Online estimation of noise parameters for Kalman filter

A Bayesian probabilistic method is proposed for online estimation of the process noise and measurement noise parameters for Kalman filter. Kalman filter is a well-known recursive algorithm for state estimation of dynamical systems. In this algorithm, it is required to prescribe the covariance matrices of the process noise and measurement noise. However, inappropriate choice of these covariance matrices substantially deteriorates the performance of the Kalman filter. In this paper, a probabilistic method is proposed for online estimation of the noise parameters which govern the noise covariance matrices. The proposed Bayesian method not only estimates the optimal noise parameters but also quantifies the associated estimation uncertainty in an online manner. By utilizing the estimated noise parameters, reliable state estimation can be accomplished. Moreover, the proposed method does not assume any stationarity condition of the process noise and/or measurement noise. By removing the stationarity constraint, the proposed method enhances the applicability of the state estimation algorithm for nonstationary circumstances generally encountered in practice. To illustrate the efficacy and efficiency of the proposed method, examples using a fifty-story building with different stationarity scenarios of the process noise and measurement noise are presented.

[1]  Mohinder S. Grewal,et al.  Kalman Filtering: Theory and Practice , 1993 .

[2]  Ka-Veng Yuen,et al.  Bayesian Probabilistic Approach for the Correlations of Compression Index for Marine Clays , 2009 .

[3]  S. Sangsuk-Iam,et al.  Analysis of discrete-time Kalman filtering under incorrect noise covariances , 1990 .

[4]  Ka-Veng Yuen,et al.  Structural health monitoring of Canton Tower using Bayesian framework , 2012 .

[5]  J. Beck,et al.  Updating Models and Their Uncertainties. I: Bayesian Statistical Framework , 1998 .

[6]  Costas Papadimitriou,et al.  Fatigue predictions in entire body of metallic structures from a limited number of vibration sensors using Kalman filtering , 2011 .

[7]  J. Beck,et al.  Entropy-Based Optimal Sensor Location for Structural Model Updating , 2000 .

[8]  Silian Lin,et al.  Identification of Natural Frequencies and Dampings of In Situ Tall Buildings Using Ambient Wind Vibration Data , 2004 .

[9]  A. H. Mohamed,et al.  Adaptive Kalman Filtering for INS/GPS , 1999 .

[10]  K. Yuen.  Bayesian Methods for Structural Dynamics and Civil Engineering , 2010 .

[11]  Lambros S. Katafygiotis,et al.  Bayesian time–domain approach for modal updating using ambient data , 2001 .

[12]  J. Beck,et al.  Model Selection using Response Measurements: Bayesian Probabilistic Approach , 2004 .

[13]  Cheng-Wu Chen,et al.  A novel regression prediction model for structural engineering applications , 2013 .

[14]  Tsung-Chien Chen,et al.  Intelligent fuzzy weighted input estimation method for the input force on the plate structure , 2010 .

[15]  Lambros S. Katafygiotis,et al.  An efficient simulation method for reliability analysis of linear dynamical systems using simple additive rules of probability , 2005 .

[16]  Ying Lei,et al.  A Two-Stage Kalman Estimation Approach for the Identification of Structural Parameters under Unknown Inputs , 2011 .

[17]  Ka-Veng Yuen,et al.  Selection of noise parameters for Kalman filter , 2007 .

[18]  Chan Ghee Koh,et al.  Identification and Uncertainty Estimation of Structural Parameters , 1994 .

[19]  James L. Beck,et al.  Propagating uncertainties for loss estimation in performance-based earthquake engineering using moment matching , 2009 .

[20]  Chung Bang Yun,et al.  Along-wind gust effect on elevated structures☆ , 1979 .

[21]  Lambros S. Katafygiotis,et al.  Model updating using noisy response measurements without knowledge of the input spectrum , 2005 .

[22]  J. Beck.  Bayesian system identification based on probability logic , 2010 .

[23]  K. Yuen,et al.  A novel probabilistic method for robust parametric identification and outlier detection , 2012 .

[24]  Bungale S. Taranath,et al.  Wind and Earthquake Resistant Buildings: Structural Analysis and Design , 2004 .

[25]  Alberto Zasso,et al.  Wind-induced dynamics and loads in a prismatic slender building: A modal approach based on unsteady pressure measurements , 2012 .

[26]  Yi-Qing Ni,et al.  Variability of measured modal frequencies of a cable-stayed bridge under different wind conditions , 2007 .

[27]  S. F. Schmidt,et al.  The Kalman filter - Its recognition and development for aerospace applications , 1981 .

[28]  Ka-Veng Yuen,et al.  Ambient interference in long-term monitoring of buildings , 2010 .

[29]  Ka-Veng Yuen,et al.  Bayesian Methods for Updating Dynamic Models , 2011 .

[30]  R. Mehra.  On the identification of variances and adaptive Kalman filtering , 1970 .

[31]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[32]  James L. Beck,et al.  Structural Health Monitoring via Measured Ritz Vectors Utilizing Artificial Neural Networks , 2006, Comput. Aided Civ. Infrastructure Eng..

[33]  Guanrong Chen,et al.  Kalman Filtering with Real-time Applications , 1987 .

[34]  Harold W. Sorenson,et al.  Recursive fading memory filtering , 1971, Inf. Sci..

[35]  James B. Rawlings,et al.  A new autocovariance least-squares method for estimating noise covariances , 2006, Autom..

[36]  J. Beck,et al.  Bayesian State and Parameter Estimation of Uncertain Dynamical Systems , 2006 .