Modelling manufacturing processes using Markov chains

Optimizing manufacturing processes with inaccurate models of the process will lead to unre-liable results. This can be true when there is a strong human influence on the manufacturing process and many variable aspects. This study investigates modelling a manufacturing process influenced by human inter-action with very variable products being processed. To develop a more accurate process model for such pro-cesses radio frequency identification (RFID) tags can be used to track products through the process. The tags record information for each product and this data can be used to produce more accurate models of the manu-facturing process. The data produced has been used to create a Markov chain model. This model is used to predict future product paths for use in discrete event simulation. In this case an IT refurbishment company is used as a case study. RFID tags have been utilized to track the IT products moving through the refurbishment process and this information has been used to produce a Markov chain model.