
浏览全部资源
扫码关注微信
上海理工大学 管理学院,上海 200093
刘超,男,2003年生,江西赣州人,在读硕士研究生;主要研究方向为故障诊断;E-mail:13479918019@163.com。
收稿日期:2025-07-27,
网络出版日期:2025-09-18,
移动端阅览
刘超,刘勤明,叶春明等.基于扩散卷积神经网络的三相感应电动机轴承故障诊断研究[J].机械强度,DOI:10.16579/j.issn.1001.9669.XXXX.XX.001.
LIU Chao,LIU Qinming,YE Chunming,et al.Research on fault diagnosis of three-phase induction motor bearings based on diffusion-convolutional neural network[J].Journal of Mechanical Strength,DOI:10.16579/j.issn.1001.9669.XXXX.XX.001.
刘超,刘勤明,叶春明等.基于扩散卷积神经网络的三相感应电动机轴承故障诊断研究[J].机械强度,DOI:10.16579/j.issn.1001.9669.XXXX.XX.001. DOI:
LIU Chao,LIU Qinming,YE Chunming,et al.Research on fault diagnosis of three-phase induction motor bearings based on diffusion-convolutional neural network[J].Journal of Mechanical Strength,DOI:10.16579/j.issn.1001.9669.XXXX.XX.001. DOI:
目的
2
针对工业领域中三相感应电动机轴承故障诊断中数据稀缺的问题,即实际故障样本不足限制了神经网络模型的有效训练,提出了一种新型扩散卷积神经网络(Diffusion-Convolutional Neural Network
DCNN)模型。DCNN模型融合了去噪扩散概率模型(Denoising Diffusion Probabilistic Model, DDPM)与卷积神经网络(Convolutional Neural Network, CNN)的优势,突破了传统深度学习方法在处理小样本数据时的局限性。
方法
2
首先,DCNN模型利用格拉姆角差场(Gramian Angular Difference Field, GADF)将原始振动信号转换为信息丰富的二维时频图像,以此增强数据特征的表达能力。其次,通过DDPM生成器网络模拟了实际故障数据的分布,生成了具有物理意义的高质量虚拟样本,从而扩充了训练数据集。再次,DCNN模型引入了改进的U-Net结构作为核心去噪模块,通过时间编码与条件嵌入技术,加强了模型对复杂故障特征的识别能力。最后,采用Wasserstein距离减少了生成数据与实际数据间的偏差来优化模型训练,并通过谱归一化增强了模型的稳定性。随后通过系统训练的CNN分类器被用于最终的故障诊断。
结果
2
结果表明,所提DCNN模型性能优于传统生成模型,诊断准确率达到99.95%,较传统方法提升显著,验证了所提模型在处理小样本故障诊断问题时的有效性和优异性。
Objective
2
Addressing the issue of data scarcity in bearing fault diagnosis of three-phase induction motors within industrial settings
where insufficient actual fault samples hinder the effective training of neural network models
a novel diffusion-convolutional neural network (DCNN) model was proposed. The DCNN model integrates the advantages of the denoising diffusion probabilistic model (DDPM) and convolutional neural network (CNN)
thereby overcoming the limitations of conventional deep learning approaches in handling small-sample datasets.
Methods
2
Firstly
the DCNN model employed the Gramian angular difference field (GADF) to transform raw vibration signals into information-rich two-dimensional time-frequency images
enhancing the representational capacity of data features. Secondly
the DDPM generator network simulated the distribution of actual fault data to generate physically meaningful
high-quality synthetic samples
thus augmenting the training dataset. Furthermore
the DCNN incorporated an improved U-Net architecture as the core denoising module; through temporal encoding and conditional embedding techniques
the model's capability to recognize complex fault characteristics was strengthened. Finally
the Wasserstein distance was utilized to minimize the discrepancy between generated and real data to optimize model training
while spectral normalization was applied to enhance model stability. The CNN classifier
trained systematically thereafter
was employed for final fault diagnosis.
Results
2
Results demonstrate that the proposed DCNN model exhibits superior performance surpassing traditional generative models
achieving a diagnostic accuracy of 99.95%
representing a significant improvement over conventional methods. These findings validate the efficacy and excellence of the proposed model in addressing small-sample fault diagnosis challenges.
GAWDE S , PATIL S , KUMAR S , et al . Multi-fault diagnosis of industrial rotating machines using data-driven approach:a review of two decades of research [J]. Engineering Applications of Artific-ial Intelligence , 2023 , 123 : 106139 .
ZHANG J F , ZHANG Q H , HE X , et al . Compound-fault diagnosis of rotating machinery:a fused imbalance learning method [J]. IEEE Transactions on Control Systems Technology , 2021 , 29 ( 4 ): 1462 - 1474 .
HAN T , XIE W Z , PEI Z Y . Semi-supervised adversarial discrim-inative learning approach for intelligent fault diagnosis of wind turbine [J]. Information Sciences , 2023 , 648 : 119496 .
RUAN D W , WANG J , YAN J P , et al . CNN parameter design based on fault signal analysis and its application in bearing fault diagnosis [J]. Advanced Engineering Informatics , 2023 , 55 : 101877 .
PING Z W , WANG D W , ZHANG Y , et al . Few-shot aero-engine bearing fault diagnosis with denoising diffusion based data augmentation [J]. Neurocomputing , 2025 , 622 : 129327 .
YANG X Y , YE T Y , YUAN X F , et al . A novel data augmentation method based on denoising diffusion probabilistic model for fault diagnosis under imbalanced data [J]. IEEE Transactions on Industr-ial Informatics , 2024 , 20 ( 5 ): 7820 - 7831 .
马波 , 蔡伟东 , 赵大力 . 基于GAN样本生成技术的智能诊断方法 [J]. 振动与冲击 , 2020 , 39 ( 18 ): 153 - 160 .
MA Bo , CAI Weidong , ZHAO Dali . Intelligent diagnosis method based on GAN sample generation technology [J]. Journal of Vibration and Shock , 2020 , 39 ( 18 ): 153 - 160 . (In Chinese)
杨星宇 , 宋春生 , 吴啸阳 . 基于多传感器数据融合及GAN的齿轮箱故障诊断方法 [J]. 机械强度 , 2025 , 47 ( 6 ): 37 - 47 .
YANG Xingyu , SONG Chunsheng , WU Xiaoyang . Gearbox fault diagnosis method based on multi-sensor data fusion and GAN [J]. Journal of Mechanical Strength , 2025 , 47 ( 6 ): 37 - 47 . (In Chinese)
梁浩鹏 , 曹洁 , 赵小强 . 基于GADF和PAM-Resnet的旋转机械小样本故障诊断方法 [J]. 控制与决策 , 2023 , 38 ( 12 ): 3465 - 3472 .
LIANG Haopeng , CAO Jie , ZHAO Xiaoqiang . Small sample fault diagnosis method for rotating machinery based on GADF and PAM-Resnet [J]. Control and Decision , 2023 , 38 ( 12 ): 3465 - 3472 . (In Chinese)
强睿儒 , 赵小强 . 基于格拉姆角差场和生成对抗网络的小样本滚动轴承故障诊断方法 [J]. 华南理工大学学报(自然科学版) , 2024 , 52 ( 10 ): 64 - 75 .
QIANG Ruiru , ZHAO Xiaoqiang . A small sample rolling bearing fault diagnosis method based on Gramian angular difference field and generative adversarial network [J]. Journal of South China University of Technology (Natural Science Edition) , 2024 , 52 ( 10 ): 64 - 75 . (In Chinese)
吕哲 , 马波 , 于功也 , 等 . 基于生成对抗网络与个性机理模型的旋转机械故障诊断方法 [J]. 机电工程 , 2022 , 39 ( 9 ): 1203 - 1210 .
LÜ Zhe , MA Bo , YU Gongye , et al . Intelligent fault diagnosis method of rotating machinery based on GAN-MCGM [J]. Journal of Mechanical & Electrical Engineering , 2022 , 39 ( 9 ): 1203 - 1210 . (In Chinese)
文利燕 , 陈金陵 , 姜斌 , 等 . 基于联合对抗域自适应网络的跨工况故障诊断方法 [J]. 控制与决策 , 2025 , 40 ( 5 ): 1503 - 1511 .
WEN Liyan , CHEN Jinling , JIANG Bin , et al . A joint adversarial domain adaptive network based cross working conditions fault diagnosis method [J]. Control and Decision , 2025 , 40 ( 5 ): 1503 - 1511 . (In Chinese)
李天昊 , 李志星 , 王衍学 . 基于小样本下改进ChaosNet的轴承故障诊断 [J]. 组合机床与自动化加工技术 , 2024 ( 2 ): 182 - 185 .
LI Tianhao , LI Zhixing , WANG Yanxue . Research on intelligent diagnosis of bearing faults based on improved ChaosNet with small samples [J]. Modular Machine Tool & Automatic Manufacturing Technique , 2024 ( 2 ): 182 - 185 . (In Chinese)
郝伟 , 丁昆 , 暴长春 , 等 . 小样本下多尺度卷积关系网络的轴承故障诊断方法 [J]. 中国测试 , 2024 , 50 ( 3 ): 160 - 168 .
HAO Wei , DING Kun , BAO Changchun , et al . Bearing fault diagnosis method based on multi-scale convolutional relation network with limited samples [J]. China Measurement & Test , 2024 , 50 ( 3 ): 160 - 168 . (In Chinese)
胡若晖 , 张敏 , 许文鑫 . 基于DCGAN和DANN网络的滚动轴承跨域故障诊断 [J]. 振动与冲击 , 2022 , 41 ( 6 ): 21 - 29 .
HU Ruohui , ZHANG Min , XU Wenxin . Cross-domain fault dia-gnosis of rolling element bearings using DCGAN and DANN [J]. Journal of Vibration and Shock , 2022 , 41 ( 6 ): 21 - 29 . (In Chinese)
黄汉坤 , 岑健 , 赵必创 , 等 . 深度生成式故障诊断模型研究 [J]. 机床与液压 , 2025 , 53 ( 4 ): 205 - 213 .
HUANG Hankun , CEN Jian , ZHAO Bichuang , et al . Research on deep generative fault diagnosis models [J]. Machine Tool & Hydr-aulics , 2025 , 53 ( 4 ): 205 - 213 . (In Chinese)
李东东 , 刘宇航 , 赵阳 , 等 . 基于改进生成对抗网络的风机行星齿轮箱故障诊断方法 [J]. 中国电机工程学报 , 2021 , 41 ( 21 ): 7496 - 7507 .
LI Dongdong , LIU Yuhang , ZHAO Yang , et al . Fault diagnosis method of wind turbine planetary gearbox based on improved generative adversarial network [J]. Proceedings of the CSEE , 2021 , 41 ( 21 ): 7496 - 7507 . (In Chinese)
ZHAO P C , ZHANG W , CAO X S , et al . Denoising diffusion probabilistic model-enabled data augmentation method for intelligent machine fault diagnosis [J]. Engineering Applications of Artificial Intelligence , 2025 , 139 : 109520 .
孙元帅 , 孔繁钦 , 聂晓音 , 等 . 基于图卷积和多传感融合的跨设备故障诊断方法 [J/OL]. 机械强度 : 1 - 10 [ 2025-07-15 ]. https://link.cnki.net/urlid/41.1134.TH.20241230.1108.004 https://link.cnki.net/urlid/41.1134.TH.20241230.1108.004 .
SUN Yuanshuai , KONG Fanqin , NIE Xiaoyin , et al . Cross-device fault diagnosis method based on graph convolution and multi-sensor fusion [J/OL]. Journal of Mechanical Strength : 1 - 10 [ 2025-07-15 ]. https://link.cnki.net/urlid/41.1134.TH.20241230.1108.004. https://link.cnki.net/urlid/41.1134.TH.20241230.1108.004. (In Chinese)
孟昱煜 , 张沣琦 , 火久元 , 等 . 基于改进去噪扩散概率模型的风电机组故障样本生成方法 [J]. 振动与冲击 , 2025 , 44 ( 4 ): 286 - 297 .
MENG Yuyu , ZHANG Fengqi , HUO Jiuyuan , et al . Wind turbine fault sample generation method based on improved denoising diffusion probability model [J]. Journal of Vibration and Shock , 2025 , 44 ( 4 ): 286 - 297 . (In Chinese)
雷亚国 , 贾峰 , 孔德同 , 等 . 大数据下机械智能故障诊断的机遇与挑战 [J]. 机械工程学报 , 2018 , 54 ( 5 ): 94 - 104 .
LEI Yaguo , JIA Feng , KONG Detong , et al . Opportunities and challenges of mechanical intelligent fault diagnosis under big data [J]. Journal of Mechanical Engineering , 2018 , 54 ( 5 ): 94 - 104 . (In Chinese)
HO J , JAIN A N , ABBEEL P . Denoising diffusion probabilistic models [C]// Processings of the Advances in Neural Information Processing Systems 33 (NeurIPS 2020) . New York : IEEE , 2020 : 6840 - 6851 .
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
京公网安备11010802024621