Mastering System Identification in 100 Exercises
This book enables readers to understand system identification and linear system modeling through 100 practical exercises without requiring complex theoretical knowledge. The contents encompass state-of-the-art system identification methods, with both time and frequency domain system identification methods covered, including the pros and cons of each. Each chapter features MATLAB exercises, discussions of the exercises, accompanying MATLAB downloads, and larger projects that serve as potential assignments in this learn-by-doing resource.
Why Read This Book
You should read this book if you want hands-on, practical training in system identification: it teaches core time- and frequency-domain methods through 100 MATLAB exercises and worked discussions so you learn by doing rather than only from theory. The book is especially useful for turning abstract identification concepts into repeatable workflows for experiment design, model estimation, and validation.
Who Will Benefit
Engineers or graduate students with basic signals-and-systems and MATLAB skills who need practical competence in building, selecting, and validating linear system models for control, audio, communications, or measurement applications.
Level: Intermediate — Prerequisites: Familiarity with linear systems (convolution, transfer functions), basic probability/statistics, and comfortable with MATLAB; prior exposure to FFTs and least-squares estimation is helpful.
Key Takeaways
- Implement common identification methods (ARX, ARMAX, OE) in MATLAB and interpret their results.
- Estimate nonparametric impulse and frequency responses using time- and frequency-domain approaches.
- Select model structure and order using practical validation metrics and experiment design ideas.
- Validate models with residual analysis, cross-validation, and frequency-domain checks to detect bias and noise issues.
- Apply subspace and state-space identification techniques for multi-input multi-output systems.
- Translate applied identification workflows into reproducible MATLAB code and project-style assignments.
Topics Covered
- How to use this book and MATLAB setup
- Basic concepts of system identification and notation
- Nonparametric identification: impulse and frequency response estimation
- Time-domain parametric methods: ARX, ARMAX, OE
- Prediction error and maximum likelihood approaches
- Subspace and state-space identification methods
- Frequency-domain identification techniques
- Model structure selection, order determination, and model reduction
- Noise, bias, and experiment design for identification
- Model validation: residuals, cross-validation, and diagnostics
- Advanced exercises and project assignments
- Appendices: MATLAB code, datasets, and further reading
Languages, Platforms & Tools
How It Compares
More hands-on and exercise-driven than Ljung's "System Identification: Theory for the User" (theory-focused); complements Pintelon & Schoukens' frequency-domain treatments by providing practical MATLAB exercises and broader time-domain coverage.
