Recurrent Auto-Encoder Model for Large-Scale Industrial Sensor Signal Analysis

TL;DR

This paper introduces a recurrent auto-encoder with partial reconstruction and a rolling window approach for analyzing large-scale industrial sensor signals, enabling effective feature extraction, visualization, and clustering of system states.

Contribution

It proposes a novel partial reconstruction technique and a rolling window sampling method for improved feature extraction from industrial sensor time series.

Findings

Effective summarization of sensor data into fixed-length vectors.

Enhanced visualization and clustering of industrial system states.

Applicable to large-scale industrial processes for sensor signal analysis.

Abstract

Recurrent auto-encoder model summarises sequential data through an encoder structure into a fixed-length vector and then reconstructs the original sequence through the decoder structure. The summarised vector can be used to represent time series features. In this paper, we propose relaxing the dimensionality of the decoder output so that it performs partial reconstruction. The fixed-length vector therefore represents features in the selected dimensions only. In addition, we propose using rolling fixed window approach to generate training samples from unbounded time series data. The change of time series features over time can be summarised as a smooth trajectory path. The fixed-length vectors are further analysed using additional visualisation and unsupervised clustering techniques. The proposed method can be applied in large-scale industrial processes for sensors signal analysis purpose, where clusters of the vector representations can reflect the operating states of the industrial system.