面向数据稀缺风电机组故障检测的生成式多领域迁移学习

中文摘要 AI 辅助

正常行为模型已在风电机组可靠故障检测中展现出应用前景，但这类无监督异常检测模型需要充足的无故障训练数据来学习机组的正常运行行为。在数据稀缺场景下，例如新部署的风电机组，这些模型可能会导致故障检测性能不佳。本研究提出一种基于星型生成对抗网络（Star Generative Adversarial Networks, StarGAN）的多领域生成式域映射方法，以提升数据稀缺风电机组的故障检测性能。该模型将数据稀缺机组的SCADA（数据采集与监视控制系统）测量数据映射为多个数据丰富机组的测量数据，通过在转换过程中保留运行状态，数据稀缺域中发生的故障可被数据丰富域中预训练的可靠正常行为模型映射并检测。结合集成融合策略的优势，研究表明在严重数据稀缺场景下，该方法生成的异常分数可与基于大规模代表性数据集训练的模型相媲美；当可用训练数据少于2周时，该方法始终优于基于稀缺数据训练的模型，仅2周累积训练数据即可实现平均异常分数相似度较传统微调方法高16%、较单源域映射方法高10%。作为无监督模型选择的一步，本研究还提出一种代理指标，可在无异常的情况下于训练阶段检测模型性能不佳的情况。本研究揭示了在训练数据不具代表性的场景下，多领域映射用于风电机组故障检测的潜力与挑战。

英文摘要

Normal behavior models have shown promise for reliable fault detection in wind turbines. However, these unsupervised anomaly detection models require sufficient fault-free training data to learn the normal operation behavior of turbines. Under data scarcity, for example in newly deployed wind turbines, these models may result in poor fault detection performance. In this work, we propose a multi-domain generative domain mapping approach based on Star Generative Adversarial Networks (StarGAN) to improve fault detection on data-scarce wind turbines. Our model maps SCADA measurements from a data-scarce turbine to resemble those of several data-rich turbines. By preserving the operational state during translation, faults occurring in a data-scarce domain can be mapped and detected by reliable pre-trained normal behavior models of data-rich domains. Highlighting the benefits of an ensemble fusion strategy, we show that under severe data scarcity our method can produce anomaly scores comparable to models trained on large representative datasets. Our approach can consistently outperform models trained on scarce data when less than 2 weeks of training data are available. With just 2 weeks of accumulated training data, we achieve an anomaly score similarity that is, on average, +16% higher than conventional fine-tuning, and +10% higher than single-source domain mapping. As a step towards unsupervised model selection, we propose a proxy metric that detects poor performance at training time, despite an absence of anomalies. Our study presents the potential and challenges of multi-domain mapping for wind turbine fault detection under unrepresentative training data.

发表机构

• School of Engineering and Computer Science, Bern University of Applied Sciences（伯尔尼应用科学大学工程与计算机科学学院）
• Faculty of Informatics, Università della Svizzera italiana（瑞士意大利语大学信息学院）
• Department of Geoscience and Remote Sensing, Delft University of Technology（代尔夫特理工大学地球科学与遥感系）

机构由 AI 辅助整理，请以论文原文为准。