Physical and Data-Driven Models Hybridisation for Modelling the Dynamic State of a Four-Stroke Marine Diesel Engine

Abstract

Accurate, reliable, and computationally inexpensive models of the dynamic state of combustion engines are a fundamental tool to investigate new engine designs, develop optimal control strategies, and monitor their performance. The use of those models would allow to improve the engine cost-efficiency trade-off, operational robustness, and environmental impact. To address this challenge, two state-of-the-art alternatives in literature exist. The first one is to develop high fidelity physical models (e.g., mean value engine, zero-dimensional, and one-dimensional models) exploiting the physical principles that regulate engine behaviour. The second one is to exploit historical data produced by the modern engine control and automation systems or by high-fidelity simulators to feed data-driven models (e.g., shallow and deep machine learning models) able to learn an accurate digital twin of the system without any prior knowledge. The main issues of the former approach are its complexity and the high (in some case prohibitive) computational require-

Health assessment framework of marine engines enabled by digital twins

“…Both steps of the calibration process utilise the MATLAB default particle-swarm optimisation algorithm, which is most effective in determining a global minimum, particularly since the Wiebe function utilised to model combustion, is known to yield similar results with widely different combinations of parameters. 42 Consequently, the gradient-free algorithm employed herein is suitable in overcoming the local minima encountered. The objective functions of two-step calibration process are shown in Appendix I.…”

“…38,39 Additionally, advanced optimisation methods, including genetic algorithms have been utilised to calibrate combustion parameters, 40,41 as well as more sophisticated mesh-adaptive direct search optimisation algorithms. 42 However, the detailed steps and challenges of the above calibration approaches are not explicitly highlighted.…”

Physically plausible propeller noise prediction via recursive corrections leveraging prior knowledge and experimental data

“…HMs are able to exploit the physical knowledge of the phenomenon and available historical data, to deliver both accurate and physically plausible results, usually surpassing the performance of both PM or DDM (Coraddu et al, 2018(Coraddu et al, , 2021a(Coraddu et al, , 2022.…”

A Framework to Assure the Trustworthiness of Physical Model-Based Digital Twins for Marine Engines

“…DDMs do not require prior knowledge of the machinery systems; instead, they rely on an extensive amount of data. HMs combine PMs and DDMs to compensate for both methods' drawbacks; however, limited applications are reported in the pertinent literature [17].…”