• norsk
    • English
  • norsk 
    • norsk
    • English
  • Logg inn
Vis innførsel 
  •   Hjem
  • Fakultet for ingeniørvitenskap (IV)
  • Institutt for maskinteknikk og produksjon
  • Vis innførsel
  •   Hjem
  • Fakultet for ingeniørvitenskap (IV)
  • Institutt for maskinteknikk og produksjon
  • Vis innførsel
JavaScript is disabled for your browser. Some features of this site may not work without it.

Digitalization of Subsea Maintenance - Application of Industry 4.0 in Prognostics of Technical Condition and Residual Life

Hansen, Emil Halseth; Skare, Olav Helland
Master thesis
Åpne
19626_FULLTEXT.pdf (Låst)
19626_COVER.pdf (Låst)
Permanent lenke
http://hdl.handle.net/11250/2615336
Utgivelsesdato
2018
Metadata
Vis full innførsel
Samlinger
  • Institutt for maskinteknikk og produksjon [2600]
Sammendrag
The objective for the thesis is to contribute to enhanced production safety and availability of Equinor's subsea equipment. Through introducing methods, providing new technologies and concepts, the study highlights challenges and recommends improving measures regarding subsea assets in a lifelong impact.

Today the Subsea Control Module (SCM) is subject to corrective maintenance in Equinor's operation. The SCM is considered a production critical equipment, and experience arbitrary failures. This entails shut-down of production, and subsequent financial losses. Operational data for the SCMs is trended and analyzed to identify correlation to historical failure. The analysis revealed no correlation.

The study presents models applicable for predicting failure and estimating residual life. The current situation in Equinor is not sufficient in predicting failure of electrical components. This thesis identifies shortcomings of Equinor's operation, and provide guidance to enhance predictive abilities and maintenance performance. The thesis suggests a future-oriented maintenance concept to meet and overcome these obstacles. Predictive Analytics will form the basis in this concept, complemented by technologies within Maintenance 4.0. The following recommendations is given:

- Conduct Predictive Analytics pilot study on SCM using Machine Learning algorithms and pattern recognition.

- Enhance knowledge of electrical component degradation \& visualization of trended parameters to provide the ability to estimate Remaining Useful Life (RUL).

- Implement Predictive Maintenance aspects into the maintenance management loop. Predictive Analytics and Machine Learning ensure required technical condition.

- Overcome shortcomings and implement proposed concept. It is recommended to hybrid machines as a part of the decision making, together with operators. Digital Twin will serve as a tool for visualization and assistance.
Utgiver
NTNU

Kontakt oss | Gi tilbakemelding

Personvernerklæring
DSpace software copyright © 2002-2019  DuraSpace

Levert av  Unit
 

 

Bla i

Hele arkivetDelarkiv og samlingerUtgivelsesdatoForfattereTitlerEmneordDokumenttyperTidsskrifterDenne samlingenUtgivelsesdatoForfattereTitlerEmneordDokumenttyperTidsskrifter

Min side

Logg inn

Statistikk

Besøksstatistikk

Kontakt oss | Gi tilbakemelding

Personvernerklæring
DSpace software copyright © 2002-2019  DuraSpace

Levert av  Unit