Our study proposed an integrated Markovian and backpropagation neural network for reliability
computations. We made use of current state transition matrix for the failure of the items in different
states. Therefore, a Markovian model was proposed and integrated via neural network for reliability
assessment. We verified the confidence of integrated approach using analytical methods. The
computational results illustrated the applicability of our proposed model. A case study was conducted
to imply the implementation of the approach. The model considered two features of automated flexible
manufacturing systems equipped with automated guided vehicle (AGV) namely, the reliability of
machines and the reliability of AGVs in a multiple AGV jobshop manufacturing system. The results
showed the application of the discussed approaches is fully based on the condition of the system under
study and the limitation obliged by the management. The limitation of the study was the availability of
required data to handle the reliability computations for various purposes (considering past data or real
time computations. The managerial implications of the model can be treated as the capability of the
proposed methodology to provide the reliability of the system at any time, help the decision maker to
make suitable maintenance policy and determine the most defected AGVs and machines for
replacement or specification improvement.