Fast diesel engine models for real-time prediction in dynamic conditions are required to predict engine performance parameters, to identify emerging failures early on and to establish trends in performance reduction. In order to address these issues, two main alternatives exist: one is to exploit the physical knowledge of the problem, the other one is to exploit the historical data produced by the modern automation system. Unfortunately, the first approach often results in hard-to-tune and very computationally demanding models that are not suited for real-time prediction, while the second approach is often not trusted because of its questionable physical grounds. In this paper, the authors propose a novel hybrid model, which combines physical and data-driven models, to model diesel engine exhaust gas temperatures in operational conditions. Thanks to the combination of these two techniques, the authors were able to build a fast, accurate and physically grounded model that bridges the gap between the physical and data driven approaches. In order to support the proposal, the authors will show the performance of the different methods on real-world data collected from the Holland Class Oceangoing Patrol Vessel.

Diesel engines will remain a fundamental component of propulsion systems due to their maturity, reliability, and power density. Building Digital Twins of the propulsion system is one feasible solution to pursue the optimal propulsions system operation, estimating system states and efficiency. This work will investigate a modelling approach that combines high accuracy while satisfying real-time prediction capabilities by coupling a physics-based model with a data-driven modelling approach. We will demonstrate that the proposed hybridisation framework can provide state-of-the-art prediction capabilities in real-time, utilising operational data from a turbocharged, four-stroke medium-speed diesel engine.

The hydromechanics analysis of floating offshore wind turbines is a fundamental and time consuming part of the design process, traditionally analysed with methods of computational fluid dynamics. In this work, an alternative computational framework is suggested, able to significantly accelerate the design process with minimal accuracy loss. Through the use of a state-of-the-art potential-flow code, a surrogate model is developed with the aim to approximate the Response Amplitude Operators of any arbitrary floating offshore wind turbine of the spar buoy type. The results, measured in terms of accuracy and computational effort, demonstrate that this approach is able to approximate the potential-flow solver with very high accuracy at a fraction of the computational cost.