Development of Electronic Component Life Prediction Model Using Rough Set Theory in Case Study of Relay

Abstract

Despite the greatly increasing use of relays for various circuits, equipment, and electrical networks in a power system, little is known about how to select suitable relay products to ensure the reliability of relay life. Accordingly, there is a need to develop a model for predicting reliability and thus improve life expectancy. In this work, we identify the relationship between the initial relay performance information and the reliability life through long-term tests. A reliability prediction model for relay lifetime based on rough set theory is developed by the following steps: Firstly, the parameters affecting relay life are obtained. Secondly, discrete data values are divided into attribute values and a decision-making table is constructed. Third, a relative importance index based on attribute values is defined. Fourth, decision-making rules are formulated. Finally, decision-making rules are acquired by the analysis of actual relay parameters. Experimental results confirm the effectiveness of the proposed prediction model. The method can be applied not only to the relay product screening of an actual working system, but also to the reliability life prediction or product screening of other products.Zhuo Li received his Ph.D. degree in circuits and systems from Tianjin University, China, in 2015. He joined the Computer Science Department, University of Arizona, as a postdoc in 2016. He is currently working in the School of Microelectronics at Tianjin University. His main research interests include router architectures, fast packet processing, wireless communications, and future internet architectures, e.g., named data networking and information-centric networking. He is a member of IEEE.