Calcium-magnesium-alumino-silicate (CMAS) corrosion is a critical factor which causes the failure of thermal barrier coating (TBC). CMAS attack significantly alters the temperature and stress fields in TBC, resulting in their delamination or spallation. In this work, the evolution process of TBC prepared by suspension plasma spraying (SPS) under CMAS attack is investigated. The CMAS corrosion leads to the formation of the reaction layer and subsequent bending of TBC. Based on the observations, a corrosion model is proposed to describe the generation and evolution of the reaction layer and bending of TBC. Then, numerical simulations are performed to investigate the corrosion process of free-standing TBC and the complete TBC system under CMAS attack. The corrosion model constructs a bridge for connecting two numerical models. The results show that the CMAS corrosion has a significant influence on the stress field, such as the peak stress, whereas it has little influence on the steady-state temperature field. The peak of stress increases with holding time, which increases the risk of the rupture of TBC. The Mises stress increases nonlinearly along the thick direction of the reaction layer. Furthermore, in the traditional failure zone, such as the interface of the top coat and bond coat, the stress obviously changes during CMAS corrosion.

Remaining useful life (RUL) prediction plays a core role in industrial prognostics and health management (PHM), requiring data-driven models with higher predictive capability for accurate long time series prediction. Developing reliable deep learning-based models based on multi-sensor monitoring data is fundamental for accurately predicting vibration trends during bearing operation and is crucial for bearing fault diagnosis and RUL prediction. In this work, a method for constructing a health index based on vibration signal is developed to describe the performance features of rolling bearings, which mainly includes feature extraction, sensitive feature index selection, dimensionality reduction, and normalization methods. In addition, a new RUL prediction method, TCN–Transformer, is developed which can efficiently learn and integrate local and global features of vibration signals, addressing the long time series prediction problem in RUL prediction. The TCN extracts local features, while the Transformer learns global features, both of which are seamlessly integrated through a specially designed feature fusion attention module. Both the health indicator (HI) constructed from extracted time domain and frequency domain feature parameters and the RUL prediction method were rigorously validated using the IEEE PHM 2012 Data Challenge dataset for rolling bearing prognostics. By employing the proposed HI construction method, the average comprehensive bearing performance index, used to evaluate RUL prediction accuracy, is improved by 8.69% across the entire dataset compared to the original feature-based composite index. The proposed RUL prediction model can more accurately predict the RUL of rolling bearings under different conditions, reducing the RMSE and MAE by 14.62% and 9.26%, respectively, and improving the SCORE by 13.04%. These results underscore the efficacy and superiority of our approach in RUL prediction of rotating machinery across varying conditions.