Preventive Maintenance Using Continuous-Time Semi-Markov Processes

A method is presented to determine the amount of preventive maintenance to be performed on equipment in order to maximize availability. The method uses a continuous-time semi-Markov process that assumes equipment can fail due to both deterioration and random occurrences. Preventive maintenance can be performed from working state to prevent deterioration failure. An example is used to demonstrate the method using MATLAB and Maple software. Additional flexibility in equipment modeling using semi-Markov processes is described.