DEVELOPMENT OF MACHINE LEARNING MODEL ON ESTIMATING FUEL CONSUMPTION FOR KMP. KIRANA VII

Junior, James Janto (2024) DEVELOPMENT OF MACHINE LEARNING MODEL ON ESTIMATING FUEL CONSUMPTION FOR KMP. KIRANA VII. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5019201101-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (5MB) | Request a copy

Abstract

Fuel consumption in shipping operations constitutes a substantial portion of operational costs and contributes to environmental pollution. Efficiently estimating fuel consumption is crucial for optimizing vessel operations, reducing operational expenses, and minimizing the environmental impact of ships. This study focuses on combining fuel optimization and machine learning, which is a subfield of artificial intelligence, offers powerful tools for analyzing complex data patterns and making accurate predictions. By training models on historical data, machine learning algorithms can learn the relationships between various factors and fuel consumption, enabling the development of accurate predictive models. This study is using 2 algorithms, Ridge regressor and XGBoost. Models made from both algorithms respectively have a R² of 0,886 and 0,9306. XGBoost model is much more accurate than using ridge regressor. The model can be more developed overtime by inputing more datas.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Machine Learning, R², Ridge Regressor, XGBoost
Subjects:	T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.74 Linear programming V Naval Science > VM Naval architecture. Shipbuilding. Marine engineering > VM276.A1 Fuel (Including supplies, costs, etc.) V Naval Science > VM Naval architecture. Shipbuilding. Marine engineering > VM381 Passenger ships
Divisions:	Faculty of Marine Technology (MARTECH) > Marine Engineering > 36202-(S1) Undergraduate Thesis
Depositing User:	James Janto Junior
Date Deposited:	07 Aug 2024 07:34
Last Modified:	25 Sep 2024 03:17
URI:	http://repository.its.ac.id/id/eprint/113138

Actions (login required)

View Item