A FUSION PROGNOSTICS METHOD FOR REMAINING USEFUL LIFE PREDICTION OF ELECTRONIC PRODUCTS

摘要

Prognostics and health management methods can provide advance warning of failure; reduce the life cycle cost of a product by decreasing inspection costs, downtime, and inventory; and assist in the design and logistical support of fielded and future electronic products. This paper presents a fusion prognostic method to predict the remaining useful life of fielded products. This method uses the data-driven method to detect anomalies and trend the parameters related to the failure of the product. A physics of failure analysis is then used to identify and prioritize the failure mechanisms and create the corresponding failure definitions in terms of the parameters related to the failure. Based on the parameter trending and the failure definition, the remaining useful life of the product can be predicted.