1. Eduard Petlenkov, TTÜ automaatikainstituudi dotsent eduard.petlenkov@dcc.ttu.ee

2. Model Based Control Model structure independentModel structure dependent Neural Networks (NN) based Models Choosing proper structure of the model may increase accuracy of the model Adaptivity by using network’s ability to learn Model may become Nonanalytical or hardly analytical Overparameterized Easy realization of the model’s structure relevant to the control algorithm Adaptivity by using network’s ability to learn Analytical models (for example, state- space representation of nonlinear models) Restricted class of systems to which the control technique can be applied

3. H(s), H(z)

5. V i (t) V o (t) y(t) DC Servo Motor

7. NARX (Nonlinear Autoregressive Exogenous) model: ANARX (Additive Nonlinear Autoregressive Exogenous) model: or

8. Easy to change the order of the model Always realizable in the classical state-space form Linearizable by dynamic feedback

9. n-th sub- layer 1 st sub-layer is a sigmoid function

10. NN ANARX model NN-ANARX model

11. y(t)u(t) Reference signal v(t) Nonlinear System Dynamic Output Feedback Linearization NN-based ANARX model HSA * Parameters (W 1, …, W n, C 1, …, C n ) * HSA=History-Stack Adaptation Controller

12. SISO systems: Numerical calculation of u(t) by Newton’s Method, which needs several iterations to converge MIMO systems: Numerical algorithms do not converge or calculation takes too much time

13. n-th sub- layer (nonlinear) 1 st sub- layer (linear)

14. = Let’s define: (*) where If m=r and T 2 is not singular or close to singular then

16. Identification by MIMO NN-SANARX model u1u1 u2u2 y1y1 y2y2

20. u(t) y(t ) v(t) Parameters (W 1, …, W n, C 1, …, C n ) Nonlinear system NN-based ANARX model Dynamic Output Feedback Linearization Algorithm Parameters (a 1, …, a n, b 1, …, b n ) reference model

21. Dynamic output feedback linearization of ANARX model

22. NN-ANARX model Dynamic output feedback linearization of NN-ANARX model

23. Input-Output equation:

24. Linear second order discrete time reference model with poles p 1 =-0.9, p 2 =0.8, zero n 1 =-0.5, steady-state gain K ss =1 It defines the desired behavior of the closed loop system (=control system) Parameters of the reference model for control algorithm are as follows:

25. Here We know that Thus, and