Journal
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
Volume 4, Issue 4, Pages 339-346Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s13042-012-0093-9
Keywords
Hybrid models; Fuzzy estimators; Construction operations management; Activity duration
Categories
Ask authors/readers for more resources
In this work we apply hybrid (fuzzy-stochastic) modelling in construction operations management (COM). One of the most prevailing methods for the COM is the Program (or Project) evaluation review technique, mostly known as PERT. Nevertheless, both classic and fuzzy PERT presents evident drawbacks. Such drawbacks are the subjectivity of estimates for activity durations, the specification to a certain beta distribution and the assumption for applicability of this probability distribution to all project activities. Regarding the fuzzy PERT, a major drawback is the arbitrary choice of fuzzy numbers for the activity duration. In an attempt to reduce these drawbacks and reach more realistic results we propose an alternative hybrid (fuzzy-stochastic) approach. By combining the generalized beta distribution and the fuzzy estimators method, we find the fuzzy activity times (earliest start/finish-latest start/finish) of a project network and also a fuzzy probability for an activity's duration to be in a certain time interval. A numerical example is given for thorough comprehension of the proposed method.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available