计算机科学 ›› 2017, Vol. 44 ›› Issue (5): 268-271.doi: 10.11896/j.issn.1002-137X.2017.05.048
占鹏飞,吕鑫,毛莺池,徐淑芳,王龙宝,马鸿旭
ZHAN Peng-fei, LV Xin, MAO Ying-chi, XU Shu-fang, WANG Long-bao and MA Hong-xu
摘要： 卡尔曼滤波模型被广泛运用于大坝的变形预测,然而其参数的识别,尤其是状态和观测噪音协方差矩阵的识别,主要来源于工程经验和领域专家知识。因此提出一种自学习的参数识别方法,该方法基于历史数据,结合Monte Carlo和拒绝采样算法获取卡尔曼滤波参数。具体地,从训练样本中挑选出与真实值最接近的实测值对状态噪音进行估计,并通过计算它与总体误差的差值来确定观测噪音。实验表明,相比已有的同类方法,该方法的准确性更高,更适用于大坝变形预测。
| [1] GU C S,WU Z R.Safety Monitering of Dams and Dam Foundations－Theories & Methods and Their Application[M].Nanjing:Hohai University Press,2006.(in Chinese) 顾冲时,吴中如.大坝与坝基安全监控理论和方法及其应用[M].南京:河海大学出版社,2006. [2] WANG W,SHEN Z Z,LI T F.Safety Early Warning Evaluation Model for Dams Based on Coupled Method of Genetic Algorithm and Adapting Particle Swarm Optimization Algorithm [J].Chinese Journal of Geotechnical Engineering,2009,31(8):1242-1247.(in Chinese) 王伟,沈振中,李桃凡.遗传算法与自适应粒子群算法耦合的大坝安全预警评价模型[J].岩土工程学报,2009,31(8):1242-1247. [3] KOSE E,TASCI L.Prediction of the Vertical Displacement on the Crest of Keban Dam[J].Journal of Grey System,2015,27(1):12-20. [4] XU H Z,WU Z R,SHI B,et al.Neural Network Method for Determining the Component Proportion of Dam Effect Variable [J].Journal of Hydraulic Engineering,2003,34(6):111-114.(in Chinese) 徐洪钟,吴中如,施斌,等.确定大坝效应量分量比例的神经网络方法[J].水利学报,2003,34(6):111-114. [5] JIANG C,XU F,LV X,et al.A Novel Changeable Sliding Window Method for Predicting Horizontal Displacement of Dam Foundation[C]∥2015 14th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES).IEEE,2015(3):497-500. [6] HE J,YANG G.Application of Cloud Model Based Kalman Filtering to Determination of Crack Opening Monitoring Index of Concrete Gravity Dam[J].Water Resources and Power,2015(3):57-59.(in Chinese) 何军,杨光.基于卡尔曼滤波的云模型在某混凝土重力坝裂缝监控指标拟定中的应用[J].水电能源科学,2015(3):57-59. [7] SU G N,ZHENG D J,SUN B B.Application of Kalman Filtering Grey Model in Prediction of Dam Deformation [J].Water Resources and Power,2014(4):37-40.(in Chinese) 苏观南,郑东健,孙斌斌.卡尔曼滤波灰色模型在大坝变形预测中的应用[J].水电能源科学,2014(4):37-40. [8] ZHANG L M,LIU W D,QIN P.Deforamation Analysis of RCC Arch Dam Vertical Displacement Based on Kalman Filter Me-thod[J].Hydropower Automation and Dam Monitoring,2011,35(6):52-54.(in Chinese) 张黎明,刘为东,秦鹏.基于卡尔曼滤波法的碾压混凝土拱坝垂直位移变形分析[J].水电自动化与大坝监测,2011,35(6):52-54. [9] WELCH G,BISHOP G.An introduction to the kalman filter[J].University of North Carolina at Chapel Hill,2006,8(7):127-132 . [10] KALMAN R E.A new approach to linear filtering and prediction problems[J].Journal of basic Engineering,1960,82(1):35-45. [11] FARAGHER R.Understanding the basis of the Kalman filter via a simple and intuitive derivation[J].IEEE Signal processing magazine,2012,29(5):128-132. [12] MAYBECK P S.Stochastic models,estimation,and control[M].Academic Press,1982. [13] MURPHY K P.Machine learning:a probabilistic perspective[M].MIT Press,2012. |
| No related articles found! |
|
||
首页