Modelling thermomechanical degradation of moulded electronic packages using physics-based digital twin

Semiconductor devices are commonly encapsulated with Epoxy-based Moulding Compounds (EMC) to form an electronic package. EMC typically occupies a large volume within a package, and thus, governs its thermomechanical behaviour. When exposed to high temperatures (150°C and above), electronic packages predominantly show oxidation of the outer layer...

Evaluating railway track stiffness using axle box accelerations: A digital twin approach

While various train-borne techniques have been developed for measuring railway track stiffness, differentiating stiffness at different track layers remains a challenge. This study proposes a digital twin framework for the vehicle–track interaction system, which enables track stiffness evaluations based on axle box accelerations (ABA). The...

Towards deep probabilistic graph neural network for natural gas leak detection and localization without labeled anomaly data

Deep learning has been widely applied to automated leakage detection and location of natural gas pipe networks. Prevalent deep learning approaches do not consider the spatial dependency of sensors, which limits leakage detection performance. Graph deep learning is a promising alternative to prevailing approaches as it can model spatial...