- author = "Miha Kovacic and Bozidar Sarler and Uros Zuperl",
- title = "Natural gas consumption prediction in Slovenian industry - a case study",
- journal = "Materials and Geoenvironment",
- year = "2016",
- volume = "63",
- number = "2",
- pages = "91--96",
- month = oct,
- keywords = "genetic algorithms, genetic programming, natural gas, consumption, modelling, linear regression, artificial neural networks, industry",
- ISSN = "1854-7400",
-
URL = "
https://www.degruyter.com/view/j/rmzmag.2016.63.issue-2/rmzmag-2016-0008/rmzmag-2016-0008.xml?format=INT",
-
DOI = "
10.1515/rmzmag-2016-0008",
- size = "6 pages",
- abstract = "In accordance with the regulations of the Energy Agency of the Republic of Slovenia, each natural gas supplier regulates and determines the charges for the differences between the ordered (predicted) and the actually supplied quantities of natural gas. Yearly charges for these differences represent up to 2percent of supplied natural gas costs. All the natural gas users, especially industry, have huge problems finding the proper method for efficient natural gas consumption prediction and, consequently, the decreasing of mentioned costs. In this study, prediction of the natural gas consumption in Store Steel Ltd. (steel plant) is presented. On the basis of production data, several models for natural gas consumption have been developed using linear regression, genetic programming and artificial neural network methods. The genetic programming approach outperformed linear regression and artificial neural networks.",
-
notes = "RMZ Product Type: Journals/Yearbooks Open Access
Store Steel d.o.o., Zelezarska cesta 3, Store, Slovenia and Institute of Metals and Technology, Lepi pot 11, Ljubljana, Slovenia
Institute of Metals and Technology, Lepi pot 11, Ljubljana, Slovenia
Univerza v Mariboru, Fakulteta za strojnistvo, Smetanova ulica 17, 2000 Maribor, Slovenia",
