- مبلغ: ۸۶,۰۰۰ تومان
- مبلغ: ۹۱,۰۰۰ تومان
Overheads, especially site overhead costs, constitute a significant component of a contractor's budget in a construction project. The estimation of site overhead costs based on traditional approach is either accurate but time consuming (in case of the use of detailed analytical methods) or fast but inaccurate (in case of the use of index methods). The aim of the research presented in this paper was to develop an alternative model which allows fast and reliable estimation of site overhead costs. The paper presents the results of the authors' work on development of a regression model, based on artificial neural networks, that enables prediction of the site overhead cost index, which used in conjunction with other cost data, allows to estimate site overhead costs. To develop the model, a database including 143 cases of completed construction projects was used. The modelling involved a number of artificial neural networks of the multilayer perceptrons type, each with varying structures, activation functions and training algorithms. The neural network selected to be the core of developed model allows the prediction of the costs' index and aids in the estimation of the site overhead costs in the early stages of a construction project with satisfactory precision.
5. Summary and conclusions
This research resulted in development of a novel estimation method of site overhead cost index. The approach proposed by the authors of the paper is based on artificial intelligence tools namely neural networks. A regressive model which employs artificial neural network chosen from a number of investigated networks has been proposed. The model is capable of mapping nonlinear relationships between a set of values of describing variables (which are features that characterize the construction site overheads for a project) onto a set of values of described variable which constituted the site overhead cost index. The describing variables of the model included characteristics of a construction project in relation to the type of works, the location of the construction site, the time of works completion, as well as the organizational assumptions for the construction process. The advantage of using neural networks approach instead of a classical multivariate regres sion approach is that there is no need to assume a priori functional relationships. The ANN, chosen to be the core of the proposed model, was fitted to the data (values often describing variables and one described variable) during the training process. The proposed neural networks based approach revealed its superiority over a classical multivariate linear regression approach. On the other hand, when compared to the traditional method of site overhead cost estimation, which is a preliminary detailed analysis of all the cost components, the use of the developed novel model is significantly faster and offers variant analysis of several sets of values of describing variables at a glance.