An Unsupervised Reconstruction-Based Fault Detection Algorithm for Maritime Components

• Published in: IEEE access Vol. 7; pp. 16101 - 16109
• Main Authors: Ellefsen, Andre Listou, Bjorlykhaug, Emil, Aesoy, Vilmar, Zhang, Houxiang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Automatic fault detection; Component reliability; Datasets; deep learning; Degradation; Fault detection; Machine learning algorithms; Maintenance engineering; Maritime industry; Prediction algorithms; Prognostics and health management; Random noise; Reconstruction; Signal processing algorithms; unsupervised learning
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2895394

In recent years, the reliability and safety requirements of ship systems have increased drastically. This has prompted a paradigm shift toward the development of prognostics and health management (PHM) approaches for these systems' critical maritime components. In light of harsh environmental conditions with varying operational loads, and a lack of fault labels in the maritime industry generally, any PHM solution for maritime components should include independent and intelligent fault detection algorithms that can report faults automatically. In this paper, we propose an unsupervised reconstruction-based fault detection algorithm for maritime components. The advantages of the proposed algorithm are verified on five different data sets of real operational run-to-failure data provided by a highly regarded industrial company. Each data set is subject to a fault at an unknown time step. In addition, different magnitudes of random white Gaussian noise are applied to each data set in order to create several real-life situations. The results suggest that the algorithm is highly suitable to be included as part of a pure data-driven diagnostics approach in future end-to-end PHM system solutions.