Fast Seismic Assessment of Built Urban Areas with the Accuracy of Mechanical Methods Using a Feedforward Neural Network

Miguel-Rodríguez, Jaime de; Morales‐Esteban, Antonio; Requena-Garcia-Cruz, María-Victoria; Blanco, Zapico; Segovia-Verjel, María-Luisa; Romero-Sánchez, Emilio; Estêvão, João Miguel Carvalho

doi:10.3390/su14095274

Cited by 11 publications

(7 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These structures are divided into 6 groups according their number of stories (two or three), and the relative proportions of their X, Y, Z dimensions. This works represents a step ahead of the contribution originally presented in [18] by the authors.…”

Section: Methodsmentioning

confidence: 91%

“…Where nx, ny, nz = the number of spans in X, Y and Z, and sx, sy, sz = the number of steps in X, Y and Z. By Applying the values used for the generation of the dataset, then T = 9 × 9 × 3 × 24 9 × 24 9 × 10 3 and therefore, T > 10 18 . This accounts for the vast variety of samples that fall under the parameter scope and justifies the random sampling used to create the dataset.…”

Section: Dataset Generation (Network Input)mentioning

confidence: 99%

“…The loads considered in the analysis have been: self-weight of all the elements; additional dead loads (slabs, roofs and ceilings); and, a permanent live load. They have been combined in different hypotheses as presented in [18]. All the models have been fixed-based.…”

Section: Nonlinear Static Analyses (Network Output)mentioning

confidence: 99%

See 2 more Smart Citations

Fragility Assessment of Rc Buildings in Southern Spain Based on Neural Network Predictions

de Miguel-Rodríguez,

Requena-García-Cruz,

Romero-Sánchez

et al. 2023

Proceedings of the 8th International Conference on Computational Methods in Structural Dynamics and Earthquake Engineering (COM

View full text Add to dashboard Cite

The computational burden needed to perform a fragility analysis of structures can be excessive and beyond the capability of regular computing systems. In this work, a Neural Network (NN) implementation is presented to make fragility analyses attainable. Neural Networks allow finding solutions to complex problems at a fraction of the computational time required by conventional analyses. The fragility assessment has been developed for low-and mid-rise 3D buildings located in southern Spain, a moderate earthquake prone area. Nonlinear static analyses are carried out to determine the capacity curves of reinforced concrete buildings, avoiding their specific modelling. The curves are predicted with minimal error, requiring only basic geometric and material parameters of the structures to be specified. Four levels of performance-based seismic design have been considered to assess the seismic performance. Fragility curves have been developed for the structural models with different types of structural configurations and heights. Finally, it should be noted that fragility curves have not been obtained to date for the reinforced concrete buildings of the area.

show abstract

Section: Methodsmentioning

confidence: 91%

Section: Dataset Generation (Network Input)mentioning

confidence: 99%

See 1 more Smart Citation

Fragility Assessment of Rc Buildings in Southern Spain Based on Neural Network Predictions

de Miguel-Rodríguez,

Requena-García-Cruz,

Romero-Sánchez

et al. 2023

Proceedings of the 8th International Conference on Computational Methods in Structural Dynamics and Earthquake Engineering (COM

View full text Add to dashboard Cite

show abstract

“…For example, applications of an artificial neural network (ANN) model [20] and of a SWOT-quantitative strategic planning matrix (QSPM) [21] have been recently developed for the evaluation of seismic vulnerability in different municipalities in Iran. Other studies evaluated the seismic vulnerability of large sets of buildings in urban environments through a procedure based on the fast calculation of capacity curves of low-rise reinforced concrete buildings using neural networks [22]. Building capacity curves for 256 reinforced concrete buildings with between four and seven floors were obtained in [23], where the influence of the structural parameters on the seismic performance was quantified using a set of artificial neural network algorithms.…”

Section: Introductionmentioning

confidence: 99%

Seismic Vulnerability Assessment at an Urban Scale by Means of Machine Learning Techniques

Ferranti,

Greco,

Pluchino

et al. 2024

Buildings

View full text Add to dashboard Cite

Seismic vulnerability assessment in urban areas would, in principle, require the detailed modeling of every single building and the implementation of complex numerical calculations. This procedure is clearly difficult to apply at an urban scale where many buildings must be considered; therefore, it is essential to have simplified, but at the same time reliable, approaches to vulnerability assessment. Among the proposed strategies, one of the most interesting concerns is the application of machine learning algorithms, which are able to classify buildings according to their vulnerability on the basis of training procedures applied to existing datasets. In this paper, machine learning algorithms were applied to a dataset which collects and catalogs the structural characteristics of a large number of buildings and reports the damage observed in L’Aquila territory during the intense seismic activity that occurred in 2009. A combination of a trained neural network and a random forest algorithm allows us to identify an opportune “a-posteriori” vulnerability score, deduced from the observed damage, which is compared to an “a-priori” vulnerability one, evaluated taking into account characteristic indexes for building’s typologies. By means of this comparison, an inverse approach to seismic vulnerability assessment, which can be extended to different urban centers, is proposed.

show abstract

“…This type of careful analyses of case studies or sectors can provide useful information [11], which can be used later in global analyses. For the seismic assessment of historical buildings, nonlinear static analysis (NLSA) is usually carried out [12]. Despite its simplifications, it has been proved to be a suitable approach for a preliminary assessment of historical buildings, as suggested in [8,13].…”

Section: Introductionmentioning

confidence: 99%

A Model for the Structural and Seismic Assessment of the Mosque-Cathedral of Cordoba

Requena-Garcia-Cruz,

Romero-Sánchez,

Morales-Esteban

et al. 2023

Proceedings of the 8th International Conference on Computational Methods in Structural Dynamics and Earthquake Engineering (COM

View full text Add to dashboard Cite

Monumental heritage buildings were typically built without considering the seismic action. Therefore, they are potentially susceptible to seismic damage. The structural assessment and the vulnerability analysis of historical buildings is a complicated task. It requires a complex study and specialised technical skills. In order to gain some insight and to provide refined results, a model for the structural and the seismic performance of the Abd ´al-Rahman I sector of the Mosque-Cathedral of Cordoba (Spain) has been presented. The Mosque-Cathedral of Cordoba, its monumental core and its surroundings were included in the World Heritage List in 1984. Its structural system is based on parallel arcades and naves. It was started to be built in the 8 th century and it has been enlarged several times. This monumental building is located in a seismic area of the southern Iberian Peninsula, characterised by large/very large earthquakes of long-return periods. In this work, a novel 3D model has been developed based on the finite element (FE) method in the OpenSees framework. The model has been elaborated through the analysis of historical data and in situ verifications. An experimental campaign has been carried out to calibrate the numerical model. Gravitational and horizontal nonlinear static analyses have been performed to determine the structural and the seismic capacity of the structure. The results have shown that the building presents the worst seismic behaviour in the direction perpendicular to the arcades. This study represents a pioneer experiment concerning the structural and seismic analysis of this building.

show abstract

Fast Seismic Assessment of Built Urban Areas with the Accuracy of Mechanical Methods Using a Feedforward Neural Network

Cited by 11 publications

References 61 publications

Fragility Assessment of Rc Buildings in Southern Spain Based on Neural Network Predictions

Fragility Assessment of Rc Buildings in Southern Spain Based on Neural Network Predictions

Seismic Vulnerability Assessment at an Urban Scale by Means of Machine Learning Techniques

A Model for the Structural and Seismic Assessment of the Mosque-Cathedral of Cordoba

Contact Info

Product

Resources

About