An Optimal Burn-In Policy for Cellular Phone Lithium-Ion Batteries Using a Feature Selection Strategy and Relevance Vector Machine

Abstract

The early detection of defective lithium-ion batteries in cellular phones is critical due to the rapid increase in popularity and mass production of cellular phones. It is essential for manufacturers to design an optimal burn-in policy to differentiate between normal and weak batteries in short cycles prior to shipping them to the marketplace. A novel approach to determine the optimal burn-in policy using a feature selection strategy and relevance vector machine (RVM) is proposed. The sequential floating forward search (SFFS) is used as the feature selection method to find an optimal feature subset from the entire sequence of the batteries’ quality characteristics while preserving the original variables. Given the selected feature subset, the RVM is applied to classify batteries into two groups and simultaneously obtain the posterior probabilities. To achieve better discrimination performance with less risk, a new characteristic is extracted from the discharge profile. Subsequently, an optimization cost model is developed by introducing a classification instability penalty to ensure the stability of the optimal number of burn-in cycles. A case study utilizing cellular phone lithium-ion batteries randomly selected from manufactured lots is presented to illustrate the proposed methodology. Furthermore, we conduct a comparison with the cumulative degradation (CD) method and non-cumulative degradation (NCD) method based on the Wiener process. The results show that our proposed burn-in test method performs better than comparable methods.

Data Preparation for Precursor Identification in Unstable Approach Events in Flight Data

“…It could be executed by two main methods, feature selection, and feature extraction. Compared to feature extraction, feature selection that outputs a feature subset from the original feature set so as to preserve the original feature representation outperforms feature extraction which alters the original representation [13]. Feature selection methods include filter, wrapper [11], embedded [1], and hybrid [4].…”

A lifecycle cost model considering both component and system burn-in for operationally unrepairable systems

“…Some others studied more complex arrangements of components such as in a non-series system (Kim and Kuo, 2009) or when multiple failure modes are present (Cha and Finkelstein, 2015; Xiang et al , 2013). There are also studies that estimate reliability based either on the underlying physics-of-failure (White, 2008; Cook et al , 2019) or on degradation properties (Cha, 2006a; Tsai et al , 2011; Xiang et al , 2016; Yu et al , 2018) which are subsequently used to obtain burn-in strategies (Kurz et al , 2017; Lyu et al , 2019).…”