Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Big Data in Maintenance Decision Support Systems: Aggregation of Disparate Data Types
KTH, School of Industrial Engineering and Management (ITM), Production Engineering.
2016 (English)In: Euromaintenance 2016 Conference Proceedings, 2016, p. 503-512Conference paper, Published paper (Refereed)
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.

Place, publisher, year, edition, pages
2016. p. 503-512
National Category
Mechanical Engineering
Identifiers
URN: urn:nbn:se:kth:diva-205918OAI: oai:DiVA.org:kth-205918DiVA, id: diva2:1090722
Conference
Euromaintenance 30 May-1 June 2016, Athens, Greece
Funder
XPRES - Initiative for excellence in production research
Note

QC 20170519

Available from: 2017-04-25 Created: 2017-04-25 Last updated: 2017-05-19Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Website

Search in DiVA

By author/editor
Wang, Lihui
By organisation
Production Engineering
Mechanical Engineering

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 184 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf