• Computers and Concrete
• /
• 제29권3호
• /
• pp.145-159
• /
• 2022

In this study, the extreme learning machine and deep learning models were devised to estimate the bond strength of corroded reinforcement in concrete. The six inputs and one output were used in this study. The compressive strength, concrete cover, bond length, steel type, diameter of steel bar, and corrosion level were selected as the input variables. The results of bond strength were used as the output variable. Moreover, the Analysis of variance (Anova) was used to find the effect of input variables on the bond strength of corroded reinforcement in concrete. The prediction results were compared to the experimental results and each other. The extreme learning machine and the deep learning models estimated the bond strength by 99.81% and 99.99% accuracy, respectively. This study found that the deep learning model can be estimated the bond strength of corroded reinforcement with higher accuracy than the extreme learning machine model. The Anova results found that the corrosion level was found to be the input variable that most affects the bond strength of corroded reinforcement in concrete.

• Computers and Concrete
• /
• 제27권4호
• /
• pp.305-317
• /
• 2021

The bond between the concrete and bar is a main factor affecting the performance of the reinforced concrete (RC) members, and since the steel corrosion reduces the bond strength, studying the bond behavior of concrete and GFRP bars is quite necessary. In this research, a database including 112 concrete beam test specimens reinforced with spliced GFRP bars in the splitting failure mode has been collected and used to estimate the concrete-GFRP bar bond strength. This paper aims to accurately estimate the bond strength of spliced GFRP bars in concrete beams by applying three soft computing models including multivariate adaptive regression spline (MARS), Kriging, and M5 model tree. Since the selection of regularization parameters greatly affects the fitting of MARS, Kriging, and M5 models, the regularization parameters have been so optimized as to maximize the training data convergence coefficient. Three hybrid model coupling soft computing methods and genetic algorithm is proposed to automatically perform the trial and error process for finding appropriate modeling regularization parameters. Results have shown that proposed models have significantly increased the prediction accuracy compared to previous models. The proposed MARS, Kriging, and M5 models have improved the convergence coefficient by about 65, 63 and 49%, respectively, compared to the best previous model.

• 콘크리트학회논문집
• /
• 제24권4호
• /
• pp.415-422
• /
• 2012

이 연구에서는 FRP 부재를 이용한 표면매입 보강에서, FRP의 부착강도를 평가하기 위하여 총 78개의 기존실험 결과를 분석하고, 기존 연구자들에 의해 제안된 식들을 평가하였다. 그 결과 FRP부재의 형상계수(폭-두께비)와 강성을 반영한 Seracino의 식이 부착내력을 가장 근사하게 예측하는 것으로 나타났다. 그러나 Seracino의 식은 실험 결과를 다소 과소평가하는 양상을 보이고 특히 부착길이가 작을수록 그 경향이 두드러진 것으로 나타났다. 이는 부착길이 증가에 따른 영향이 Seracino의 식에는 전혀 반영되어있지 않기 때문으로 볼 수 있다. 기존 실험 결과의 분석을 통하여 부착길이와 강도와의 상관관계를 찾고 또한 여러 개의 FRP부재를 인접하여 배치시 발생하는 무리효과를 고려하여 Seracino 식을 수정 제안하였다. 이 제시된 식을 이용하여 기존 실험체에 대한 내력을 계산하고 평가한 결과, 제안된 식으로서 표면매입 보강된 FRP의 부착강도를 매우 근사하게 예측할 수 있는 것으로 나타났다.

• Computers and Concrete
• /
• 제22권2호
• /
• pp.249-259
• /
• 2018

This paper presents Artificial Neural Network (ANN) models for evaluating bond strength of deformed, plain and cold formed bars in low strength concrete. The ANN models were implemented using the experimental database developed by conducting experiments in three different universities on total of 138 pullout and 108 splitting specimens under monotonic loading. The key parameters examined in the experiments are low strength concrete, bar development length, concrete cover, rebar type (deformed, cold-formed, plain) and diameter. These deficient parameters are typically found in non-engineered reinforced concrete structures of developing countries. To develop ANN bond model for each bar type, four inputs (the low strength concrete, development length, concrete cover and bar diameter) are used for training the neurons in the network. Multi-Layer-Perceptron was trained according to a back-propagation algorithm. The ANN bond model for deformed bar consists of a single hidden layer and the 9 neurons. For Tor bar and plain bars the ANN models consist of 5 and 6 neurons and a single hidden layer, respectively. The developed ANN models are capable of predicting bond strength for both pull and splitting bond failure modes. The developed ANN models have higher coefficient of determination in training, validation and testing with good prediction and generalization capacity. The comparison of experimental bond strength values with the outcomes of ANN models showed good agreement. Moreover, the ANN model predictions by varying different parameters are also presented for all bar types.

• 콘크리트학회논문집
• /
• 제11권4호
• /
• pp.129-136
• /
• 1999

For the prediction of concrete-steel bond ability in reinforced concrete, many countries establish specifications for the pullout test. But these methods hardly to consider many parameters such as strength, shape, diameter and location of steel, concrete restrict condition by loading plate, strength of concrete and cover depth etc, and it is difficult to solve concentration and disturbance of stress. The purpose of this study is to propose a New Ring Test method which can be rational quantity evaluations of bond splitting mechanism. For this purpose, pullout test was carried out to assess the effect of several variables on bond splitting properties between reinforcing bar and concrete. Key variables are concrete compressive strength, concrete cover, bar diameter and rib spacing. Failure mode was examined and maximum bond stress-slip relationships were presented to show the effect of above variables. As the result, it appropriately expressed general characteristics of bond splitting mechanism, and it proved capability for standard test method.

• Structural Engineering and Mechanics
• /
• 제84권5호
• /
• pp.651-664
• /
• 2022

A precise prediction of the ultimate bond strength between rebar and surrounding concrete plays a major role in structural design, as it effects the load-carrying capacity and serviceability of a member significantly. In the present study, Gaussian models are employed for modelling bond strength of ribbed steel bars embedded in concrete. Gaussian models offer a non-parametric method based on Bayesian framework which is powerful, versatile, robust and accurate. Five different Gaussian models are explored in this paper-Gaussian Process (GP), Variational Heteroscedastic Gaussian Process (VHGP), Warped Gaussian Process (WGP), Sparse Spectrum Gaussian Process (SSGP), and Twin Gaussian Process (TGP). The effectiveness of the models is also evaluated in comparison to the numerous design formulae provided by the codes. The predictions from the Gaussian models are found to be closer to the experiments than those predicted using the design equations provided in various codes. The sensitivity of the models to various parameters, input feature space and sampling is also presented. It is found that GP, VHGP and SSGP are effective in prediction of the bond strength. For large data set, GP, VHGP, WGP and TGP can be computationally expensive. In such cases, SSGP can be utilized.

• 한국지반공학회논문집
• /
• 제27권11호
• /
• pp.71-81
• /
• 2011

동착강도는 동토지반 말뚝기초 설계시 지지력을 결정하는 주요 설계정수이다. 동착강도는 동결온도, 구속응력, 말뚝표면 특성, 토사종류 등 다양한 인자들에 의해 동시다발적인 영향을 받는 것으로 보고되고 있다. 하지만 동착강도에 대한 연구는 소수의 인자들만 반영할 수 있는 실험연구를 중심으로 수행되어온 경향이 있으며, 설계정수로서 동착강도를 산정하기 위한 방법들은 동결온도, 말뚝재료 등의 주요 인자들만을 고려할 수 있는 한계가 있어 왔다. 본 연구는 인공신경망 이론을 동착강도 산정에 활용함으로서 다양한 영향인자 조건에서 동착강도를 예측할 수 있는 방안을 모색하기 위한 목적으로 수행되었다. 인공신경망 학습을 위하여 총 5종류의 연구사례로부터 137개의 자료를 수집하였으며, 그 중 100개를 학습자료로, 37개를 실증자료로 구분하였다. 연구결과 단계적 인공신경망 학습을 통하여 동착강도 산정 시 다양한 영향인지를 다차원적으로 고려하여 예측하는 방법이 병행되어야 할 필요성을 확인하였으며, 5개 영향인자를 동시에 고려하여 동착강도를 예측할 수 있는 신뢰성 높은 학습결과를 도출 및 검증하였다. 또한, 매개변수 연구결과 동착강도는 동결온도와 말뚝재료의 변화에 가장 민감하게 반응하는 것으로 나타났고 수직응력에 의한 영향은 일부 온도구간에서만 뚜렷하게 나타나며 토사종류와 재하속도의 변화에 따라 동착강도가 증가하는 경향이 변화하는 특성을 나타내었다.

• Computers and Concrete
• /
• 제14권3호
• /
• pp.327-345
• /
• 2014

This paper presents the application of multi-gene genetic programming (MGP) technique for modeling the bond strength of ribbed steel bars in concrete. In this regard, the experimental data of 264 splice beam tests from different technical papers were used for training, validating and testing the model. Seven basic parameters affecting on the bond strength of steel bars were selected as input parameters. These parameters are diameter, relative rib area and yield strength of steel bar, minimum concrete cover to bar diameter ratio, splice length to bar diameter ratio, concrete compressive strength and transverse reinforcement index. The results show that the proposed MGP model can be alternative approach for predicting the bond strength of ribbed steel bars in concrete. Moreover, the performance of the developed model was compared with the building codes' empirical equations for a complete comparison. The study concludes that the proposed MGP model predicts the bond strength of ribbed steel bars better than the existing building codes' equations. Using the proposed MGP model and building codes' equations, a parametric study was also conducted to investigate the trend of the input variables on the bond strength of ribbed steel bars in concrete.

• Structural Engineering and Mechanics
• /
• 제72권4호
• /
• pp.479-489
• /
• 2019

The corrosion of reinforcement leads to a gradual decay of structural strength and durability. Several models for crack occurrence prediction and crack width propagation are investigated in this paper. Analytical and experimental models were used to predict the bond strength in the period of corrosion propagation. The manner of flexural strength loss is calculated by application of these models for different scenarios. As a new approach, the variation of the concrete beam neutral axis height has been evaluated, which shows a reduction in the neutral axis height for the scenarios without loss of bond. Alternatively, an increase of the neutral axis height was observed for the scenarios including bond and concrete section loss. The statistical properties of the parameters influencing the strength have been deliberated associated with obtaining the time-dependent bending strength during corrosion propagation, using Monte Carlo (MC) random sampling method. Results showed that the ultimate strain in concrete decreases significantly as a consequence of the bond strength reduction during the corrosion process, when the section reaches to its final limit. Therefore, such sections are likely to show brittle behavior.

• Computers and Concrete
• /
• 제14권3호
• /
• pp.233-245
• /
• 2014

In this paper, a rule based Mamdani type fuzzy logic model for prediction of slippage at maximum tensile strength and slippage at rupture of structural lightweight concretes were discussed. In the model steel rebar diameters and development lengths were used as inputs. The FL model and experimental results, the coefficient of determination R2, the Root Mean Square Error were used as evaluation criteria for comparison. It was concluded that FL was practical method for predicting slippage at maximum tensile strength and slippage at rupture of structural lightweight concretes.