Spatiotemporal and layout-adaptive prediction of leak gas dispersion by encoding-prediction neural network

Abstract

Gas leak accident has been troublesome issues in the chemical industries. Predicting dispersion boundaries are important to make rapid and proper actions. Currently, computational fluid dynamics (CFD) are used to predict the dispersion boundaries. However, when the facility-layout of a workplace is often modified, using CFD is not desirable since it requires large computational expenses. This study proposes an encoding-prediction neural network to learn representations between dispersion of leak gas, velocity field, and facility-layouts. This network predict volume fraction field of leak gas in t + kΔt timestep by observing that data in t ∼ t + (k-1)Δt timestep. Training and test losses are decreased to 1.04 × 10−5 and 1.46 × 10−5, respectively. The network predicts dispersion of leak gas through recursive prediction scheme, the predicted results shows good agreement with ground truth. Methodology to generated various facility-layouts, and preprocessing methods to deal with skewed data are suggested. The methodology and results proposed in this study would be useful for developing the CFD surrogate model.