A global attention based gated temporal convolutional network for machine remaining useful life prediction

Xu Xinyao, Zhou Xiaolei, Fan Qiang, Yan Hao, Wang Fangxiao

Abstract: Highlights•A novel gated temporal convolutional network with a global attention mechanism is proposed for the RUL prediction tasks of machines.•The label confusion problem for RUL prediction tasks is discussed, and the strategies for data preprocessing, prediction framework, and model structure are proposed to handle this problem.•The proposed method is verified on the CMAPSS dataset and the XJTU-SY dataset. It achieves state-of-the-art performance on the majority of tasks on both datasets.

External IDs:dblp:journals/ress/XinyaoXQHF25