A methodology to predict key aspects of the structural response of masonry walls under blast loading using artificial neural networks (ANN) is presented in this paper. The failure patterns of masonry walls due to in and out-of-plane loading are complex due to the potential opening and sliding of the mortar joint interfaces between the masonry stones. To capture this response, advanced computational models can be developed requiring a significant amount of resources and computational effort. The article uses an advanced non-linear finite element model to capture the failure response of masonry walls under blast loads, introducing unilateral contact-friction laws between stones and damage mechanics laws for the stones. Parametric finite simulations are automatically conducted using commercial finite element software linked with MATLAB R2019a and Python. A dataset is then created and used to train an artificial neural network. The trained neural network is able to predict the out-of-plane response of the masonry wall for random properties of the blast load (standoff distance and weight). The results indicate that the accuracy of the proposed framework is satisfactory. A comparison of the computational time needed for a single finite element simulation and for a prediction of the out-of-plane response of the wall by the trained neural network highlights the benefits of the proposed machine learning approach in terms of computational time and resources. Therefore, the proposed approach can be used to substitute time consuming explicit dynamic finite element simulations and used as a reliable tool in the fast prediction of the masonry response under blast actions.
A numerical investigation of masonry walls subjected to blast loads is presented in this article. A non-linear finite element model is proposed to describe the structural response of the walls. A unilateral contact–friction law is used in the interfaces of the masonry blocks to provide the discrete failure between the blocks. A continuum damage plasticity model is also used to account for the compressive and tensile failure of the blocks. The main goal of this article is to investigate the different collapse mechanisms that arise as an effect of the blast load parameters and the static load of the wall. Parametric studies are conducted to evaluate the effect of the blast source–wall (standoff) distance and the blast weight on the structural response of the system. It is shown that the traditional in-plane diagonal cracking failure mode may still dominate when a blast action is present, depending on the considered standoff distance and the blast weight when in-plane static loading is also applied to the wall. It is also highlighted that the presence of an opening in the wall may significantly reduce the effect of the blasting action.
8 July 2025 in European Journal of Computational Mechanics
Architects consider the brickwork patterns vital for the aesthetics of the walls. The different brick bonding patterns can influence the resistance of masonry walls when subject to in-plane and out-of-plane loading. This study investigates the effect of different bonding patterns under a blast load of 50 kg TNT at a standoff distance of 20 m. Advanced non-linear finite element models were adopted, considering unilateral contact-friction and continuum damage mechanics laws, to capture different failure types. The adoption of a simplified micro-modelling approach provided meaningful results on the behaviour of the wall. The in-plane and out-of-plane response of walls with different bonding patterns was investigated and comparisons were made. This study concluded that the stack bond has a weaker binding pattern than other widely used bonds like English bond and Stretcher bond due to the lack of interlocking between the masonry units. Shear failure and vertical cracking were seen as the typical failures in all the three walls, with the stack bond depicting higher deflections under both in-plane and blast loading.