Approach to Prediction of R/C Buildings’ Seismic Damage as Pattern Recognition Problem Using Artificial Neural Networks

Morfidis, Konstantinos; Kostinakis, Konstantinos

doi:10.7712/120117.5636.17237

Cited by 3 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This conclusion is based on the investigation of the relevant literature (see e.g. [3][4][5][6][7][8][9]15]). More specifically, the choice of MFPN in the framework of the FA problem's formulation and solution is based on the fact that this type of networks can approach continuous functions with any desirable level of accuracy (e.g.…”

Section: The Second Stage Of Problem's Formulationmentioning

confidence: 99%

“…As regards the solution of the PR problem the MFPN are also a reliable option as it was presented in many references (see e.g. [8,9,21,22,23]).…”

Section: The Second Stage Of Problem's Formulationmentioning

confidence: 99%

“…The main assumption is the utilization of the Forward Stepwise Method (see e.g. [8,15,26]) for the parametric investigation for the optimum combination of input parameters. Thus, the procedure of Figure 4 is not a unique option for the accomplishment of the optimum performance of the utilized networks.…”

Section: The Second Stage Of Problem's Formulationmentioning

confidence: 99%

“…In the current section the procedure that was presented in the section 2.3 for the formulation of closed-form equations which can be used in practice for the seismic vulnerability assessment of R/C buildings is applied. This formulation is based on optimum configured and trained MFPNs which are presented in research works of Morfidis and Kostinakis [8,15]. More specifically, closed-form expressions which correspond to the solution of the FA and the PR problem will be developed.…”

Section: Practical Applications: Closed-form Equations For the Predicmentioning

confidence: 99%

“…More specifically, in the field of earthquake engineering the corresponding studies are enough but less than the studies which are focused on other scientific fields of civil engineering (see e.g. [3][4][5][6][7][8][9]). Thus, for the seismic vulnerability assessment of existing buildings at urban scale or at regional state, methods such as the seismic vulnerability curves were developed and widely used (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Use of Artificial Neural Networks in the R/C Buildings’ Seismic Vulnerabilty Assessment: The Practical Point of View

Morfidis¹,

Kostinakis²

2019

Proceedings of the 7th International Conference on Computational Methods in Structural Dynamics and Earthquake Engineering (COM

Self Cite

View full text Add to dashboard Cite

Section: The Second Stage Of Problem's Formulationmentioning

confidence: 99%

“…As regards the solution of the PR problem the MFPN are also a reliable option as it was presented in many references (see e.g. [8,9,21,22,23]).…”

Section: The Second Stage Of Problem's Formulationmentioning

confidence: 99%

Section: The Second Stage Of Problem's Formulationmentioning

confidence: 99%

Section: Practical Applications: Closed-form Equations For the Predicmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Use of Artificial Neural Networks in the R/C Buildings’ Seismic Vulnerabilty Assessment: The Practical Point of View

Morfidis¹,

Kostinakis²

2019

Proceedings of the 7th International Conference on Computational Methods in Structural Dynamics and Earthquake Engineering (COM

Self Cite

View full text Add to dashboard Cite

Classification of buildings' potential for seismic damage using a machine learning model with auto hyperparameter tuning

Kostinakis

Morfidis

Demertzis

et al. 2023

Engineering Structures

View full text Add to dashboard Cite

R/C buildings’ seismic damage prediction based on semi-supervised automatic differentiation variational inference deep autoencoder

Demertzis,

Kostinakis,

Morfidis

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Structural damage from earthquakes has been assessed using a variety of methodologies, both statistical and, more recently, utilizing Machine Learning (ML) algorithms. The effectiveness of data-driven procedures, even when applied to extremely time-consuming scenarios and data sets that reflect substantial expertise and research, completely depends on the quality of the underlying data. The performance of the intelligent model can also be impacted by a lack of in-depth knowledge and expertise in using complex machine learning architectures. This can also prevent some crucial hyperparameters from being adjusted, which ultimately reduces the algorithm’s reliability and generalizability. The present research offers a Bayesian-based semi-supervised Automatic Differentiation Variational Inference (ADVI) deep autoencoder for forecasting seismic damage of R/C buildings. It is a state-of-the-art, intelligent technology that automatically converts the variables in the issue into actual coordinate space using an upgraded ADVI technique. Finally, using a brand-new Adaptive Learning Rate Gradient Algorithm (ALRGA), it chooses a technique in this area that is a function of the changed variables and optimizes its parameters. Using the sophisticated ADVI technique to establish a posterior distribution without having an analytical solution is an upgraded version of the semi-supervised learning method. Estimating seismic damage to buildings is accelerated and greatly simplified by the suggested methodology, which eliminates the computational complexity of the analytical methods. By performing Nonlinear Time History Analyses of 3D R/C structures exposed to 65 earthquakes, a realistic dataset for the model evaluation is produced. The system’s strong generalizability and the proposed methodology’s detailed convergence stability reveal that it is a valuable method that can outperform other ML algorithms.

show abstract

Approach to Prediction of R/C Buildings’ Seismic Damage as Pattern Recognition Problem Using Artificial Neural Networks

Abstract: Abstract. In the present paper the investigation of the problem of reinforced concrete (r/c) buildings' seismic damage prediction is exhibited utilizing Artificial Neural Networks (ANN

Cited by 3 publications

References 18 publications

Use of Artificial Neural Networks in the R/C Buildings’ Seismic Vulnerabilty Assessment: The Practical Point of View

Use of Artificial Neural Networks in the R/C Buildings’ Seismic Vulnerabilty Assessment: The Practical Point of View

Classification of buildings' potential for seismic damage using a machine learning model with auto hyperparameter tuning

R/C buildings’ seismic damage prediction based on semi-supervised automatic differentiation variational inference deep autoencoder

Contact Info

Product

Resources

About