基于GRU和卷积注意力的改进ACGAN故障诊断方法
收稿日期: 2025-03-03
修回日期: 2025-03-26
录用日期: 2025-05-03
网络出版日期: 2025-07-03
基金资助
国家自然科学基金(62373029)
Improved ACGAN for fault diagnosis based on GRU and convolutional block attention module
Received date: 2025-03-03
Revised date: 2025-03-26
Accepted date: 2025-05-03
Online published: 2025-07-03
Supported by
National Natural Science Foundation of China(62373029)
由于机电伺服系统（EMA）在实际应用中故障数据样本少，会影响故障诊断方法的分类效果。针对故障数据缺失下机电伺服系统的故障诊断问题，设计了一种基于门控循环单元（GRU）和卷积注意力的改进辅助分类生成对抗网络（ACGAN）故障诊断方法，能够稳定地生成各故障类别高质量数据。首先，在ACGAN中引入Wasserstein距离与梯度惩罚，优化损失函数，提升对抗训练稳定性。其次，在生成器和判别器中加入GRU和卷积注意力模块（CBAM），增强网络对关键特征和时序特征的提取能力，克服了卷积网络在处理时序数据时的局限性，提高了生成样本的质量。最后，通过共享分类器与判别器网络参数，利用平衡数据集微调分类器，进一步提高模型的诊断性能。基于搭建的EMA实验台，得到由大量正常数据与少量故障数据组成的不平衡实验数据集，通过对比和消融实验，验证了所提方法的有效性和优越性。
关键词： 机电伺服系统; 门控循环单元; 卷积注意力模块; 故障诊断; 辅助分类生成对抗网络
彭朝琴 , 李奇聪 , 张海尼 , 吴红 , 马云鹏 . 基于GRU和卷积注意力的改进ACGAN故障诊断方法[J]. 航空学报, 2026 , 47(2) : 431929 -431929 . DOI: 10.7527/S1000-6893.2025.31929
Due to the limited number of fault data samples in practical applications of Electro-Mechanical Actuator （EMA）， the classification performance of fault diagnosis methods can be affected. To address the fault diagnosis problem in EMA with missing fault data， an improved Auxiliary Classifier Generative Adversarial Network （ACGAN） fault diagnosis method based on Gated Recurrent Unit （GRU） and Convolutional Block Attention Module （CBAM） is designed， which can stably generate high-quality data for each fault category. First， Wasserstein distance and gradient penalty are introduced into the ACGAN to optimize the loss function and improve the stability of adversarial training. Second， GRU and CBAM are added to both the generator and discriminator to enhance the ability of network to extract key region features and temporal features. This overcomes the limitations of convolutional networks in handling sequential data， and improves the quality of generated samples. Finally， parameter sharing between the classifier and discriminator is implemented， and the balanced dataset is used to fine-tune the classifier and further improve the diagnostic performance of the model. Based on the EMA test rig， an unbalanced dataset consisting of a large amount of normal data and a small amount of fault data is obtained， and the effectiveness and superiority of the proposed method are verified through comparison and ablation experiments.
| [1] | FU J， MARE J C， FU Y L. Modelling and simulation of flight control electromechanical actuators with special focus on model architecting， multidisciplinary effects and power flows［J］. Chinese Journal of Aeronautics， 2017， 30（1）： 47-65. |
| [2] | PENG Z Q， HUANG X C， TANG D Y， et al. Health indicator construction based on multisensors for intelligent remaining useful life prediction： A reinforcement learning approach［J］. IEEE Transactions on Instrumentation and Measurement， 2023， 72： 1-13. |
| [3] | MAZZOLENI M， PREVIDI F， SCANDELLA M， et al. Experimental development of a health monitoring method for electro-mechanical actuators of flight control primary surfaces in more electric aircrafts［J］. IEEE Access， 2019， 7： 153618-153634. |
| [4] | ZENG Y X， ZHANG Y J， YAN X Y， et al. EMA health indicator extraction based on improved multivariate state estimation technique with a composite operator［J］. IEEE Sensors Journal， 2023， 23（17）： 19894-19904. |
| [5] | 刘俊志. 飞机机电系统故障诊断方法研究［D］. 成都： 电子科技大学， 2023： 1-2. |
| LIU J Z. Research on fault diagnosis methods for aircraft electromechanical systems［D］. Chengdu： University of Electronic Science and Technology of China， 2023： 1-2 （in Chinese）. | |
| [6] | DING Y F， JIA M P， MIAO Q H， et al. A novel time-frequency transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearings［J］. Mechanical Systems and Signal Processing， 2022， 168： 108616. |
| [7] | YIN Z Y， HU N Q， CHEN J G， et al. A review of fault diagnosis， prognosis and health management for aircraft electromechanical actuators［J］. IET Electric Power Applications， 2022， 16（11）： 1249-1272. |
| [8] | WANG J Y， ZENG Z G， ZHANG H， et al. An hybrid domain adaptation diagnostic network guided by curriculum pseudo labels for electro-mechanical actuator［J］. Reliability Engineering and System Safety， 2022， 228： 108770. |
| [9] | 崔江， 周凡， 陈永凡， 等. 一种基于GAMF-CNN的航空发电机整流器故障诊断技术［J］. 航空学报， 2024， 45（24）： 330398. |
| CUI J， ZHOU F， CHEN Y F， et al. A technique for aerospace generator rectifier fault diagnosis based on GAMF-CNN［J］. Acta Aeronautica et Astronautica Sinica， 2025， 45（24）： 330398 （in Chinese）. | |
| [10] | HUANG T， ZHANG Q， TANG X A， et al. A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems［J］. Artificial Intelligence Review， 2022， 55（2）： 1289-1315. |
| [11] | ENCALADA-DáVILA á， MOYóN L， TUTIVéN C， et al. Early fault detection in the main bearing of wind turbines based on gated recurrent unit （GRU） neural networks and SCADA data［J］. IEEE/ASME Transactions on Mechatronics， 2022， 27（6）： 5583-5593. |
| [12] | CHEN Z， HE C. Transformer-based unsupervised cross-sensor domain adaptation for electromechanical actuator fault diagnosis［J］. Machines， 2023， 11（1）： 102. |
| [13] | 许伯强， 王彪， 孙丽玲， 等. 基于改进EEMD和强化视觉Transformer模型的风电机组故障预警［J/OL］. 电工技术学报，（2025-03-12）［2025-05-07］. . |
| XU B Q， WANG B， SUN L L， et al. Fault warning of wind turbine based on improved EEMD and enhanced visual transformer model［J/OL］. Transactions of China Electrotechnical Society，（2025-03-12）［2025-05-07］. （in Chinese）. | |
| [14] | GAO H H， ZHANG X R， GAO X J， et al. ICoT-GAN： Integrated convolutional transformer GAN for rolling bearings fault diagnosis under limited data condition［J］. IEEE Transactions on Instrumentation and Measurement， 2023， 72： 1-14. |
| [15] | YANG J S， LIU J， XIE J S， et al. Conditional GAN and 2-D CNN for bearing fault diagnosis with small samples［J］. IEEE Transactions on Instrumentation and Measurement， 2021， 70： 1-12. |
| [16] | 张鹏， 曹曦丹， 王浩， 等. 基于WGAN-GP数据增强的航空发动机引气状态分类方法［J］. 计算机应用与软件， 2025， 42（1）： 373-382. |
| ZHANG P， CAO X D， WANG H， et al. Classification of aero-engine bleed air states based on WGAN-GP data augmentation［J］. Computer Applications and Software， 2025， 42（1）： 373-382 （in Chinese）. | |
| [17] | ZHONG H Y， YU S， TRINH H， et al. Fine-tuning transfer learning based on DCGAN integrated with self-attention and spectral normalization for bearing fault diagnosis［J］. Measurement， 2023， 210： 112421. |
| [18] | SHAO S Y， WANG P， YAN R Q. Generative adversarial networks for data augmentation in machine fault diagnosis［J］. Computers in Industry， 2019， 106： 85-93. |
| [19] | 焦华超， 孙文磊， 王宏伟. 基于WLT-ACGAN的轴承故障数据生成方法［J/OL］. 中国机械工程，（2024-09-12）［2025-05-07］. . |
| JIAO H C， SUN W L， WANG H W. Bearing fault data generation method based on WLT-ACGAN［J/OL］. Chinese Journal of Mechanical Engineering（2024-09-12）［2025-05-07］. （in Chinese）. | |
| [20] | GULRAJANI I， AHMED F， ARJOVSKY M， et al. Improved training of Wasserstein GANs［C］∥Advances in Neural Information Processing Systems 30. Red Hook， NY： Curran Associates， 2017： 5767-5777. |
| [21] | MENG Z， LI Q， SUN D Y， et al. An intelligent fault diagnosis method of small sample bearing based on improved auxiliary classification generative adversarial network［J］. IEEE Sensors Journal， 2022， 22（20）： 19543-19555. |
| [22] | 彭朝琴， 李奇聪， 陈娟， 等. 基于GRU和改进注意力机制的多信息融合的EMA故障诊断方法［J/OL］. 北京航空航天大学学报， （2023-10-25）［2025-05-07］. . |
| PENG Z Q， LI Q C， CHEN J， et al. Fault diagnosis method for EMA based on multi-source signal fusion with GRU and improved attention mechanism［J/OL］. Journal of Beijing University of Aeronautics and Astronautics，（2023-10-25）［2025-05-07］. （in Chinese）. | |
| [23] | WOO S， PARK J， LEE J Y， et al. CBAM： Convolutional block attention module［C］∥Proceedings of the European Conference on Computer Vision. 2018： 3-19. |
| [24] | ZHOU J Q， YUE C X， LIU X L， et al. Classification of tool wear state based on dual attention mechanism network［J］. Robotics and Computer-Integrated Manufacturing， 2023， 83： 102575. |
| [25] | HE J L， XU Y D， PAN Y， et al. Adaptive weighted generative adversarial network with attention mechanism： A transfer data augmentation method for tool wear prediction［J］. Mechanical Systems and Signal Processing， 2024， 212： 111288. |
| [26] | YANG J， GUO Y Q， ZHAO W L. Long short-term memory neural network based fault detection and isolation for electro-mechanical actuators［J］. Neurocomputing， 2019， 360： 85-96. |
| [27] | VANDERMAATEN L， HINTON G. Visualizing data using t-SNE［J］. Journal of Machine Learning Research， 2008， 9： 2579-2605. |
/
| 〈 |
|
〉 |
CJA