Transient running stability assessment of industrial rotating machinery based on bag of correlated vibration feature representation

Abstract

The objective of this paper is to monitor and assess the running stability of industrial machinery operating under transient conditions. A new method called bag of correlated feature representation (BOCFR) is presented in this paper, aiming to extract structural information hidden in the data. At first, Bag-of-Words (BoW) model is employed to cluster the collected training samples. For a new observed signal, correlogram is subsequently constructed with BoW to reflect its dynamic characteristic. Entropy is then calculated aiming to periodically analyze the dynamic characteristics of machine running status over time. Together with the BOCFR, a unified framework by means of hypothesis testing, is finally proposed, which is evaluated based on simulation scenarios and real-engineering applications: comparison results with typical techniques demonstrates the proposed method achieving the promising performance.