A COMPARISON BETWEEN DATA-DRIVEN AND PHYSICS OF FAILURE PHM APPROACHES FOR SOLDER JOINT FATIGUE
Publication or External Link
Prognostics and systems health management technology is an enabling discipline of technologies and methods with the potential of solving reliability problems that have been manifested due to complexities in design, manufacturing, environmental and operational use conditions, and maintenance. Over the past decade, research has been conducted in PHM to provide benefits such as advance warning of failures, enable forecasted maintenance, improve system qualification, extend system life, and diagnose intermittent failures that can lead to field failure returns exhibiting no-fault-found symptoms. While there are various methods to perform prognostics, including model-based and data-driven methods, these methods have some key disadvantages. This thesis presents a fusion prognostics approach, which combines or ―fuses together‖ the model based and data-driven approaches, to enable increasingly better
estimates of remaining useful life. A case study using an electronics system to illustrate a step by step implementation of the fusion approach is also presented. The various benefits of the fusion approach and suggestions for future work are included.