• Computers and Concrete
• /
• v.11 no.6
• /
• pp.603-620
• /
• 2013

This paper improves genetic programming (GP) and weight genetic programming (WGP) and proposes soft-computing polynomials (SCP) for accurate prediction and visible polynomials. The proposed genetic programming system (GPS) comprises GP, WGP and SCP. To represent confined compressive strength and strain of circular concrete columns in meaningful representations, this paper conducts sensitivity analysis and applies pruning techniques. Analytical results demonstrate that all proposed models perform well in achieving good accuracy and visible formulas; notably, SCP can model problems in polynomial forms. Finally, concrete compressive strength and lateral steel ratio are identified as important to both confined compressive strength and strain of circular concrete columns. By using the suggested formulas, calculations are more accurate than those of analytical models. Moreover, a formula is applied for confined compressive strength based on current data and achieves accuracy comparable to that of neural networks.

• Journal of the Korea Concrete Institute
• /
• v.23 no.6
• /
• pp.741-747
• /
• 2011

In this study, autogenous shrinkage strain and prediction models of concrete specimens were compared with strength level and development rate. Also, concrete autogeneous shrinkage under various curing conditions was investigated. The results showed that autogeneous shrinkage increased as concrete strength increased. However, when the concrete strength was almost identical, the initial autogeneous shrinkage of OPC was larger than BFS, but the final autogeneous shrinkage of BFS was larger than OPC. Early wet curing reduced autogeneous shrinkage strain. Especially, when the early wet curing was applied for more than 24 hours, final autogeneous shrinkage was significantly reduced. The results showed that the existing EC2 models do not reflect concrete properties properly. Therefore, the revised model was proposed to better predict autogeneous shrinkage.

• Computational Structural Engineering
• /
• v.23 no.3
• /
• pp.61-68
• /
• 2010

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.3
• /
• pp.195-202
• /
• 2021

Concrete quality is mainly managed through the reliable prediction and control of compressive strength. Although related industries have established a relevant datasets based on the mixture proportions and compressive strength gain, whereas they have not been shared due to various reasons including technology leakage. Consequently, the costs and efforts for quality control have been wasted excessively. This study aimed to develop a web-based numerical model, which would present diverse optimal values including concrete strength prediction to the user, and to establish a sustainable database (DB) collection system by inducing the data entered by the user to be collected for the DB. The system handles the overall technology related to the concrete. Particularly, it predicts compressive strength at a mean accuracy of 89.2% by applying the artificial neural network method, modeled based on extensive DBs.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2001.05a
• /
• pp.169-174
• /
• 2001

This study concerns crack effect on concrete anchor system and prediction of tensile capacity, as governed by concrete cone failure, of single anchors located at center of concrete specimen. To Investigate crack effect three different types of crack such as crack width of 0.2mm and 0.5nm, crack depth of loom and 20cm, and crack location of center and biased point were simulated. The static tensile load was subjected to 7/8 in. CIP anchor embedded in concrete of strength 280kg/$cm^{2}$. Tested pullout capacity was compared to prediction value by each current design method (such as ACI 349-97, ACI 349 revision and CEB-FIP which is based on CC Method), In these comparison CC Method and ACI revision showed almost same value in uncracked concrete specimen, however in cracked concrete CC Method showed conservativeness. Therefore the design by ACI 349 revision is recommended for the safe and economic design.

• Computers and Concrete
• /
• v.12 no.6
• /
• pp.775-783
• /
• 2013

A novel reliability-based work model of k/n (G) system has been developed. Unit failure probability is given based on the load and strength distributions and according to the stress-strength interference theory. Then a dynamic reliability prediction model of repairable k/n (G) system is established using probabilistic differential equations. The resulting differential equations are solved and the value of k can be determined precisely. The number of work unit k in repairable k/n (G) system is obtained precisely. The reliability of whole life cycle of repairable k/n (G) system can be predicted and guaranteed in the design period. Finally, it is illustrated that the proposed model is feasible and gives reasonable prediction.

• Computers and Concrete
• /
• v.21 no.1
• /
• pp.47-54
• /
• 2018

Artificial neural network models can be successfully used to simulate the complex behavior of many problems in civil engineering. As compared to conventional computational methods, this popular modeling technique is powerful when the relationship between system parameters is intrinsically nonlinear, or cannot be explicitly identified, as in the case of concrete behavior. In this investigation, an artificial neural network model was developed to assess the residual compressive strength of self-compacted concrete at elevated temperatures ($20-900^{\circ}C$) and various relative humidity conditions (28-99%). A total of 332 experimental datasets, collected from available literature, were used for model calibration and verification. Data used in model development incorporated concrete ingredients, filler and fiber types, and environmental conditions. Based on the feed-forward back propagation algorithm, systematic analyses were performed to improve the accuracy of prediction and determine the most appropriate network topology. Training, testing, and validation results indicated that residual compressive strength of self-compacted concrete, exposed to high temperatures and relative humidity levels, could be estimated precisely with the suggested model. As illustrated by statistical indices, the reliability between experimental and predicted results was excellent. With new ingredients and different environmental conditions, the proposed model is an efficient approach to estimate the residual compressive strength of self-compacted concrete as a substitute for sophisticated laboratory procedures.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2019.05a
• /
• pp.67-68
• /
• 2019

The mechanical and durability characteristics of concrete structures depend on the construction environment, material conditions, design conditions, and temperature and humidity environment after casting. However, wired communicati-on sensors which are mainly used in the field have many limitations in their usability and monitoring. In this study, all temperature and humidity data measured from embedded sensors are monitored via a wireless sensor network. Based on the measured temperature data, the predicted compressive strength of the concrete was compared with the actual compressive strength. As a result, The error between predicted strength and experimental strength has decreased over time.

• Smart Structures and Systems
• /
• v.30 no.2
• /
• pp.195-207
• /
• 2022

Computational drawbacks associated with regular predictive models have motivated engineers to use hybrid techniques in dealing with complex engineering tasks like simulating the compressive strength of concrete (CSC). This study evaluates the efficiency of tree potential metaheuristic schemes, namely shuffled complex evolution (SCE), multi-verse optimizer (MVO), and beetle antennae search (BAS) for optimizing the performance of a multi-layer perceptron (MLP) system. The models are fed by the information of 1030 concrete specimens (where the amount of cement, blast furnace slag (BFS), fly ash (FA1), water, superplasticizer (SP), coarse aggregate (CA), and fine aggregate (FA2) are taken as independent factors). The results of the ensembles are compared to unreinforced MLP to examine improvements resulted from the incorporation of the SCE, MVO, and BAS. It was shown that these algorithms can considerably enhance the training and prediction accuracy of the MLP. Overall, the proposed models are capable of presenting an early, inexpensive, and reliable prediction of the CSC. Due to the higher accuracy of the BAS-based model, a predictive formula is extracted from this algorithm.

• KEPCO Journal on Electric Power and Energy
• /
• v.5 no.3
• /
• pp.201-207
• /
• 2019

An anchorage system is essential for most reinforced concrete structures to connect building components. Therefore, the prediction of strength of the anchor is very important issue for safety of the structures themselves as well as structural components. The prediction models in existing design codes are, however, not applicable for large anchors because they are based on the small size anchors with diameters under 50 mm. In this paper, new prediction models for strength of a single anchor, especially the tensile strength of a single anchor, is developed from the experimental results with consideration of size effect. Size effect in the existing models such as ACI or CCD method is based on the linear fracture mechanics which is very conservative way to consider the size effect. Therefore, new models are developed based on the nonlinear fracture mechanics rather than the linear fracture mechanics for more reasonable prediction. New models are proposed by the regression analysis of the experimental results and it can predict the tensile strength of both small and large anchors.