| Summary: | In modern manufacturing, the detection and prediction of machine anomalies, i.e., the inactive state of the machine during operation, is an important issue. Accurate inactive state detection models for factory machines can result in increased productivity. Moreover, they can guide engineers in implementing appropriate maintenance actions, which can prevent catastrophic failures and minimize economic losses. In this paper, we present a novel two-step data-driven method for the non-active detection of industry machines. First, we propose a feature extraction approach that aims to better distinguish the pattern of the active state and non-active state of the machine by multiple statistical analyses, such as reliability, time-domain, and frequency-domain analyses. Next, we construct a method to detect the active and non-active status of an industrial machine by applying various machine learning methods. The performance evaluation with a real-world dataset from the automobile part manufacturer demonstrates the proposed method achieves high accuracy.
|
|---|