Data based tools for sensors continuous monitoring in industry applications

  • L. Galotto
  • , A. D.M. Brun
  • , R. B. Godoy
  • , F. R.R. Maciel
  • , J. O.P. Pinto

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

This paper presents a 10 years experience of data driven models for sensor validation applied for petroleum and natural gas industry. Auto-associative kernel regression has been used as the main modeling method. The models achieved were embedded in software called Sentinell, which is used for sensors diagnosis. The software is being used in a natural gas compression station, and it has been evaluated in other industries such as: refineries, offshore petroleum platforms, and thermoelectric power plants. In this work the theoretical background is presented, as well as the performance metrics indexes used to evaluate the models. The developed methodology and the results in the real plants are presented and discussed. The experience of these previous works might open future applications in high reliability automated processes.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE 24th International Symposium on Industrial Electronics, ISIE 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages600-605
Number of pages6
ISBN (Electronic)9781467375542
DOIs
StatePublished - Sep 28 2015
Externally publishedYes
Event24th IEEE International Symposium on Industrial Electronics, ISIE 2015 - Buzios, Rio de Janeiro, Brazil
Duration: Jun 3 2015Jun 5 2015

Publication series

NameIEEE International Symposium on Industrial Electronics
Volume2015-September

Conference

Conference24th IEEE International Symposium on Industrial Electronics, ISIE 2015
Country/TerritoryBrazil
CityBuzios, Rio de Janeiro
Period06/3/1506/5/15

Keywords

  • Auto-Associative Kernel Regression
  • Data Based Models
  • Sensors Monitoring

Fingerprint

Dive into the research topics of 'Data based tools for sensors continuous monitoring in industry applications'. Together they form a unique fingerprint.

Cite this