Mechanisms for Integrated Feature Normalization and Remaining Useful Life Estimation Using LSTMs Applied to Hard-Disks

TL;DR

This paper presents a deep learning approach using LSTMs to accurately predict the remaining useful life of hard disks, addressing data challenges and enabling early failure detection in smart systems.

Contribution

It introduces a novel LSTM-based framework with mechanisms for feature normalization and transfer learning for RUL prediction of hard disks.

Findings

Achieved 84.35% average precision in predicting failures within ten days.

Demonstrated effective online prediction with unorganized, imbalanced data.

Validated transfer learning across different hard disk models.

Abstract

With emerging smart communities, improving overall system availability is becoming a major concern. In order to improve the reliability of the components in a system we propose an inference model to predict Remaining Useful Life (RUL) of those components. In this paper we work with components of backend data servers such as hard disks, that are subject to degradation. A Deep Long-Short Term Memory (LSTM) Network is used as the backbone of this fast, data-driven decision framework and dynamically captures the pattern of the incoming data. In the article, we discuss the architecture of the neural network and describe the mechanisms to choose the various hyper-parameters. Further, we describe the challenges faced in extracting effective training sets from highly unorganized and class-imbalanced big data and establish methods for online predictions with extensive data pre-processing, feature extraction and validation through online simulation sets with unknown remaining useful lives of the hard disks. Our algorithm performs especially well in predicting RUL near the critical zone of a device approaching failure. With the proposed approach we are able to predict whether a disk is going to fail in next ten days with an average precision of 0.8435. We also show that the architecture trained on a particular model can be used to predict RUL for devices in different models from same manufacturer through transfer learning.