DEVELOPMENT OF THE CONSTRUCTION PRODUCTIVITY ESTIMATION MODEL USING ARTIFICIAL NEURAL NETWORK FOR FINISHING WORKS FOR FLOORS WITH MARBLE

Estimation of the productivity is an important task in the management of construction projects. The quality of construction management depends on accurate estimation of the construction productivity. In this paper, Multi-layer perceptron trainings using the back-propagation algorithm neural network is formulated and presented for estimation of the productivity of construction projects. Data used in the study are for residential, commercial and educational projects from different part from Iraq. These are used in training the model and evaluating its performance. Ten influencing factors are utilized for productivity forecasting by ANN model, they include age, experience, number of the assist labor, height of the floor, size of the marbles tiles, security conditions, health status for the work team, weather conditions, site condition, and availability of construction materials. One model was built for the prediction the productivity of marble finishing works for floors. It was found that ANNs have the ability to predict the productivity for finishing works with a very good degree of accuracy of the coefficient of correlation (R) was 89.55%, and average accuracy percentage of 90.9%.

[1]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[2]  Alice J. O'Toole,et al.  Neural computing: Theory and practice: Philip D. Wasserman, Van Nostrand Reinhold: New York, 1989, $36.95, 230 pp. ISBN 442-207-433 , 1990 .

[3]  Ian Flood,et al.  Expert judgment in forecasting construction project completion , 1997 .

[4]  Deborah J. Fisher,et al.  NEUROMODEX - NEURAL NETWORK SYSTEM FOR MODULAR CONSTRUCTION DECISION MAKING , 1994 .

[5]  Aminah Robinson Fayek,et al.  Predicting Industrial Construction Labor Productivity using Fuzzy Expert Systems , 2005 .

[6]  Ashraf Elazouni,et al.  Estimating Resource Requirements at Conceptual Design Stage Using Neural Networks , 1997 .

[7]  Soundar Kumara,et al.  Neuroform—Neural Network System for Vertical Formwork Selection , 1992 .

[8]  Tarek Hegazy,et al.  NEURAL NETWORK MODEL FOR PARAMETRIC COST ESTIMATION OF HIGHWAY PROJECTS , 1998 .

[9]  Miroslaw J. Skibniewski,et al.  Estimating construction productivity: neural-network-based approach , 1994 .

[10]  Khan Ai. Topping Bhv. and Bahreininejad A..  Parallel training of neural networks for finite elementmesh generation , 1993 .

[11]  Hojjat Adeli,et al.  Regularization neural network for construction cost estimation , 1998 .

[12]  Tarek Hegazy,et al.  Analogy‐Based Solution to Markup Estimation Problem , 1994 .

[13]  James E. Rowings,et al.  Construction Labor Productivity Modeling with Neural Networks , 1998 .

[14]  Murray Smith,et al.  Neural Networks for Statistical Modeling , 1993 .