One of the most urgent problems related to highway infrastructure is that the cost of maintaining a network of bridges with an acceptable level of service is more than the available budgeted funds. Low prioritization of the available resources allocated to bridge projects exacerbates the situation. About 42 percent of the 574,000 highway bridges in the United States were reported by FHWA to be structurally deficient or functionally obsolete. Traditional management practices have become inadequate as ways to face this serious problem. Priority-setting schemes for bridge projects range from those done on a subjective basis in which engineering judgment is used to those that use very complex optimization models. However, currently used priority-setting schemes do not have the ability to optimize the system's benefits to obtain optimal solutions. The present objective is to show how artificial neural networks (ANNs) can be used to optimize the system's resources to generate the group of bridge improvements that minimizes the loss of the network benefits. ANNs are algorithms with characteristics that are able to solve certain classes of optimization problems. The advantages of using ANNs include improvements in the speed of operation by parallel implementation either in hardware or in software. It is also possible to implement ANNs by optical devices that operate at higher speeds than traditional electronic chips.
Discussion(0)
No comments yet. Be the first to comment.