Machine learning approaches in reliability and maintenance: classifications of recent literature

摘要

Reliability and maintenance (R&M) engineering is conventionally notorious for a lack of sufficient failure data to develop robust statistical models. The increasing miniaturization of data collection devices such as wireless sensors has provided a promising infrastructure for gathering information about parameters of the physical systems, which enable practitioners and researchers to apply machine learning (ML) algorithms to improve the efficiency of R&M analysis. The number of published papers on ML in R&M is enormous, this paper will therefore categorizes those papers that were published between 2017 to 16/May/2020, that are written in English, that have received a top 5% number of citations in the year published, and that use support vector methods, random forests, and cluster analysis.