A Multi-channel Long-term External Attention Network for Aeroengine Remaining Useful Life Prediction

Accurately estimating the remaining useful life (RUL) of aircraft engines can effectively prevent aircraft crashes and human casualties. In some RUL prediction methods, particularly for aircraft engines running under complex conditions, they are difficult to comprehensively characterise the engine degradation process, resulting in poor predicted RUL. To address the above challenge, a multi-channel long-term external attention network (MLEAN) is proposed for the RUL prediction of turbofan engines. Firstly, the pre-processed samples are transformed to enable MLEAN to focus on learning inter-sensor correlations within the same degradation stage. To improve the feature representation capability of the network, multi-channel time attention network (MTANet) is then designed to realise multiscale and multi-frequency feature learning, which effectively achieves multi-perspective analysis of long-term dependencies in different channels. Then, external attention block (EAB) is introduced to memorise important degraded features from different samples, which can improve the ability of global feature extraction and generalization ability of the network. The performance of MLEAN is examined on the C-MAPSS public dataset. The evaluation metrics RMSE and Score values are 13.71 and 680 respectively. In comparison experiments, the proposed MLEAN performs better than the listed state-of-the-art RUL prediction methods.