Index Geophysics

hrv PRIMJENA PLANIRANJA EKSPERIMENATA U OPLEMENJIVANJU MINERALNIH SIROVINA

eng APPLICATION OF EXPERIMENTS PLANNING IN THE MINERAL PROCESSING

hrv Statističko planiranje eksperimenata bavi se metodama takvog izvođenja eksperimenta koje osigurava sakupljanje podataka primjerenih statističkoj analizi na osnovi koje je moguće donijeti objektivne i valjane zaključke. Tim metodama obuhvaćena su dva usko povezana problema ekperimentiranja: plan eksperimenta i statistička obrada rezultata. Štoviše, planovi za izvođenje eksperimenata sastavljeni su tako da uravnotežuju odnos između preciznosti statističkog zaključivanja i troškova eksperimentiranja. Faktorski planovi primjenjuju se za eksperimente koji uključuju više zavisnih varijabli tj. faktora, a potrebno je ispitati ukupni utjecaj faktora na zavisnu varijablu. U slučaju k faktora od kojih svaki prima samo dvije različite vrijednosti, često se primjenjuje potpuni plan kojim se zavisna varijabla ispituje u svakoj od kombinacija vrijednosti faktora. Ako se zavisna varijabla ispituje na više od dvije različite vrijednosti svakog od faktora, moguće je, osim procjene utjecaja pojedinog faktora ili njihovih međudjelovanja, odrediti i nelinearnu regresijsku jednadžbu ovisnosti zavisne varijable o faktorima. U slučaju dvaju faktora takva jednadžba predstavlja plohu u trodimenzionalnom prostoru pa se općenito plan za određivanje nelinearne regresijske jednadžbe može nazvati plan za plohu zavisne varijable. Centralno složen plan je jedan od takvih planova. U radu su na primjeru ispitivanja apsorpcije vode briketa u ovisnosti o četri faktora (pritisak, temperatura, sadržaja vlage, grano-sastav ugljena) prikazani potpuni faktorski plan i centralno složeni plan i njihova analiza. U glavnim crtama opisane su metode analize i izvođenja zaključaka.

eng Statistical design of experiments deals with methods of planning the experiment so that appropriate data are collected, which may be analyzed by statistical methods resulting in objective and valid conclusions. These methods extend over two closely related experimental problems: the design of the experiment and the statistical analysis of the data. Moreover, designed experiments maintain a balance between statistical accuracy and the cost of the experimental process. Factorial designs are used in experiments involving several factors where it is necessary to study the joint effects of these factors on a dependent variable i.e. response. In case of k factors, each at only two levels, the full 2k factorial design in which the response is tested in all possible combinations of settings is widely used. If the response is investigated with more than two different values of each factor then, in addition to the effect estimates of factors and their interactions, the curvilinear regression equation of the relationship between response and factors can be obtained. In case of two factors such equation represents a surface in three-dimensional space, so designs for fitting the response surface are often called response surface designs. One of them is the central composite design. The paper presents the full 24 factorial design and the central composite design and their analysis exemplified by the results of investigation about how the four factors (pressure, humidity, temperature and granulation of the coal) affect the water absorption. The methods of analysis and the way of drawing conclusions have been outlined.

PFAFF, SLAVKA

SALOPEK, BRANKO

hrv satističko planiranje eksperimenata;potpuni faktorski plan;centralno složen plan;oplemenjivanje mineralnih sirovina

eng satistical design of experiments;full factorial design;central composite design;mineral processing

Faculty of Mining, Geology and Petroleum Engineering University of Zagreb

2004

text

info:eu-repo/semantics/article

info:eu-repo/semantics/publishedVersion

application/pdf

https://hrcak.srce.hr/13375

hrv https://hrcak.srce.hr/file/20497

Rudarsko-geološko-naftni zbornik

ISSN 1849-0409 (Online)

Volume 16

Issue 1

hrv

info:eu-repo/semantics/openAccess

The author and publisher rights are visible during the submission process, and ethical codex is available at http://hrcak.srce.hr/ojs/index.php/rgn/about/editorialPolicies#custom-0 .

The Bulletin is open access (OA, green model, CC-BY) journal what means that electronic versions of articles are accessible to readers, without any fees or registration.When use, please refer to Creative Commons license (BY type, http://creativecommons.org/licenses/by/4.0/ ).

Publisher copyright policies & self-archiving is also described at Sherpa organisation web (RoMEO service) based at the University of Nottingham (http://www.sherpa.ac.uk/romeo/pub/2374/).

All volumes of the Bulletin (from 1989) are available at Hrčak journal pages (http://hrcak.srce.hr/rgn-zbornik?lang=en).