一种基于偏差校正式递推融合框架的烧结矿氧化亚铁含量实时检测方法
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG UNIV
- Filing Date
- 2026-06-22
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to achieve real-time and accurate detection of ferrous oxide content in sintered ores. Cross-modal alignment and enhancement methods fail to adequately utilize anomalous information, and the direct coupling mechanism of state-space models cannot explicitly utilize modal inconsistencies, making it difficult to balance real-time performance and robustness.
A bias-corrected recursive fusion framework is adopted. By combining a consistent difference feature alignment enhancement module and a bias correction coupled Mamba module, and combining process variables and infrared image data, cross-modal feature alignment and state correction are achieved, thereby improving the robustness and real-time detection capability of the model.
It improves the accuracy and stability of ferrous oxide content detection in sinter, enhances the sensitivity to anomalies under complex working conditions, and maintains the model's real-time online detection capability.
Smart Images
Figure CN122417201A_ABST