A neural network model for predicting cost-flow for water industry projects

This paper explains the need for cost-flow forecasting in water industry projects and investigates the methods currently used to perform such a task. The paper also introduces neural network as an alternative approach to existing methods. The method used to model the system is described. The relationship between the number of nodes used and the accuracy of the neural network in modelling the cost-flow is closely examined. An optimal solution is proposed for the case and a prototype system is described. The results of the investigation of the number of nodes used and testing of the prototype neural network for sample cases are presented and discussed.