浏览全部资源
扫码关注微信
1.成都工业学院 智能制造学院,成都 610031
2.四川大学 机械工程学院,成都 610065
张慧云,女,1978年生,陕西渭南人,硕士研究生,副教授;主要研究方向为机械设计与制造;E-mail:149449567@qq.com。
左芳君(通信作者),女,1979年生,陕西渭南人,博士研究生,副教授;主要研究方向为可靠性系统工程、寿命与可靠性;E-mail:448613724@qq.com。
收稿日期:2024-07-24,
修回日期:2024-11-04,
纸质出版日期:2025-06-15
移动端阅览
张慧云,左芳君,李航,等. 基于掩码对比学习的半监督齿轮箱变工况故障诊断[J]. 机械强度,2025,47(6):72-81.
ZHANG Huiyun,ZUO Fangjun,LI Hang,et al. Semi-supervised gearbox fault diagnosis under variable working conditions based on masked contrastive learning[J]. Journal of Mechanical Strength,2025,47(6):72-81.
张慧云,左芳君,李航,等. 基于掩码对比学习的半监督齿轮箱变工况故障诊断[J]. 机械强度,2025,47(6):72-81. DOI: DOI:10.16579/j.issn.1001.9669.2025.06.009.
ZHANG Huiyun,ZUO Fangjun,LI Hang,et al. Semi-supervised gearbox fault diagnosis under variable working conditions based on masked contrastive learning[J]. Journal of Mechanical Strength,2025,47(6):72-81. DOI: DOI:10.16579/j.issn.1001.9669.2025.06.009.
针对实际工程中变工况齿轮箱故障样本标注困难且数据分布差异显著,导致故障诊断模型精度降低的问题,提出了一种基于掩码对比学习的半监督齿轮箱变工况故障诊断方法。首先,利用随机掩码隐藏无标签数据集中部分信息,为每个无标签样本生成两个不同掩码实例;其次,采用动态卷积神经网络对掩码实例动态加权聚合,实现对不同掩码实例判别性特征建模;然后,构建对比学习框架,以最大化不同掩码实例特征间的相似性为优化目标,通过增强掩码视角实例对的特征表示一致性,降低模型对标签的依赖;最后,在微调阶段引入域条件特征校正策略生成目标域特征修正量,并根据最小化域间特征分布差异性度量对齐源域特征和目标域修正特征,显式地减少由于工况变化引起的域间分布差异。通过齿轮箱变工况故障数据集进行验证,证明了所提方法的有效性。
To address the problem that it is difficult to label variable working condition gearbox fault samples and the significant data distribution discrepancies in practical engineering
which result in reduced accuracy of fault diagnosis models
a semi-supervised gearbox fault diagnosis method based on masked contrastive learning is proposed. Firstly
a random mask was used to hide part of the information in the unlabeled dataset
generating two different masked instances for each unlabeled sample. Secondly
a dynamic convolutional neural network was employed to dynamically weight and aggregate the masked instances
enabling discriminative feature modeling of different masked instances. Then
a contrastive learning framework was constructed with the optimization goal of maximizing the similarity between features of different masked instances. By enhancing the consistency of feature representations of masked instance pairs
the model's dependency on labels was reduced. Finally
during the fine-tuning phase
a domain-conditioned feature correction strategy was introduced to generate target domain feature corrections. By aligning source domain features and target domain corrected features according to the metric of minimizing domain feature distribution discrepancies
the method explicitly reduces the domain distribution differences caused by varying working conditions. Validation on a variable working condition gearbox fault dataset demonstrates the effectiveness of the proposed method.
张荣涛 , 陈志高 , 李彬彬 , 等 . 基于深度卷积神经网络模型和XGBoost算法的齿轮箱故障诊断研究 [J]. 机械强度 , 2020 , 42 ( 5 ): 1059 - 1066 .
ZHANG Rongtao , CHEN Zhigao , LI Binbin , et al . Research on gear box fault diagnosis based on dcnn and XGBoost algorithm [J]. Journal of Mechanical Strength , 2020 , 42 ( 5 ): 1059 - 1066 . (In Chinese)
ZHAO X L , YAO J Y , DENG W X , et al . Intelligent fault diagnosis of gearbox under variable working conditions with adaptive intraclass and interclass convolutional neural network [J]. IEEE Transactions on Neural Networks and Learning Systems , 2023 , 34 ( 9 ): 6339 - 6353 .
YU J B , ZHANG Y . Challenges and opportunities of deep learning-based process fault detection and diagnosis:a review [J]. Neural Computing and Applications , 2023 , 35 ( 1 ): 211 - 252 .
ZHI Z , LIU L S , LIU D T , et al . Fault detection of the harmonic reducer based on CNN-LSTM with a novel denoising algorithm [J]. IEEE Sensors Journal , 2022 , 22 ( 3 ): 2572 - 2581 .
张智禹 , 尹爱军 , 谭建 . 融合注意力机制的改进DBN变工况齿轮箱故障诊断方法 [J]. 振动与冲击 , 2021 , 40 ( 14 ): 47 - 52 .
ZHANG Zhiyu , YIN Aijun , TAN Jian . Improved DBN method with attention mechanism for the fault diagnosis of gearboxes under varying working condition [J]. Journal of Vibration and Shock , 2021 , 40 ( 14 ): 47 - 52 . (In Chinese)
周兴康 , 余建波 . 基于深度一维残差卷积自编码网络的齿轮箱故障诊断 [J]. 机械工程学报 , 2020 , 56 ( 7 ): 96 - 108 .
ZHOU Xingkang , YU Jianbo . Gearbox fault diagnosis based on one-dimension residual convolutional auto-encoder [J]. Journal of Mechanical Engineering , 2020 , 56 ( 7 ): 96 - 108 . (In Chinese)
陈仁祥 , 张晓 , 张旭 , 等 . 改进掩码自编码器的滚动轴承半监督故障诊断 [J]. 仪器仪表学报 , 2024 , 45 ( 1 ): 26 - 33 .
CHEN Renxiang , ZHANG Xiao , ZHANG Xu , et al . Improved semi-supervised fault diagnosis of rolling bearings with mask autoencoder [J]. Chinese Journal of Scientific Instrument , 2024 , 45 ( 1 ): 26 - 33 . (In Chinese)
ZHANG T C , CHEN J L , LIU S , et al . Domain discrepancy-guided contrastive feature learning for few-shot industrial fault diagnosis under variable working conditions [J]. IEEE Transactions on Industrial Informatics , 2023 , 19 ( 10 ): 10277 - 10287 .
李东东 , 赵阳 , 赵耀 . 一种变工况下风电机组行星齿轮箱的故障诊断方法 [J]. 电机与控制学报 , 2023 , 27 ( 1 ): 33 - 45 .
LI Dongdong , ZHAO Yang , ZHAO Yao . Fault diagnosis method for wind turbine planetary gearbox under variable working conditions [J]. Electric Machines and Control , 2023 , 27 ( 1 ): 33 - 45 . (In Chinese)
邵海东 , 林健 , 闵志闪 , 等 . 分布外样本干扰下基于改进半监督原型网络的齿轮箱跨域故障诊断 [J]. 机械工程学报 , 2024 , 60 ( 4 ): 212 - 221 .
SHAO Haidong , LIN Jian , MIN Zhishan , et al . Improved semi-supervised prototype network for cross-domain fault diagnosis of gearbox under out-of-distribution interference samples [J]. Journal of Mechanical Engineering , 2024 , 60 ( 4 ): 212 - 221 . (In Chinese)
余浩帅 , 汤宝平 , 张楷 , 等 . 小样本下混合自注意力原型网络的风电齿轮箱故障诊断方法 [J]. 中国机械工程 , 2021 , 32 ( 20 ): 2475 - 2481 .
YU Haoshuai , TANG Baoping , ZHANG Kai , et al . Fault diagnosis method of wind turbine gearboxes mixed with attention prototype networks under small samples [J]. China Mechanical Engineering , 2021 , 32 ( 20 ): 2475 - 2481 . (In Chinese)
LEI Z H , ZHANG P , CHEN Y J , et al . Prior knowledge-embedded meta-transfer learning for few-shot fault diagnosis under variable operating conditions [J]. Mechanical Systems and Signal Processing , 2023 , 200 : 110491 .
TANG T , WANG J , YANG T , et al . An improved prototypical network with L2 prototype correction for few-shot cross-domain fault diagnosis [J]. Measurement , 2023 , 217 : 113065 . (In Chinese)
YAN Z T , LIU H M . SMoCo:a powerful and efficient method based on self-supervised learning for fault diagnosis of aero-engine bearing under limited data [J]. Mathematics , 2022 , 10 ( 15 ): 2796 .
CHEN Y P , DAI X Y , LIU M C , et al . Dynamic convolution:attention over convolution kernels [C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . New York : IEEE , 2020 : 11030 - 11039 .
CHEN X L , HE K M . Exploring simple Siamese representation learning [C]// Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . New York : IEEE , 2021 : 15750 - 15758 .
LI S , LIU C , LIN Q X , et al . Domain conditioned adaptation network [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2020 , 34 ( 7 ): 11386 - 11393 .
JIA S X , WANG J R , ZHANG X , et al . A weighted subdomain adaptation network for partial transfer fault diagnosis of rotating machinery [J]. Entropy , 2021 , 23 ( 4 ): 424 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构