Prediction of Peak Pressure by Blast Wave Propagation Between Buildings Using a Conditional 3D Convolutional Neural Network

Abstract

To predict the damage resulting from an explosion in the middle of a city, where buildings are concentrated, the peak pressure reaching the walls of the buildings or in between buildings should be accurately and rapidly calculated. However, predicting peak pressure between buildings is known to be very difficult because of the diffraction and reflection of blast waves, which have generally been analyzed by numerical analysis methods. However, numerical analysis is not suitable in a military operation environment which requires rapid analysis, because it takes considerable time and resources. This study proposes a deep neural network that quickly and accurately predicts the peak pressure caused by the propagation of blast waves, for the effective analysis of weapon effectiveness and damage in urban environments. The proposed deep learning model is based on a 3-dimensional convolutional neural network (3D CNN) model that processes the spatial information of explosion and measurement in the 3D spaces using 3D kernels. To predict the peak pressure between buildings separated by an arbitrary distance using a single model, we also propose using conditional convolution, which modulates the prediction output according to the building distance. The proposed models were trained with a dataset constructed through finite element analysis with various building distances, explosion locations, and explosive weights. The experiment with a fixed building distance showed that the relative error of the proposed 3D CNN is less than 7%, which is 2.5 times more accurate than a simple multi-layer perceptron (MLP) model. For unseen building layouts, the conditional 3D convolution showed 3.6 times lower error than the MLP model, demonstrating the effectiveness of the conditional convolution for prediction in arbitrary building layouts. Most importantly, the proposed deep learning models took less than one minute per prediction, which is significantly faster than finite element analysis, which takes 6 to 8 hours to analyze a single simulation case.