Product development network modelling extensions to the cycle elimination method

This paper considers Product Development (PD) project networks, which are characterized by stochastic activity durations and activity rework or iteration (i.e., potential to repeat some activities several times during PD execution). The Cycle Elimination (CE) approach presented in Nasr et al. (2016) reduces the computational complexity of analyzing iterative PD project networks by considering an approximate network with no iteration. We build on the CE approach to investigate practical scenarios which arise in real world PD projects which are not accounted for by the CE approach. These scenarios include: (i) forward probabilities, (ii) dynamic rework probabilities and proportions, (iii) multiple dependency relationships between activities, and (iv) different rework through indirect connections. We demonstrate these extensions using two case studies. The first case study considers a software development process, where we collected the data by interviewing the managers of the company. The second case study involves a hardware development process (adapted from Pinkett (1998)), where the results show that the proposed method outperformed three existing techniques from the literature. Both cases were solved using the proposed modification to the CE approach, and then simulated to gauge the accuracy of the proposed method showing very promising results.