USING DATA MINING TECHNIQUES IN CATALYTIC CRACKING PROCESS MODELING – A COMPARATIVE STUDY

Marinoiu Cristian
Additional contact information
Marinoiu Cristian: PETROLEUM-GAS UNIVERSITY OF PLOIESTI

Annals - Economy Series, 2017, vol. 4, 74-81

Abstract: Despite notable successes achieved in trying to obtain viable alternatives to the use of oil as a source of energy and raw materials, oil industry remains one of the main pillars of sustainable development of modern society. Continued modernization of the industry by using the latest technologies in all its important links - extraction, transport, refining - led to substantial reduction of its negative impact on the environment. Particularly, refineries benefited from a special technological contribution, which resulted in a significant plus in efficiency and reliability. In order to always maintain these high standards, the control of oil refining chemical processes must be based on simplebut at the same time performant mathematical models. One way to achieve this objective is the use of modern data mining methods. In this paper we propose to compare the performance of three data mining methods in order to be used in catalytic cracking process modeling in a refinery.

Keywords: data mining; catalytic cracking; regularization; multicollinearity; overfitting; support vector machine (search for similar items in EconPapers)
Date: 2017
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.utgjiu.ro/revista/ec/pdf/2017-04/11_Maronoiu.pdf

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cbu:jrnlec:y:2017:v:4:p:74-81

Access Statistics for this article

More articles in Annals - Economy Series from Constantin Brancusi University, Faculty of Economics Contact information at EDIRC.
Bibliographic data for series maintained by Ecobici Nicolae ( this e-mail address is bad, please contact ).