Multi-step-ahead prediction using dynamic recurrent neural networks

In numerous problems, such as in process control utilizing predictive control algorithms, it is required that a variable of interest be predicted multiple time-steps ahead into the future without having measurements of that variable in the horizon of interest. Additionally, in applications involving forecasting and fault diagnosis the availability of multistep-ahead predictors (MSP) is desired. MSPs are difficult to design because lack of measurements in the prediction horizon necessitates the recursive use of single-step-ahead predictors for reaching the final point in the horizon. Even small prediction errors resulting from noise at each point in the horizon accumulate and propagate, often resulting in poor prediction accuracy. We present a method for designing MSP using dynamic recurrent neural networks. The method is based on a dynamic gradient descent learning algorithm and its effectiveness is demonstrated through applications to an open-loop unstable process system, namely a heat-exchanger.

[1]  P. Werbos,et al.  Long-term predictions of chemical processes using recurrent neural networks: a parallel training approach , 1992 .

[2]  Tianyou Chai,et al.  Soft sensing based on artificial neural network , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).

[3]  Sheng Chen,et al.  Representations of non-linear systems: the NARMAX model , 1989 .

[4]  John Ringwood,et al.  Incorporation of statistical methods in multi-step neural network prediction models , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

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

[6]  Sheng Chen,et al.  Orthogonal least squares methods and their application to non-linear system identification , 1989 .

[7]  Sheng Chen,et al.  Identification of MIMO non-linear systems using a forward-regression orthogonal estimator , 1989 .

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

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

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

[11]  Girijesh Prasad,et al.  A neural net model-based multivariable long-range predictive control strategy applied in thermal power plant control , 1997 .

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

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

[14]  Amir F. Atiya,et al.  A comparison between neural-network forecasting techniques-case study: river flow forecasting , 1999, IEEE Trans. Neural Networks.

[15]  Mukul Agarwal,et al.  Long-range prediction for poorly-known systems , 1995 .

[16]  Lennart Ljung,et al.  Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[17]  Simon Haykin,et al.  A Signal Processing Framework Based on Dynamic Neural Networks with Application to Problems in Adaptation, Filtering and Classification , 2001 .

[18]  Bernard Delyon,et al.  Nonlinear black-box models in system identification: Mathematical foundations , 1995, Autom..

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

[20]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[21]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

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

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

[24]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.