Data Driven Digital Twin Applications Towards Green Ship Operations

Due to the growing rate of energy consumption and its consequent emissions, the International Maritime Organization (IMO) has devised strict rules for an extensive reduction in Greenhouse Emissions (GHG), which forces the shipping industry to search for more energy-efficient solutions. Therefore, alongside with the Energy Efficiency Design Index (EEDI), improving the energy efficiency of existing ships under the Energy Efficiency Existing Ship Index (EEXI) is of considerable importance. This paper address this issue by proposing a digital twin framework supported by big data analytics for ship performance monitoring. The proposed framework is developed by the respective data sets from a selected vessel. For this purpose, a cluster analysis is implemented using the Gaussian Mixture Models (GMMs) with the Expectation Maximization (EM) algorithm. By this approach, the most frequent operating regions of the engine is detected, the shapes of these frequent operating regions are captured, and the relationships between different navigation and performance parameters of the engine are determined. That will make the basis for a digital twin application in shipping. The main objective of this research study is to develop a digital twin of a marine engine by considering the engine operational conditions that can be utilized toward green ship operations. The contribution of this paper and the outcomes can facilitate the shipping industry to meet the IMO requirements enforced by its regulations.