Estimating the performance of externally reinforced concrete beams using neural networks

The load-carrying capacity of reinforced concrete beams can be compromised by concrete cracking, and the intrusion of moisture, oxygen and salt that cause corrosion of the steel reinforcement. The corrosion effectively reduces the cross-sectional area of the reinforcing steel, resulting in a loss of load-carrying capacity. A relatively inexpensive method of repairing such beams and restoring the load-carrying capacity to an acceptable value is the use of external reinforcement. This is accomplished by bonding steel plates or fiber-reinforced composites to the tensile and shear faces of the beams. Unfortunately, analytical tools such as finite element analysis (FEM) are not ideally suited to evaluating external reinforcement design solutions. These models are computationally expensive (making them slow to arrive at an answer, especially when dealing with complicated three-dimensional composite forms), they can be inconvenient to use, and they have a limited ability to model heterogeneous and nonisotropic materials. An empirical solution is therefore proposed that involves the development of a neural network model of the performance of externally reinforced beams, developed from laboratory observations of actual beam behaviour.