• Computers and Concrete
• /
• 제19권6호
• /
• pp.651-658
• /
• 2017

High-performance concrete, besides aggregate, cement, and water, incorporates supplementary cementitious materials, such as fly ash and blast furnace slag, and chemical admixture, such as superplasticizer. Hence, it is a highly complex material and modeling its behavior represents a difficult task. This paper presents an evolutionary system for the prediction of high performance concrete strength. The proposed framework blends a recently developed version of genetic programming with a local search method. The resulting system enables us to build a model that produces an accurate estimation of the considered parameter. Experimental results show the suitability of the proposed system for the prediction of concrete strength. The proposed method produces a lower error with respect to the state-of-the art technique. The paper provides two contributions: from the point of view of the high performance concrete strength prediction, a system able to outperform existing state-of-the-art techniques is defined; from the machine learning perspective, this case study shows that including a local searcher in the geometric semantic genetic programming system can speed up the convergence of the search process.

• 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.

• Computers and Concrete
• /
• 제33권2호
• /
• pp.137-145
• /
• 2024

The technique of experimentally determining concrete's compressive strength for a given mix design is time-consuming and difficult. The goal of the current work is to propose a best working predictive model based on different machine learning algorithms such as Gradient Boosting Machine (GBM), Stacked Ensemble (SE), Distributed Random Forest (DRF), Extremely Randomized Trees (XRT), Generalized Linear Model (GLM), and Deep Learning (DL) that can forecast the compressive strength of ternary geopolymer concrete mix without carrying out any experimental procedure. A geopolymer mix uses supplementary cementitious materials obtained as industrial by-products instead of cement. The input variables used for assessing the best machine learning algorithm not only include individual ingredient quantities, but molarity of the alkali activator and age of testing as well. Myriad statistical parameters used to measure the effectiveness of the models in forecasting the compressive strength of ternary geopolymer concrete mix, it has been found that GBM performs better than all other algorithms. A sensitivity analysis carried out towards the end of the study suggests that GBM model predicts results close to the experimental conditions with an accuracy between 95.6 % to 98.2 % for testing and training datasets.

• Steel and Composite Structures
• /
• 제43권6호
• /
• pp.785-796
• /
• 2022

Concrete-encased steel (CES) beam, in which structural steel is encased in a reinforced concrete (RC) section, is widely applied in high-rise buildings as transfer beams due to its high load-carrying capacity, great stiffness, and good durability. However, these CES beams are prone to shear failure because of the low shear span-to-depth ratio and the heavy load. Due to the high load-carrying capacity and the brittle failure process of the shear failure, the accurate strength prediction of CES beams significantly influences the assessment of structural safety. In current design codes, design formulas for predicting the shear strength of CES beams are based on the so-called "superposition method". This method indicates that the shear strength of CES beams can be obtained by superposing the shear strengths of the RC part and the steel shape. Nevertheless, in some cases, this method yields errors on the unsafe side because the shear strengths of these two parts cannot be achieved simultaneously. This paper clarifies the conditions at which the superposition method does not hold true, and the shear strength of CES beams is investigated using a compatible truss-arch model. Considering the deformation compatibility between the steel shape and the RC part, the method to obtain the shear strength of CES beams is proposed. Finally, the proposed model is compared with other calculation methods from codes AISC 360 (USA, North America), Eurocode 4 (Europe), YB 9082 (China, Asia), JGJ 138 (China, Asia), and AS/NZS 2327 (Australia/New Zealand, Oceania) using the available test data consisting of 45 CES beams. The results indicate that the proposed model can predict the shear strength of CES beams with sufficient accuracy and safety. Without considering the deformation compatibility, the calculation methods from the codes AISC 360, Eurocode 4, YB 9082, JGJ 138, and AS/NZS 2327 lead to excessively conservative or unsafe predictions.

• Computers and Concrete
• /
• 제27권1호
• /
• pp.21-28
• /
• 2021

The Artificial Neural Network (ANN) is a system, which is utilized for solving complicated problems by using nonlinear equations. This study aims to investigate compressive strength, rebound hammer number (RN), and ultrasonic pulse velocity (UPV) of sustainable concrete containing various amounts of fly ash, silica fume, and blast furnace slag (BFS). In this study, the artificial neural network technique connects a nonlinear phenomenon and the intrinsic properties of sustainable concrete, which establishes relationships between them in a model. To this end, a total of 645 data sets were collected for the concrete mixtures from previously published papers at different curing times and test ages at 3, 7, 28, 90, 180 days to propose a model of nine inputs and three outputs. The ANN model's statistical parameter R2 is 0.99 of the training, validation, and test steps, which showed that the proposed model provided good prediction of compressive strength, RN, and UPV of sustainable concrete with the addition of cement.

• Computers and Concrete
• /
• 제5권1호
• /
• pp.21-36
• /
• 2008

Steel fiber reinforced concrete is increasingly used day by day in various structural applications. An extensive experimentation was carried out with w/cm ratio ranging from 0.25 to 0.40, and fiber content ranging from zero to1.5 percent by volume with an aspect ratio of 80 and silica fume replacement at 5%, 10% and 15%. The influence of steel fiber content in terms of fiber reinforcing index on the compressive strength of high-performance fiber reinforced concrete (HPFRC) with strength ranging from 45 85 MPa is presented. Based on the test results, equations are proposed using statistical methods to predict 28-day strength of HPFRC effecting the fiber addition in terms of fiber reinforcing index. A strength model proposed by modifying the mix design procedure, can utilize the optimum water content and efficiency factor of pozzolan. To examine the validity of the proposed strength model, the experimental results were compared with the values predicted by the model and the absolute variation obtained was within 5 percent.

• Smart Structures and Systems
• /
• 제31권1호
• /
• pp.1-11
• /
• 2023

Assessment of the compressive strength of concrete plays a major role during formwork removal and in the prestressing process. In concrete, temperature changes occur due to hydration which is an influencing factor that decides the compressive strength of concrete. Many methods are available to find the compressive strength of concrete, but the maturity method has the advantage of prognosticating strength without destruction. The temperature-time factor is found using a LM35 temperature sensor through the IoT technique. An experimental investigation was carried out with 56 concrete cubes, where 35 cubes were for obtaining the compressive strength of concrete using a universal testing machine while 21 concrete cubes monitored concrete's temperature by embedding a temperature sensor in each grade of M25, M30, M35, and M40 concrete. The mathematical prediction model equation was developed based on the temperature-time factor during the early age compressive strength on the 1^st, 2^nd, 3^rd and 7^th days in the M25, M30, M35, and M40 grades of concrete with their temperature. The 14^th, 21^st and 28^th day's compressive strength was predicted with the mathematical predicted equation and compared with conventional results which fall within a 2% difference. The compressive strength of concrete at any desired age (day) before reaching 28 days results in the discovery of the prediction coefficient. Comparative analysis of the results found by the predicted mathematical model show that, it was very close to the results of the conventional method.

• Computers and Concrete
• /
• 제21권5호
• /
• pp.505-511
• /
• 2018

This paper investigates the potential of a hybrid model which combines the least squares support vector machine (LSSVM) and an improved particle swarm optimization (IMPSO) techniques for prediction of concrete compressive strength. A modified PSO algorithm is employed in determining the optimal values of LSSVM parameters to improve the forecasting accuracy. Experimental data on concrete compressive strength in the literature were used to validate and evaluate the performance of the proposed IMPSO-LSSVM model. Further, predictions from five models (the IMPSO-LSSVM, PSO-LSSVM, genetic algorithm (GA) based LSSVM, back propagation (BP) neural network, and a statistical model) were compared with the experimental data. The results show that the proposed IMPSO-LSSVM model is a feasible and efficient tool for predicting the concrete compressive strength with high accuracy.

• 콘크리트학회논문집
• /
• 제23권2호
• /
• pp.185-193
• /
• 2011

이 연구에서는 FRP 전단보강 및 무보강 콘크리트 보의 전단강도를 정확하게 평가하기 위하여 통합전단설계방법을 개발하였다. 이를 위하여, FRP의 전단강도 기여분과 콘크리트의 전단강도 기여분을 각각 정의하였다. 기존의 FRP 전단강도 평가모델과 실험 결과를 비교 분석한 결과, Triantafillou의 FRP 전단강도 평가모델이 FRP의 유효변형률과 전단강도의 추정이 우수하므로 Triantafillou의 모델을 이용하여 FRP의 전단강도 기여분을 정의하였다. 콘크리트 전단강도 기여분은 선행 연구에서 제안된 변형도 기반 전단강도모델을 이용하여 정의하였다. 콘크리트 단면의 압축대에 작용하는 압축응력과 전단응력의 상관관계를 고려하기 위하여 콘크리트 재료파괴기준을 이용하여 콘크리트 전단강도 기여분을 산정하였다. 제안한 설계방법은 기존 실험 연구 결과와 비교하여 유효성을 검증하였다. 비교 결과 제안한 설계방법은 다양한 설계변수 범위에서 FRP 전단보강 및 무보강 콘크리트 보의 전단강도를 정확하게 평가하는 것으로 나타났다.

• 한국구조물진단유지관리공학회 논문집
• /
• 제16권5호
• /
• pp.148-160
• /
• 2012

본 연구에서는 콘크리트 구조물의 합리적인 압축강도 및 탄산화 예측식을 제안하고, 이 제안식의 현장적용을 통한 보다 효율적인 터널 진단 및 유지관리 기법을 개발하였다. 이를 위하여 공용연수가 약 30년 이상 경과하였으며, 약 15년 동안 수회에 걸친 진단 및 점검으로 무수히 많은 현장 내구성 측정 데이터가 축적된 서울메트로를 대상 시설물로 선정하였다. 압축강도 및 탄산화 분석결과 80% 이상의 정확도를 확보하는 각각의 예측식을 도출하였으며, 기존 제안식과의 비교분석을 통하여 본 연구 제안식의 신뢰도를 확인하였다. 또한 제안식의 현장적용 결과 압축강도 및 탄산화 깊이에 대한 예측치의 평균오차율이 약 20%내외로서 80% 이상의 높은 정확도를 확보하는 것으로 분석되어 현장적용의 적합성을 확인하였다. 현장조사 전 내구성 예측 맵(Map)을 활용한 효율적인 유지관리 기법을 개발하였다. 예측 맵(Map) 활용 시 진단기술자 및 시설물 담당자는 설계기준강도에 미달되거나 탄산화로 철근부식 가능성이 높은 취약부위를 한 눈에 파악할 수 있으므로 일일이 조사를 수행하는 과정에서 취약부위를 도출해야 하는 현 조사기법 보다 효과적으로 터널 조사 및 유지관리를 수행할 수 있을 것으로 기대된다.