the spatial-temporal evolution of dam deformation is conducive for managers to master the overall deformation of the dam's space.The existing predictive research on dam deformation can be divided into two parts.The first part is only making time series prediction for instrument part with distribution deformation,and the second part is using a method of spatial interpolation at the current moment to obtain unknown point's value of deformation.Both of these cannot use the historical deformation time series data to predict the deformation of the undistributed instrument.To solve this problem,combining the advantages of traditional spatial-temporal prediction model(STK)and neural network modelssuch such as BP and Gated Recurrent Unit(GRU),this paper constructed a spatio-temporal sequence prediction algorithm named BP-STK-GRU.The main steps are described as follows.Firstly,GRU optimizes the historical time series of individual measuring points.Secondly,BP fits the overall trend of spatio-temporal data at measuring points of the next moment.Thirdly,STK fits the stable parts of BP prediction results.Lastly,the spatial residual value and the overall BP space prediction are combined to get the deformation of the undistributed instrument.The experimental results show that the method is effective,and it has good performance in predicting the stability and accuracy of the deformation value of the unknown point.
引文
[1] JHA S K,PUPPALA H.Assessment of subsurface temperature distribution from the gauged wells of Puga Valley,Ladakh[J].Geothermal Energy,2017,5(1):3-17.
[2] QIU L T,SHEN Z Z,NIE B S.Deformation Prediction of Dam Based on Stepwise Regression Analysis-Markov Chain Model[J].Water Resources and Power,2014,32(5):51-55.(in Chinese)邱莉婷,沈振中,聂柏松.基于逐步回归分析——马尔可夫链模型的大坝变形预测[J].水电能源科学,2014,32(5):51-55.
[3] LI S,SHU H,DONG L.Research and realization of Kriging interpolation based on spatial-temporal variogram[J].Computer Engineering and Applications,2011,47(23):25-26.(in Chinese)李莎,舒红,董林.基于时空变异函数的Kriging插值及实现[J].计算机工程与应用,2011,47(23):25-26.
[4] WANG J M,ZHANG J,DENG Z B,et al.Slope deformation analysis with space-time Kriging interpolation method[J].Journal of China Coal Society,2014,39(5):874-879.(in Chinese)王建民,张锦,邓增兵,等.时空Kriging插值在边坡变形监测中的应用[J].煤炭学报,2014,39(5):874-879.
[5] LI L,REVESZ P.Interpolation methods for spatio-temporal geographic data[J].Computers Environment&Urban Systems,2004,28(3):201-227.
[6] HAYHOE H,LAPEN D,ANDREWS C.Using weather indices to predict survival of winter wheat in a cool temperate environment[J].International Journal of Biometeorology,2003,47(2):62-72.
[7] ASTERIOU D,HALL S G.ARIMA Models and the Box-Jenkins Methodology[M]∥Applied Econometrics Palgrave MacMillan.2011:265-286.
[8] HAN R L,TONG L J,ZHU S H,et al.The Coordinated Development of Economy and Environment Based on ARMA Model in Shenyang Economic Zone[J].Scientia Geographica Sinica,2014,34(1):32-39.(in Chinese)韩瑞玲,佟连军,朱绍华,等.基于ARMA模型的沈阳经济区经济与环境协调发展研究[J].地理科学,2014,34(1):32-39.
[9] BARZAGHI R,CAZZANIGA N E,DE GAETANI C I,et al.Estimating and Comparing Dam Deformation Using Classical and GNSS Techniques[J].Sensors,2018,18(3):756-766.
[10]GOURINE B,KHELIFA S.Analysis of Dam Deformation Using Artificial Neural Networks Methods and Singular Spectrum Analysis[C]∥Euro-Mediterranean Conference for Environmental Integration.Springer,Cham,2017:871-874.
[11]SU H Z,LI X,YANG B B,et al.Wavelet support vector machine-based prediction model of dam deformation[J].Mechanical Systems and Signal Processing,2018,110:412-427.
[12]DAI B,GU C,ZHAO E,et al.Statistical model optimized random forest regression model for concrete dam deformation monitoring[J].Structural Control&Health Monitoring,2018,25(8):e2170.
[13]ZHANG H L,FAN Z D.Nonlinear Monitoring Model of Concrete Dam Deformation Based on Improved PSO-ELM Algorithm[J].Water Resources&Power,2018,36(1):82-84.(in Chinese)张海龙,范振东.基于改进PSO-ELM算法的混凝土坝变形非线性监控模型[J].水电能源科学,2018,36(1):82-84.
[14]SU H Z,WEN Z P,YAN X Q,et al.Early-warning model of deformation safety for roller compacted concrete arch dam considering time-varying characteristics[J].Composite Structures,2018,203:373-381.
[15]JIN S J,BAO T F,CHEN D H,et al.EMD decomposition method-based dam deformation prediction model and its application[J].Water Resources&Hydropower Engineering,2017,48(12):41-44.(in Chinese)金盛杰,包腾飞,陈迪辉,等.基于EMD分解法的大坝变形预测模型及应用[J].水利水电技术,2017,48(12):41-44.
[16]DEY R,SALEMT F M.Gate-variants of Gated Recurrent Unit(GRU)neural networks[C]∥International Midwest Symposium on Circuits and Systems.IEEE,2017:1597-1600.
[17]NIU Z W,YU Z Y,LI B,et al.Short-term wind power forecasting model based on deep gated recurrent unit neural network[J].Electric Power Automation Equipment,2018,38(5):36-42.(in Chinese)牛哲文,余泽远,李波,等.基于深度门控循环单元神经网络的短期风功率预测模型[J].电力自动化设备,2018,38(5):36-42.
[18]JI K.Evaluation of Mining Engineering technology innovation ability and application based on BP neural network[C]∥International Conference on Industrial Technology and Management.IEEE,2017:55-59.
[19]WANG J,SHI P,JIANG P,et al.Application of BP Neural Network Algorithm in Traditional Hydrological Model for Flood Forecasting[J].Water,2017,9(1):1-48.
[20]SHEN C,LI C,SI Y.Spatio-temporal autocorrelation measures for nonstationary series:A new temporally detrended spatiotemporal Moran’s index[J].Physics Letters A,2016,380(1-2):106-116.
[21]SIDAK E V,SMIRNOV D A,BEZRUCHKO B P.Estimation of the coupling delay time from time series of self-oscillatory systems with allowance for the autocorrelation function of phase noise[J].Technical Physics Letters,2014,40(10):934-936.
