On-line Monte Carlo simulacija

Ivanković, Margita (2017) On-line Monte Carlo simulacija. = On-line Monte Carlo simulation. Undergraduate thesis , Sveučilište u Zagrebu, Fakultet strojarstva i brodogradnje, UNSPECIFIED. Mentor: Essert, Mario.

[img]
Preview
Text
Ivankovic_2017_zavrsni_preddiplomski.pdf - Published Version Jezik dokumenta:Croatian

Download (1MB) | Preview
[img] Text
Ivanković_Margita_autorska_izjava_zavrsni_2017.pdf - Published Version
Restricted to Repository staff only Jezik dokumenta:Croatian

Download (495kB)

Abstract (Croatian)

Monte Carlo metoda je numerička metoda rješavanja matematičkih problema slučajnim uzorkovanjem velikog broja varijabli. Koristi se za rješavanje problema koji su prekomplicirani za riješiti analitički. U web2py mrežnom okviru je izrađena on-line Monte Carlo simulacija s primjerima vezanim za slaganje tolerancija odnosno dimenzija i utjecaj tolerancija elektroničkih komponenti na strujni krug. Za opis raspodjele tolerancija je korištena normalna distribucija. PERT metoda skupa s Monte Carlom može procjeniti trajanje projekta što je također simulirano u aplikaciji. Monte Carlo simulacija povezana s Latin hypercube uzorkovanjem je korištena u obliku preinačenog mcerp 0.11 Python modula.

Abstract

The Monte Carlo method is a numerical method of solving mathematical problems by random sampling a large number of variables. It is used for obtaining numerical solutions to problems which are too complicated to solve analytically. On-line Monte Carlo simulation is made in web2py framework with examples based on tolerance stackup and effects of electrical component variations in electrical circuit. Normal distribution is used to describe tolerance range. PERT method used with Monte Carlo can estimate the time needed to complete given project which is also shown in web application. Monte Carlo method that uses Latin hypercube sampling is used with Python module mcerp 0.11.

Item Type: Thesis (Undergraduate thesis)
Uncontrolled Keywords: Monte Carlo; web2py; slučajno uzorkovanje; Latin hypercube; tolerancije; normalna distribucija; PERT; mcerp
Keywords (Croatian): Monte Carlo; web2py; random sampling; Latin hypercube; tolerance; normal distribution; PERT; mcerp
Subjects: TECHNICAL SCIENCE > Mechanical Engineering
Divisions: 900 Department of Robotics and Production System Automation > 910 Chair of Engineering Automation
Date Deposited: 25 Sep 2017 08:08
Last Modified: 10 Oct 2017 11:31
URI: http://repozitorij.fsb.hr/id/eprint/7982

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

Nema podataka za dohvacanje citata