Feature selection based root cause analysis for energy monitoring and targeting

Tibor Kulcsar, Miklos Balaton, Laszlo Nagy, J. Abonyi

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Energy Monitoring (EM) systems are based on monitoring the difference between targeted and measured energy consumption. Data-driven dynamic targeting models can be used to estimate values of key energy indicators (KEI). In some cases it is difficult to determine which process variables influence the KEIs. We developed an automated root cause analysis (RCA) technique to find the most important driving factors of energy efficiency. The proposed concept is based on the application of feature selection algorithms. We applied Orthogonal Least Squares (OLS) and Random Forest Regression (RFR) to find the proper set of input variables of the targeting models. The concept of the resulted energy monitoring system is applied at the Duna Refinery of MOL Hungarian Oil and Gas Company.

Original languageEnglish
Pages (from-to)709-714
Number of pages6
JournalChemical Engineering Transactions
Volume39
Issue numberSpecial Issue
DOIs
Publication statusPublished - 2014

Fingerprint

Feature extraction
Monitoring
Energy efficiency
Oils
Energy utilization
Gases
Industry
pinazepam

ASJC Scopus subject areas

  • Chemical Engineering(all)

Cite this

Feature selection based root cause analysis for energy monitoring and targeting. / Kulcsar, Tibor; Balaton, Miklos; Nagy, Laszlo; Abonyi, J.

In: Chemical Engineering Transactions, Vol. 39, No. Special Issue, 2014, p. 709-714.

Research output: Contribution to journalArticle

Kulcsar, Tibor ; Balaton, Miklos ; Nagy, Laszlo ; Abonyi, J. / Feature selection based root cause analysis for energy monitoring and targeting. In: Chemical Engineering Transactions. 2014 ; Vol. 39, No. Special Issue. pp. 709-714.
@article{daacf6e53c694b958acffe6745c15a15,
title = "Feature selection based root cause analysis for energy monitoring and targeting",
abstract = "Energy Monitoring (EM) systems are based on monitoring the difference between targeted and measured energy consumption. Data-driven dynamic targeting models can be used to estimate values of key energy indicators (KEI). In some cases it is difficult to determine which process variables influence the KEIs. We developed an automated root cause analysis (RCA) technique to find the most important driving factors of energy efficiency. The proposed concept is based on the application of feature selection algorithms. We applied Orthogonal Least Squares (OLS) and Random Forest Regression (RFR) to find the proper set of input variables of the targeting models. The concept of the resulted energy monitoring system is applied at the Duna Refinery of MOL Hungarian Oil and Gas Company.",
author = "Tibor Kulcsar and Miklos Balaton and Laszlo Nagy and J. Abonyi",
year = "2014",
doi = "10.3303/CET1439119",
language = "English",
volume = "39",
pages = "709--714",
journal = "Chemical Engineering Transactions",
issn = "1974-9791",
publisher = "AIDIC-Italian Association of Chemical Engineering",
number = "Special Issue",

}

TY - JOUR

T1 - Feature selection based root cause analysis for energy monitoring and targeting

AU - Kulcsar, Tibor

AU - Balaton, Miklos

AU - Nagy, Laszlo

AU - Abonyi, J.

PY - 2014

Y1 - 2014

N2 - Energy Monitoring (EM) systems are based on monitoring the difference between targeted and measured energy consumption. Data-driven dynamic targeting models can be used to estimate values of key energy indicators (KEI). In some cases it is difficult to determine which process variables influence the KEIs. We developed an automated root cause analysis (RCA) technique to find the most important driving factors of energy efficiency. The proposed concept is based on the application of feature selection algorithms. We applied Orthogonal Least Squares (OLS) and Random Forest Regression (RFR) to find the proper set of input variables of the targeting models. The concept of the resulted energy monitoring system is applied at the Duna Refinery of MOL Hungarian Oil and Gas Company.

AB - Energy Monitoring (EM) systems are based on monitoring the difference between targeted and measured energy consumption. Data-driven dynamic targeting models can be used to estimate values of key energy indicators (KEI). In some cases it is difficult to determine which process variables influence the KEIs. We developed an automated root cause analysis (RCA) technique to find the most important driving factors of energy efficiency. The proposed concept is based on the application of feature selection algorithms. We applied Orthogonal Least Squares (OLS) and Random Forest Regression (RFR) to find the proper set of input variables of the targeting models. The concept of the resulted energy monitoring system is applied at the Duna Refinery of MOL Hungarian Oil and Gas Company.

UR - http://www.scopus.com/inward/record.url?scp=84908086441&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908086441&partnerID=8YFLogxK

U2 - 10.3303/CET1439119

DO - 10.3303/CET1439119

M3 - Article

AN - SCOPUS:84908086441

VL - 39

SP - 709

EP - 714

JO - Chemical Engineering Transactions

JF - Chemical Engineering Transactions

SN - 1974-9791

IS - Special Issue

ER -