Predicting Remaining Useful Life using Time Series Embeddings based on Recurrent Neural Networks

TL;DR

This paper introduces Embed-RUL, a novel RUL estimation method using RNN-based time series embeddings that is robust to noise and missing data, outperforming existing methods on real-world datasets.

Contribution

Embed-RUL is a new approach that does not assume degradation trends and effectively handles noisy, incomplete sensor data for RUL prediction.

Findings

Embed-RUL outperforms state-of-the-art methods on benchmark datasets.

Embeddings effectively distinguish normal and degraded machine states.

The method is robust to noise and missing data in sensor readings.

Abstract

We consider the problem of estimating the remaining useful life (RUL) of a system or a machine from sensor data. Many approaches for RUL estimation based on sensor data make assumptions about how machines degrade. Additionally, sensor data from machines is noisy and often suffers from missing values in many practical settings. We propose Embed-RUL: a novel approach for RUL estimation from sensor data that does not rely on any degradation-trend assumptions, is robust to noise, and handles missing values. Embed-RUL utilizes a sequence-to-sequence model based on Recurrent Neural Networks (RNNs) to generate embeddings for multivariate time series subsequences. The embeddings for normal and degraded machines tend to be different, and are therefore found to be useful for RUL estimation. We show that the embeddings capture the overall pattern in the time series while filtering out the noise, so that the embeddings of two machines with similar operational behavior are close to each other, even when their sensor readings have significant and varying levels of noise content. We perform experiments on publicly available turbofan engine dataset and a proprietary real-world dataset, and demonstrate that Embed-RUL outperforms the previously reported state-of-the-art on several metrics.