Comparative evaluation of MFP and RBF neural networks’ ability for instant estimation of r/c buildings’ seismic damage level

Morfidis, Konstantinos; Kostinakis, Konstantinos

doi:10.1016/j.engstruct.2019.109436

Cited by 33 publications

(34 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the FNN model is not recommended for a GMR-dependent seismic damage assessment. Hand-crafted IMs were required by the FNN model to achieve high prediction performance, as demonstrated in previous studies [15][16][17]. In terms of the computing resources, GPUs are more expensive with less memory size than CPUs.…”

Section: Discussionmentioning

confidence: 88%

“…Two damage classes-namely, the collapse class and the non-collapse class-were defined in the machine learning-based approaches to predict the collapse of ductile r/c building frames [53]. Five damage states of r/c buildings in neural network-based approaches were used to classify the seismic structural damage states [16,17,23]. Three damage states were used to evaluate the performance of r/c buildings after earthquake events in [22,25,54], following the guidelines of the Applied Technology Council (ATC)-20 [55] and ATC-40 [56].…”

Section: Case Study 41 Benchmark Building and Nlthamentioning

confidence: 99%

“…states [16,17,23]. Three damage states were used to evaluate the performance of r/c buildings after earthquake events in [22,25,54], following the guidelines of the Applied Technology Council (ATC)-20 [55] and ATC-40 [56].…”

Section: Case Study 41 Benchmark Building and Nlthamentioning

confidence: 99%

“…To overcome the disadvantage of low-dimensional IMs, multivariate regression models were used to obtain a fragility estimation and facilitate more accurate and reliable regional seismic risk estimates by incorporating multiple IMs (up to five) into a vectorial IM [14]. Two artificial neural network (ANN) models, i.e., the feedforward neural network (FNN) and radial basis function (RBF) network models with 14 IMs as inputs, were adopted to predict the seismic-induced damage states of 30 reinforced concrete (r/c) buildings [15][16][17]. It was found that trained FNN and RBF models could reliably and rapidly predict the resultant damage states of r/c buildings after earthquake events.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks

Yuan

Tanksley

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Contemporary deep learning approaches for post-earthquake damage assessments based on 2D convolutional neural networks (CNNs) require encoding of ground motion records to transform their inherent 1D time series to 2D images, thus requiring high computing time and resources. This study develops a 1D CNN model to avoid the costly 2D image encoding. The 1D CNN model is compared with a 2D CNN model with wavelet transform encoding and a feedforward neural network (FNN) model to evaluate prediction performance and computational efficiency. A case study of a benchmark reinforced concrete (r/c) building indicated that the 1D CNN model achieved a prediction accuracy of 81.0%, which was very close to the 81.6% prediction accuracy of the 2D CNN model and much higher than the 70.8% prediction accuracy of the FNN model. At the same time, the 1D CNN model reduced computing time by more than 90% and reduced resources used by more than 69%, as compared to the 2D CNN model. Therefore, the developed 1D CNN model is recommended for rapid and accurate resultant damage assessment after earthquakes.

show abstract

Section: Discussionmentioning

confidence: 88%

Section: Case Study 41 Benchmark Building and Nlthamentioning

confidence: 99%

Section: Case Study 41 Benchmark Building and Nlthamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks

Yuan

Tanksley

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Comparison between static and dynamic analysis of elevated water tank was studied by Gaikwad and Mangulkar (2013) by considering the hydrodynamic effect on the elevated water tank, to compare the effects of impulsive and convective pressure. Morfidisa and Kostinakis (2019) studied the seismic damage state using artificial neural networks (ANN)-based methods such as multilayer feedforward perceptron networks (MFPN) and the radial-basis function networks (RBFN) and led to the best configured MFPN and RBFN on the basis of the optimization of their predictions about the seismic damage state of the samples and concluded that the MFPNs were more efficient than the RBFNs. Jagadale et al (2019) carried out a case study on a bridge model for determining the damages using PZT patches and found that there were noticeable changes in frequencies for moderate and severe damages, hence proving the efficiency of PZT.…”

Section: Introductionmentioning

confidence: 99%

Seismic performance of existing water tank after condition ranking using non-destructive testing

Nayak

Thakare

2019

Int J Adv Struct Eng

View full text Add to dashboard Cite

There has been a collaborative attempt to address the seismic vulnerability of existing structures in India after an earthquake in Bhuj, Gujarat, in 2001. Seismic diagnosis and seismic retrofit for the existing tanks have become a remarkable issue to be worked since deterioration is a cosmopolitan and natural phenomenon. It is important to know the exact reason for distress and type of distress. To manage such issues, a proper method of repair and rehabilitation with detailed plans and methodology is required. This paper is aimed at evolving systematic investigation metrology for condition ranking procedure based on the analytical hierarchy process (AHP) and strengthening by various retrofitting strategies. For that case study, an existing elevated water tank is considered, which was designed according to state of the art over 40 years ago as per old Indian Standard (IS) code. The ranking assessment of the elevated service reservoir was carried out using different non-destructive tests (NDTs). DER, i.e., degree (D), extent (E) and relevancy (R) rating technique was employed to find out the condition index of the elevated service reservoir (ESR). After finding the condition ranking of the existing structure, an analysis was carried out using SAP 2000 to find the present-day seismic requirements using IS codes. After knowing the seismic demand of the water tank, various retrofitting methods were adopted for improving the drift capacity and flexural capacity of the structure. The results were finally used to address some of the critical issues of the seismic response of the retrofitted structure in terms of a time period, mode shapes, base shear, displacement, acceleration, and velocity. From the case study result of seismic retrofit for the existing elevated water tank, it is confirmed that a relatively simple seismic retrofit method is effective to keep the tank functional after an earthquake.Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

show abstract

Enhancing seismic performance prediction of RC frames using MFF-ANN model approach

Nair,

Mol

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Comparative evaluation of MFP and RBF neural networks’ ability for instant estimation of r/c buildings’ seismic damage level

Cited by 33 publications

References 39 publications

Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks

Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks

Seismic performance of existing water tank after condition ranking using non-destructive testing

Enhancing seismic performance prediction of RC frames using MFF-ANN model approach

Contact Info

Product

Resources

About