Technology Category
Machine Learning: Other Foundations of Machine LearningData Mining & Knowledge Management: Anomaly/Outlier DetectionMultiagent Systems: Other Foundations of Multi Agent Systems
Cross-Machine Anomaly Detection Leveraging Pre-trained Time-series Model
🤖 AI Summary
This work addresses the challenge of cross-machine anomaly detection, where machines sharing the same nominal configuration exhibit individual behavioral discrepancies that hinder generalization. To tackle this issue, the authors propose a framework leveraging the pretrained time-series foundation model MOMENT. Their approach employs a random forest classifier to disentangle machine-invariant operational state features from MOMENT embeddings, which are then integrated with an unsupervised anomaly detection module to identify anomalies on target machines. Evaluated on datasets from three industrial machines performing identical processes, the method significantly outperforms baselines using raw signals or direct MOMENT embeddings, demonstrating strong generalization to unseen machines. The key innovation lies in an interpretable feature disentanglement mechanism that effectively extracts domain-invariant representations.
Technology Category
Application Category
📝 Abstract
Achieving resilient and high-quality manufacturing requires reliable data-driven anomaly detection methods that are capable of addressing differences in behaviors among different individual machines which are nominally the same and are executing the same processes. To address the problem of detecting anomalies in a machine using sensory data gathered from different individual machines executing the same procedure, this paper proposes a cross-machine time-series anomaly detection framework that integrates a domain-invariant feature extractor with an unsupervised anomaly detection module. Leveraging the pre-trained foundation model MOMENT, the extractor employs Random Forest Classifiers to disentangle embeddings into machine-related and condition-related features, with the latter serving as representations which are invariant to differences between individual machines. These refined features enable the downstream anomaly detectors to generalize effectively to unseen target machines. Experiments on an industrial dataset collected from three different machines performing nominally the same operation demonstrate that the proposed approach outperforms both the raw-signal-based and MOMENT-embedding feature baselines, confirming its effectiveness in enhancing cross-machine generalization.
Problem
Research questions and friction points this paper is trying to address.
cross-machine anomaly detection
time-series anomaly detection
domain-invariant features
machine behavior variation
industrial anomaly detection
Innovation
Methods, ideas, or system contributions that make the work stand out.
cross-machine anomaly detection
domain-invariant features
pre-trained time-series model
feature disentanglement
unsupervised anomaly detection
🔎 Similar Papers
No similar papers found.
