To understand the mathematical modelling of systems.
To observe systems by their behaviour using Parametric Identification methods using online and offline Data’s
To observe systems by their behaviour using Nonparametric Identification Methods using Online and Offline Data’s
To estimate and validate the data’s using parametric and recursive estimation methods
To perform case studies on electromechanical and process control systems
UNIT I NONPARAMETRIC IDENTIFICATION 6+6
Transient and frequency analysis methods, impulse and step response methods, correlation method, spectral analysis.
UNIT II PARAMETRIC INDENTIFICATION 6+6
Steps in identification process, determining model structure and dimension, Linear and nonlinear model structures (ARX, ARMAX, Box-Jenkins, FIR, Output Error models), Input signals: commonly
used signals, spectral properties, and persistent excitation, Residual analysis for determining adequacy of the estimated models.
UNIT III PARAMETRIC ESTIMATION 6+6
Linear regression, least square estimation, statistical analysis of LS methods, Minimizing prediction error- identifiability, bias, Least squares, relation between minimizing the prediction error and the MLE, MAP, Convergence and consistency, asymptotic distribution of parameter estimates, Instrumental Variable Method.
UNIT IV RECURSIVE ESTIMATION 6+6
Forgetting Factor method, Kalman Filter interpretation Identification in practice: Aliasing due to sampling, closed loop data, model order estimation, robustness considerations, model validation.
UNITV CASE STUDIES 6+6
Electro Mechanical Systems, Process Control Systems using tlab/Equivalent System Identification Toolbox.
TOTAL: 60 PERIODS
COURSE OUTCOMES (COs)
- Be familiar with different model structures, parameterization, identifiability, structure determination and order estimation
- Be able to perform parameter estimation using different identification techniques
- Be able to identify plants online using recursive estimation methods
- Be able to set up an experiment, identify a nominal model, assess the accuracy and precision of this model,
- Be appropriate design choices to arrive at a validated model.
- jung, L. System Identification: Theory for the User, 2nd Edition, Prentice-Hall, 1999, ISBN 0-13- 656695-2.
- Torsten Soderstrom, PetreStoica, System Identification, Prentice Hall International (UK) Ltd. 1989.
- Karel J. Keesman, System Identification, An introduction, Springer, 2011.
- Zhu, Y. Multivariable System Identification for Process Control, Pergamon, 2001.
- Landan ID, “System Identification and Control Design,” Prentice Hall
- ArunK.Tangirala,Principles of System Identification: Theory and Practice,CRC Press,2014.