System Identification: Theory for the User
Description
This is a complete, coherent description of the theory, methodology and practice of System Identification. The completely revised Second Edition introduces subspace methods, methods that utilize frequency domain data, and these key non-linear black box methods: neural networks, wavelet transforms, neuro-fuzzy modeling and hinging hyperplanes. KEY TOPICS: Leader in the field Lennart Ljung introduces systems and models, time-invariant linear systems, time-varying and nonlinear systems. He presents several approaches to system identification, including nonparametric time- and frequency-domain methods; parameter estimation; convergence and consistency; asymptotic distribution of parameter estimates; linear regressions, iterative search and recursive estimation. He also presents detailed coverage of key issues that can make or break system identification projects: defining objectives, designing experiments, selecting criteria, and controlling the bias distribution of transfer-function estimates. MARKET: For all engineering and control systems professionals, faculty and students.
More details
Other editions
Additional editions
Previous edition
Person
Content
1. Introduction.
PART I. SYSTEMS AND MODELS.
2. Time-Invariant Linear Systems.3. Simulation, Prediction, and Control.
4. Models of Linear Time-Invariant Systems.
5. Models for Time-Varying and Nonlinear Systems.
PART II. METHODS.
6. Nonparametric Time- and Frequency-Domain Methods.7.Parameter Estimation Methods.
8.Covergence and Consistency.
9. Asymptotic Distribution of Parameter Estimates.
10. Computing the Estimate.
11. Recursive Estimation Methods.
PART III. USER'S CHOICES.
12. Options and Objectives.13. Affecting the Bias Distribution of Transfer-Function Estimates.
14. Experiment Design.
15. Choice of Identification Criterion.
16. Model Structure Selection and Model Validation.
17. System Identification in Practice.
Appendix I. Some Concepts from Probability Theory.
Appendix II. Some Statistical Techniques for Linear Regressions.