Frank L. Greitzer and Thomas A. Ferryman Predicting Remaining Life of Mechanical Systems

摘要

A diverse set of challenges faces government and industry for life-cycle maintenance of aging equipment.Advancements in sensor and computer technologies are making it feasible to install sensors and smallpowerful computers on complex equipment to monitor the general condition or state (i.e., health) of thatequipment. Methods for analyzing system status and health and for predicting system life expectancyneed to be made more powerful, insightful, reliable, and robust for data collected onboard systems in realtime. This paper reports on a project that is developing robust analytic methods for predicting remaininglife of mechanical systems. The project is focused specifically on the investigation of a generalizedstatistical method for characterizing and predicting system degradation.