| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Uporaba evolucijskih metod za napovedovanje stroškov inženirskih projektov : magistrsko delo
Authors:ID Šket, Kristijan (Author)
ID Brezočnik, Miran (Mentor) More about this mentor... New window
ID Palčič, Iztok (Comentor)
Files:.pdf MAG_Sket_Kristijan_2023.pdf (2,01 MB)
MD5: 7C632DE077543BCE3CA7FEFE0FE92E9B
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FS - Faculty of Mechanical Engineering
Abstract:Magistrsko delo obsega napovedovanje stroškov inženirskih projektov v orodjarstvu, katerih cilj so transferna orodja za preoblikovanje pločevine. Cilj dela je s pomočjo genetskega programiranja in programskega okolja BricsCAD na podlagi stroškovne analize že izdelanih transfernih orodij ustvariti napovedne matematične modele za napovedovanje stroškov vsebinsko podobnih projektov v prihodnosti. Za zadostno genetsko raznovrstnost v začetnih generacijah smo organizme ustvarili s polnim, rastočim in delno polnim, delno rastočim načinom. Kot najbolj točen napovedni model v fazi testiranja se je izkazal model z delno polnim, delno rastočim načinom stvarjenja, ki je dosegel povprečno točnost 97,59 %. Ustvarjeni napovedni model je funkcijske gene izbiral iz osnovnih matematičnih operacij: seštevanja, odštevanja, množenja in deljenja. Za uporabo priporočamo model, pridobljen z rastočim načinom in naborom funkcijskih genov iz osnovnih računskih operacij brez operacije deljenja. Model je zgolj 0,25 % manj točen, vendar je enostavnejši za uporabo in za delovanje zahteva poznavanje le trinajstih in ne sedemnajstih spremenljivk.
Keywords:evolucijske metode, genetsko programiranje, modeliranje in optimizacija, projektno vodenje v orodjarstvu, obvladovanje stroškov
Place of publishing:Maribor
Place of performance:Maribor
Year of publishing:2023
Number of pages:1 spletni vir (1 datoteka PDF (XIV, 62 f.))
PID:20.500.12556/DKUM-83831 New window
UDC:004.8.02:[657.478:658.5](043.2)
COBISS.SI-ID:152277507 New window
Publication date in DKUM:24.04.2023
Views:904
Downloads:187
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FS
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:19.02.2023

Secondary language

Language:English
Title:Applying evolutionary methods for cost prediction in engineering projects
Abstract:This master thesis covers the cost prediction of engineering projects in the toolmaking industry aimed at transfer tools for sheet metal forming. The aim of the work is to use genetic programming and the BricsCAD software environment - based on a cost analysis of transfer tools already produced - to create predictive mathematical models to forecast the costs of fundamentally similar projects in the future. To ensure sufficient genetic diversity of organisms in the initial generations, we have created organisms with grow, full and ramped-half-and-half methods of creation. The ramped-half-and-half model proved to be the most accurate predictive model in the testing phase, it achieved an average accuracy of 97.59%. The predictive model created selected the function genes from the basic mathematical operations: of addition, subtraction, multiplication, and division. We recommend using a model obtained in a growing mode and a set of functional genes from basic computational operations without the operation of division. The model is only 0.25% less accurate, but it is more robust and requires knowledge of 13 variables rather than 17.
Keywords:evolutionary methods, genetic programming, modelling and optimization, project management in the tool industry, cost management


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica