Introduction
This bi-monthly seminar series explores real-world applications of physics-informed machine learning (Φ-ML) methods to the engineering practice. They cover a wide range of topics, offering a cross-sectional view of the state of the art on Φ-ML research, worldwide.
Participants have the opportunity to hear from leading researchers and learn about the latest developments in this emerging field. These seminars also offer the chance to identify and spark collaboration opportunities.
About the event
Engineering structures, such as bridges, tunnels, power plants or buildings, are key to the functioning of society. So far, they have been designed, built and maintained using deterministic finite element models that rely on numerous empirical assumptions and codified safety factors. The predictions of such models often bear little resemblance to the behaviour of the actual structure.
Lately, advances in monitoring using sensor networks is providing an unprecedented amount of data from structures in operation. This seminar will present a novel statistical finite element construction, dubbed as statFEM, that boosts the predictive accuracy of models by synthesising their output with sensor data. As a case study, the application of statFEM in digital twinning of an operational steel railway bridge along the West Coast Mainline will be discussed.
Watch on demand:
