A new likelihood approach to autonomous multiple model estimation.

This paper presents an autonomous multiple model (AMM) estimation algorithm for hybrid systems with sudden changes in their parameters. Estimates of Kalman filters (KFs) that are tuned and employed for different system modes are merged based on a newly defined likelihood function without any necessity for filter interaction. The proposed likelihood function is composed of two measures, the filter agility measure and the steady-state error measure. These measures are derived based on filter adaptation rules. The numerical results show that the proposed algorithm, so called Competing AMM (CAMM), guarantees both steady-state estimation accuracy and quick parameter tracking.

[1]  H. Saito,et al.  Design and on-orbit evaluation of magnetic attitude control system for the “REIMEI” microsatellite , 2008, 2008 10th IEEE International Workshop on Advanced Motion Control.

[2]  Thiagalingam Kirubarajan,et al.  Estimation with Applications to Tracking and Navigation , 2001 .

[3]  Erik Hartikainen,et al.  Enhanced Network-State Estimation using Change Detection , 2006, Proceedings. 2006 31st IEEE Conference on Local Computer Networks.

[4]  Zhenyu Yang,et al.  Joint Parametric Fault Diagnosis and State Estimation Using KF-ML Method , 2014 .

[5]  Rui Xiong,et al.  A double-scale and adaptive particle filter-based online parameter and state of charge estimation method for lithium-ion batteries , 2018 .

[6]  Halil Ersin Soken,et al.  Multiple-Model Adaptive Estimation of Time-Varying Residual Magnetic Moment for Small Satellites , 2015 .

[7]  Yuanxi Yang.  Adaptively Robust Kalman Filters with Applications in Navigation , 2010 .

[8]  Xiaoming Hu,et al.  An optimization approach to adaptive Kalman filtering , 2009, Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference.

[9]  V. Jilkov,et al.  Survey of maneuvering target tracking. Part V. Multiple-model methods , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[10]  Dan Simon,et al.  Optimal State Estimation: Kalman, H∞, and Nonlinear Approaches , 2006 .

[11]  Yang Genke,et al.  Multiobjective extremal optimization with applications to engineering design , 2007 .

[12]  Rafael Wisniewski,et al.  In-orbit estimation of time-varying residual magnetic moment , 2014, IEEE Transactions on Aerospace and Electronic Systems.

[13]  Krishna Dev Kumar,et al.  Fault estimation of satellite reaction wheels using covariance based adaptive unscented Kalman filter , 2017 .

[14]  Fredrik Gustafsson,et al.  Adaptive filtering and change detection , 2000 .

[15]  H. Michalska,et al.  An adaptive GLR estimator for state estimation of a maneuvering target , 2005, Proceedings of the 2005, American Control Conference, 2005..

[16]  T. Ortmaier,et al.  Adaptive High-Gain Observer for Joint State and Parameter Estimation: A Comparison to Extended and Unscented Kalman Filter , 2014 .

[17]  Qinghua Zhang,et al.  Stochastic Hybrid System Actuator Fault Diagnosis by Adaptive Estimation , 2015 .

[18]  Hongye Su,et al.  An adaptive observer for joint estimation of states and parameters in both state and output equations , 2011 .

[19]  Amir Averbuch,et al.  Interacting Multiple Model Methods in Target Tracking: A Survey , 1988 .

[20]  Mahendra P. Singh,et al.  An adaptive unscented Kalman filter for tracking sudden stiffness changes , 2014 .

[21]  Jerome R. Busemeyer,et al.  Parameter Estimation with Quantum Inspired Techniques and Adaptive Multiple-Model Filters , 2018, 2018 Annual American Control Conference (ACC).

[22]  Nicolas Boizot,et al.  An adaptive high-gain observer for nonlinear systems , 2010, Autom..

[23]  Zhen Sun,et al.  Nonlinear System Identification and Its Applications in Fault Detection and Diagnosis , 2013 .

[24]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

[25]  Sirish L. Shah,et al.  Constrained dual ensemble Kalman filter for state and parameter estimation , 2013, 2013 American Control Conference.

[26]  S. Sakai,et al.  A multiple model adaptive estimation algorithm for systems with parameter change , 2016, 2016 55th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE).

[27]  Yonggang Zhang,et al.  A Novel Adaptive Kalman Filter With Inaccurate Process and Measurement Noise Covariance Matrices , 2018, IEEE Transactions on Automatic Control.