Bond strength assessment is important for reinforced concrete structures with rebar corrosion since the bond degradation can threaten the structural safety. In this study, to assess the bond strength in concrete-corroded rebar interface, one of the machine learning techniques, artificial neutral network (ANN), was utilized for the application. From existing literature, data related to the bond strength of concrete and corroded rebar were collected. The ANN model was applied to understand the factors on bond property degradation. For the input in the ANN model, the following factors were considered the relative bond strength: (1) corrosion level; (2) crack width; (3) cover-to-diameter ratio; and (4) concrete strength. For the cases with confinement (stirrups), (5) the diameter/stirrups spacing ratio was also considered. The assessment was conducted from input with single parameter to multiple parameters. The scaled feed-forward multi-layer perception ANN model with the error back-propagation algorithm of gradient descent and momentum was found to match the experimental and computed results. The correlation of each parameter to the bond strength degradation was clarified. In cases without confinement, the relative importance was (1) > (2) > (4) > (3), while it was (2) > (1) > (3) > (5) > (4) for the cases with confinement.

Premature debonding failure is a serious problem for reinforced concrete (RC) members strengthened with carbon fibre reinforced polymer (CFRP) laminates. Although various mechanical anchorage systems have been proposed to prevent debonding between CFRP and RC beam, these systems are generally difficult to apply to narrow RC beams due to width limitations. In this study, to resolve the debonding problems, an innovative hybrid end-anchorage system was developed, which achieves self-locking of the externally bonded CFRP sheets. To achieve this hybrid anchorage, both ends of the CFRP sheet were wrapped around twin rods, and the sheet was bonded along the length of the tension side of the beam. Then, to fix the twin rods, two L-shaped brackets were bolted on the side of the beams. In total, five RC beam specimens with rectangular cross sections were prepared and strengthened in different manners and then subjected to four-point bending tests. The enhancement effect of the hybrid anchorage on the flexural behaviour of the strengthened RC beams was validated. With a larger CFRP width, the strengthening effect was more notable, especially when the concrete strength grade was higher. Existing formulas were used to calculate the characteristic moments of the strengthened RC beams, including the cracking moment, yield moment and ultimate moment, and the applicability of the models was examined. Based on the test results, the formula for the ultimate moment of the specimens with the end anchorage requires further investigation.