| description abstract | The interface bond strength between carbon fiber-reinforced polymer (CFRP) layers and concrete is a crucial metric for determining the mechanical properties of CFRP-reinforced concrete. This bond strength is essential for evaluating CFRP-reinforced concrete’s performance and ensuring the materials’ structural integrity. A database was established using the experimental data in the literature to evaluate the interface bond strength. This database comprised 360 groups of different conditions test results of CFRP-reinforced concrete, which were used to create a prediction model using an artificial neural network. The database was randomly divided into two data sets: 310 groups were used for training the neural network model and 50 for simulated prediction. A three-layer artificial neural network model was trained using the backpropagation algorithm, which is widely used in artificial neural networks. The model’s input layer considered seven parameters, including the type of CFRP layer, surface form, CFRP layer thickness, anchorage length, failure mode, concrete compressive strength, and normalized concrete cover thickness. These parameters were selected based on their known influence on the interface bond strength between the CFRP layers and concrete. The output layer of the model represented the interface bond strength between the CFRP layers and concrete. The model’s results indicated that the backpropagation (BP) neural network model had strong capability of prediction and generalization. The predicting error was minimal, a crucial aspect of the model’s accuracy. Further, this approach allows for integrating many factors that influence the interface bond strength between the CFRP layers and concrete, providing accurate predictions of the bond strength. It can be used as a valuable tool for evaluating the performance of CFRP-reinforced concrete. This research develops an accurate method to predict the bond strength between CFRP layers and concrete using artificial neural networks. A strong bond is crucial for the structural integrity of concrete reinforced with CFRP. The neural network model considers factors like the type and thickness of CFRP used, how the concrete surface is prepared, and the concrete’s strength. Engineers can use this neural network tool to evaluate how well CFRP will reinforce specific concrete mixtures and structures before construction. This allows structures to be designed and built with optimal, cost-effective use of CFRP to reinforce concrete in applications like bridges and buildings. The neural network approach integrates many technological and material factors into one predictive model, providing a useful evaluation method for the construction industry. | |
