The luxury yacht market is increasingly driven by a demand for sustainability, emphasizing the need for enhanced monitoring and optimization of energy consumption, particularly in the yacht’s hotel sector. To address this demand, we propose a novel system that leverages artificial intelligence (AI) and digital twin (DT) technologies. This system integrates various network-connected sensors, smart plugs, and actuators, such as HVAC systems, lighting, and automated blinds, and is orchestrated by an advanced AI algorithm. Given the challenge of limited experimental data on energy consumption and passenger habits, our approach involves the development of a modular digital twin of the yacht. This DT enables the simulation of different configurations and operational scenarios, generating substantial virtual data for training AI models. Specifically, we employ a Long-Short-Term Memory (LSTM) neural network for time series analysis, which predicts future consumption based on current usage patterns and passenger behavior. This methodology offers a general framework applicable to various yacht designs, enhancing sustainability and operational efficiency across the industry.
Leaveraging Digital Twin & Artificial Intelligence in Consumption Forecasting System for Sustainable Luxury Yacht
Dini, Pierpaolo
Primo
;Paolini, Davide;Saponara, Sergio;
2024-01-01
Abstract
The luxury yacht market is increasingly driven by a demand for sustainability, emphasizing the need for enhanced monitoring and optimization of energy consumption, particularly in the yacht’s hotel sector. To address this demand, we propose a novel system that leverages artificial intelligence (AI) and digital twin (DT) technologies. This system integrates various network-connected sensors, smart plugs, and actuators, such as HVAC systems, lighting, and automated blinds, and is orchestrated by an advanced AI algorithm. Given the challenge of limited experimental data on energy consumption and passenger habits, our approach involves the development of a modular digital twin of the yacht. This DT enables the simulation of different configurations and operational scenarios, generating substantial virtual data for training AI models. Specifically, we employ a Long-Short-Term Memory (LSTM) neural network for time series analysis, which predicts future consumption based on current usage patterns and passenger behavior. This methodology offers a general framework applicable to various yacht designs, enhancing sustainability and operational efficiency across the industry.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
