Identification of Stable FOPDT Process Parameters usingNeural Networks

This research work develops a discrete time method for identification as well as modelling of stable unknown process dynamics in the form of first order plus dead time (FOPDT) process models. A linear three layered Feed-foreword Artificial Neural Network (ANN) is used to yield the relationship between input and output data from unknown plant. Thereafter, this relationship between input and output in terms of ANN weights is represented in mathematical equations for unknown plant characteristics to be identified. Some literature examples are used to test and compare the proposed method on MATLAB platform.

[1]  R. Buizza,et al.  Neural Network Load Forecasting with Weather Ensemble Predictions , 2002, IEEE Power Engineering Review.

[2]  Somanath Majhi,et al.  State space approach for identification of real-time plant dynamics , 2017, 2017 Indian Control Conference (ICC).

[3]  Somanath Majhi,et al.  Dynamic model identification of a real-time simple level control system , 2016 .

[4]  S. Majhi.  Relay based identification of processes with time delay , 2007 .

[5]  Tao Liu,et al.  A tutorial review on process identification from step or relay feedback test , 2013 .

[6]  S. Thomas Alexander,et al.  Adaptive Signal Processing , 1986, Texts and Monographs in Computer Science.

[7]  Furong Gao,et al.  Alternative identification algorithms for obtaining a first-order stable/unstable process model from a single relay feedback test , 2008 .

[8]  R.J. Cohen,et al.  Linear and nonlinear ARMA model parameter estimation using an artificial neural network , 1997, IEEE Transactions on Biomedical Engineering.

[9]  Tarek A. Tutunji,et al.  Parametric system identification using neural networks , 2016, Appl. Soft Comput..

[10]  Somanath Majhi,et al.  Identification of FOPDT and SOPDT process dynamics using closed loop test. , 2014, ISA transactions.

[11]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[12]  Tianyou Chai,et al.  An Alternating Identification Algorithm for a Class of Nonlinear Dynamical Systems , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Berkman Sahiner,et al.  Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images , 1996, IEEE Trans. Medical Imaging.

[14]  Isaac Chairez Oria.  Adaptive Neural Network Nonparametric Identifier With Normalized Learning Laws , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[15]  W.J. Tompkins,et al.  Neural-network-based adaptive matched filtering for QRS detection , 1992, IEEE Transactions on Biomedical Engineering.

[16]  M. Chidambaram,et al.  Identification using single symmetrical relay feedback test , 2005, Comput. Chem. Eng..