Supervised Contrastive Learning based Dual-Mixer Model for Remaining Useful Life Prediction

TL;DR

This paper introduces a novel Dual-Mixer model with a supervised contrastive learning-based training method for more accurate Remaining Useful Life prediction, demonstrating superior performance on the C-MAPSS dataset.

Contribution

It proposes a spatial-temporal homogeneous feature extractor and a contrastive learning-based training method to improve RUL prediction accuracy and robustness.

Findings

Dual-Mixer outperforms existing models on most metrics.

FSGRI training improves RMSE by 7.00% and MAPE by 2.41%.

Method is validated on the C-MAPSS dataset.

Abstract

The problem of the Remaining Useful Life (RUL) prediction, aiming at providing an accurate estimate of the remaining time from the current predicting moment to the complete failure of the device, has gained significant attention from researchers in recent years. In this paper, to overcome the shortcomings of rigid combination for temporal and spatial features in most existing RUL prediction approaches, a spatial-temporal homogeneous feature extractor, named Dual-Mixer model, is firstly proposed. Flexible layer-wise progressive feature fusion is employed to ensure the homogeneity of spatial-temporal features and enhance the prediction accuracy. Secondly, the Feature Space Global Relationship Invariance (FSGRI) training method is introduced based on supervised contrastive learning. This method maintains the consistency of relationships among sample features with their degradation patterns during model training, simplifying the subsequently regression task in the output layer and improving the model's performance in RUL prediction. Finally, the effectiveness of the proposed method is validated through comparisons with other latest research works on the C-MAPSS dataset. The Dual-Mixer model demonstrates superiority across most metrics, while the FSGRI training method shows an average improvement of 7.00% and 2.41% in RMSE and MAPE, respectively, for all baseline models. Our experiments and model code are publicly available at https://github.com/fuen1590/PhmDeepLearningProjects.