Advanced data cluster analyses in digital twin development for marine engines towards ship performance quantification.

Due to the growing rate of energy consumption, it is necessary to develop frameworks for enhancing ship energy efficiency. This paper proposes a solution for this issue by introducing a digital twin framework for quantifying ship performance. For this purpose, extensive low-level clustering is performed using Gaussian Mixture Models (GMM) with the Expectation Maximization algorithm on a dataset of a selected vessel to detect the vessel's most frequent operating regions. Then, a regression analysis is performed in each operating region, to identify their shapes using Singular Value Decomposition (SVD). The results of SVD make the basis for model development in digital twin applications. For this reason, a low-level clustering is performed so that a more accurate model can be developed in future. Moreover, based on the resulting cluster analysis, an energy efficiency index is developed, and the energy efficiency of each cluster has been evaluated to identify the most efficient operating condition. Hence, the main contribution of this research is to develop a digital twin framework of a marine engine which can be utilized for green ship operations. The same contribution can facilitate the shipping industry to meet the International Maritime Organization energy efficiency requirements. • Introducing a digital twin framework for quantifying ship performance. • Capturing 7 operating regions of a selected vessel using GMM-EM approach. • Finding the most frequent operating region of the selected vessel. • Utilizing two different methods to find the proper number of clusters for GMM-EM. • Using SVD to find the relationship between variables and shape of each operating region. • Defining an Energy Efficiency Index to find the most energy efficient operating region. [ABSTRACT FROM AUTHOR]