Building Project Cost Estimate Model Based On Genetic Fuzzy Neural Network

The purpose of this paper is to develop a set of building project cost estimate system and to probe a effective and practical project cost estimate method used for construction in order to reduce the cost and raise the working efficiency and reliability of the whole system.Firstly, the influence of key factors on its performance is analyzed for theory support in building project cost estimate. Afterward, genetic algorithm, fuzzy system and neural network is described for technology support in building project cost estimate. Later on, a knowledge frame based on genetic fuzzy neural network is proposed for building project cost estimate, and the definite content can be stated as follows: Aim at handling weakness of poor convergence and insufficient forecast, an improved fuzzy neural network method based on SOFM (self-organizing feature map) and genetic algorithm was proposed to replace the fashionable T-S fuzzy neural network. The method illustrated how to apply SOFM and genetic algorithm to improve the fault such as poor convergence and insufficient forecast. After optimizing of T-S fuzzy neural network model, construct project cost estimate model had been built up. Finally, the model was set up with the purpose of comparing generalization ability by 18 examples and 2 testing samples. Comparing the simulation, a positive result was found that SOFM fuzzy neural network had a better performance in reducing the forecast error and iterating times than BP, BP optimized by genetic algorithm, GA-BP, fuzzy neural work. Therefore, this model is fit for handling construct project cost estimate.The study of building project cost estimate based on genetic fuzzy neural network provides technological condition for realizing low cost and efficient production in large scale.At the same time, this study is also a good try of building project cost estimate control technology to automatic and intelligent control.