Dynamic Anomaly Detection: A Multimodal Spatiotemporal Cross-Fusion Transformer Approach.
Saved in:
| Title: | Dynamic Anomaly Detection: A Multimodal Spatiotemporal Cross-Fusion Transformer Approach. |
|---|---|
| Authors: | Deng, Zefu1 (AUTHOR), Xu, Dongliang2 (AUTHOR) 61265@njnu.edu.cn |
| Source: | Energies (19961073). Jun2026, Vol. 19 Issue 11, p2605. 20p. |
| Subject Terms: | *Fault diagnosis, *Multisensor data fusion, *Outlier detection, *Rotating machinery, *Deep learning, *Transformer models, *Industrial equipment |
| Abstract: | Accurate fault diagnosis is critical for the reliable and secure operation of modern industrial equipment; however, traditional unimodal data representations often fail to fully capture the complex, multi-dimensional characteristics of mechanical faults. To address this limitation, this paper proposes CFNET, a novel multimodal cross-fusion recognition framework designed for the robust fault diagnosis of rotating machinery, including vane pumps and bearings. The proposed framework employs an innovative three-modal input strategy that systematically extracts deep spatial and temporal features using parallel ResNet50 and stacked GRU networks. To break through the limitations of conventional decision-level fusion, CFNET introduces a dynamic mid-layer cross-fusion mechanism driven by adaptive attention weights, effectively enhancing feature interaction depth while preventing redundancy during back-propagation. Furthermore, handcrafted prior features are integrated via skip connections to supplement the deep learning representations. The aggregated multi-dimensional features are ultimately processed by a Transformer architecture for feature sparsification and high-precision classification. Extensive experiments rigorously validate the superiority of the proposed method. On a custom-built industrial vane pump test rig, CFNET achieved a maximum accuracy improvement of 25% over traditional unimodal methods. Furthermore, it demonstrated state-of-the-art performance on two authoritative benchmark datasets, achieving impressive recognition accuracies of 98.12% and 99.92% on the Paderborn University and Case Western Reserve University bearing datasets, respectively. These results underscore the exceptional robustness, efficiency, and industrial applicability of the CFNET framework. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
Be the first to leave a comment!
