الفهرس | Only 14 pages are availabe for public view |
Abstract Production rates are considered an essential aspect of the construction industry because it is the indicators of the productivity efficiency of construction sector. Hence, the efficient management, which considers labors as the most important factor, leads to higher productivity and achieves the goal with lower cost, time, and high quality. However, there is a gap in identifying factors affecting rebar workers. Therefore, this study tries to bridge this gap by developing a neural network model for estimating rebar labor’s production rates. Thus, a questionnaire has been distributed to a group of consultants and contractors and statistical software program (IBM SPSS) has been used to statistically analyze the collected data. Mainly, to show the effect of different analytical methods on the ranking of the outputs. The first method depends on applying project management professional (PMP) matrix method, while the second method depends on the probability and the impact to validate the results of the first method. The results indicate that ”project type” is the most important factor affecting labor productivity. Also, the application of factors has led to a model that can be used in estimating rebar’s labor production rate. Reliable values have been successfully predicted by Artificial Neural Network (ANN). Additionally, the research presents a software program, which is used to measure production rate (Output) based on the data provided in the form of factors affecting the rebar labor (Input). This helps to measure productivity growth in a low-cost residential building in a later work. Moreover, it supports fundamentals building by predicting productivity of rebar labor, to establish a database for executed projects in the future to develop productivity estimation process. |