To predict the tensile capacity of adhesive anchors, a multilayered feed-forward neural network trained with the back-propagation algorithm is constructed. The ANN model have 5 inputs, including the compressive strength of concrete, tensile strength of concrete, anchor diameter, hole diameter, embedment of anchors, and ultimate load. The predictions obtained from the trained ANN show a good agreement with the experiments. Meanwhile, the predicted ultimate tensile capacity of anchors is close to the one calculated from the strength formula of the combined cone-bond failure model.
The present paper concerns the fracture characteristics and ductility of cracked concrete beam externally bonded with carbon fiber-reinforced polymer (CFRP) sheet as well as the integration behaviors between CFRP/concrete interfacial debonding and concrete cracking.Three-point bending tests were carried out on the CFRP-strengthened cracked concrete beams with varying specimen depth and initial crack length.A straingauge method was developed to monitor the crack initiation and propagation in concrete,and the CFRP/concrete interfacial bonding behaviors,respectively.Clip gauges were used to measure crack mouth opening displacement (CMOD) and the deflection at midspan.Experimental results revealed that CFRP-strengthened specimen shows a higher load capacity under the same deformation level and a better inelastic deformation capacity compared with the unstrengthened one.For there are two manifest peak values in the obtained load versus displacement curve,the ductility of CFRP-strengthened concrete beams were investigated using index expressed as area ratio on the load versus displacement curve.The calculated results indicated that the contribution from CFRP sheet to the ductility improvement of specimen is notable when the deflection at midspan exceeded 10.5 times the first-crack deflection.