Automatic Remaining Useful Life Estimation Framework with Embedded Convolutional LSTM as the Backbone

TL;DR

This paper introduces an embedded convolutional LSTM (ECLSTM) model for more accurate Remaining Useful Life prediction by preserving multi-level temporal information, combined with an automated hyperparameter tuning framework, outperforming existing methods.

Contribution

The paper proposes a novel ECLSTM model that embeds multiple 1D convolutions into LSTM to better capture temporal features for RUL estimation, along with an automated hyperparameter optimization framework.

Findings

ECLSTM outperforms state-of-the-art methods on benchmark datasets.

The automated hyperparameter tuning improves model performance and efficiency.

Embedded convolutions enhance temporal information preservation in RUL prediction.

Abstract

An essential task in predictive maintenance is the prediction of the Remaining Useful Life (RUL) through the analysis of multivariate time series. Using the sliding window method, Convolutional Neural Network (CNN) and conventional Recurrent Neural Network (RNN) approaches have produced impressive results on this matter, due to their ability to learn optimized features. However, sequence information is only partially modeled by CNN approaches. Due to the flatten mechanism in conventional RNNs, like Long Short Term Memories (LSTM), the temporal information within the window is not fully preserved. To exploit the multi-level temporal information, many approaches are proposed which combine CNN and RNN models. In this work, we propose a new LSTM variant called embedded convolutional LSTM (ECLSTM). In ECLSTM a group of different 1D convolutions is embedded into the LSTM structure. Through this, the temporal information is preserved between and within windows. Since the hyper-parameters of models require careful tuning, we also propose an automated prediction framework based on the Bayesian optimization with hyperband optimizer, which allows for efficient optimization of the network architecture. Finally, we show the superiority of our proposed ECLSTM approach over the state-of-the-art approaches on several widely used benchmark data sets for RUL Estimation.