BlastOFormer: Attention and Neural Operator Deep Learning Methods for Explosive Blast Prediction

2025-05-26

AI Summary

To address the challenge of real-time, high-accuracy prediction of blast-induced shockwave pressure fields in complex environments, this paper proposes a novel Transformer architecture integrating signed distance function (SDF)-based geometric encoding, mesh-to-mesh attention, and neural operators. The method overcomes the dual bottlenecks of poor generalizability in empirical models and prohibitive computational cost in high-fidelity CFD simulations. Trained on a high-fidelity CFD dataset generated by blastFoam, the model achieves state-of-the-art performance in both original and logarithmic domains (R² = 0.9516), with inference latency of only 6.4 ms—over 600,000× faster than conventional CFD solvers. It significantly outperforms CNN- and FNO-based baselines while ensuring strong generalizability and spatial consistency. This work establishes a deployable AI-driven solver paradigm for explosion safety assessment and real-time defensive decision-making.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Accurate prediction of blast pressure fields is essential for applications in structural safety, defense planning, and hazard mitigation. Traditional methods such as empirical models and computational fluid dynamics (CFD) simulations offer limited trade offs between speed and accuracy; empirical models fail to capture complex interactions in cluttered environments, while CFD simulations are computationally expensive and time consuming. In this work, we introduce BlastOFormer, a novel Transformer based surrogate model for full field maximum pressure prediction from arbitrary obstacle and charge configurations. BlastOFormer leverages a signed distance function (SDF) encoding and a grid to grid attention based architecture inspired by OFormer and Vision Transformer (ViT) frameworks. Trained on a dataset generated using the open source blastFoam CFD solver, our model outperforms convolutional neural networks (CNNs) and Fourier Neural Operators (FNOs) across both log transformed and unscaled domains. Quantitatively, BlastOFormer achieves the highest R2 score (0.9516) and lowest error metrics, while requiring only 6.4 milliseconds for inference, more than 600,000 times faster than CFD simulations. Qualitative visualizations and error analyses further confirm BlastOFormer's superior spatial coherence and generalization capabilities. These results highlight its potential as a real time alternative to conventional CFD approaches for blast pressure estimation in complex environments.

Problem

• Predicting blast pressure fields accurately and efficiently
• Overcoming speed-accuracy trade-offs in traditional methods
• Real-time blast estimation in complex environments

Innovation

• Transformer-based surrogate model for blast prediction
• Uses signed distance function (SDF) encoding
• Grid-to-grid attention architecture inspired by OFormer/ViT