paper-with-me

Papers

Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study

2026-04-15 · Sergej Krasnikov, Lukas Meitz, Samineh Bagheri, Michael Heider, Thorsten Schöler, Jörg Hähner arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.13928

Code (0)

등록된 구현이 없습니다.

Tasks

Unsupervised Anomaly Detection

Similar Papers 제목 키워드 기반

Deep Anomaly Detection on Tennessee Eastman Process Data

2023-03-10 · Fabian Hartung, Billy Joe Franks, Tobias Michels, Dennis Wagner 외

This paper provides the first comprehensive evaluation and analysis of modern (deep-learning) unsupervised anomaly detection methods for chemical process data. We focus on the Tennessee Eastman process dataset, which has…

Anomaly DetectionChemical ProcessUnsupervised Anomaly Detection

ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defects

2025-03-06 · Paul J. Krassnig, Dieter P. Gruber

Automatic visual inspection using machine learning-based methods plays a key role in achieving zero-defect policies in industry. Research on anomaly detection approaches is constrained by the availability of datasets tha…

Anomaly DetectionDefect DetectionSelf-Supervised Anomaly DetectionSupervised Anomaly Detection+3

A Survey on RGB, 3D, and Multimodal Approaches for Unsupervised Industrial Anomaly Detection

2024-10-29 · Yuxuan Lin, Yang Chang, Xuan Tong, Jiawen Yu 외

In the advancement of industrial informatization, Unsupervised Industrial Anomaly Detection (UIAD) technology effectively overcomes the scarcity of abnormal samples and significantly enhances the automation and reliabili…

Anomaly Detection

FABLE : Fabric Anomaly Detection Automation Process

2023-06-16 · Simon Thomine, Hichem Snoussi, Mahmoud Soua

Unsupervised anomaly in industry has been a concerning topic and a stepping stone for high performance industrial automation process. The vast majority of industry-oriented methods focus on learning from good samples to …

Anomaly DetectionDefect DetectionDomain GeneralizationSpecificity

Breaking the Bias: Recalibrating the Attention of Industrial Anomaly Detection

2024-12-11 · Xin Chen, Liujuan Cao, Shengchuan Zhang, Xiewu Zheng 외

Due to the scarcity and unpredictable nature of defect samples, industrial anomaly detection (IAD) predominantly employs unsupervised learning. However, all unsupervised IAD methods face a common challenge: the inherent …

Anomaly DetectionComputational EfficiencyQuantizationSensitivity