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. INDEX TERMS Automatic fault detection, deep learning, maritime industry, prognostics and health management, unsupervised learning.
Today, most research studies that aim to predict the remaining useful life (RUL) of industrial components based on deep learning techniques are using piecewise linear (PwL) run-to-failure targets to model the degradation process. However, this PwL degradation model assumes a constant initial RUL value in which only time is needed to model normal operating conditions. Thus, it ignores the entire diagnostics aspect. To provide high and reliable RUL prediction accuracy, a prognostics algorithm must incorporate diagnostics information. This paper will provide the Prognostics and Health Management Community an empirical study that validates the PwL degradation model against other, more recent data-driven labeling approaches. We compare three different data-driven labeling approaches for RUL predictions. First, an unsupervised reconstruction-based fault detection algorithm is used to provide valuable diagnostics information. Then, optimized initial RUL values are calculated based on this information. Finally, these values are used to construct PwL, descriptive statistics, and anomaly score function run-to-failure targets for subset FD001 in the popular and publicly available C-MAPSS data set. A deep network structure is proposed and trained on the three different run-to-failure targets in order to predict the RUL. During the training process, a genetic algorithm approach is used to tune a selected search space of hyper-parameters. The results suggest that the network trained on PwL run-to-failure targets with the optimized initial RUL values performs the best and provides the most reliable RUL prediction accuracy. This network also outperforms the most robust results in the literature. INDEX TERMS Data-driven labeling approaches, deep learning, fault detection, prognostics and health management, remaining useful life.
Enthusiasm for ship autonomy is flourishing in the maritime industry. In this context, data-driven prognostics and health management (PHM) systems have emerged as the optimal way to improve operational reliability and system safety. However, further research is needed to enhance the essential actions relating to such a system. Fault detection is the first and most crucial action of any data-driven PHM system. In this article, we propose a fault-type independent spectral anomaly detection algorithm for marine diesel engine degradation in autonomous ferries. The benefits of the algorithm are verified on three fault types where the nature of degradation differs. Both normal operation data and faulty degradation data have been collected from a marine diesel engine using two different engine load profiles. These profiles aim to replicate real autonomous ferry crossing operations, environmental conditions that the ferry may encounter. First, the data are subjected to a feature selection process to remove irrelevant and redundant features. Then, a multiregime normalization method is performed on the data to merge the engine loads into one context. Finally, a variational autoencoder is trained to estimate velocity and acceleration calculations of the anomaly score. Generic and dynamic threshold limits are simultaneously established to detect the fault time step online. The algorithm achieved an accuracy of 97.66% in the final test when the acceleration was used as the fault detector. The results suggest that the algorithm is independent of fault types with different nature of degradation related to the marine diesel engine.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.