Višekriterijsko adaptivno oblikovanje planova pokusa

Cajner, Hrvoje (2011) Višekriterijsko adaptivno oblikovanje planova pokusa. = Multicriteria adaptive design of experimental plans. Doctoral thesis , Sveučilište u Zagrebu, Fakultet strojarstva i brodogradnje, UNSPECIFIED. Mentor: Šakić, Nikola.

[img]
Preview
Text
07_07_2011_Doktorski_rad_HRVOJE_CAJNER.pdf Jezik dokumenta:Croatian

Download (3MB) | Preview

Abstract (Croatian)

Prilikom odabira modela planova pokusa, što je važna faza u većini znanstvenih istraživanja, potrebno je voditi računa o adekvatnosti modela, obliku rezultata koji se žele dobiti, te preciznosti modela odnosno pogrešci koja se nužno pojavljuje. Budući da se područje planova pokusa počelo razvijati, pa tako i uporabljati, u vrijeme kada je njihovom uporabom ostvarena velika ušteda u resursima, nije se dovoljno istražila mogućnost minimiziranja ostalih parametara eksperimentiranja kao što su cijena, utrošeno vrijeme i sl. Općenito se može reći da se vrlo malo istraživanja u literaturi odnosi na spomenuti problem. Istraživanje će se, u ovom radu, odnositi na razvoj metodologije i modela koji će biti potpora pri izboru i konačnom oblikovanju planova pokusa. Cilj je istražiti odnos pogreške pokusa odabranog modela (preciznost), troškova realizacije pokusa, te vremena potrebnog za eksperimentiranje. \Novorazvijeni model, koji predstavlja rezultat ovih istraživanja, trebao bi omogućiti pronalaženje optimalnih planova pokusa sa stajališta novouvedenih kriterija optimalnosti.

Abstract

The process of choosing the experimental design is a significant phase in scientific researches. It is important to take into consideration the adequacy, the shape of results and the imprecision of the model as the side effect of error of estimation. In general, the result of using the design of experiments provides the significance benefits and cost saving. Due to limited resources like time, costs and complexity of design points realization we must take these facts in account when designing experiments. The scope of this research is to maximize the precision of model using multi-criteria approach. The study refers to research and development of the new model which will be a support in the design of experiments. The objective of study is to examine and understand the relation between prediction of variance (model precision), experiment costs, time expenditure. The new-developed model will provide a possibility of designing optimal experiments with respect to new added criteria.

Item Type: Thesis (Doctoral thesis)
Uncontrolled Keywords: planovi pokusa; troškovi; vrijeme eksperimentiranja; optimalnost planova
Keywords (Croatian): Design of experiments; experimental design; error of design; desirability function; experimental costs; response surface methodology; central composite design
Divisions: 700 Department of Industrial Engineering > 720 Chair of Production Control
700 Department of Industrial Engineering
Date Deposited: 22 Sep 2014 18:00
Last Modified: 16 Oct 2015 13:02
URI: http://repozitorij.fsb.hr/id/eprint/1411

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

Nema podataka za dohvacanje citata