Abstract: In the remaining useful life prediction of aero-engine, a remaining useful life prediction model (FAResNet) is proposed based on feature attention mechanism and residual network (ResNet) to solve the problem that most deep learning methods do not carry out adaptive weighting for different sensor input features. A feature attention mechanism module with squeeze excitation was used for adaptive weighting processing of multi-sensor input features. Two parallel ResNet branches were used to extract time series features along the time dimension and feature fusion along the sensor feature dimension respectively to deeply mine the hidden features of the data. Simulation experiments on open data sets demonstrate the effectiveness of the proposed model, which has lower prediction errors than other deep learning models.