为解决风电机组运行工况变化导致数据分布差异且标签空间不一致场景下的诊断问题,提出一种基于融合权重领域对抗的部分域适应方法（FWDAN）,用于旋转机械跨工况故障诊断。FWDAN的核心思想是在样本和类别双重层面施加训练权重,以在对抗训练过程中弱化外部类样本的作用,强化对共享类样本的学习,从而促进领域间共享诊断知识的迁移和提高对目标任务的诊断性能。对于样本级权重生成,将标签信息耦合进样本数据中充分挖掘样本的特征表示,进一步根据源域和目标域数据特性差异,应用不同的统计方法生成权重用于辅助模型训练,实现促进模型积极迁移和降低负迁移风险的目的。建立在滚动轴承和齿轮箱数据集上的两个诊断案例的实验结果表明,所提方法相比其他方法具有更高的诊断准确度和更强的泛化能。
Abstract
To address the diagnosis problem in the scenario of varying data distribution and inconsistent label space due to the change of wind turbine working conditions, a partial domain adaptation method （FWDAN） based on fusion weights domain adversarial is proposed for cross-working condition fault diagnosis of rotating machinery. The core idea of FWDAN is to apply the training weights at both the sample and category to weaken the role of outlier category samples in the adversarial training process and enhance the learning of shared category samples, thus facilitating the transfer of shared diagnostic knowledge between domains and improving the diagnostic performance. For sample-level weight generation, the label information is coupled into the sample data to fully explore the feature representation. Further, different statistical methods are applied to generate weights for assisting model training according to the differences between source and target domain data to achieve the purpose of promoting positive model transfer and reducing the risk of negative transfer. The experimental results of two diagnostic cases built on rolling bearing and gearbox datasets show that the proposed method has higher diagnostic accuracy and stronger generalization ability than other methods.
关键词
风电机组 /
故障诊断 /
迁移学习 /
领域适应 /
对抗训练
Key words
wind turbines /
fault diagnosis /
transfer learning /
domain adaptation /
adversarial training
中图分类号：
TH133.33
TH132.425
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 陈雪峰, 郭艳婕. 风电装备振动监测与诊断[M]. 北京: 科学出版社, 2016: 4-5.
CHEN X F, GUO Y J.Vibration monitoring and diagnosis of wind power equipment[M]. Beijing: Science Press, 2016: 4-5.
[2] 齐咏生, 单成成, 高胜利, 等. 基于AEWT-KELM的风电机组轴承故障诊断策略[J]. 太阳能学报, 2022, 43(8): 281-291.
QI Y S, SHAN C C, GAO S L, et al.Fault diagnosis strategy of wind turbines bearing based on AEWT-KELM[J]. Acta energiae solaris sinica, 2022, 43(8): 281-291.
[3] LI X, ZHANG W, DING Q, et al.Multi-Layer domain adaptation method for rolling bearing fault diagnosis[J]. Signal processing, 2019, 157(C): 180-197.
[4] 安文杰, 陈长征, 田淼, 等. 基于迁移学习的风电机组轴承故障诊断研究[J]. 太阳能学报, 2023, 44(6): 367-373.
AN W J, CHEN C Z, TIAN M, et al.Research on bearing fault diagnosis of wind turbines based on transfer learning[J]. Acta energiae solaris sinica, 2023, 44(6): 367-373.
[5] 康守强, 胡明武, 王玉静, 等. 基于特征迁移学习的变工况下滚动轴承故障诊断方法[J]. 中国电机工程学报, 2019, 39(3): 764-772, 955.
KANG S Q, HU M W, WANG Y J, et al.Fault diagnosis method of a rolling bearing under variable working conditions based on feature transfer learning[J]. Proceedings of the CSEE, 2019, 39(3): 764-772, 955.
[6] 雷春丽, 薛林林, 焦孟萱, 等. 结合改进ResNet与迁移学习的风力机滚动轴承故障诊断方法[J]. 太阳能学报, 2023, 44(6): 436-444.
LEI C L, XUE L L, JIAO M X, et al.Fault diagnosis method of wind turbines rolling bearing based on improved ResNet and transfer learning[J]. Acta energiae solaris sinica, 2023, 44(6): 436-444.
[7] DENG M Q, DENG A D, ZHU J, et al.Intelligent fault diagnosis of rotating components in the absence of fault data: a transfer-based approach[J]. Measurement, 2021, 173: 108601.
[8] ZHANG Y C, JI J C, REN Z H, et al.Digital twin-driven partial domain adaptation network for intelligent fault diagnosis of rolling bearing[J]. Reliability engineering & system safety, 2023, 234: 109186.
[9] DENG Y F, HUANG D L, DU S C, et al.A double-layer attention based adversarial network for partial transfer learning in machinery fault diagnosis[J]. Computers in industry, 2021, 127: 103399.
[10] LI X, ZHANG W.Deep learning-based partial domain adaptation method on intelligent machinery fault diagnostics[J]. IEEE transactions on industrial electronics, 2021, 68(5): 4351-4361.
[11] LI W H, CHEN Z Y, HE G L.A novel weighted adversarial transfer network for partial domain fault diagnosis of machinery[J]. IEEE transactions on industrial informatics, 2021, 17(3): 1753-1762.
[12] GANIN Y, USTINOVA E, AJAKAN H, et al. Domain-adversarial training of neural networks[EB/OL].2015: arXiv: 1505.07818. http://arxiv.org/abs/1505.07818.pdf.
[13] WANG Y, SUN X J, LI J, et al.Intelligent fault diagnosis with deep adversarial domain adaptation[J]. IEEE transactions on instrumentation and measurement, 2020, 70: 2503509.
[14] GAO D W, ZHU Y S, YAN K, et al.Joint learning system based on semi-pseudo-label reliability assessment for weak-fault diagnosis with few labels[J]. Mechanical systems and signal processing, 2023, 189: 110089.
[15] LI X Q, JIANG H K, LIU S W, et al.A unified framework incorporating predictive generative denoising autoencoder and deep Coral network for rolling bearing fault diagnosis with unbalanced data[J]. Measurement, 2021, 178: 109345.
基金
江苏省重点研发计划（BE2020034）; 江苏省碳达峰碳中和科技创新专项资金（BA2022214）; 中央高校基本科研业务费（3203002101C3）
PDF(1906 KB)
