prikaz prve stranice dokumenta Sustavi upravljanja zasnovani na kliznim režimima uz primjenu inteligentnih metoda
No public access
scientific master's theses
Sustavi upravljanja zasnovani na kliznim režimima uz primjenu inteligentnih metoda
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2002. urn:nbn:hr:168:595208
Barić, Miroslav
University of Zagreb
Faculty of Electrical Engineering and Computing
Department of Control and Computer Engineering

Institutional repository: FER Repository

Cite this document

Barić, M. (2002). Sustavi upravljanja zasnovani na kliznim režimima uz primjenu inteligentnih metoda (Scientific master's theses). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:595208

Barić, Miroslav. "Sustavi upravljanja zasnovani na kliznim režimima uz primjenu inteligentnih metoda." Scientific master's theses, University of Zagreb, Faculty of Electrical Engineering and Computing, 2002. https://urn.nsk.hr/urn:nbn:hr:168:595208

Barić, Miroslav. "Sustavi upravljanja zasnovani na kliznim režimima uz primjenu inteligentnih metoda." Scientific master's theses, University of Zagreb, Faculty of Electrical Engineering and Computing, 2002. https://urn.nsk.hr/urn:nbn:hr:168:595208

Barić, M. (2002). 'Sustavi upravljanja zasnovani na kliznim režimima uz primjenu inteligentnih metoda', Scientific master's theses, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 02 January 2025, https://urn.nsk.hr/urn:nbn:hr:168:595208

Barić M. Sustavi upravljanja zasnovani na kliznim režimima uz primjenu inteligentnih metoda [Scientific master's theses]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2002 [cited 2025 January 02] Available at: https://urn.nsk.hr/urn:nbn:hr:168:595208

M. Barić, "Sustavi upravljanja zasnovani na kliznim režimima uz primjenu inteligentnih metoda", Scientific master's theses, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2002. Available at: https://urn.nsk.hr/urn:nbn:hr:168:595208

Metadata
TitleSustavi upravljanja zasnovani na kliznim režimima uz primjenu inteligentnih metoda
Title (english)Computationally intelligent methods in sliding mode based control systems
AuthorMiroslav Barić
MentorNedjeljko Perić (mentor)
Committee memberNikola Bogunović (predsjednik povjerenstva)
Committee memberIvan Petrović (član povjerenstva)
Committee memberJuraj Božičević (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
(Department of Control and Computer Engineering)
Zagreb
Defense date and country2002-11-27, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Process Computing
Universal decimal classification
(UDC)		004 - Computer science and technology. Computing. Data processing
Abstract
Prikazane su osnove teorije sustava promjenjive strukture i prikazana je njihova primjena u sustavima automatskog upravljanja. Objašnjen je princip rada sustava upravljanja zasnovanih na kliznim režimima. Istaknute su značajke ovakvog pristupa, s posebnim osvrtom na nedostatke. Dan je pregled primjene inteligentnih metoda u sklopu sustava upravljanja s kliznim režimom rada. Istaknut je značaj primjene umjetnih neuronskih mreža. Predložen je algoritam upravljanja promjenjive strukture za sustave sa izraženim ”unmatched” neodređenostima. U relizaciji upravljačkog signala razmotrena je primjena statičkih neuronskih mreža: MLP i RBF. Predložen je algoritam adaptacije parametara obiju mrežnih struktura, zasnovan na analizi stabilnosti. Pokazana je ograničenost svih veličina u sustavu upravljanja. Provjera valjanosti algoritma provedena je simulacijama u programskom paketu Matlab/Simulink. Simulacije su provedene za sustav upravljanja elektroničkim ventilom rasplinjača.
Abstract (english)
Basics of the variable structure systems and their application as control strategy are demonstrated. The principle of the sliding mode control is explained, with the special attention given to its drawbacks. An overview of applications of the soft computing methods as a part of the sliding mode controller is given. The application of the neural networks is specially pointed. The variable structure control algorithm designed for systems with unmatched uncertainties and disturbances if proposed. The application of MLP and RBF neural networks in the context of the algorithm is considered. Weights adaptation algorithm derived from the stability analysis is proposed. The ultimate boundedness of all signals inside the system is demonstrated. The verification of the proposed algorithm is performed using Matlab/Simulink. Simulation studies are carried on for the electronic throttle control system.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:595208
Study programmeTitle: Postgraduate master programe in computing
Study programme type: university
Study level: postgraduate
Academic / professional title: magistar inženjer računarstva (magistar inženjer računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Created on2019-04-30 09:30:41