Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Krasnikov, Sergej, Meitz, Lukas, Bagheri, Samineh, Heider, Michael, Schöler, Thorsten, Hähner, Jörg
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.13928
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911595730305024
author Krasnikov, Sergej
Meitz, Lukas
Bagheri, Samineh
Heider, Michael
Schöler, Thorsten
Hähner, Jörg
author_facet Krasnikov, Sergej
Meitz, Lukas
Bagheri, Samineh
Heider, Michael
Schöler, Thorsten
Hähner, Jörg
contents Industrial time-series data from real production environments exhibits substantially higher complexity than commonly used benchmark datasets, primarily due to heterogeneous, multi-stage operational processes. As a result, anomaly detection methods validated under simplified conditions often fail to generalize to industrial settings. This work presents an empirical study on a unique dataset collected from fully operational industrial machinery, explicitly capturing pronounced process-induced variability. We evaluate which model classes are capable of capturing this complexity, starting with a classical Isolation Forest baseline and extending to multiple autoencoder architectures. Experimental results show that Isolation Forest is insufficient for modeling the non-periodic, multi-scale dynamics present in the data, whereas autoencoders consistently perform better. Among them, temporal convolutional autoencoders achieve the most robust performance, while recurrent and variational variants require more careful tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13928
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study
Krasnikov, Sergej
Meitz, Lukas
Bagheri, Samineh
Heider, Michael
Schöler, Thorsten
Hähner, Jörg
Machine Learning
Industrial time-series data from real production environments exhibits substantially higher complexity than commonly used benchmark datasets, primarily due to heterogeneous, multi-stage operational processes. As a result, anomaly detection methods validated under simplified conditions often fail to generalize to industrial settings. This work presents an empirical study on a unique dataset collected from fully operational industrial machinery, explicitly capturing pronounced process-induced variability. We evaluate which model classes are capable of capturing this complexity, starting with a classical Isolation Forest baseline and extending to multiple autoencoder architectures. Experimental results show that Isolation Forest is insufficient for modeling the non-periodic, multi-scale dynamics present in the data, whereas autoencoders consistently perform better. Among them, temporal convolutional autoencoders achieve the most robust performance, while recurrent and variational variants require more careful tuning.
title Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study
topic Machine Learning
url https://arxiv.org/abs/2604.13928