Improving Semi-Supervised Learning for Remaining Useful Lifetime Estimation Through Self-Supervision
This addresses data imbalance and labeling challenges in predictive maintenance for industries, though it is incremental as it builds on existing semi-supervised learning methods.
The paper tackles the problem of remaining useful lifetime (RUL) estimation in machines, where data near failure is rare and labeling is delayed, by proposing a semi-supervised learning approach with self-supervised pre-training. It outperforms competing methods and a supervised baseline under realistic conditions on the NASA C-MAPSS dataset.
RUL estimation suffers from a server data imbalance where data from machines near their end of life is rare. Additionally, the data produced by a machine can only be labeled after the machine failed. Semi-Supervised Learning (SSL) can incorporate the unlabeled data produced by machines that did not yet fail. Previous work on SSL evaluated their approaches under unrealistic conditions where the data near failure was still available. Even so, only moderate improvements were made. This paper proposes a novel SSL approach based on self-supervised pre-training. The method can outperform two competing approaches from the literature and a supervised baseline under realistic conditions on the NASA C-MAPSS dataset.