Development Of The Mathematical Model For Predicating The Construction Productivity In IRAQ Using The Artificial Neural Perceptron Network

Abstract

The main objective of this research is to development a mathematical model for predicating the construction productivity of floor using artificial neural perceptron network ANPN, because the methods currently used to estimation the productivity such as the personal experience, is a traditional methods inaccurate. Therefore, it can be adopt new and advanced techniques to predicating the productivity construction with accurate, speed and ease of use.In this research have been identified ten independent variables affect on the construction productivity of floor, the data collection from construction project in Mosul (Iraq) through the design of the data collection form (Form measurement of work). In this research, One model was built for the prediction the total productivity of building project. A number of issues in relation to ANPN construction such as the effect of ANPN geometry and internal parameters on the performance of ANNs models were investigated. Information on the relative importance of the factors affecting the above productivity parameters predictions were presented and practical equations for the predictions of the above construction productivity were developed.. It was found that ANPNs have the ability to predict the Total productivity for finishing works for building project with a good degree of accuracy of the coefficient of correlation (R) was 96.2%, and average accuracy percentage of 96.4%.