A Multi-Granularity Supervised Contrastive Framework for Remaining Useful Life Prediction of Aero-engines

TL;DR

This paper introduces a multi-granularity supervised contrastive framework for aero-engine RUL prediction, improving feature space structure and prediction accuracy through a novel training strategy and network design.

Contribution

It proposes a new contrastive learning framework tailored for RUL prediction, addressing sample imbalance and minibatch issues, with a scalable network structure and multi-phase training.

Findings

Enhanced RUL prediction accuracy on CMPASS dataset

Effective feature space alignment for samples with same RUL

Scalable network structure validated with LSTM baseline

Abstract

Accurate remaining useful life (RUL) predictions are critical to the safe operation of aero-engines. Currently, the RUL prediction task is mainly a regression paradigm with only mean square error as the loss function and lacks research on feature space structure, the latter of which has shown excellent performance in a large number of studies. This paper develops a multi-granularity supervised contrastive (MGSC) framework from plain intuition that samples with the same RUL label should be aligned in the feature space, and address the problems of too large minibatch size and unbalanced samples in the implementation. The RUL prediction with MGSC is implemented on using the proposed multi-phase training strategy. This paper also demonstrates a simple and scalable basic network structure and validates the proposed MGSC strategy on the CMPASS dataset using a convolutional long short-term memory network as a baseline, which effectively improves the accuracy of RUL prediction.