Remaining useful life predictions for turbofan engine degradation based on concurrent semi-supervised model

As a crucial and expensive component of the aircraft, it is important to effectively predict its remaining useful life (RUL) so as to reduce maintenance costs and improve maintenance strategies. In this paper, a novel concurrent semi-supervised model is proposed to estimate the RUL of the aero-engine. This semi-supervised model can provide satisfying prediction results with only a small amount of labeled data. And the concurrent structure is designed to improve the stability and accuracy of the prediction. The proposed method is verified on the popular C-MAPSS dataset and is compared with a variety of state-of-the-art approaches. The experimental results demonstrate that the proposed method is effective in the task of remaining useful life prediction.