Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Big Data in Maintenance Decision Support Systems: Aggregation of Disparate Data Types
KTH, Skolan för industriell teknik och management (ITM), Industriell produktion.
2016 (engelsk)Inngår i: Euromaintenance 2016 Conference Proceedings, 2016, s. 503-512Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

There is need to obtain reliable information on current and future asset health status to support maintenance decision making process. Within maintenance two main sources of data can be distinguished: Computerized Maintenance Management System (CMMS) for asset registry and maintenance work records; and Condition Monitoring Systems (CM) for direct asset components health state monitoring. There are also other sources of information like SCADA (Supervisory Control and Data Acquisition) for process and control monitoring that can provide additional contextual information leading to better decision making. However data produced acquired and processed and in those system are of disparate types, nature and granularity. This variety includes: event data about failures or performed maintenance work mostly descriptions in unstructured natural language; process variables obtained from different types of sensors and different physical variables from transducers, acquired with different sampling frequencies. Indeed, condition monitoring data are so disparate in nature that maintainers deal with scalars (temperature) through waveforms (vibration) to 2D thermography images and 3D data from machine geometry measuring. Integration and aggregation of those data is not a trivial task and requires modelling of knowledge about those data types, their mutual dependencies and dependencies with monitored processes. There are some attempts of standardisation that try to enable integration of CBM data from different sources. The conversion of those amount of data in meaningful data sets is required for better machine health assessment and tracking within the specific operational context for the asset. This will also enhance the maintenance decision support system with information on how different operational condition can affect the reliability of the asset for concrete contextual circumstances.

sted, utgiver, år, opplag, sider
2016. s. 503-512
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-205918OAI: oai:DiVA.org:kth-205918DiVA, id: diva2:1090722
Konferanse
Euromaintenance 30 May-1 June 2016, Athens, Greece
Forskningsfinansiär
XPRES - Initiative for excellence in production research
Merknad

QC 20170519

Tilgjengelig fra: 2017-04-25 Laget: 2017-04-25 Sist oppdatert: 2017-05-19bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Website

Søk i DiVA

Av forfatter/redaktør
Wang, Lihui
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric

urn-nbn
Totalt: 248 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf