First edition of the Spring Doctoral School on

Data-driven Model Identification of Dynamical Systems

Nancy, France April, 3-6, 2017

 

The 4-days Spring Doctoral School consisted of a series of lectures followed by computer exercises.

Final program table

    April 3, 2017 - 9h00-17h00
    Lecturer: Prof. Lennart Ljung (Linköping University, Sweden)

      2-day course on System Identification: A Prediction Error Perspective

      Overview

      • Theme 1: Overview of the problem area. Overall principles. Basic model structures. Bias and Variance. Model quality and uncertainty. Model validation.
      • Computer exercise 1. Getting hands on experience with real data. Simple models and model validation.
      • Theme 2: More on Linear models. Frequency domain data. Subspace Techniques. New approaches with regularization. High order, regularized simple models, advantages and disadvantages.
      • Computer exercise 2: Tests of subspace methods (N4SID, MOESP, CVA) and regularization. Experience of choice of model orders and auxiliary variables.

      April 4, 2017 - 8h30-16h30
      Lecturer: Prof. Lennart Ljung (Linköping University, Sweden)

      • Theme 3: Non-linear model structures. Wiener and Hammerstein models, Neural Networks. Grey box models with physical structure.
      • Computer exercise 3: Hands on identification of non-linear models.
      • Theme 4: Special questions. Experiment design. Concluding remarks.

       

      April 5, 2017 - 8h30-17h00
      Lecturer:  Prof. Hugues Garnier (University of Lorraine, France)

      Data-driven approaches for direct continuous-time model identification

      Overview

        • Theme 1: Overview of continuous-time linear model identification. Basic SVF-based and optimal instrumental variable (IV)-based estimators. Practical and software aspects.
        • Computer exercise 1. Getting hands on experience with the CONTSID toolbox methods with real data.
        • Theme 2: Benefits for practical applications. IV extensions to advanced situations (MISO systems, time-delay systems, simple process models, LTV systems,...).
        • Computer exercise 2: Getting hands on experience on advanced situations.

         

        April 6, 2017 -  8h30-12h15
        Lecturer: Prof. Marion Gilson (University of Lorraine, France)

        Frequency-domain, closed-loop, Hammerstein and LPV model identification

        Overview

            • Theme 1: Frequency-domain identification. Closed-loop system identification. Instrumental variable-based techniques.
            • Computer exercise 1: Hands on frequency-domain and closed-loop model identification.
            • Theme 2: Hammerstein and Linear Parameter Varying (LPV) model identification.
            • Computer exercise 2: Hands on identification of Hammerstein and LPV models.

            April 6, 2017 -  13h30-17h00
            Lecturer: Mathieu Cuenant (MathWorks)

            Identification and controls - An industrial perspective