A Quantile Regression Approach for Remaining Useful Life Estimation with State Space Models

TL;DR

This paper presents a novel RUL estimation method combining State Space Models with Simultaneous Quantile Regression, achieving superior accuracy and efficiency over traditional models for predictive maintenance in industrial settings.

Contribution

It introduces a new approach integrating SSM and SQR for improved RUL prediction, addressing model uncertainty and enabling multiple quantile estimations.

Findings

Outperforms LSTM, Transformer, Informer in accuracy

Demonstrates computational efficiency of SSM models

Effective in high-stakes industrial applications

Abstract

Predictive Maintenance (PdM) is pivotal in Industry 4.0 and 5.0, proactively enhancing efficiency through accurate equipment Remaining Useful Life (RUL) prediction, thus optimizing maintenance scheduling and reducing unexpected failures and premature interventions. This paper introduces a novel RUL estimation approach leveraging State Space Models (SSM) for efficient long-term sequence modeling. To handle model uncertainty, Simoultaneous Quantile Regression (SQR) is integrated into the SSM, enabling multiple quantile estimations. The proposed method is benchmarked against traditional sequence modelling techniques (LSTM, Transformer, Informer) using the C-MAPSS dataset. Results demonstrate superior accuracy and computational efficiency of SSM models, underscoring their potential for high-stakes industrial applications.