Multi-Sensor Prognostics using an Unsupervised Health Index based on LSTM Encoder-Decoder

TL;DR

This paper introduces an unsupervised health index based on LSTM encoder-decoder models for estimating remaining useful life from multi-sensor data, applicable even when degradation patterns are unknown.

Contribution

It presents a novel LSTM-ED based method to compute an unsupervised health index for RUL estimation without assuming specific degradation patterns.

Findings

Effective on Turbofan Engine and Milling Machine datasets.

Significant correlation between HI and maintenance costs in industry data.

Outperforms some existing approaches in RUL estimation.

Abstract

Many approaches for estimation of Remaining Useful Life (RUL) of a machine, using its operational sensor data, make assumptions about how a system degrades or a fault evolves, e.g., exponential degradation. However, in many domains degradation may not follow a pattern. We propose a Long Short Term Memory based Encoder-Decoder (LSTM-ED) scheme to obtain an unsupervised health index (HI) for a system using multi-sensor time-series data. LSTM-ED is trained to reconstruct the time-series corresponding to healthy state of a system. The reconstruction error is used to compute HI which is then used for RUL estimation. We evaluate our approach on publicly available Turbofan Engine and Milling Machine datasets. We also present results on a real-world industry dataset from a pulverizer mill where we find significant correlation between LSTM-ED based HI and maintenance costs.