I highly suggest you start with System Identification theory for the user, by Lennart Ljung (you can find it here http://www.amazon.com/System-Identification-Theory-User-Edition/dp/0136566952). It may be a bit tough at the the beginning, especially because of the notation, but is very complete and recognized in the control community as a reference book on the field.

I think the book by K.J. Keesman is a very good one (see: http://www.amazon.ca/System-Identification-Introduction-Karel-Keesman/dp/0857295217). It has both fundamental and advanced examples and theories on "Systems Identification". Good luck.

Hi

I have some PDF files of some nice and fundamental system identification boos like

""Introduction to Mathematical Systems Theory: Linear Systems, Identification and Control

Christiaan Heij, André C.M. Ran, F. van Schagen""

or

""Lennart_Ljung]_System_Identification,_Theory""

or

""System identification: advances and case studies

Raman K. Mehra""

I can send them to your mail if you need them

[email protected]

best wishes

Hi, Prof. Ganti Prasad Rao have done a great work on System Identification.

"Identification of continuous-time systems" by G.P. Rao. This is one of the best papers in system Identification.

If you are facing any problem to download this article jut send me a message.

http://ece.ut.ac.ir/Classpages/S87/ECE150/Papers/Misc/01595896.pdf.

Best wishes

D Kranthi Kumar

The reference has to be sufficiently rich in frequency in the sense that if there are p parameters to be identified, the reference input has to contain a number of distinct frequencies q exceeding the integer part of p/2 ( mathematically, it suffices p/2 if p is even). The identification quality improves, in general, as q increases in the sense that the transient is better.

The practical generation of those frequencies can be simply a combination of different sinusoids or some periiodic function whose Fourier series contains ( at least) the necessary minimum number q of frequencies.

It is not necessary to generate the reference signal with a significant amplitude, that is , the identification quality is achievable in many cases with sufficiently rich ( in frequency) signals of small amplitudes.

If an adaptive tracking objective is also suited togetehr with parametrical identification ( asympototic tracking of a reference, for instance, or asymptotic regulation) then an extra reference of very small amplitude being sufficiently rich in frequency can be added to the reference to be tracked in order to approximately achieve both objectives.

It is not easy to recommend the best reference for system identification for different levels of engineers and researchers.

I summarize the comments based on my hands-on experience in this area.

I recommend the order of references to read from the beginner (entry level) level to the senior level.

(1) G.P. Rao, "Identification of continuous-time systems" suggested by Kranthi Deveerasetty (Entry level)

(2) Highlights of system identification provided by Manuel De la Sen

(3) K.J. Keesman, "System Identification: An Introduction" suggested by Jimmy Omony

R.K. Mehra, "System identification: advances and case studies" suggested by Mahmood Dadkhah

C. Heij, A.C.M. Ran, F. van Schagen, "Introduction to Mathematical Systems Theory: Linear Systems, Identification and Control" suggested by Mahmood Dadkhah

(4) Survey on the history of system identification

M. Gevers， “A personal view of the development of system identification: A 30-year journey through an exciting field，” IEEE Control Systems Magazine, 26(6)， December 2006, pp. 93-105.

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=4019326

M. Gevers， “A personal view of the development of system identification", available in the following link.

"We show how two landmark papers, (Ho and Kalman, 1965) and (Astrom and Bohlin, 1965), gave birth to two main streams of research that have dominated the development of system identification over the last fourty years. The Ho-Kalman paper, which gave a first solution to state-space realization theory, led to stochastic realization, and much later to subspace identification. The Astrom-Bohlin paper laid the foundations for Maximum Likelihood methods based on parametric input-output models, which later became known as the highly successful Prediction Error Identification framework."

http://perso.uclouvain.be/michel.gevers/PublisMig/C124.pdf

(5) L. Ljung, "System identification - Theory for the User" suggested by Riccardo Ferrari and Mahmood Dadkhah (Senior Level)

This book contains many new computer-based examples designed for market-leading software, MATLAB's System Identification Toolbox developed by L. Ljung's research group.

(6) Suggest to read a book in probability/stochastic process before starting to read L. Ljung's classical book "System identification - Theory for the User".

Probability/stochastic process is highly related to some research topics of Control theory, information theory, and queuing theory. The following IEEE NOMS 2010 paper is an engineering application of probability/stochastic process and queuing theory.

Y. Hong, C. Huang, and J. Yan, "Analysis of SIP Retransmission Probability Using a Markov-Modulated Poisson Process Model," Proceedings of IEEE/IFIP Network Operations and Management Symposium (IEEE NOMS), Osaka, Japan, April 2010, pp. 179-186. Available in the following RG link.

http://www.researchgate.net/publication/224146897_Analysis_of_SIP_retransmission_probability_using_a_Markov-Modulated_Poisson_Process_model

According to Amazon's Customer Reviews provided by the following link, entry-level engineers struggle to understand Ljung's book, while senior-level engineers benefit much from Ljung's book.

http://www.amazon.com/System-Identification-Theory-User-Edition/product-reviews/0136566952/ref=cm_cr_dp_see_all_summary/177-2932041-7499544?ie=UTF8&showViewpoints=1&sortBy=byRankDescending

Google Scholar indicates that Ljung's classical book has been cited by 18,297 until March 19, 2014. The most cited book in the system identification area.

http://scholar.google.ca/citations?view_op=view_citation&hl=en&user=2lo28DgAAAAJ&citation_for_view=2lo28DgAAAAJ:u5HHmVD_uO8C

(7) The following IEEE CST 2001 paper shows how to apply system identification approach to estimate the gain margin and phase margin of the real-world control system.

W.K. Ho, T.H. Lee, H.P. Han, and Y. Hong, "Self-Tuning IMC-PID Control with Interval Gain and Phase Margin Assignment," IEEE Transactions on Control Systems Technology, 9(3), May 2001, pp. 535-541. Available in the following RG Link.

https://www.researchgate.net/publication/3332273_Self-tuning_IMC-PID_control_with_interval_gain_and_phase_marginsassignment

(8) H. Hjalmarsson, M. Gevers, S. Gunnarsson, and O. Lequin proposed Iterative feedback tuning (IFT) approach to tune controller parameters for those control model (or control plant) whose parameters are difficult to be identified relatively accurately using system identification approach.

H. Hjalmarsson, M. Gevers, S. Gunnarsson, and O. Lequin, "Iterative feedback tuning: theory and applications," IEEE Control Systems Magazine, vol.18, no.4, Aug 1998, pp .26-41,

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=710876

A. Juditsky, H. Hjalmarsson, A. Benveniste, B. Delyon, L. Ljung, J. Sjoberg, Q. Zhang, "Nonlinear black-box models in system identification: Mathematical foundations," Automatica, 31(12), December 1995, pp. 1725-1750.

http://www.sciencedirect.com/science/article/pii/0005109895001191

By cooperating with his peer researchers including Stanford University researcher, H. Hjalmarsson integrated iterative feedback tuning with PID controller to solve controller tuning issues caused by plant uncertainty of nonlinear system. H. Hjalmarsson was elected to the Class of 2013 IEEE fellow last year due to his fundamental contribution to iterative feedback tuning.

WK Ho, Y Hong, A Hansson, H Hjalmarsson, and JW Deng, "Relay auto-tuning of PID controllers using iterative feedback tuning," Automatica 39 (1), January 2003, pp. 149-157. Available in the following RG Link.

https://www.researchgate.net/publication/223504459_Relay_auto-tuning_of_PID_controllers_using_iterative_feedback_tuning

Only PID Control and Smith Predictor were listed in the "Leaders of the Pack - From the plant to academia, InTech's 50 most influential industry innovators" since the year 1774. InTech. International Society of Automation. 1 August 2003. Available from the following link.

http://www.isa.org/InTechTemplate.cfm?Section=Article_Index1&template=/ContentManagement/ContentDisplay.cfm&ContentID=28889

PID Control was listed twice (the dominant control method in the industrial application -- (1) John G. Ziegler and Nathaniel B. Nichols and classical PID Control; (2) Karl Johan Astrom and modern PID Control (IEEE Medal of Honor, 1993)

http://en.wikipedia.org/wiki/IEEE_Medal_of_Honor

The next popular method is Smith Predictor: Otto J.M. Smith and Smith Predictor.

http://en.wikipedia.org/wiki/Otto_J._M._Smith

(9) Recent discussions on control system design approaches can be found in the following RG link.

"What are trends in control theory and its applications in physical systems (from a research point of view)?"

https://www.researchgate.net/post/What_are_trends_in_control_theory_and_its_applications_in_physical_systems_from_a_research_point_of_view2

Article Self-tuning IMC-PID control with interval gain and phase mar...

Article Relay auto-tuning of PID controllers using iterative feedback tuning

Conference Paper Analysis of SIP retransmission probability using a Markov-Mo...

The best Reference for me is : Lennart LJUNG: System Identification Theory for the user. Second Edition

The best references I have found sound and easy to follow are Tangirala Arun K:Principles of System Identification, theory and practice (check https://www.amazon.com/Principles-System-Identification-Theory-Practice/dp/1439895996) and System Identification theory for the user, by Lennart Ljung