Effective maintenance management is essential to reduce the adverse effect of equipment failure to operation. This can be accomplished through accurately predicting the equipment failure such that appropriate actions can be planned and taken in order to minimize the impact of equipment failure to operation. This study presents a development of model based on continuous time Markov process for a degraded multi-state system to evaluate the system performance. The system degradation was quantified by five distinct level of systems production output ranging from perfect functioning state to complete failure with zero output. At any point in time, the system can experience Poisson failure from any state upon which minimal repair will be performed. This research explored a method of estimating of transition rates as well as definition of states for the Markov process by utilizing historical production data. The results indicate the applicability of Markov process in estimating the reliability and availability of multi-state systems.