Autoencoder-based Representation Learning from Heterogeneous Multivariate Time Series Data of Mechatronic Systems
This work addresses the high cost of labeling data for condition monitoring in mechatronic systems, though it appears incremental as it builds on existing autoencoder methods.
The paper tackles the problem of requiring large labeled datasets for predictive tasks in mechatronic systems by proposing an unsupervised autoencoder-based feature extraction method that handles heterogeneous time series data, reducing the need for labeled training data as validated on three public datasets.
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.