Reinforced Concrete Frame Failure Prediction Using Neural Network Algorithm

Dehkordi, Behzad Zemani; Abdipour, Roohollah; Motaghed, Sasan; Charkh, Ali Khooshe; Sina, Hooman; Zad, Mohammad Sadegh Shahid

doi:10.3923/jas.2012.498.501

Cited by 8 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although, ANNs have also been employed to predict the response of more intricate RC structural forms (e.g. RC frames) [9][10][11] with the whole structure modelled as a single ANN, the latter approach lacks generality as it is case-dependent and its application to other problems requires re-training of the ANN employed. In order to successfully formulate a scheme suitable for the analysis of any RC structure, it is imperative that the ANNs employed are capable of realistically predicting the nonlinear behaviour of the individual members (e.g.…”

Section: Introductionmentioning

confidence: 99%

Framework for the development of artificial neural networks for predicting the load carrying capacity of RC members

2020

View full text Add to dashboard Cite

This paper aims at establishing a framework for the development of artificial neural networks (ANNs) capable of realistically predicting the load-carrying capacity of reinforced concrete (RC) members. Multilayer back propagation neural networks are developed through the use of MATLAB and enriched databases which contain information describing the variation of load-carrying capacity in relation to key design parameters associated with the RC specimens (i.e. beams) considered. This work forms the basis for the development of a knowledge-based structural analysis tool capable of predicting RC structural response. A detailed discussion is provided on the different aspects of the proposed framework which include (1) the formation and analysis of the relevant (experimental) data, (2) the architecture of the ANNs, (3) the training/calibration process they undergo and finally, (4) ways of extending their applicability enabling them to predict the behaviour of RC structural forms with design parameters not represented in the available experimental database. Non-linear finite element analysis is used for validating the predictions of the ANN models developed. The comparative study reveals that the ANN models developed through the proposed framework are capable of effectively predicting the load-carrying capacity s of the RC structural forms considered quickly, accurately and without requiring significant computational resources. Keywords Artificial neural network • Database • Sampling method • Ultimate limit state • Reinforced concrete • Training process • Finite element analysis • Failure • Latin hypercube sampling List of symbols v Shear span b Width of the beam specimen cross-section d Effective depth of the beam specimen cross-section A s Area of longitudinal reinforcement acting in tension A sw Area of transverse reinforcement v ∕d Shear span to depth ratio f c Uniaxial compressive strength of concrete f yl Yield stress of longitudinal reinforcement bars f yw Yield stress of transverse reinforcement bars s Spacing between shear links l Ratio of tensile reinforcement (l = A s ∕b ⋅ d) w Ratio of transverse reinforcement (l = A sw ∕b ⋅ s) V u Shear strength Abbreviations CFP Compressive force path ANN Artificial neural network ULS Ultimate limit state LHS Latin hypercube sampling * Afaq Ahmad,

show abstract

Section: Introductionmentioning

confidence: 99%

Framework for the development of artificial neural networks for predicting the load carrying capacity of RC members

2020

View full text Add to dashboard Cite

show abstract

“…The main input parameters of PSHA include the minimum magnitude, mmin, the annual rate of seismicity, λ (corresponding to mmin), and the value of b related to the Gutenberg-Richter relation, the upper limit of the earthquake magnitude, mmax. Numerous studies have been performed on the contribution of input parameters in the results of PSHA [18]. Some of these publications have shown the high importance of mmin in the PSHA [19,20].…”

Section: An Overview Of the Concepts And Relationships Of The Pshamentioning

confidence: 99%

“…In most cases, the PSHA threshold value is set at a minimum of about 4 or 5 because smaller values rarely cause significant damage [24]. In 2004, McGuire made the following statement; lower limit mmin is selected based on the minimum magnitude that causes damage or loss and should be considered for hazard reduction purposes [18]. Although these expressions have different expressions, they all convey the same meaning.…”

Section: Mmin Definitionsmentioning

confidence: 99%

A Reliable Method for Determining the Tapered Minimum Magnitude in a Probabilistic Seismic Hazard Analysis

motaghed,

fakhriyat

2023

IJRRS

View full text Add to dashboard Cite

One of the inputs of probabilistic seismic hazard analysis (PSHA) is the minimum magnitude (mmin) of damaging earthquakes. Recent studies have shown that the choice of mmin can affect the results of PSHA. That is, if the mmin value is low, the PSHA will be overestimated. Therefore, it is important to choose the mmin value in such a way that earthquakes with greater magnitude than mmin have the capability to damage the structure. Obviously, the mmin depends on the characteristics of the structure and the earthquake. The mechanism of occurrence of earthquakes in each region is such that earthquakes with different characteristics can occur. Therefore, earthquakes with the same magnitude cause different levels of damage to the structure. This paper uses a tapered line instead of the cut-off magnitude for mmin. In this regard, we model The 3, 5, and 8-story intermediate concrete frame using Opensees software and perform time history dynamic analysis based on 246 earthquake accelerograms. The structural damage is assumed based on the drift ratio. The drift ratio of 0.004 is assumed as the limit state for the operational performance (OP) level. Using the non-uniform distance number, the mmin taper line is obtained as [4.5, 5.5]. This number can be used as the integral lower bound in the PSHA.

show abstract

“…In this model, the degradation in stiffness and strength, pinching, and asymmetric slip for different values of model parameters is applicable. The values of the parameters of this model are selected empirically [54][55][56].…”

Section: Structural Modelingmentioning

confidence: 99%

Implementation of AI for The Prediction of Failures of Reinforced Concrete Frames

motaghed,

Shahid zadeh,

khooshecharkh

et al. 2022

IJRRS

View full text Add to dashboard Cite

Reinforced concrete tall building failure, in residual areas, can cause catastrophic disaster if they can't survive during the destructive earthquakes. Hence, determining the damage of these buildings in the earthquake and detecting the probable mechanism formation are necessary for insurance purposes in urban areas. This paper aims to determine the failure modes of the moment resisting concrete frames (MRFs) according to the damage of the beam and column. To achieve this goal, a 15-storey moment resisting reinforced concrete frame is modeled via IDARC software, and nonlinear dynamic time history analysis is performed through 60 seismic accelerograms. Then the collapse and non-collapse vectors are constructed obtaining the results of dynamic analysis in both modes. The artificial neural network is used for the classification of the obtained modes. The results show good agreement in failures classes. Hence it is possible to introduce the simple weight factor for frame status identification.

show abstract

Reinforced Concrete Frame Failure Prediction Using Neural Network Algorithm

Cited by 8 publications

References 12 publications

Framework for the development of artificial neural networks for predicting the load carrying capacity of RC members

Framework for the development of artificial neural networks for predicting the load carrying capacity of RC members

A Reliable Method for Determining the Tapered Minimum Magnitude in a Probabilistic Seismic Hazard Analysis

Implementation of AI for The Prediction of Failures of Reinforced Concrete Frames

Contact Info

Product

Resources

About