Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Datadrivna underhållsstrategier inom tillverkningsindustrier
Högskolan Väst, Institutionen för ekonomi och it, Avd för informatik.
Högskolan Väst, Institutionen för ekonomi och it, Avd för informatik.
2018 (Svenska)Självständigt arbete på grundnivå (kandidatexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
Abstract [en]

The ever-increasing competition on the market in the manufacturing industry places new demands on the manufacturing industry to streamline its production. Maintaining the production operations for manufacturing industry is important in order to remain competitive. If a machine stops working, it may cause major costs in both repair and downtime. Driving a machine until it breaks before performing maintenance is not a sustainable maintenance work, the machine must be serviced before the error occurs. Scheduled maintenance can make improvement to this, but may also be resource-intensive. The machines need to be constantly monitored and maintenance should be performed when monitoring systems show trends that the machine condition deteriorates. This essay aims at studying the phenomenon of ”Predictive Maintenance” to see what opportunities advanced data collection and analysis technologies have for a manufacturing industry. The essay was conducted through interviews at the company GKN in Trollhättan, which is active in manufacturing for aircraft engines and other air components. The result has also been compared with previous research in the field, which describes computer-driven maintenance work techniques. This was to find out how a manufacturing industry can work proactively with data-driven maintenance strategies to prevent, in time, production failure. The result shows that there are advanced technologies that can send data using sensor technology, then use complex algorithms that analyze the sensor data to prevent production errors occurring. Applying the techniques to GKN is likely to increase their proactive possibilities, but the results from the GKN interviews indicate that there are more challenges than choosing a system for preventive maintenance. It was found in the interviews that there is a lack of communication in the need for a system solution, that the knowledge of the machines is limited to the operators and that the studied company lacks experience in analyzing data.

Ort, förlag, år, upplaga, sidor
2018. , s. 61
Nyckelord [en]
Predictive Maintenance, Internet of Things, Machine Learning, Condition Based Maintenance, Condition Monitoring, Machine-2-machine
Nationell ämneskategori
Samhällsvetenskap
Identifikatorer
URN: urn:nbn:se:hv:diva-12739Lokalt ID: EIC501OAI: oai:DiVA.org:hv-12739DiVA, id: diva2:1232137
Ämne / kurs
Informatik
Utbildningsprogram
Systemutveckling - IT och samhälle
Handledare
Examinatorer
Tillgänglig från: 2018-07-23 Skapad: 2018-07-10 Senast uppdaterad: 2018-07-23Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Av organisationen
Avd för informatik
Samhällsvetenskap

Sök vidare utanför DiVA

GoogleGoogle Scholar

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 228 träffar
RefereraExporteraLänk till posten
Permanent länk

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