Prof. Andrea Coraddu

University of Strathclyde

1 dicembre 2020 alle ore 9.15 - 11

Piattaforma web MTeams: Join Microsoft Teams Meeting

La partecipazione è libera

Abstract:

Data Analytics is improving our way to understand complex phenomena as and even faster than a-priory physical models have done in the past. Engineering Systems are composed by many complex elements, and their mutual interaction is not easy to model and predict adopting the conventional first principles physics model based on a-priory physical knowledge, because of the significant number of parameters which influence their behaviour. Moreover, state-of-the-art models built upon the physical knowledge of the system may have prohibitive computational requirements. First-principles physics models describe the behaviour of systems based on governing physical laws and taking into account their mutual interactions. The higher the detail in the modelling of the physical equations the higher the expected accuracy of the results and the computational time required for the simulation. These models are generally rather tolerant to extrapolation and do not require an extensive amount of operational measurements. On the other hand, when employing models that are computationally fast enough to be used for online optimisation, the expected accuracy in the prediction of operational variables is relatively low. Additionally, the construction of the model is a process that requires competence in the field, and availability of technical details which are often not easy to get access.

Data-Driven Models, instead, exploit advanced statistical techniques in order to build models directly based on a large amount of historical data collected by the recent advanced automation systems without having any a-priory knowledge of the underlining physical system. Data-Driven Models are extremely useful when it comes to continuously monitor physical systems to avoid preventive or corrective maintenance and take decisions based on the actual condition of the system. Unfortunately, Data-Driven Models need a large amount of data to achieve satisfying accuracies, and this can be a drawback when the data’s collection might require a stop of the asset. For these reasons, the different modelling philosophies must be exploited in conjunction in order to solve their drawbacks and take the best of each approach.
The seminar will focus on Physical, Data-Driven, and Hybrid Models for marine engineering applications. Example and real-life problems will be proposed and analysed, from bearings fault prediction to energy optimisations, and fuel consumption predictions.

Short Bio:

Dr Coraddu has been Assistant Professor in the Department of Naval Architecture, Ocean & Marine Engineering at the University of Strathclyde since October 2018. His relevant professional and academic experiences include working as Teaching Associate at the University of Strathclyde, Research Associate at the School of Marine Science and Technology at Newcastle University, Research Engineer as part of the DAMEN R&D department based in Singapore, and serving as Postdoctoral Research Fellow at the University of Genoa, where he was awarded a Laurea and a PhD in Naval Architecture and Marine Engineering.

Dr Coraddu’s research focuses on modelling, optimisation and analysis of ship power plants and propulsion systems for efficiency improvement and reduction of environmental footprint. His primary research involves taking advantage of on-board data availability in assessing vessel performance, energy optimisation, and real-time monitoring of the primary systems. Utilising the latest learning algorithms and theoretical results in machine learning, Dr Coraddu is developing Data-Driven approaches to investigate the behaviour of complex on-board systems and their mutual interaction.