Advancing Sustainable Maritime with AI/ML Enhanced Hardware-in-the-Loop Testing

Abstract

This paper explores the potential of Hardware-in-the-Loop (HIL) testing and simulations in advancing sustainable maritime. HIL testing is a technique that combines physical components and a virtual real-time system. HIL is a powerful method for developing control algorithms and doing optimization for vehicles and vessels in a laboratory. By combining HIL testing with artificial intelligence (AI) and machine learning (ML), improvements in fuel and cost efficiency, emission reduction, risk mitigation, and sustainability reporting can be achieved. This study reviews literature in the maritime and related fields where AI and ML are being used to address sustainability objectives. This paper also reports the implementation of a Mechanical-level HIL (MHIL) test bench, which features a real marine engine attached to a simulation model that comprises a vessel and a hybrid powertrain. The ultimate objective of this study is to identify AI/ML-driven research opportunities for the MHIL test bench. The results reveal five potential classes of AI/ML/HIL research: data-driven modeling, optimal engine and hybrid drive control, multi-objective optimization of navigation, proactive maintenance and condition monitoring, as well as opportunities for regulation and sustainability compliance.