AI 中文总结
针对多相管道泄漏检测模型在流型转换时性能下降的问题，提出MGSB架构，结合流型条件特征融合等技术，在分布偏移下的泄漏检测性能优于基线模型，为工业多相管道鲁棒泄漏检测提供可行路径。
AI 中文摘要
多相管道的泄漏检测模型在部署于与训练阶段不同的流型时往往性能下降。现有评估通常在分布内运行条件下评估性能，掩盖了流型转换（如泡状流到段塞流）引发的失效。我们提出流形门控特征偏差（MGSB），这是一种感知流型的架构，结合了流型条件特征融合、TT-RoughPath编码器和Mean-Teacher一致性正则化，以提升分布偏移下的鲁棒性。在留一组评估中，MGSB的检测F1值为0.930，分布外（OOD）F1值为0.783，在严重特征损坏下显著优于CNN-LSTM和全连接基线。 ablation研究显示，所提出的架构而非训练过程是OOD鲁棒性的主要贡献因素，而马氏距离分析证实留出条件确实为分布外。这些结果表明，显式的感知流型建模是工业多相管道中实现鲁棒、传感器无关的泄漏检测的可行路径。
英文摘要
Leak detection models for multiphase pipelines often degrade when deployed under flow regimes that differ from training. Existing evaluations typically assess performance under in-distribution operating conditions, masking failures caused by regime transitions such as bubble-to-slug flow. We propose the Manifold Gated Signature Bias (MGSB), a regime-aware architecture combining regime-conditioned feature fusion, a TT-RoughPath encoder, and Mean-Teacher consistency regularization to improve robustness under distribution shift. Under leave-one-group-out evaluation, MGSB achieves a detection F1 of 0.930 and an OOD F1 of 0.783, substantially outperforming CNN-LSTM and fully connected baselines under severe feature corruption. Ablations show the proposed architecture, not the training procedure, is the primary contributor to OOD robustness, while Mahalanobis-distance analysis confirms the held-out conditions are genuinely out-of-distribution. These results show that explicit regime-aware modelling is a practical path toward robust, sensor-agnostic leak detection in industrial multiphase pipelines.
