| Autor: |
El Mekkaoui, Sara, Boukachab, Ghait, Benabbou, Loubna, Berrado, Abdelaziz |
| Zdroj: |
WMU Journal of Maritime Affairs; Sep2024, Vol. 23 Issue 3, p329-346, 18p |
| Abstrakt: |
This paper introduces a methodology for monitoring the vessel arrival process, a critical factor in enhancing maritime operational efficiency. This approach uses deep learning sequence models and Statistical Process Control Charts to track the variability in a vessel arrival process. The proposed solution uses the predictive deep learning model to get a vessel's estimated time of arrival, produces quality characteristics, and applies statistical control charts to monitor their variability. The paper presents the results of applying the proposed methodology for vessel arrivals at a coal terminal, which demonstrates the effectiveness of the method. By enabling precise monitoring of arrival times, this methodology not only supports efficient ship and port operations planning but also aids in the timely adoption of operational adjustments. This can significantly contribute to operational measures aimed at reducing shipping emissions and optimizing resource utilization. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink