Suboptimalno multikriterijsko upravljanje megavatnim vjetroagregatom

master's thesis

• Title (english): Suboptimal multi criteria control of a megawatt-scale wind turbine
• Author: Luka Santrić
• Mentor: Nedjeljko Perić (mentor)
• Committee member: Nedjeljko Perić (predsjednik povjerenstva)
• Committee member: Željko Ban (član povjerenstva)
• Committee member: Mato Baotić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-09-25, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Sustav upravljanja vjetroagregatom megavatne snage temelji se na optimalnom iskorištavanju dostupne energije vjetra te na redukciji strukturnih opterećenja komponenti vjetroagregata. S obzirom na nelinearnost matematičkog modela vjetroagregata te na spregu pojedinih podsustava, teško je postići optimizaciju multikriterijskog problema s ograničenjima koja bi se izvodila u stvarnom vremenu na postojećem ugradbenom računalnom sustavu vjetroagregata. Stoga je zadatak ovoga rada bio suboptimalan pristup koji se temelji na izvedenoj optimizaciji u cijelom radnom području vjetroagregata i njenoj aproksimaciji korištenjem neuronske mreže. Postavljen je matematički model vjetroagregata te su identificirana ograničenja sustava upravljanja. Ponašanje projektiranog suboptimalnog regulatora simulacijski je provjereno, kao i njegova izvedivost za upravljanje u realnom vremenu.

Abstract (english)

Wind turbine control system is based on the optimal use of available wind energy and the reduction of the structural loads of wind turbine components. Due to the nonlinearity of the mathematical model of wind turbine and the complexity of certain subsystems, it is difficult to achieve multi-criterion optimization solution with constraints in real time on the existing embedded systems. Thus the goal of this study was suboptimal approach based on the model predictive control in the entire working area of wind turbine and its approximation using neural networks. A mathematical model of wind turbine is identified with constraints. Suboptimal controller is verified with simulations along with its implementation feasibility in real-time.

• Keywords: vjetroturbina; modelski prediktivno upravljanje; MPC; neuronske mreže
• Keywords (english): wind turbine; model predictive control; MPC; neural network
• Language: croatian
• URN:NBN: urn:nbn:hr:168:627413
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije (magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 11:41:36