Autoencoder-based Representation Learning from Heterogeneous Multivariate Time Series Data of Mechatronic Systems

TL;DR

This paper introduces an autoencoder-based unsupervised feature extraction method tailored for heterogeneous multivariate time series data in mechatronic systems, reducing the need for labeled data and improving classification performance.

Contribution

It proposes a novel autoencoder approach that effectively handles heterogeneous data, enabling better unsupervised feature learning for mechatronic system analysis.

Findings

Effective feature extraction from heterogeneous data

Reduced labeled data requirements

Validated on three public datasets

Abstract

Sensor and control data of modern mechatronic systems are often available as heterogeneous time series with different sampling rates and value ranges. Suitable classification and regression methods from the field of supervised machine learning already exist for predictive tasks, for example in the context of condition monitoring, but their performance scales strongly with the number of labeled training data. Their provision is often associated with high effort in the form of person-hours or additional sensors. In this paper, we present a method for unsupervised feature extraction using autoencoder networks that specifically addresses the heterogeneous nature of the database and reduces the amount of labeled training data required compared to existing methods. Three public datasets of mechatronic systems from different application domains are used to validate the results.