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...

Characterizing the Effects of Al(OH)3 and Mg(OH)2 on Reaction Products and Drying Shrinkage Characteristics of Alkali-activated Slag

This study is undertaken to explore the relationship between the reaction products and the drying shrinkage of alkali-activated slag (AAS) with the varying hydroxide dosage. AAS pastes were firstly produced with either Al(OH)3 or Mg(OH)2 to investigate the effects of hydroxide on the composition of reaction products and the drying shrinkage of...