Integration between neuro-fuzzy system and Monte Carlo simulation for duration estimation of the bored piles
by Thoedtida Thipparat
International Journal of Business and Systems Research (IJBSR), Vol. 7, No. 2, 2013

Abstract: Traditional methods of duration prediction of the bored pile projects are far from accurate and consistent. This can be attributed to the fact that the problem in estimating the construction duration is very complex and not yet precisely understood. Neuro-fuzzy system (NFS) has been proposed to deal with several problems associated with cognitive uncertainty caused by human subjectivity. Despite the relative merits of the NFS, it cannot determine non-cognitive caused by factors such as constant change of site conditions, low technical competence of workers, material unavailability, and bad weather conditions. These factors result in the variation in activity duration. An alternative stochastic approach is necessary for providing more rational estimation of activity duration. In this paper, the probability distribution of activity duration is obtained by integrating the NFS with Monte Carlo simulation. The estimators can make a decision regarding risk factors and their impacts on the estimated duration by employing the proposed method. As a result, a more realistic estimation of the actual duration can be provided.

Online publication date: Thu, 28-Nov-2013

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Business and Systems Research (IJBSR):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com