Cross-modal fault detection improves industrial sensor monitoring robustness
Robust Fault Detection in Mechanical Multimodal Time Series via Self-Supervised Cross-Modal Reconstruction
Machine Learning
Summary
Detecting problems early in machines is important for safety and smooth operation. The authors show a new way to check multiple types of sensor data together, rather than separately, to better spot faults. Their approach learns how different sensor signals relate normally, so unusual changes stand out more clearly. This method also adapts when machines work under different conditions, helping find problems even in new situations. Tests on real industrial data showed it works better than older techniques, especially when conditions change.
What this means in practice
- •For industrial system operators: Improve machine fault alerts by detecting anomalies through combined sensor data, even under varying operational conditions.
- •For maintenance engineers: Enhance early fault identification by using cross-modal sensor analysis that adapts to changes in machine behavior and environment.
Authors
Magnus Munk Jensen, Dorte Hammershøi, Rafał Wiśniewski, Olga Fink
Abstract
Fault detection is essential in industrial systems, enabling early identification of abnormal behaviour and improving safety, reliability, and operational efficiency. Modern systems increasingly rely on heterogeneous sensing modalities that capture complementary aspects of the underlying physical process. However, existing data-driven anomaly detection methods often process each modality independently or use simple feature-level fusion, limiting their ability to exploit cross-modal relationships that characterize normal system behaviour. Their performance also commonly assumes similar training and deployment distributions, whereas real-world operation is affected by changing operating conditions, environmental influences, and system degradation that induce distribution shifts and reduce detection performance, especially in unseen regimes. In this work, we propose a multimodal anomaly detection framework based on cross-modal reconstruction of heterogeneous time-series sensor data. Rather than modeling each modality independently, the framework learns system dynamics by reconstructing each modality from the others, thereby exploiting complementary information across modalities. This integrates information across sensing channels without requiring explicit temporal alignment or identical sampling rates, while improving robustness to sensor noise, missing measurements, and modality-specific disturbances. To address distribution shifts during real-world deployment, anomalies are identified using cross-modal reconstruction error and an adaptive test-time thresholding mechanism that adjusts to changing operating conditions. Experiments on three industrial case studies show strong fault detection performance and substantially improved robustness under out-of-distribution conditions, with the largest gains observed in the most challenging operating regimes.