基于鲁棒半监督分类框架的高炉炼铁过程故障诊断方法
By combining a robust semi-supervised classification framework (RSCF) with supervised and unsupervised learning, the problem of imbalanced fault data in the blast furnace ironmaking process is solved, achieving efficient and accurate fault detection and early warning, and improving the robustness and real-time performance of the model.
CN118916738BActive Publication Date: 2026-07-17ZHEJIANG UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG UNIV
- Filing Date
- 2024-07-13
- Publication Date
- 2026-07-17
Smart Images
Figure CN118916738B_ABST
Abstract
本发明提出了一种基于鲁棒半监督分类框架的高炉炼铁过程故障诊断方法，以提高故障诊断性能。鲁棒半监督分类框架结合了有监督和无监督两部分，能够有效利用有限的高炉标记样本和大量的未标记样本。在有监督部分，为解决标记数据和未标记数据之间的巨大差距，采用了一种名为训练信号退火方法（TSA）的新训练技术以防止过拟合。此外，无监督损失部分通过利用未标记数据来增强模型的平滑性，其通过促使模型在加入对抗干扰前后的输出结果一致来实现。然后，基于幂迭代法和有限差分法设计了一种高效的对抗扰动计算方法。最终，通过对有监督损失和无监督损失的整体训练，实现了更为鲁棒的故障诊断模型。
Need to check novelty before this filing date? Find Prior Art