Prescriptive and descriptive quality metrics for the quality assessment of operational data: Quality assessment for data-driven and hybrid models in the process industry

Research output: Contribution to book/conference proceedings/anthology/reportConference contributionContributedpeer-review

Contributors

Abstract

In the process industry data-driven and hybrid modeling approaches are increasingly popular in regards to process monitoring, optimization and control. The major problem with process data is that the data collected in process plants during operation, even though available in vast amounts, might generally be low in information content. The collected data usually represents certain operating points while anomalies, ramp-up and shut-down are rare occurrences and therefore only seldom covered. Due to its possibly low quality, the use of such data might lead to an inadequate model coverage and overall low model performance. Data quality assessment prior to modeling is crucial to allow an estimation of model quality prior to the model development. Therefore, the following paper discusses prescriptive and descriptive assessment metrics for the quality assessment of process data and their potential application in the quality assurance of data-driven and hybrid models. This approach will in later application support the user in their choice of modeling approach.

Details

Original languageEnglish
Title of host publicationGI-Jahrestagung
EditorsDaniel Demmler, Daniel Krupka, Hannes Federrath
PublisherGesellschaft fur Informatik (GI)
Pages1061-1064
Number of pages4
ISBN (electronic)9783885797203
ISBN (print)9783885797203
Publication statusPublished - 2022
Peer-reviewedYes

Publication series

SeriesLecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)
VolumeP-326
ISSN1617-5468

Conference

Title2022 Informatik in den Naturwissenschaften, INFORMATIK 2022 - 2022 Computer Science in the Natural Sciences, INFORMATIK 2022
Duration26 - 30 September 2022
CityHamburg
CountryGermany

External IDs

dblp conf/gi/ViedtMKU22
Mendeley e74a4518-064d-3d74-9590-d51186146933
ORCID /0000-0002-5814-5128/work/142242028
ORCID /0000-0001-5165-4459/work/142248262
ORCID /0000-0001-7012-5966/work/142253168

Keywords

ASJC Scopus subject areas

Keywords

  • Data quality assessment, hybrid modeling, prescriptive data quality metrics