Simulation Methods of Failure Random Variates Generation for Considering Preventive Maintenance

• Main Authors: Shu-Te Fang, 方樹德
• Other Authors: Chun-Yuan Cheng
• Format: Others
• Language: zh-TW
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/15023941415431086344

碩士 === 朝陽科技大學 === 工業工程與管理系碩士班 === 96 === It usually is required to use numerical method to obtain the optimal preventive maintenance (PM) policy since the failure rate function is changed after each PM. This makes the theoretical method complicated to use and is not suitable for real cases. Therefore, it can been considered to use the simulation method to obtain a near optimal PM policy. However, there are not many literatures relating to the simulation method for obtaining a PM policy. The critical step of simulation method for obtaining a near optimal preventive maintenance (PM) policy is the generation of the failure random variates (RV). In this research, we develop three different methods for generating failure RV which include the inverse-offset method, the inverse-trace-back method, and the rejection method. The three RV generating methods are applied to the finite-time-span preventive maintenance model with age reduction effect. The minimal repair is performed when the system or equipment is failed between each PM. The procedure and examples for obtaining the near optimal PM policies is also provided in this research. It is found that there are no significant differences among the three proposed RV generating methods when comparing the dispersion of the generated RV. However, the rejection method is the simplest method for obtaining the near optimal PM policies.