BPNN and Pontryagain Estimate and Optimize the Investment of New Projects

The traditional estimate method debases the precision and accuracy of estimation result. Based on the BP neural network, this paper sets up the model of cost estimation of highway engineering. The BP neural network model is trained by a sample data obtained from some performed typical engineering to come true quick cost-estimating. It is sure that the method is practical and the estimating results are reliable according to lots of examples. What is more, this paper introduces the concept of cash flow and builds an optimal control model under some hypotheses to study cost control of new projects and then solve the model using Pontryagain minimum theory, and illustrates the validity of the method through an example which shows that not only the total cost is less in the optimized investment plan than the original plan, but also the cash flow needed by the project is more steady, both of which facilitate the implementation of the project.