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

Janos 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 - Jan 1 2013

ASJC Scopus subject areas

  • Chemical Engineering(all)

Fingerprint Dive into the research topics of 'Historical process data based energy monitoring - Model based time-series segmentation to determine target values'. Together they form a unique fingerprint.

  • Cite this