Predikcija PVT svojstava neuronskom mrežom

master's thesis

• Title: Predikcija PVT svojstava neuronskom mrežom : diplomski rad
• Title (english): Prediction of PVT properties with neural networks : master’s thesis
• Author: Marčelo Pavić
• Mentor: Domagoj Vulin (mentor)
• Committee member: Domagoj Vulin (predsjednik povjerenstva)
• Committee member: Tomislav Kurevija (član povjerenstva)
• Committee member: Luka Perković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Mining, Geology and Petroleum Engineering; (Department of Petroleum and Gas Engineering and energy); Zagreb
• Defense date and country: 2017-02-17, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mining, Petroleum and Geology Engineering; Petroleum Mining

Abstract

Umjetne neuronske mreže su nova tehnologija koja je nastala kao pokušaj oponašanja rada ljudskog mozga, a našla je primjenu u rješavanju složenih nelinearnih problema na mnogo različitih područja. U ovom radu su neuronske mreže korištene za predikciju pVT (engl. pressure-volume-temperature) svojstava nafte iz polja Žutica. Mreže su trenirane na tri različita seta podataka, za predikciju volumnog faktora nafte, plinskog faktora i tlaka zasićenja nafte. Napravljeno je ukupno 28 različitih modela neuronskih mreža, a razlikuju se po arhitekturi, broju iteracija, stopi učenja i broju podataka u setu za treniranje, kalibraciju i verifikaciju.

Abstract (english)

Abstract: Artificial neural networks are new technology which was developed to simulate human brain and it is used for solving difficult nonlinear problems in many different areas. In this thesis neural networks are used for predicting of PVT (pressure-volume-temperature) properties of oil from Žutica field. Three different data sets were used for training neural networks for prediction of oil formation volume factor, solution gas-oil ratio and bubble point pressure. It was produced 28 different models of neural networks, based on different architecture, number of learning cycles, learning rates or number of data in training, cross-validate or test sets.

• Keywords: predikcija; pVT; neuronska mreža; neuroni; nepovratna mreža; aktivacijska funkcija
• Keywords (english): prediction; pVT; neural network; neuron; feedforward; activation function
• Language: croatian
• URN:NBN: urn:nbn:hr:169:299292
• Study programme: Title: Petroleum engineering; specializations in: Petroleum engineering, Energy production and supply, Environmental protection in petroleum engineering; Course: Petroleum engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka naftnog rudarstva (magistar/magistra inženjer/inženjerka naftnog rudarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2017-03-21 13:16:54