Entry requirements

120 credits including Linear Algebra II, Probability and Statistics, Signals and Systems, and Signal Processing or Automatic Control II.

Learning outcomes

The aim of this course is to guide the student how to translate theoretical concepts into engineering practice.

Students who pass the course should be able to

• describe the different phases that constitute the process of building models, from design identification experiment to model validation
• account for and apply the stochastic concepts used in analysis of system identification methods, and to explain why different system identification methods and model structures are necessary in engineering practice
• describe and motivate basic properties of identification methods like the least squares method and the prediction error method, and describe the principles behind recursive identification and its fields of application
• find and apply techniques for identification of multivariable systems as state space representations
• show working knowledge of the available tools, and to reason how to choose identification methods and model structures for real-life problems.
• discuss relations to similar fields of research

Content

The system identification problem - from data to model, recursive and batch. Model structures and input signals. The least squares and prediction error approaches. The stochastic setting. Model validation and practical aspects. Recursive identification schemes and applications (e.g. adaptive control). State space representations. Identification of multivariable (MIMO) systems. Orientation on realated research areas (e.g. machine learning).

The theoretical study will be complemented with a mini project based on realistic case studies.

Instruction

Lectures, laboratory work and a mini project. Guest lecture.

Assessment

Written examination (3 credits), laboratory work (1 credit) and mini project (1 credit).