Neural Network Identifier Design for Dynamic Systems

Student: Iachmeneva Viktoriia

Supervisor: Olga Andrianova

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Applied Mathematics (Bachelor)

Year of Graduation: 2020

In this work, dynamic systems with time-varying constraints are studied. The problem of designing the neural network identifier for dynamic systems is presented. The solution is constructed by using Barrier Lyapunov Functions, Attractive Ellipsoid Method and Riccati equations. The structure of neural network identifier is described, the main theorem on the stability of the system dynamics in deviations between the real and estimated state is proved. The result of this work may be useful in control design for constrained systems wit unknown right-hand side.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses