Abstract：Aiming at the problem of inaccurate life prediction caused by multiple degradation information during the operation of complex aviation equipment, a multi-information fusion life prediction model based on kernel principal component analysis (Kernel Principal Component Analysis,KPCA) and bidirectional long short-term memory (Bi-directional Long Short-Term Memory ,BLSTM) neural network is proposed. First, the kernel principal component method is used to perform dimensionality reduction and information fusion on the multi-dimensional degraded data set to obtain a low-dimensional feature data set that can characterize equipment degradation. Then use the BLSTM neural network model to predict the remaining life of aviation equipment (Remaining Useful Life,RUL) with multi-dimensional degradation information, and obtain the mapping relationship between the monitoring data and the remaining life. Finally, the C-MAPSS aero-engine degradation data set is used to simulate and verify the proposed multi-information fusion life prediction model. The results show that KPCA can perform dimensionality reduction and fusion of multi-state nonlinear monitoring data. The proposed KPCA-BLSTM can predict RUL under multi-dimensional degradation information very well, and by building support vector machines (Support Vector Regression ,SVR), Convolutional neural network (Convolutional Neural Networks ,CNN) and BLSTM neural network models are compared with the prediction results of the proposed model. The proposed model error and score are better than the other three models, indicating that the proposed model has higher prediction accuracy.