Real-time Online Prediction of Data Driven Bearing Residual Life

作者：Haiya Wang, Zhongqing Yu, Lu Guo · 发表于：Journal of Physics Conference Series · 年份：2020 · DOI：10.1088/1742-6596/1437/1/012025 · 被引用次数：5 · 研究领域：Machine Fault Diagnosis Techniques、Engineering Diagnostics and Reliability、Fault Detection and Control Systems

Abstract In order to realize the predictive maintenance of key components under massive vibration data, real-time online prediction of the remaining life of different types of bearings, a data driven real-time online prediction method for bearing residual life is introduced. The method realizes the construction of the data-driven bearing residual life prediction model by selecting the bearing vibration data Spearman characteristic parameter selection, principal component analysis (PCA), health index fusion, and BP neural network fitting. The built model is continuously updated by real-time online acquisition of data to achieve real-time online prediction of bearing residual life. The accuracy and feasibility of the method for predicting the remaining life of different types of bearings are verified by experiments. Using this method to predict the remaining life of the bearing helps to achieve predictive maintenance of critical components, reduce unplanned downtime, increase production efficiency, and reduce production costs.