Data imputation of missing values from marine systems sensor data. Evaluation, visualisation, and sensor failure detection

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

12 Downloads (Pure)

Abstract

To enable Condition-Based maintenance, sensors need to be installed, and thus Internet of Ships (IoS) needs to be implemented. IoS presents several challenges, an example of which is the imputation of missing values. A data assessment imputation framework that is utilised to assess the accuracy of any imputation model is presented. To complement this study, a real-time imputation tool is proposed based on an open-source stack. A case study on a total of 4 machinery systems parameters obtained from sensors installed on a cargo vessel is presented to highlight the implementation of this framework. The multivariate imputation technique is performed by applying Kernel Ridge Regression (KRR). As the explanatory variables may also contain missing values, GA-ARIMA is utilised as the univariate imputation technique. The case study results demonstrate the applicability of the suggested framework in the case of marine machinery systems.
Original languageEnglish
Title of host publicationRINA Maritime Innovation and Emerging Technologies Online Conference 2021 Proceedings
Place of PublicationLondon
PublisherRoyal Institution of Naval Architects
Number of pages9
Publication statusE-pub ahead of print - 17 Mar 2021
EventRoyal Institution of Naval Architects Maritime Innovation and Emerging Technologies Online Conference 2021 - Online
Duration: 17 Mar 202118 Mar 2021
https://www.rina.org.uk/Maritime_innovation_2021.html

Conference

ConferenceRoyal Institution of Naval Architects Maritime Innovation and Emerging Technologies Online Conference 2021
Abbreviated titleRINA Maritime Innovation and Emerging Technologies Online Conference 2021
Period17/03/2118/03/21
Internet address

Keywords

  • data imputation
  • machine learning
  • marine machinery systems
  • condition-based maintenance (CBM)
  • data monitoring
  • imputation assessment

Fingerprint

Dive into the research topics of 'Data imputation of missing values from marine systems sensor data. Evaluation, visualisation, and sensor failure detection'. Together they form a unique fingerprint.

Cite this