ABSTRACT

Representing the entire operational range of an ocean-going vessel with linear equations is often a formidable task. In this research study, a data-driven localized model is presented for ship performance prediction as a part of the digital twin development. For this purpose, different operational conditions of the vessel, i.e., data clusters, are identified using the Gaussian Mixture Models (GMM) coupled with the Expectation Maximization (EM) algorithm. Subsequently, Singular Value Decomposition (SVD) as a part of the Eigensystem Realization Algorithm (ERA) is applied to each cluster to establish the relationships between different operational and navigational variables and capture the system dynamics in localized operational conditions in each cluster.

INTRODUCTION

In the preceding years, the application of numerical modeling and computational simulations has become more prevalent, revolutionizing various industries towards more data-driven predictive approaches. This paradigm shift, is gaining momentum increasingly in diverse fields of research, ranging from engineering (Taghavi et al., 2023; Bhuvela et al., 2023; Namazi and Taghavipour, 2021; Alvandifar et al., 2021) to healthcare (Shoaib and Ramamohan, 2022; Bagherian et al., 2020) and environmental sciences (Xiu et al., 2020; Hardesty, 2017; Chen, 2020). The maritime industry, with complex operational dynamics in its various sectors and its ever-increasing reliance on efficiency and precision, is no exception to this trend. Simulations and numerical modeling, when used for detailed analysis of the behavior of the various systems of ocean-going vessels, can play a crucial role in the design and optimization phase (Barone et al., 2023), safety and risk analysis (Chang et al., 2021), operational efficiency improvement (Barone et al., 2023), predictive maintenance scheduling (Liu et al., 2022; Makridis et al., 2020), autonomous vessels development (Wang et l., 2022; Hasan et al., 2023), and economic analysis.

Moreover, since shipping is the fundamental mode of international trade, lower operational costs in this industry can lead to reduced freight rates imposed on the overall supply chain. As a result, reducing the operational costs associated with this industry can have a profound effect on the global economy. As a result, many research topics have been investigating the economic aspect of the shipping industry (Akbar et al., 2021). Of all the operational costs of shipping, fuel consumption accounts for approximately 45-50% (Rodrigue 2020), a reduction of which has the potential to yield substantial economic benefits. Hence, improving fuel efficiency can be attractive for all ship owners, attracting more interest among the researchers. As an example, Taghavifar and Perera (2023) assess the lifecycle emissions and costs associated with using Liquefied Natural Gas (LNG) as an alternative fuel for ocean-going diesel-operated ships. A reliable model that simulates a ship's behavior is crucial for enhancing fuel efficiency. Such a model facilitates optimization and predictive analysis, enabling the testing of various potential scenarios to assess their effectiveness. By identifying key factors contributing to fuel consumption using the developed model, fuel consumption across diverse operational scenarios can be optimized.

This content is only available via PDF.
You can access this article if you purchase or spend a download.