Mixup Domain Adaptations for Dynamic Remaining Useful Life Predictions

TL;DR

This paper introduces a novel mix-up domain adaptation method for dynamic RUL prediction that effectively aligns source and target domains, outperforming existing approaches in multiple datasets.

Contribution

The paper proposes MDAN, a three-stage mix-up domain adaptation framework with self-supervised learning for improved RUL predictions under domain shifts.

Findings

MDAN outperforms recent methods in 12/12 cases on benchmark datasets.

MDAN achieves significant improvements on bearing machine dataset in 8/12 cases.

The approach effectively aligns source and target domains using mix-up strategies.

Abstract

Remaining Useful Life (RUL) predictions play vital role for asset planning and maintenance leading to many benefits to industries such as reduced downtime, low maintenance costs, etc. Although various efforts have been devoted to study this topic, most existing works are restricted for i.i.d conditions assuming the same condition of the training phase and the deployment phase. This paper proposes a solution to this problem where a mix-up domain adaptation (MDAN) is put forward. MDAN encompasses a three-staged mechanism where the mix-up strategy is not only performed to regularize the source and target domains but also applied to establish an intermediate mix-up domain where the source and target domains are aligned. The self-supervised learning strategy is implemented to prevent the supervision collapse problem. Rigorous evaluations have been performed where MDAN is compared to recently published works for dynamic RUL predictions. MDAN outperforms its counterparts with substantial margins in 12 out of 12 cases. In addition, MDAN is evaluated with the bearing machine dataset where it beats prior art with significant gaps in 8 of 12 cases. Source codes of MDAN are made publicly available in \url{https://github.com/furqon3009/MDAN}.