Εμφάνιση απλής εγγραφής

Fuel consumption and weather routing with the use of artificial intelligence

dc.contributor.advisorArtikis, Alexandros
dc.contributor.advisorΑρτίκης, Αλέξανδρος
dc.contributor.authorRafalias, Aristeidis
dc.contributor.authorΡαφαλιάς, Αριστείδης
dc.date.accessioned2024-11-29T11:25:49Z
dc.date.available2024-11-29T11:25:49Z
dc.date.issued2024-11
dc.identifier.urihttps://dione.lib.unipi.gr/xmlui/handle/unipi/17150
dc.identifier.urihttp://dx.doi.org/10.26267/unipi_dione/4573
dc.format.extent76el
dc.language.isoenel
dc.publisherΠανεπιστήμιο Πειραιώςel
dc.titleFuel consumption and weather routing with the use of artificial intelligenceel
dc.title.alternativeΗ κατανάλωση καυσίμου και ο σχεδιασμός διαδρομής με γνώμονα τον καιρό μέσω της τεχνητής νοημοσύνηςel
dc.typeMaster Thesisel
dc.contributor.departmentΣχολή Ναυτιλίας και Βιομηχανίας. Τμήμα Ναυτιλιακών Σπουδώνel
dc.description.abstractENThis thesis explores how artificial intelligence (AI) can be used to solve two important problems facing the maritime sector: maximising fuel efficiency and putting effective weather routing into practice. The shipping sector, a vital component of international trade, is coming under growing pressure to lessen its environmental impact without sacrificing operational effectiveness. This study investigates the revolutionary potential of AI-driven approaches in accomplishing these objectives. The study starts by placing the economic and environmental issues facing the shipping sector in context and highlighting how urgent it is to comply with global laws like the Energy Efficiency Operational Index (EEOI) and the IMO 2050 agenda. These frameworks emphasise how important it is to implement creative ways to reduce greenhouse gas emissions and improve energy efficiency. The technical foundation of this thesis is a comparison of two prediction techniques: Deep Neural Networks (DNN) and the Simplified Naval Architecture Method (SNAM). While SNAM provides a simple approach to fuel consumption estimation based on environmental parameters and vessel design, DNN uses complicated, nonlinear data interactions to achieve greater forecast accuracy. While more work is required for containerships, the analysis shows that DNN is advantageous in situations involving bulk carriers and oil tankers. The study also looks at how AI is being incorporated into weather routing, demonstrating how it can evaluate real-time weather data to create the best routes that save fuel and improve safety. Case studies demonstrate observable advantages in fuel economy, cost reduction, and environmental compliance, including AI-based technologies like OptiNav and Sofar Pathfinder. In the end, this study highlights AI's potential to completely transform the marine sector by providing workable solutions for sustainability and legal compliance. The results support the wider use of AI technologies to promote environmental responsibility and efficiency in international shipping.el
dc.contributor.masterShipping Managementel
dc.subject.keywordArtificial intelligenceel
dc.subject.keywordFuel consumptionel
dc.subject.keywordWeather routingel
dc.date.defense2024-11-19


Αρχεία σε αυτό το τεκμήριο

Thumbnail

Αυτό το τεκμήριο εμφανίζεται στις ακόλουθες συλλογές

Εμφάνιση απλής εγγραφής


Βιβλιοθήκη Πανεπιστημίου Πειραιώς
Επικοινωνήστε μαζί μας
Στείλτε μας τα σχόλιά σας
Created by ELiDOC
Η δημιουργία κι ο εμπλουτισμός του Ιδρυματικού Αποθετηρίου "Διώνη", έγιναν στο πλαίσιο του Έργου «Υπηρεσία Ιδρυματικού Αποθετηρίου και Ψηφιακής Βιβλιοθήκης» της πράξης «Ψηφιακές υπηρεσίες ανοιχτής πρόσβασης της βιβλιοθήκης του Πανεπιστημίου Πειραιώς»