Recent Advances on GERT Method Based on Bayesian Networks

Background: Identification of key processes and key paths plays an important role in project management and control. Therefore, in order to reduce the expected time of the project, some analysis methods other than engineering technology must be adopted. The Graphical Evaluation and Review Technique (GERT) is a useful tool in system analysis and design. The GERT can process the relationships in network diagrams, which is a network with feedback function and has been applied in many fields. Methods: In this paper, based on Bayesian network model and GERT network, a new method for analyzing project process has been studied. Firstly, all the variable nodes of the GERT network are determined. Secondly, the variable nodes in the GERT network are divided into tandem nodes, aggregation nodes, distributed nodes, and self-loop nodes in the Bayesian network. Third, the GERT network parsing method is used to calculate the expected time of the partial variable node. Then the network structure of the Bayesian network is constructed by connecting the nodes with the directed edges. Results: Thus, a GERT Bayesian model is established. Based on the posterior probability of Bayesian network, we have determined the key process, improved the key process and shortened the processing time. Conclusion: Finally, this method is used to analyze an ERP project activity flow chart with self-loop structure, identify the key processes and key paths, and determine the time period. Therefore, the validity and reliability of the method in project process management are verified.