Keywords: shear, anchors, concrete, neural networks, database, capacity.

Anchors are commonly used to attach structural steel members to concrete and transfer loads into concrete. In many situations, anchors in concrete are required to resist shear forces such as those connecting steel beams to reinforced concrete columns and steel columns to concrete foundations. When anchors under shear installed close to the edge of concrete members, concrete breakout failure is likely to occur and the failure load associated with it is not easily predictable. In recent years, artificial neural networks (ANNs) have been applied to many reinforced concrete problems. ANNs have been successfully used in concrete mix-design [1,2], estimating the shear capacity of reinforced concrete deep beams [3,4], evaluating the capacity of slender reinforced concrete columns [5] and predicting deflections of reinforced concrete beams externally strengthened with FRP laminates [6].

The current paper investigates the feasibility of using feed forward back-propagation neural networks for predicting the concrete shear capacity of anchor bolts located near a concrete edge. In the developed neural network, the nodes of the input layer represent the anchor outside diameter, concrete compressive strength, anchor embedment depth and the edge distance from the anchor bolt to the edge of concrete in the direction of the shear force. One node is used in the output layer to represent the concrete shear capacity of the anchor bolts. The training of the ANN was achieved using a database of 205 test results extracted from the comprehensive worldwide database of mechanical anchors compiled by the ACI committees 349 and 355 [7].

Predictions of the concrete shear capacity of anchors using the trained neural network are in good agreement with experimental results and those calculated from the concrete capacity design method [8]. The parametric study conducted using the trained network shows that:

• The concrete edge distance in the direction of the applied shear force has the most influential effect on the concrete shear capacity of anchor bolts.
• Both the embedment depth and diameter of anchor bolts have a small influence on the concrete shear capacity of anchor bolts.
• The concrete shear capacity of anchor bolts is nonlinearly affected by the concrete compressive strength.

1

Oh, Ju-Won, Lee, In-Won, Kim, Ju-Tae, Lee, Gyu-Won, "Application of neural networks for proportioning of concrete mixes", ACI Materials Journal, 96(1), 61-67, 1999.

2

Seung-Chang Lee, "Prediction of concrete strength using artificial neural networks", Engineering Structures, 25(7), 849-857, 2003. doi:10.1016/S0141-0296(03)00004-X

3

Goh, A.T.C., "Prediction of ultimate shear strength of deep beams using neural networks", ACI Structural Journal, 92(1),. 28-32, 1995.

4

Sanad, A. and Saka, M.P., "Prediction of ultimate shear strength of reinforced-concrete deep beams using neural networks", Journal of Structural Engineering, ASCE, 127(7), 818-828, 2001. doi:10.1061/(ASCE)0733-9445(2001)127:7(818)

5

Chuang, P.H.; Goh, Anthony T.C.; Wu, X., "Modeling the capacity of pin- ended slender reinforced concrete columns using neural networks", Journal of Structural Engineering, ASCE, 124(7), 830-838, 1998. doi:10.1061/(ASCE)0733-9445(1998)124:7(830)

6

Flood, I., Muszynski, L. and Nandy, S., "Rapid analysis of externally reinforced concrete beams using neural networks", Computers and Structures, 79(17), 1553-1559, 2001. doi:10.1016/S0045-7949(01)00033-5

7

ACI Committee 355, "State-of-the-art report on Anchorage to concrete", American Concrete Institute, Detroit, USA, 1991.

8

Fuchs, W., Eligehausen, R. and Breen, J.E., "Concrete capacity design (CCD) approach for fastening to concrete", ACI Structural Journal, 92(1), 73-94, 1995.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £82 +P&P)