This paper proposes an integrated Markovian and back propagation neural network approaches to
compute reliability of a system. While states of failure occurrences are significant elements for accurate
reliability computation, Markovian based reliability assessment method is designed. Due to drawbacks
shown by Markovian model for steady state reliability computations and neural network for initial
training pattern, integration being called Markov-neural is developed and evaluated. To show
efficiency of the proposed approach comparative analyses are performed. Also, for managerial
implication purpose an application case for multiple automated guided vehicles (AGVs) in
manufacturing networks is conducted.