BRIDGE MANAGEMENT BY DYNAMIC-PROGRAMMING AND NEURAL NETWORKS

Bridges and pavements represent the major investment in a highway netw ork. In addition, they are in constant need of maintenance, rehabilita tion, and replacement. One of the problems related to highway infrastr ucture is that the cost of maintaining a network of bridges with an ac ceptable level-of-service is more than the budgeted funds. For large b ridge networks, traditional management practices have become inadequat e for dealing with this serious problem. Bridge management systems are a relatively new approach developed to solve the latter problem, foll owing the successful application of similar system concepts to pavemen t management. Priority setting schemes used in bridge management syste ms range from subjective basis using engineering judgement to very com plex optimization models. However, currently used priority setting sch emes do not have the ability to optimize the system benefits in order to get optimal solutions. This paper presents a network optimization m odel which allocates a limited budget to bridge projects. The objectiv e of the model is to determine the best timing for carrying out these projects and the spending level for each year of the analysis period i n order to minimize the losses of the system benefits. A combined dyna mic programming and neural network approach was utilized to formulate the model. The bridge problem has two dimensions: the time dimension a nd the bridge network dimension. The dynamic programming sets its stag es in the time dimension, while the neural network handles the network dimension.