arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2611.06194cs.LG
收藏

面向数据稀缺资产的早期故障检测的跨资产知识迁移(无目标故障数据)

Cross-Asset Knowledge Transfer for Early Fault Detection of Data-Scarce Assets Without Target Fault Data

Charles F. Dolan School of Business, Fairfield University(费尔菲尔德大学查尔斯·F·多兰商学院);School of Economics and Management, Tiangong University(天津工业大学经济管理学院)

Zekai Wang, Yuxuan Li, Zhangyue Shi

AI总结:

本文针对无目标故障数据的数据稀缺资产早期故障检测问题,提出仅需目标正常数据的ADANN框架,在轴承数据集上取得最优迁移性能。

摘要:

工业设备集群的可靠性管理依赖早期故障预警,但同类资产的生命周期数据存在严重不平衡:少数资产积累了从运行到故障的完整历史数据,而新安装或极少发生故障的资产仅能提供正常工况数据。本文研究在目标资产未观测到任何故障数据时,如何将诊断知识从数据丰富的源资产迁移到数据稀缺的目标资产。我们将跨资产早期故障检测建模为零样本域适应问题,其中“零样本”指不存在目标故障样本,且提出的框架仅需目标资产的正常数据。该框架包含三个部分:(1)统计过程控制步骤,采用指数加权移动平均图对源资产的运行至故障数据进行标注,将人工标注工作量降至仅需验证标记片段;(2)适配域对抗神经网络(ADANN),结合域对抗训练、最大均值差异惩罚与适配分类-域(ACD)损失,该损失将分类器的正常区域锚定到目标自身的正常数据;(3)带预测 horizon 的提前标注方案,用于识别初期故障。在精确分类假设下,理论分析刻画了仅含正常数据的目标对应的域对抗项,以及源故障特征与目标正常特征保持分离的对齐状态。在公开的轴承运行至故障数据集上,ADANN 在四个迁移基线中取得最高的平均 F1 分数,相较于最强基线具有名义上显著的精度提升,且在合成噪声下验证了其鲁棒性。

英文摘要:

Reliability management of industrial fleets depends on early fault warnings, yet lifecycle data across similar assets are highly imbalanced. A few assets accumulate run-to-failure histories, while newly installed or rarely failing assets provide only normal-condition data. This paper asks how diagnostic knowledge can be transferred from a data-rich source asset to a data-scarce target asset when no fault data have been observed on the target. We formulate cross-asset early fault detection as a zero-shot domain adaptation problem, in which zero-shot refers to the absence of target fault samples, and propose a framework that requires only normal data from the target. The framework comprises (1) a statistical process control step that labels the source asset run-to-failure data with an exponentially weighted moving average chart, reducing manual annotation to verifying flagged segments, (2) an Adapted Domain-Adversarial Neural Network (ADANN) that combines domain-adversarial training and a Maximum Mean Discrepancy penalty with an Adapted Classification-Domain (ACD) loss, which anchors the classifier normal region to the target own normal data, and (3) an ahead-of-time labeling scheme with a prediction horizon that targets incipient faults. Under an exact-classification assumption, a theoretical analysis characterizes the domain-adversarial term for a normal-only target and the alignment state in which source fault features remain separated from target normal features. On a public run-to-failure bearing dataset, ADANN attains the highest mean F1-score among four transfer baselines, with a nominally significant precision gain over the strongest baseline, and its robustness is examined under synthetic noise.

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。

↑