

浏览全部资源
扫码关注微信
1.华北电力大学 河北省电力机械装备健康维护与失效预防重点实验室,保定 071003
2.华北电力大学 电力机械装备先进制造与智能运维河北省工程研究中心,保定 071003
3.滨州魏桥园区运营管理有限公司,滨州 256600
DAI Derui, E-mail: daiderui123@163.com
Received:18 May 2025,
Revised:2025-06-24,
Published:15 May 2026
移动端阅览
何玉灵,郑海,代德瑞,等. 基于双通道信息融合和VCC-FuseNet的电机滚动轴承故障诊断[J]. 机械强度,2026,48(5):105-116.
HE Yuling,ZHENG Hai,DAI Derui,et al. Fault diagnosis of motor rolling bearings based on dual-channel information fusion and VCC-FuseNet[J]. Journal of Mechanical Strength,2026,48(5):105-116.
何玉灵,郑海,代德瑞,等. 基于双通道信息融合和VCC-FuseNet的电机滚动轴承故障诊断[J]. 机械强度,2026,48(5):105-116. DOI: 10.16579/j.issn.1001.9669.2026.05.013.
HE Yuling,ZHENG Hai,DAI Derui,et al. Fault diagnosis of motor rolling bearings based on dual-channel information fusion and VCC-FuseNet[J]. Journal of Mechanical Strength,2026,48(5):105-116. DOI: 10.16579/j.issn.1001.9669.2026.05.013.
目的
2
针对电机轴承故障诊断中振动与电流等多源信号协同利用不足、跨模态特征融合深度不够的问题,提出一种基于双通道跨模态注意力融合的故障诊断模型——振动-电流耦合融合网络(Vibration-Current-Coupled Fusion Network
VCC-FuseNet)模型。
方法
2
首先,将一维振动信号和三相电流信号分别重构为格拉姆角场差分图和融合型递归图,实现多源信息的二维图像化统一表达;其次,利用双通道ConvNeXt骨干网络提取深层故障特征,并在跨模态注意力融合模块中引入Transformer机制,实现特征深度交互;最后,在永磁同步发电机(Permanent Magnet Synchronous Generator
PMSG)试验台及变转速轴承数据集上进行验证。
结果
2
结果表明,VCC-FuseNet模型在PMSG轴承故障诊断中的识别准确率达98.75%,在变转速数据集上达96.74%,相比单模态方法分别最高提升了8.39%和7.28%,验证了所提方法在电机轴承诊断中的优越性与鲁棒性。
Objective
2
To address the insufficient collaborative utilization of multi-source signals and shallow cross-modal feature fusion in motor bearing fault diagnosis
a novel model named VCC-FuseNet based on dual-channel cross-modal attention fusion was proposed.
Methods
2
Firstly
vibration signals and three-phase current signals were reconstructed into Gramian angular difference fields (GADF) and fusion-type recurrence plots (RP) for unified two-dimensional visual representation. Secondly
deep fault features were extracted using dual-channel ConvNeXt backbones
and a Transformer-based cross-modal attention fusion module was incorporated to enable deep feature interaction and fusion. Finally
the method was validated on a permanent magnet synchronous generator (PMSG) test platform and a variable-speed bearing dataset.
Results
2
The results demonstrate that VCC-FuseNet achieves recognition accuracies of 98.75% on the PMSG platform and 96.74% on the variable-speed dataset
representing improvements of up to 8.39% and 7.28% over single-modal methods
respectively. VCC-FuseNet effectively facilitates joint diagnosis using vibration and current signals with high accuracy and robustness.
ZHAO X L , JIA M P , LIN M Y . Deep Laplacian Auto-encoder and its application into imbalanced fault diagnosis of rotating machinery [J]. Measurement , 2020 , 152 : 107320 .
郭盼盼 , 张文斌 , 崔奔 , 等 . 基于改进多尺度均值排列熵和参数优化SVM的齿轮箱故障诊断方法 [J]. 机械传动 , 2024 , 48 ( 4 ): 154 - 161 .
GUO Panpan , ZHANG Wenbin , CUI Ben , et al . Gearbox fault diagnosis method based on improved multi-scale mean permutation entropy and parameter optimization SVM [J]. Journal of Mechanical Transmission , 2024 , 48 ( 4 ): 154 - 161 . (In Chinese)
刘光星 , 马一豪 . 基于LSTM-RF的电动钻机绞车齿轮箱故障诊断 [J]. 振动与冲击 , 2024 , 43 ( 21 ): 156 - 162 .
LIU Guangxing , MA Yihao . Fault diagnosis of electric drill winch gearbox based on LSTM-RF [J]. Journal of Vibration and Shock , 2024 , 43 ( 21 ): 156 - 162 . (In Chinese)
阮爱国 , 沈忠明 , 刘发炳 , 等 . 一种单样本风电机组传动链故障诊断方法 [J]. 机械传动 , 2024 , 48 ( 8 ): 161 - 168 .
RUAN Aiguo , SHEN Zhongming , LIU Fabing , et al . A single-sample fault diagnosis method of a wind turbine transmission chain [J]. Journal of Mechanical Transmission , 2024 , 48 ( 8 ): 161 - 168 . (In Chinese)
周旷 , 覃文博 , 孙天宇 . 基于可信多源领域自适应的跨域滚动轴承故障诊断 [J]. 控制与决策 , 2025 , 40 ( 7 ): 2251 - 2260 .
ZHOU Kuang , QIN Wenbo , SUN Tianyu . Cross-domain fault diagnosis of rolling bearings based on trusted multi-source domain adaptation [J]. Control and Decision , 2025 , 40 ( 7 ): 2251 - 2260 . (In Chinese)
戈淳 , 闫灶宇 , 商嘉桐 , 等 . 基于多域信息融合与改进ELM的船舶电机轴承故障诊断 [J]. 中国舰船研究 , 2025 , 20 ( 2 ): 68 - 76 .
GE Chun , YAN Zaoyu , SHANG Jiatong , et al . Fault diagnosis of ship motor bearings based on multi-domain information fusion and improved ELM [J]. Chinese Journal of Ship Research , 2025 , 20 ( 2 ): 68 - 76 . (In Chinese)
吴晨芳 , 杨世锡 , 黄海舟 , 等 . 一种基于改进的LeNet-5模型滚动轴承故障诊断方法研究 [J]. 振动与冲击 , 2021 , 40 ( 12 ): 55 - 61 .
WU Chenfang , YANG Shixi , HUANG Haizhou , et al . An improved fault diagnosis method of rolling bearings based on LeNet-5 [J]. Journal of Vibration and Shock , 2021 , 40 ( 12 ): 55 - 61 . (In Chinese)
丁伟哲 , 冉瑞生 , 胡子成 . 基于多分支CNN与改进级联森林的故障诊断 [J]. 石河子大学学报(自然科学版) , 2025 , 43 ( 2 ): 239 - 248 .
DING Weizhe , RAN Ruisheng , HU Zicheng . Fault diagnosis based on multi-branch CNN with improved cascade forest [J]. Journal of Shihezi University (Natural Science) , 2025 , 43 ( 2 ): 239 - 248 . (In Chinese)
袁九海 , 张氢 , 张建群 , 等 . 基于FDVI和CDDPM的小样本岸桥齿轮箱多类故障诊断 [J]. 振动与冲击 , 2025 , 44 ( 6 ): 306 - 317 .
YUAN Jiuhai , ZHANG Qing , ZHANG Jianqun , et al . Multi-class and small-sample fault diagnosis of shore bridge gearboxes based on FDVI and CDDPM [J]. Journal of Vibration and Shock , 2025 , 44 ( 6 ): 306 - 317 . (In Chinese)
胡孟楠 , 杨喜旺 , 黄晋英 , 等 . 基于MTF-ResDSCNN二维图像的故障诊断方法 [J]. 机械传动 , 2024 , 48 ( 2 ): 170 - 176 .
HU Mengnan , YANG Xiwang , HUANG Jinying , et al . Fault diagnosis method based on MTF-ResDSCNN two-dimensional image [J]. Journal of Mechanical Transmission , 2024 , 48 ( 2 ): 170 - 176 . (In Chinese)
VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C]// Advances in Neural Information Processing Systems . Long Beach : Curran Associates,Inc. , 2017 : 5998 - 6008 .
许一凡 , 雪增红 , 郭军 , 等 . 基于特征增强时间序列和Transformer-BiLSTM的低速重载轴承故障诊断 [J]. 机电工程 , 2025 , 42 ( 9 ): 1659 - 1668 .
XU Yifan , XUE Zenghong , GUO Jun , et al . Fault diagnosis of low-speed overloaded bearings based on FRTS and Transformer-BiLSTM [J]. Journal of Mechanical & Electrical Engineering , 2025 , 42 ( 9 ): 1659 - 1668 . (In Chinese)
刘晨宇 , 李志农 , 熊鹏伟 , 等 . 融合路径聚合网络的Swin Transformer的故障诊断方法研究 [J]. 振动与冲击 , 2024 , 43 ( 18 ): 258 - 266 .
LIU Chenyu , LI Zhinong , XIONG Pengwei , et al . Fault diagnosis method based on Swin Transformer with path aggregation networks [J]. Journal of Vibration and Shock , 2024 , 43 ( 18 ): 258 - 266 . (In Chinese)
WANG B , XIONG Y C , TAN L G . A high-precision aeroengine bearing fault diagnosis based on spatial enhancement convolution and vision transformer [J]. IEEE Transactions on Instrumentation and Measurement , 2025 , 74 : 2501915 .
ZHANG X T , LIU Y S , GONG C , et al . Electric motor bearing fault noise detection via mel-spectrum-based contrastive self-supervised transformer model [J]. IEEE Transactions on Industry Applications , 2024 , 60 ( 6 ): 8755 - 8765 .
刘湘楠 , 赵学智 , 上官文斌 . 强背景噪声振动信号中滚动轴承故障冲击特征提取 [J]. 振动工程学报 , 2021 , 34 ( 1 ): 202 - 210 .
LIU Xiangnan , ZHAO Xuezhi , SHANGGUAN Wenbin . The impact features extraction of rolling bearing under strong background noise [J]. Journal of Vibration Engineering , 2021 , 34 ( 1 ): 202 - 210 . (In Chinese)
周封 , 吕金贵 , 李隆 , 等 . 智能电机故障诊断分析及预警系统设计 [J]. 信息与控制 , 2017 , 46 ( 6 ): 738 - 745 .
ZHOU Feng , LÜ Jingui , LI Long , et al . Design of intelligent fault diagnosis and early warning system of motors [J]. Information and Control , 2017 , 46 ( 6 ): 738 - 745 . (In Chinese)
古玉锋 , 肖子叶 , 燕钢强 , 等 . 基于多传感器融合的异步电动机故障诊断研究 [J]. 机床与液压 , 2025 , 53 ( 7 ): 16 - 23 .
GU Yufeng , XIAO Ziye , YAN Gangqiang , et al . Fault diagnosis of asynchronous motors based on multi-sensor fusion [J]. Machine Tool & Hydraulics , 2025 , 53 ( 7 ): 16 - 23 . (In Chinese)
王进花 , 韩金玉 , 曹洁 , 等 . 基于AM和CNN的多级特征融合的风力发电机轴承故障诊断方法 [J]. 太阳能学报 , 2024 , 45 ( 5 ): 51 - 61 .
WANG Jinhua , HAN Jinyu , CAO Jie , et al . Fault diagnosis method of wind turbine bearing based on AM and CNN multi-level feature fusion [J]. Acta Energiae Solaris Sinica , 2024 , 45 ( 5 ): 51 - 61 . (In Chinese)
WANG Z G , OATES T . Imaging time-series to improve classification and imputation [C]// Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI) . Buenos Aires : IJCAI , 2015 : 3939 - 3945 .
施保华 , 吴婷 , 赵子睿 . 基于递归图和增强残差网络的轴承故障诊断 [J]. 轴承 , 2024 ( 12 ): 87 - 94 .
SHI Baohua , WU Ting , ZHAO Zirui . Fault diagnosis for bearings based on recurrence plot and enhance ResNet [J]. Bearing , 2024 ( 12 ): 87 - 94 . (In Chinese)
张龙 , 胡燕青 , 赵丽娟 , 等 . 采用递归图编码技术与残差网络的滚动轴承故障诊断 [J]. 西安交通大学学报 , 2023 , 57 ( 2 ): 110 - 120 .
ZHANG Long , HU Yanqing , ZHAO Lijuan , et al . Fault diagnosis of rolling bearings using recurrence plot coding technique and residual network [J]. Journal of Xi’an Jiaotong University , 2023 , 57 ( 2 ): 110 - 120 . (In Chinese)
HAN D Z , ZHOU S L , LI K C , et al . Cross-modality co-attention networks for visual question answering [J]. Soft Computing , 2021 , 25 ( 7 ): 5411 - 5421 .
WANG B H , ZHANG J C , WANG W L , et al . Fractional diversity entropy:a vibration signal measure to assist a diffusion model in the fault diagnosis of automotive machines [J]. Electronics , 2024 , 13 ( 16 ): 3155 .
JUNG W , KIM S H , YUN S H , et al . Vibration,acoustic,temperature,and motor current dataset of rotating machine under varying operating conditions for fault diagnosis [J]. Data in Brief , 2023 , 48 : 109049 .
0
Views
19
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621