arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.14766eess.SPcs.AI
收藏

基于时间跨模态知识蒸馏的转移学习用于燃气轮机振动故障检测

Temporal Cross-Modal Knowledge-Distillation-Based Transfer-Learning for Gas Turbine Vibration Fault Detection

K. N. Toosi University of Technology(K. N. 图西工业大学);MECO

Ali Bagheri Nejad, Mahdi Aliyari-Shoorehdeli, Abolfazl Hasanzadeh

AI总结:

本文提出基于时间跨模态知识蒸馏的转移学习框架,解决燃气轮机振动故障检测中时间上下文不足和数据稀缺问题,提升特征分离度和诊断准确性。

摘要:

预防机器故障优于事后修复,尤其对关键资产如燃气轮机而言,早期故障检测(FD)是工业可持续性的核心。然而,现代基于深度学习的FD模型常面临架构复杂性与实时操作约束之间的显著权衡,受限于受限振动信号窗口内的时间上下文不足。为此,本文提出一种基于时间跨模态知识蒸馏的转移学习(TCMKDTL)框架。该框架采用一个“特权”教师模型,训练于包含过去和未来信号上下文的广泛时间窗口,以将基于潜在特征的知识蒸馏到紧凑的学生模型中。为缓解数据稀缺和领域偏移问题,该框架利用基准数据集(如CWRU)上的鲁棒预训练,随后适应目标工业数据。使用实验和工业燃气轮机(MGT-40)数据集的广泛评估表明,TCMKDTL在特征分离度和诊断准确性上优于传统预训练架构。最终,该方法实现了适用于资源受限工业硬件的高性能无监督异常检测。

英文摘要:

Preventing machine failure is inherently superior to reactive remediation, particularly for critical assets like gas turbines, where early fault detection (FD) is a cornerstone of industrial sustainability. However, modern deep learning-based FD models often face a significant trade-off between architectural complexity and real-time operational constraints, often hindered by a lack of temporal context within restricted vibration signal windows. To address these challenges, this study proposes a Temporal Cross-Modal Knowledge-Distillation Transfer-Learning (TCMKDTL) framework. The framework employs a "privileged" teacher model trained on expansive temporal windows incorporating both past and future signal context to distill latent feature-based knowledge into a compact student model. To mitigate issues of data scarcity and domain shift, the framework leverages robust pre-training on benchmark datasets (such as CWRU) followed by adaptation to target industrial data. Extensive evaluation using experimental and industrial gas turbine (MGT-40) datasets demonstrates that TCMKDTL achieves superior feature separability and diagnostic accuracy compared to conventional pre-trained architectures. Ultimately, this approach enables high-performance, unsupervised anomaly detection suitable for deployment on resource-constrained industrial hardware.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑