ANN based investigations of reliabilities of the models for concrete under triaxial compression

Öztekin, Ertekin

doi:10.1108/ec-03-2015-0065

Cited by 5 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MLP-based MCS is most popularly used in MLP-based SRA [37][38][39][40]. Jha and Li [41] introduced the high dimensional model representation into MLP to approximate implicit LSFs in SRA.…”

Section: Mlp-based Mcsmentioning

confidence: 99%

Deep learning-based methods in structural reliability analysis: a review

Afshari

Zhao

Zhuang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

One of the most significant and growing research fields in mechanical and civil engineering is Structural Reliability Analysis (SRA). A reliable and precise SRA usually has to deal with complicated , aand numerically expensive problems. Artificial intelligence-based (AI) nd specifically, Deep learning-based (DL) methods, have been applied to the SRA problems to reduce the computational cost and to improve the accuracy of reliability estimation as well. This article reviews the recent advances in using DL models in SRA problems. The review includes the most common categories of DL-based methods used in SRA. More specifically, the application of supervised methods, unsupervised methods, and hybrid deep learning methods in SRA are explained. In this paper, the supervised methods for SRA are categorized as Multi-Layer Perceptron (MLP), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN ), Long short-term memory (LSTM), Bidirectional (Bi-LSTM) and Gated recurrent units (GRU). For the unsupervised methods, we have investigated methods such as Generative Adversarial Network (GAN), Autoencoders (AE), Self-Organizing Map (SOM), Restricted Boltzmann Machine (RBM), and Deep Belief Network (DBN). We have made a comprehensive survey of these methods in SRA. Aiming towards an efficient SRA, deep learning-based methods applied for approximating the limit state function (LSF) with First/Second Order Reliability Methods (FORM/SORM), Monte Carlo simulation (MCS), or MCS with importance sampling (IS). Accordingly, the current paper focuses on the structure of different DL-based models and the applications of each DL method in various SRA problems. This survey helps researchers in mechanical and civil engineering, especially those who are engaged with structural and reliability analysis or dealing with quality assurance problems.

show abstract

“…MLP-based MCS is most popularly used in MLP-based SRA [37][38][39][40]. Jha and Li [41] introduced the high dimensional model representation into MLP to approximate implicit LSFs in SRA.…”

Section: Mlp-based Mcsmentioning

confidence: 99%

Deep learning-based methods in structural reliability analysis: a review

Afshari

Zhao

Zhuang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence (AI) predictions such as those made by artificial neural networks (ANN) commonly offer results that are significantly more accurate than predictions generated by either analytical models or design guidelines. However, ANN has been characterized as “black-box” models due to the extremely large numbers of nodes and connections within their layered structures (Tsai, 2009; Tsai, 2010; Öztekin, 2016; Vardhan et al , 2017; Yan and Lin, 2017; Sadrossadat et al , 2018). Since it was first proposed by Koza (1992), genetic programming (GP) has garnered considerable research attention because of its ability to model nonlinear relationships for input–output mappings without assuming the prior form of these relationships.…”

Section: Introductionmentioning

confidence: 99%

Using genetic programming to model the bond strength of GFRP bars in concrete under the effects of design guidelines

Chuang

Tsai

2021

View full text Add to dashboard Cite

Purpose This paper aims to use a derivative of genetic programming to predict the bond strength of glass fiber-reinforced polymer (GFRP) bars in concrete under the effects of design guidelines. In developing bond strength prediction models, this paper prioritized simplicity and meaningfulness over extreme accuracy. Design/methodology/approach Assessing the bond strength of GFRP bars in concrete is a critical issue in designing and building reinforced concrete structures. Findings Ultimately, the equation of a linear form of a particular design guideline was suggested as the optimal prediction model. Improvements to the current design guidelines suggested by this model include setting a 1.31 magnification and considering the effects of the three significant parameters of bar diameter (db), minimum cover-to-bar diameter (C/db) and development length to bar diameter (l/db) under an acceptable root mean square error accuracy of around 2 MPa. Furthermore, the model suggests that the original influence parameter of concrete compressive strength (fc) may be removed from bond strength calculations. Originality/value The model suggests that the original influence parameter of concrete compressive strength (fc) may be removed from bond strength calculations.

show abstract

“…Artificial neural network is one of the most promising methods for materials design because of its excellent ability of nonlinear mapping, generalization, self-organization and selflearning. It has been proved to be of widespread utility in engineering modeling (Lam et al, 2014;Emami and Fard, 2012;Öztekin, 2016;Guo et al, 2012;Bahiraei et al, 2014;Tahavvor and Yaghoubi, 2012), as well as in predicting and optimizing for material engineering (Vaz et al, 2013;Srinivasan and Saghir, 2013;Shabani and Mazahery, 2012). The backpropagation neural network (BPNN) usually trained by back-propagation errors is perhaps the most popular network architecture today; however, many inconsistent reports have been undermining the robustness of ANNs-based system (Leema et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Prediction and optimization model of activated carbon double layer capacitors based on improved heuristic approach genetic algorithm neural network

Yang

Lin

et al. 2018

View full text Add to dashboard Cite

Purpose The purpose of this paper is to study the electrochemical properties of electrode material on activated carbon double layer capacitors. It also tries to develop a prediction model to evaluate pore size value. Design/methodology/approach Back-propagation neural network (BPNN) prediction model is used to evaluate pore size value. Also, an improved heuristic approach genetic algorithm (HAGA) is used to search for the optimal relationship between process parameters and electrochemical properties. Findings A three-layer ANN is found to be optimum with the architecture of three and six neurons in the first and second hidden layer and one neuron in output layer. The simulation results show that the optimized design model based on HAGA can get the suitable process parameters. Originality/value HAGA BPNN is proved to be a practical and efficient way for acquiring information and providing optimal parameters about the activated carbon double layer capacitor electrode material.

show abstract

ANN based investigations of reliabilities of the models for concrete under triaxial compression

Cited by 5 publications

References 40 publications

Deep learning-based methods in structural reliability analysis: a review

Deep learning-based methods in structural reliability analysis: a review

Using genetic programming to model the bond strength of GFRP bars in concrete under the effects of design guidelines

Prediction and optimization model of activated carbon double layer capacitors based on improved heuristic approach genetic algorithm neural network

Contact Info

Product

Resources

About