Application of NARX neural network for predicting marine engine performance parameters

ABSTRACT

Though the maritime industry is still predominantly reliant on a time-based, prescriptive approach to maintenance, the increasing complexity of shipboard systems, heightened expectation and competitive requirements as to ship availability and efficiency and the influence of the data revolution on vessel operations, favour a properly structured Condition Based Maintenance (CBM) regime. In this respect, Artificial Neural Networks (ANNs) can be applied for predictive maintenance strategies assisting decision makers to select appropriate maintenance actions for critical ship machinery. This paper develops a Nonlinear Autoregressive with Exogenous Input (NARX) ANN for forecasting future values of the exhaust gas outlet temperature of a marine main engine cylinder. A detailed sensitivity analysis is conducted to examine the performance and robustness of the NARX model for variations in the time series data, demonstrating virtuous performance and generalisation capabilities for forecasting and the ability to employ the model for monitoring and prognostic applications.

KEYWORDS:

• ANN
• NARX
• time series analysis
• ship condition monitoring
• marine engine

Acknowledgements

The work in this paper is partially funded by INCASS project. INCASS has received research funding from the European Union's Seventh Framework Programme under grant agreement No. 605200. This publication reflects only the authors’ views and European Union is not liable for any use that may be made of the information contained herein.

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on contributors

Mr Yiannis Raptodimos is a PhD candidate at the University of Strathclyde, Glasgow, UK. His research focuses on the development of a hybrid condition monitoring tool for ship machinery systems combining reliability tools with data-driven methods based on neural networks. He has participated and contributed in EU funded research related projects in the fields of maintenance and inspection, reliability analysis, data analytics, condition monitoring and decision support systems.

Dr Iraklis Lazakis is a senior lecturer in the Department of NAOME at the University of Strathclyde. He has developed his expertise on reliability and criticality based maintenance in order to improve ship safety and operations. He has participated and contributed in industry, UK and EU funded research related projects in the fields of maintenance, inspection, condition monitoring, decision support systems, reliability and risk analysis.

ORCID

Yiannis Raptodimos http://orcid.org/0000-0002-7508-5956

Iraklis Lazakis http://orcid.org/0000-0002-6130-9410

Additional information

Funding

The work in this paper is partially funded by INCASS project. INCASS has received research funding from the European Union’s Seventh Framework Programme under grant agreement No. 605200.