This work presents a methodology for the generation of novel 3D objects resembling wireframes of building types. These result from the reconstruction of interpolated locations within the learnt distribution of variational autoencoders (VAEs), a deep generative machine learning model based on neural networks. The data set used features a scheme for geometry representation based on a ‘connectivity map’ that is especially suited to express the wireframe objects that compose it. Additionally, the input samples are generated through ‘parametric augmentation’, a strategy proposed in this study that creates coherent variations among data by enabling a set of parameters to alter representative features on a given building type. In the experiments that are described in this paper, more than 150 k input samples belonging to two building types have been processed during the training of a VAE model. The main contribution of this paper has been to explore parametric augmentation for the generation of large data sets of 3D geometries, showcasing its problems and limitations in the context of neural networks and VAEs. Results show that the generation of interpolated hybrid geometries is a challenging task. Despite the difficulty of the endeavour, promising advances are presented.
Capacity curves obtained from nonlinear static analyses are widely used to perform seismic assessments of structures as an alternative to dynamic analysis. This paper presents a novel ‘en masse’ method to assess the seismic vulnerability of urban areas swiftly and with the accuracy of mechanical methods. At the core of this methodology is the calculation of the capacity curves of low-rise reinforced concrete buildings using neural networks, where no modeling of the building is required. The curves are predicted with minimal error, needing only basic geometric and material parameters of the structures to be specified. As a first implementation, a typology of prismatic buildings is defined and a training set of more than 7000 structures generated. The capacity curves are calculated through push-over analysis using SAP2000. The results feature the prediction of 100-point curves in a single run of the network while maintaining a very low mean absolute error. This paper proposes a method that improves current seismic assessment tools by providing a fast and accurate calculation of the vulnerability of large sets of buildings in urban environments.
This work summarises the strategy adopted in the European research project PERSISTAH. It aims to increase the resilience of the population, focusing on the existing primary schools in the Algarve (Portugal) and Huelva (Spain) regions. Software was developed to assess the seismic safety of these schools, considering different earthquake scenarios. Seismic retrofitting measures were studied and numerically tested. Some of them were also implemented in the retrofitting activities of two case study schools (one in each country). It was found that the adopted ground motion prediction equations (GMPEs) considerably affect the results obtained with the software, especially for offshore earthquake scenarios. Furthermore, the results show that the masonry buildings would be the most damaged school typologies for all the scenarios considered. Additionally, a set of guidelines was created to support the school community and the technicians related to the construction industry. The goal of these documents is to increase the seismic resilience of the population. Different activities were carried out to train schoolteachers in seismic safety based on the guidelines produced, obtaining positive feedback from them.
This paper presents a first approximation to a connectionist implementation of the Bateson-inspired concept generation model previously introduced by de-Miguel & Sancho (https://arxiv.org/abs/2307.08087v2)