الخلاصة:
Abstract
There is a time difference between the cost estimation stage of
construction projects and the implementation phase. In addition, the project
takes a long time to complete it and the cost of materials varying from time
to time in the market so cost estimation play important role in success of
any construction project at initial stage therefore the research aims to
develop one model to predict the total cost of the construction project and
develop twenty-five models to estimate the average prices of construction
items of the project with high accuracy by using artificial intelligence
techniques such as multiple linear regression analysis (MLR), support
vector machine (SVM) and artificial neural networks (ANN). The data set
used to build the models is 34 construction projects, and these projects
were collected from several government departments in Diyala province.
The optimal method based on precision, and enabling to predict the
budget of projects was MLR with precision (98.97%) while the optimal
method based on correlation factor was ANN with percentage (100%).
The optimal method based on precision, which is able to predict the
price rate of land fill work item construction works under moisture proof
layers item, ordinary concrete for walkways item, reinforced concrete lintel
item, reinforced concrete slab item, reinforced concrete stair item,
reinforced concrete for the sun bumper item, cement finishing works item,
color pigment item and works of placing marble item model was SVM.
Price rate of pentellite paints item model was MLR and for excavation the
foundation works item, filling with sub-base item, the construction works
above moisture proof layers item, construction work of section item,
reinforced concrete foundation item, reinforced concrete column item,
reinforced concrete beams item, plaster finishing works item , plastic
finishing works item , Stone packaging item model, ceramic works for
IV
floor item model, ceramic work for wall item, flattening (two opposite
layers of lime) and flatting (Tiling) tem was ANN. Also, the optimal
technique based on correlation factor, it can be used to predict price rate
for all items was ANN expect the construction works under moisture proof
item model and pentellite layer was MLR.
