JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD

Course Objectives:

• To expose students to different system identification concepts.
• To make the use of random-process models to represent non-deterministic signals and noise
• To extract the time-domain and frequency-domain structure of the signals and noise from the models

Course Outcomes

Upon the completion of this course, the student will be able to

• Apply the concepts of developing mathematical models for industrial systems,
• Develop models from first principles and data driven models.

UNIT - I

Review of Probability theory and random variable - random process - Linear Regression. ARMAX Model Structure.

UNIT - II

Concept of estimation, Recursive least squares (RLS), Consistency of estimation, Weighted LS. Convergence analysis LS. Parametric models - LS estimation, bias - Generalized Least Squares (GLS)

UNIT - III

Parameters estimation using Instrumental Variable (IV) method. Persistently exciting input signal - Likelihood functions and Maximum Likelihood Estimation (MLE) - Singular Value Decomposition (SVD).

UNIT - IV

Kalman filter, State estimation using Kalman filter, Parameter estimation using Kalman filter.

UNIT - V

Extended Kalman Filters (EKF), State and Parameter estimations of nonlinear systems using EKF.

TEXT BOOKS:

• 1. Papoulis and Pillai, Probability, Random Variables and Stochastic Process, McGraw Hill, 2002.
• 2. Jerry M. Mendel, Lessons in Estimation Theory for Signal Processing, Communications, and Control, Prentice - Hall, 1995.

REFERENCES:

• 1. Karl J Astrom, Introduction to Stochastic Control Theory, Mathematics in Series and Engg., Vol. 70.
• 2. Michel Verhaegen and Vincent Verdult, Filtering and System Identification A Least Squares Approach, Cambridge Univ. Press, 2007.
• 3. M.S. Grewal and A. P. Andrews, Kalman Filtering Theory and Practice Using Matlab, John Wiley, 2008.