Toxic gas release modeling for real-time analysis using variational autoencoder with convolutional neural networks

Jonggeol Na, Kyeongwoo Jeon, Won Bo Lee

Research output: Contribution to journalArticlepeer-review

26 Scopus citations

Abstract

High-accuracy gas dispersion models are necessary for predicting toxic gas movement, and for reducing the damage caused by toxic gas release accidents in chemical processes. In urban areas, where obstacles are large and abundant, computational fluid dynamics (CFD) would be the best choice for simulating and analyzing scenarios of accidental release of toxic chemicals. However, owing to the large computation time required for CFD simulation, it is inappropriate in emergency situations and in real-time alarm systems. In this study, a non-linear surrogate model based on deep learning is proposed using a variational autoencoder with deep convolutional layers and a deep neural network with batch normalization (VAEDC-DNN) for real-time analysis of the probability of death (Pdeath). VAEDC can extract representation features of the Pdeath contour with complicated urban geometry in the latent space, and DNN maps the variable space into the latent space for the Pdeath image data. The chlorine gas leak accident in the Mipo complex (city of Ulsan, Republic of Korea) is used for verification of the model. The proposed model predicts the Pdeath image within a mean squared error of 0.00246, and compared with other models, it exhibits superior performance. Furthermore, through the smoothness of image transition in the variable space, it is confirmed that image generation is not overfitting by data memorization.

Original languageEnglish
Pages (from-to)68-78
Number of pages11
JournalChemical Engineering Science
Volume181
DOIs
StatePublished - 18 May 2018

Keywords

  • Autoencoder
  • Computational fluid dynamics
  • Convolutional neural network
  • Deep learning
  • Surrogate model
  • Toxic gas release

Fingerprint

Dive into the research topics of 'Toxic gas release modeling for real-time analysis using variational autoencoder with convolutional neural networks'. Together they form a unique fingerprint.

Cite this