Abstract
The chapter explains techniques and approaches to optimize a ship's voyage in terms of environmental and business parameters, utilizing the digital twin (DT) concept. It demonstrates how voyage planning and navigation management, in general, is enhanced by taking into account vessel state in real time as reflected and analyzed by the digital twin ecosystem. The theoretical backbone of voyage planning entails a multitude of state-of-the-art processes from trajectory mining and path finding algorithms to multi constraining optimization by including a variety of parameters to the initial problem, such as weather avoidance, bunkering, Just in Time (JIT) arrival, predictive maintenance, as well as inventory management and charter party compliance. In this chapter, the authors showcase pertinent literature regarding navigation management as well as how the envisaged DT platform can redesign voyage planning incorporating all the aforementioned parameters in a holistic digital replica of the en-route vessel, eventually proposing mitigation solutions to improve operational efficiency in real-time, through simulation, reasoning, and analysis.
Reference36 articles.
1. Predicting dynamic fuel oil consumption on ships with automated machine learning.;FredrikAhlgren;Journal of Mechanical Science and Technology,2018
2. Vessels fuel consumption forecast and trim optimisation: A data analytics perspective
3. Avgouleas, K. & Sclavounos, P. (2008). Optimal ship routing. Research Gate.
4. Bai, Z., Shangguan, W., Cai, B. & Chai, L. (2019). Deep reinforcement learning based high-level driving behavior decision-making model in heterogeneous traffic. IEEE.
5. Bernitsas, M., Ray, D., & Kinley, P. (1981). 𝐾𝑇, 𝐾𝑄 and Efficiency Curves for the Wageningen B-series propellers. Department of Naval Architecture and Marine Engineering College of Engineering The University of Michigan .