Mohammad Saidi-Mehrabad - Professor, Faculty of Industrial & Mechanical Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran
Hamed Fazlollahtabar - Assistant Professor, Faculty of Industrial Engineering, Iran University of Science and Technology, Tehran, Iran

We compare two approaches for a Markovian model in flexible manufacturing systems (FMSs) using Monte Carlo simulation. The model,which is a development of Fazlollahtabar and Saidi-Mehrabad (2013), considers two features of automated flexible manufacturing systemsequipped with automated guided vehicle (AGV), namely, the reliability of machines and the reliability of AGVs in a multiple AGVjobshop manufacturing system. The current methods for modeling reliability of a system involve determination of system state probabilitiesand transition states. Since the failure of the machines and AGVs could be considered in different states, a Markovian model is proposedfor reliability assessment. The traditional Markovian computation is compared with a neural network methodology. Monte Carlosimulation has verified the neural network method having better performance for Markovian computations

Reliability assessment, Markovian model, Neural network, Monte Carlo simulation