Proceedings of the 2022 European Conference on Computing in Construction

     

Incooperatimg machine learning for rapid blast resilence assessment

Shady Salem 1, Islam Torky 2
1 The British University in Egypt
2 Chair of Intelligent Technical Design Bauhaus-Universität, Weimar


DOI: 10.35490/EC3.2022.171
Abstract: Numerous resilience frameworks have been introduced to assess the post blast functionality and the expected recovery time for critical infrastructures. As such, several researchers have developed blast assessment diagrams, P-I, to be incorporated with such frameworks. However, the developed diagrams are computationally expensive and requires prolonged processing time. In this context, this paper introduces different ML models to produce P-I diagrams for concrete masonry walls, front defense line in critical infrastructures. The ANN model showed the best performance with 20% accuracy. The proposed approach opens the gate for similar application considering different infrastructure components.
Keywords: Resilience, Blast, Concrete masonry wall, Pressure, Impulse
Paper:
EC32022_171

Presentation Video: