Prediction of blast loading on protruded structures using machine learning methods

Abstract

Current empirical and semi-empirical based design manuals are restricted to the analysis of simple building configurations against blast loading. Prediction of blast loads for complex geometries is typically carried out with computational fluid dynamics solvers, which are known for their high computational cost. The combination of high-fidelity simulations with machine learning tools may significantly accelerate processing time, but the efficacy of such tools must be investigated. The present study evaluates various machine learning algorithms to predict peak overpressure and impulse on a protruded structure exposed to blast loading. A dataset with over 250,000 data points extracted from ProSAir simulations is used to train, validate, and test the models. Among the machine learning algorithms, gradient boosting models outperformed neural networks, demonstrating high predictive power. These models required significantly less time for hyperparameter optimization, and the randomized search approach achieved relatively similar results to that of grid search. Based on permutation feature importance studies, the protrusion length was considered a significantly more influential parameter in the construction of decision trees than building height.

A Review of Blast Loading in the Urban Environment

“…Flood et al [117] showcased a neural network that was capable of running as much as six orders of magnitude faster than a CFD simulation for a 3D scenario, with similar results reported by Kang and Park [118]. Zahedi and Golchin [119] also compared neural network-based modelling to CFD simulations and stated that their results "demonstrate the potential for machine learning algorithms to revolutionise CFD analysis for blast loading". Winter and Hargather [120] used background-orientated schlieren (BOS) to reconstruct three-dimensional shock waves using multiple high-speed cameras pitched at varying viewing angles.…”

Harnessing Energy Balance and Genetic Algorithms for Efficient Building Demolition

“…Zahedi, M.'s research provides a reliable method of controlled blasting construction by systematically selecting the columns to be demolished. The results show that better blasting effects can be achieved in multi-stage blasting plans by removing columns that contribute more to key structural elements, especially in lower structural parts [6]. Although this research has achieved better demolition effects, it only targets the internal structure of the building and does not consider how to demolish under multi-point energy release.…”