Neural Networks and Grey Relational Analysis on Building Construction Duration Cases

The objective of this paper is to provide a tool based on artificial neural networks and grey relational analysis to aid clients and their consultants in estimating or benchmarking the construction duration. Building construction duration predictability and control have been identified as one of the key performance issues to be addressed in providing best value to construction clients. This research is based on the analysis of the 'actual time' taken to construct buildings in China. This article firstly established artificial neural networks based on simulated annealing model for building construction duration prediction. And then, the feasibility and validity are verified by the example, which get the appraisal result to compare with the result from the BP neural network. According to the simulated results, we want to find a way to control building construction duration. There are, of course, a multiplicity of factors that will affect the time taken to construct a particular project. Using grey relational analysis, we can find the core factors influencing construction duration. For the construction of very conformed the "Grey" environment, the experiment shows grey system is the objective method of assisting contractors and subcontractors of building market precisely and quickly in reaching the most appropriate decision-making of construction duration.