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。
Kalman filter is widely applied to dam deformation prediction. However, the identification of parameters to the model, especially the state and observation noise eovariance matrices, is derived mostly from the experience of engi- neering or expert knowledge. Therefore, a self-learning method was proposed for parameter identifying, in which the pa- rameters of Kalman filter are determined by the combination of Monte Carlo and rejection sampling algorithm from his- tory data. More precisely, the state noise sorted out from training ones is evaluated by samples, whose observations ap- proximate actual value completely, and the observation noise is determined by calculating the difference of the aforemen- tioned noise and overall error. The experiment result shows that the proposed method is more accurate than other con- gener ones, and it＇s more applicable to dam deformation prediction.
出处
《计算机科学》
CSCD
北大核心
2017年第5期268-271,275,共5页
Computer Science
基金
水利部公益性行业科研专项经费项目(201501007)
NSFC-广东联合基金重点项目(U1301252)
国家科技支撑计划(2013BAB06B04
HNKJ13-H17-04)
国家自然科学基金面上项目(61272543)资助
