Bearing is a key component in rotary machines. Their failures may cause the abrupt shutdown of these machines, which would result in substantial economic losses. Therefore, the prediction of the remaining useful life (RUL) of bearings is regarded as one of the critical approaches to avoid failure of bearings and their systems. In this article, an ensemble data-driven approach is proposed to predict the RUL of bearings. It uses feature extraction, an attention mechanism, and uncertainty analysis. First, the features embedded in the bearings' vibration signals are extracted. Second, a stacked gated recurrent unit (GRU) is constructed to predict the bearing RUL. A novel attention mechanism based on dynamic time warping (DTW) is developed to improve the performance of information extraction, and a Bayesian approach is employed to analyze the prediction uncertainty. Finally, the proposed approach is validated using two benchmark-bearing data sets. The results show that the proposed approach can predict the bearing RUL effectively, and the prediction uncertainty can also be evaluated.

Prognostics and health management applications rely heavily on predicting industrial equipment’s remaining useful life (RUL). The traditional RUL prediction approaches mainly consider the nonlinear mapping relationship of time series data but rarely consider the structural information of the equipment, resulting in low prediction accuracy. In order to improve the effectiveness of RUL prediction, this article develops a graph neural network (GNN)-based spatio-temporal fusion attention (STFA) approach. In the proposed approach, a spatial GNN is adopted to fuse spatial features and structural information of the equipment, and a modified attention mechanism is proposed to fuse temporal features. The fused features are then input to a fully connected layer for RUL prediction. Different from existing works, the proposed STFA can combine the information in time and space at the same time and utilize a priori knowledge about the equipment’s structure. Case studies on RUL prediction problems of a turbofan engine and a steam turbine are conducted. The results and comparison demonstrate the superiority of the proposed approach.

A steam turbine is one of the critical components in a power generation system whose failure may result in unexpected consequences, even catastrophic losses. Thus, the reliability of steam turbines needs to be guaranteed all the time, which requires that its health state can be monitored and predicted effectively. Due to various failure modes, it is difficult to build physics-of-failure models used for health prognostics for steam turbines. In this paper, a data-driven integrated framework for health prognostics for steam turbines, which is based on extreme gradient boosting (XGBoost) and dynamic time warping (DTW), is proposed. The proposed framework includes two modules: anomaly detection and remaining useful life (RUL) prediction. The anomalies refer to the overall abnormal operation of steam turbines. In the process of anomaly detection, the temporal variables which can represent the operating conditions of the considered steam turbine are selected first. Appropriately selected temporal variables can reduce the input dimension and will improve real-time performance. Then, XGBoost is used to detect anomalies based on learning historical data. In the process of RUL prediction, a similarity-based algorithm with DTW is used to gain the RUL by contrasting the measured temporal variables with those in the historical cases. The similarity-based algorithm can predict the RUL without establishing a degradation path model, which can avoid the difficulties in parameter estimation for the degradation model and model generalization. The proposed framework is validated by real case studies from an industrial steam turbine. The results show that the proposed approach can detect the anomalies successfully and predict the RUL effectively.