Shear resistance prediction of concrete beams reinforced by FRP bars using artificial neural networks

Naderpour, Hosein; Poursaeidi, O.; Ahmadi, Masoud

doi:10.1016/j.measurement.2018.05.051

Cited by 98 publications

(40 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was observed that extreme learning machine has the best result in estimating the composite beam behavior among other investigated methods. Naderpour et al [47] proposed a method in which the geometric and mechanical properties of cross-section and FRP bars, and shear span-depth ratio were considered for concrete beams. The error in the shear strength estimation was about 9.7%, which was significantly lower than other methods and relationships.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Developing a Library of Shear Walls Database and the Neural Network Based Predictive Meta-Model

Moradi

Hariri-Ardebili

2019

Applied Sciences

View full text Add to dashboard Cite

There is a large amount of useful information from past experimental tests, which are usually ignored in test-setup for the new ones. Variation of assumptions, materials, test procedures, and test objectives make it difficult to choose the right model for validation of the numerical models. Results from different experiments are sometimes in conflict with each other, or have minimum correlation. Furthermore, not all these information are easily accessible for researchers and engineers. Therefore, this paper presents the results of a comprehensive study on different experimental models for steel plate and reinforced concrete shear walls. A unique library of up to 13 parameters (mechanical properties and geometric characteristics) affecting the strength, stiffness and drift ratio of the shear walls are gathered including their sensitivity analysis. Next, a predictive meta-model is developed based on artificial neural network. It is capable of forecasting the responses for any desired shear wall with good accuracy. The proposed network can be used to as an alternative to the nonlinear numerical simulations or expensive experimental test.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Developing a Library of Shear Walls Database and the Neural Network Based Predictive Meta-Model

Moradi

Hariri-Ardebili

2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…For example, now, the effect of the shear span on the behavior of oblique cross sections reinforced with composite U stirrups [9] is being actively studied. Software design systems based on neural networks [10] are developed; and the computational tool for the RC structures strengthened with composite materials presented in existing regulatory documents is updated [11][12][13][14][15]. The release of the Code of Rules SP 164.1325800.2014, 2014, dedicated to the strengthening of reinforced concrete structures with composite materials, gave an additional incentive to conduct scientific research in this field, but did not solve all the problems.…”

Section: Introductionmentioning

confidence: 99%

Initial crack effect on the strength of oblique cross sections of reinforced concrete beams strengthened with carbon fiber

et al. 2019

View full text Add to dashboard Cite

In the theory of reinforced concrete, the issue on strength of the oblique beam sections is more complicated than that on the standard sections, since it depends on many factors. The change of at least one of them leads to a significant change in the carrying capacity and in the structural damage pattern. This is due to the fact that at the operating level of the load, all conventional reinforced concrete structures work with cracks, which must be considered in the calculation. However, in the existing regulatory documents and public sources, this issue is not specified. This paper considers the effect of initial cracks on the strength of oblique cross sections of the reinforced concrete beams strengthened with carbon fiber. The experimental studies results obtained through the transverse force testing of forty-two prototypes made of heavy concrete of B30 design grade are presented. The test samples had initial oblique cracks of 0.6-0.9 mm width and were reinforced with three composite U stirrups from the fabric based on unidirectional carbon fibers in the shear span. Initial cracks in the beams were formed at three values of the shear span – 1.5h0, 2h0 and 2.5h0. The test data show the impact of initial cracks on the efficiency of composite reinforcement of oblique cross sections of the prototypes at various values of shear spans.

show abstract

“…ANN has been applied effectively in a wide range of geotechnical studies, as an efficient computing tool to fully represent and capture pile load-settlement behaviour with an acceptable degree of accuracy (Chang et al, 2018). ANN technology has the capacity to deal with complexity and to map nonlinear complex functions, adopting substantial computer capacity to implement extremely iterated work (Di Santo et al, 2018;Li et al, 2018;Naderpour et al, 2018). In essence, the complex non-linear patterns between the individual variables (IVs) and the model target are precisely addressed, identified and mapped with high dimensional input space (Sun et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Performance analysis of an evolutionary LM algorithm to model the load-settlement response of steel piles embedded in sandy soil

et al. 2019

View full text Add to dashboard Cite

This study was implemented to examine pile load-settlement response and to develop a rapid, highly efficient predictive intelligent model, using a new computational intelligence (CI) algorithm. To achieve this aim, a series of experimental pile load tests were performed on steel, closed-ended pile models consisting of three piles with aspect ratios of 25, 17, and 12 in an attempt to make site in-situ pile-load tests unnecessary. An optimised, evolutionary, supervised Levenberg-Marquardt (LM) training algorithm was used for this process due to its remarkably robust performance. The model piles were penetrated and tested in three sand relative densities; dense, medium, and loose. Applied load (P), pile effective length (lc), pile flexural rigidity (EA), pile slenderness ratio (lc/d) and interface friction angle (δ) were identified, based on a comprehensive statistical analysis, as these parameters play a key role in governing pile settlement. To evaluate the efficiency and the generalisation ability of the proposed algorithm, graphical comparisons were made between the proposed algorithm and the experimental results with further comparisons made with conventional prediction approaches. The results revealed outstanding agreement between the targeted and predicted pile-load settlement with a coefficient of correlation of 0.985 and a Pearson's correlation coefficient, P = 2.22 x10-32 and root mean square error (RMSE) of 0.059 respectively. This, in parallel with a non-significant mean square error level (MSE) of 0.002, validates the feasibility of the proposed method and its potential in future applications.

show abstract

Shear resistance prediction of concrete beams reinforced by FRP bars using artificial neural networks

Cited by 98 publications

References 19 publications

Developing a Library of Shear Walls Database and the Neural Network Based Predictive Meta-Model

Developing a Library of Shear Walls Database and the Neural Network Based Predictive Meta-Model

Initial crack effect on the strength of oblique cross sections of reinforced concrete beams strengthened with carbon fiber

Performance analysis of an evolutionary LM algorithm to model the load-settlement response of steel piles embedded in sandy soil

Contact Info

Product

Resources

About