← Back to all news
arXiv Machine Learning By Magnus Munk Jensen, Dorte Hammersh{\o}i, Rafa{\l} Wi\'sniewski, Olga Fink

Robust Fault Detection in Mechanical Multimodal Time Series via Self-Supervised Cross-Modal Reconstruction

Read the original on arXiv Machine Learning →

The paper introduces a multimodal anomaly detection framework that uses cross‑modal reconstruction of heterogeneous time‑series sensor data to detect faults in industrial systems. By learning to reconstruct each modality from the others, the method leverages complementary information across sensing channels without requiring explicit temporal alignment or identical sampling rates. An adaptive test‑time thresholding mechanism further improves robustness to distribution shifts caused by changing operating conditions, as demonstrated by strong fault detection performance in three industrial case studies, especially under out‑of‑distribution regimes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
4d ago

Graph Foundation Models Can Become Effective Multivariate Time Series Anomaly Detectors

The paper introduces Gfm4Mtsad, an adaptation framework that enables pretrained Graph Foundation Models (GFMs) to serve as effective multivariate time series anomaly detectors. It addresses challenges such as cross‑modal feature mismatch, unreliable pseudo‑anomaly supervision, and aggregation distortion by proposing three key modules: Structure-and-Information Contract Alignment (SICA), Mechanism-Aligned Pseudo‑Anomaly Screening (MAPS), and Tail‑Gated Evidence Calibration (TGEC). Experiments with two GFM backbones show that Gfm4Mtsad outperforms existing baselines in anomaly detection performance.

By Zhuangyan Hu, Zhuoxuan Liang, Wei Li, Xiaohua Jia, Moustafa Youssef, Sumi Helal
multimodalsafety
More like this →
arXiv Machine Learning
Aug 27

Multi-Modal Anomaly Detection: A Survey

The paper surveys Multi‑Modal Anomaly Detection (MMAD), a field that identifies rare abnormal events across heterogeneous data sources used in safety‑critical domains like industrial inspection and cybersecurity. It formalizes MMAD, outlines five core characteristics, and categorizes existing methods into normality‑assumption and anomaly‑assumption paradigms, highlighting how foundation models are reshaping the field. The survey also compiles benchmarks, evaluation protocols, and identifies open problems for developing robust, adaptive, and interpretable MMAD systems.

By Xudong Mou, Zexin Wu, Chuan Luo, Shiru Chen, Xudong Liu, Chunming Hu, Renyu Yang
multimodalbenchmarkssafety
More like this →