An algorithmic approach to adaptive state filtering using recurrent neural networks

Practical algorithms are presented for adaptive state filtering in nonlinear dynamic systems when the state equations are unknown. The state equations are constructively approximated using neural networks. The algorithms presented are based on the two-step prediction-update approach of the Kalman filter. The proposed algorithms make minimal assumptions regarding the underlying nonlinear dynamics and their noise statistics. Non-adaptive and adaptive state filtering algorithms are presented with both off-line and online learning stages. The algorithms are implemented using feedforward and recurrent neural network and comparisons are presented. Furthermore, extended Kalman filters (EKFs) are developed and compared to the filter algorithms proposed. For one of the case studies, the EKF converges but results in higher state estimation errors that the equivalent neural filters. For another, more complex case study with unknown system dynamics and noise statistics, the developed EKFs do not converge. The off-line trained neural state filters converge quite rapidly and exhibit acceptable performance. Online training further enhances the estimation accuracy of the developed adaptive filters, effectively decoupling the eventual filter accuracy from the accuracy of the process model.

[1]  Thomas Parisini,et al.  Neural approximators for nonlinear finite-memory state estimation , 1997 .

[2]  Anuradha M. Annaswamy,et al.  Θ-adaptive Neural Networks: a New Approach to Parameter Estimation , 1996, IEEE Trans. Neural Networks.

[3]  Lothar Litz,et al.  Estimation of unmeasured inputs using recurrent neural networks and the extended Kalman filter , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[4]  Hans Günther Natke,et al.  Model-aided diagnosis of mechanical systems , 1996 .

[5]  Petre Stoica,et al.  Decentralized Control , 2018, The Control Systems Handbook.

[6]  Mukul Agarwal,et al.  Predictive control of a bench-scale chemical reactor based on neural-network models , 1998, IEEE Trans. Control. Syst. Technol..

[7]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[8]  Simon Haykin,et al.  Optimum nonlinear filtering , 1997, IEEE Trans. Signal Process..

[9]  James Ting-Ho Lo,et al.  Synthetic approach to optimal filtering , 1994, IEEE Trans. Neural Networks.

[10]  R. E. Kalman,et al.  New Results in Linear Filtering and Prediction Theory , 1961 .

[11]  G. Jonsson,et al.  An Application of Extended Kalman Filtering to Heat Exchanger Models , 1994 .

[12]  A. Parlos,et al.  Gain-Scheduled Nonlinear Control of U-Tube Steam Generator Water Level , 1992 .

[13]  Fred C. Schweppe,et al.  Uncertain dynamic systems , 1973 .

[14]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[15]  Yung C. Shin,et al.  Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems , 1994, IEEE Trans. Neural Networks.

[16]  Paul M. Frank,et al.  Issues of Fault Diagnosis for Dynamic Systems , 2010, Springer London.

[17]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[18]  Stephen A. Billings,et al.  Properties of neural networks with applications to modelling non-linear dynamical systems , 1992 .

[19]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[20]  A. Barron.  Approximation and Estimation Bounds for Artificial Neural Networks , 1991, COLT '91.

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

[22]  Amir F. Atiya,et al.  Application of the recurrent multilayer perceptron in modeling complex process dynamics , 1994, IEEE Trans. Neural Networks.

[23]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[24]  C. Shao,et al.  Robust nonlinear adaptive observer design using dynamic recurrent neural networks , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).

[25]  M. W. Owen,et al.  Targeted on-line modeling for an extended Kalman filter using artificial neural networks , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[26]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[27]  Amir F. Atiya,et al.  Multi-step-ahead prediction using dynamic recurrent neural networks , 2000, Neural Networks.

[28]  Andrew H. Jazwinski,et al.  Adaptive filtering , 1969, Autom..

[29]  R. German.  Sintering theory and practice , 1996 .

[30]  Amir F. Atiya,et al.  New results on recurrent network training: unifying the algorithms and accelerating convergence , 2000, IEEE Trans. Neural Networks Learn. Syst..

[31]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[32]  Arthur Gelb,et al.  Applied Optimal Estimation , 1974 .

[33]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[34]  Walter Herbert Strohmayer,et al.  Dynamic modeling of vertical U-tube steam generators for operational safety systems , 1982 .

[35]  M. Boutayeb,et al.  Convergence analysis of the extended Kalman filter used as an observer for nonlinear deterministic discrete-time systems , 1997, IEEE Trans. Autom. Control..

[36]  Lennart Ljung,et al.  Modeling Of Dynamic Systems , 1994 .

[37]  Thomas Parisini,et al.  On convergence of neural approximate nonlinear state estimators , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).

[38]  Dragan Obradovic,et al.  On-line training of recurrent neural networks with continuous topology adaptation , 1996, IEEE Trans. Neural Networks.

[39]  L. Ljung,et al.  A system identification perspective on neural nets , 1992, Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop.

[40]  Léon Personnaz,et al.  Construction of confidence intervals for neural networks based on least squares estimation , 2000, Neural Networks.

[41]  Janos Gertler,et al.  Fault detection and diagnosis in engineering systems , 1998 .

[42]  J. Suykens,et al.  Nonlinear system identification using neural state space models, applicable to robust control design , 1995 .

[43]  Jung In Choi.  Nonlinear digital computer control for the steam generator system in a pressurized water reactor plant , 1987 .

[44]  Simon Haykin,et al.  Adaptive filter theory (2nd ed.) , 1991 .

[45]  Graham C. Goodwin,et al.  Adaptive filtering prediction and control , 1984 .

[46]  Jia Lei,et al.  The state estimation of the CSTR system based on a recurrent neural network trained by HGAs , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[47]  K S Narendra,et al.  IDENTIFICATION AND CONTROL OF DYNAMIC SYSTEMS USING NEURAL NETWORKS , 1990 .

[48]  Konrad Reif,et al.  Stochastic stability of the discrete-time extended Kalman filter , 1999, IEEE Trans. Autom. Control..

[49]  R. N. Lobbia,et al.  An adaptive extended Kalman filter using artificial neural networks , 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.