Historical process data based energy monitoring - Model based time-series segmentation to determine target values

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

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Energy monitoring systems calculate actual energy use, estimate energy needs at normal operation, track energy metrics, and highlight issues related to energy efficiency of process plants. Analysis of the Key Energy Indicators (KEIs) allows the comparison of operation strategies at different operating regimes. Based on the extracted knowledge realistic targets of KEI-s can be determined. The performance of datadriven targeting models depends on operating regimes determined by a complex set of process variables. Till now this modelling task is performed manually based on heuristic and subjective evaluation of the operation. We developed a goal-oriented time-series segmentation technique to automate the selection of proper dataset used for the identification of targeting models. With the proposed tool target-models for different operating regions can be automatically determined. The concept of the resulted energy monitoring system is demonstrated at Heavy Naphtha Hydrotreater and CCR Reforming Units of MOL Hungarian Oil and Gas Company.

Original languageEnglish
Pages (from-to)931-936
Number of pages6
JournalChemical Engineering Transactions
Volume35
DOIs
Publication statusPublished - 2013

Fingerprint

Time series
Monitoring
Naphthas
Reforming reactions
Energy efficiency
Identification (control systems)
Oils
Gases
Industry
naphtha

ASJC Scopus subject areas

  • Chemical Engineering(all)

Cite this

Historical process data based energy monitoring - Model based time-series segmentation to determine target values. / Abonyi, J.; Kulcsar, Tibor; Balaton, Miklos; Nagy, Laszlo.

In: Chemical Engineering Transactions, Vol. 35, 2013, p. 931-936.

Research output: Contribution to journalArticle

@article{1fb0203b4902470a85c94b40b9ba3f00,
title = "Historical process data based energy monitoring - Model based time-series segmentation to determine target values",
abstract = "Energy monitoring systems calculate actual energy use, estimate energy needs at normal operation, track energy metrics, and highlight issues related to energy efficiency of process plants. Analysis of the Key Energy Indicators (KEIs) allows the comparison of operation strategies at different operating regimes. Based on the extracted knowledge realistic targets of KEI-s can be determined. The performance of datadriven targeting models depends on operating regimes determined by a complex set of process variables. Till now this modelling task is performed manually based on heuristic and subjective evaluation of the operation. We developed a goal-oriented time-series segmentation technique to automate the selection of proper dataset used for the identification of targeting models. With the proposed tool target-models for different operating regions can be automatically determined. The concept of the resulted energy monitoring system is demonstrated at Heavy Naphtha Hydrotreater and CCR Reforming Units of MOL Hungarian Oil and Gas Company.",
author = "J. Abonyi and Tibor Kulcsar and Miklos Balaton and Laszlo Nagy",
year = "2013",
doi = "10.3303/CET1335155",
language = "English",
volume = "35",
pages = "931--936",
journal = "Chemical Engineering Transactions",
issn = "1974-9791",
publisher = "AIDIC-Italian Association of Chemical Engineering",

}

TY - JOUR

T1 - Historical process data based energy monitoring - Model based time-series segmentation to determine target values

AU - Abonyi, J.

AU - Kulcsar, Tibor

AU - Balaton, Miklos

AU - Nagy, Laszlo

PY - 2013

Y1 - 2013

N2 - Energy monitoring systems calculate actual energy use, estimate energy needs at normal operation, track energy metrics, and highlight issues related to energy efficiency of process plants. Analysis of the Key Energy Indicators (KEIs) allows the comparison of operation strategies at different operating regimes. Based on the extracted knowledge realistic targets of KEI-s can be determined. The performance of datadriven targeting models depends on operating regimes determined by a complex set of process variables. Till now this modelling task is performed manually based on heuristic and subjective evaluation of the operation. We developed a goal-oriented time-series segmentation technique to automate the selection of proper dataset used for the identification of targeting models. With the proposed tool target-models for different operating regions can be automatically determined. The concept of the resulted energy monitoring system is demonstrated at Heavy Naphtha Hydrotreater and CCR Reforming Units of MOL Hungarian Oil and Gas Company.

AB - Energy monitoring systems calculate actual energy use, estimate energy needs at normal operation, track energy metrics, and highlight issues related to energy efficiency of process plants. Analysis of the Key Energy Indicators (KEIs) allows the comparison of operation strategies at different operating regimes. Based on the extracted knowledge realistic targets of KEI-s can be determined. The performance of datadriven targeting models depends on operating regimes determined by a complex set of process variables. Till now this modelling task is performed manually based on heuristic and subjective evaluation of the operation. We developed a goal-oriented time-series segmentation technique to automate the selection of proper dataset used for the identification of targeting models. With the proposed tool target-models for different operating regions can be automatically determined. The concept of the resulted energy monitoring system is demonstrated at Heavy Naphtha Hydrotreater and CCR Reforming Units of MOL Hungarian Oil and Gas Company.

UR - http://www.scopus.com/inward/record.url?scp=84886282577&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886282577&partnerID=8YFLogxK

U2 - 10.3303/CET1335155

DO - 10.3303/CET1335155

M3 - Article

AN - SCOPUS:84886282577

VL - 35

SP - 931

EP - 936

JO - Chemical Engineering Transactions

JF - Chemical Engineering Transactions

SN - 1974-9791

ER -