基于GAN样本生成技术的智能诊断方法

摘要
图/表
参考文献(24)
相关文章 (8)

全文: PDF (1329 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要基于数据驱动的设备故障智能诊断方法是监测设备健康状况的重要手段，然而实际应用中，难以获取到足量有效的故障数据训练智能诊断模型。鉴于设备健康状态数据充足和现有智能诊断方法故障机理利用不足，提出基于GAN（生成对抗网络，Generative Adversarial Networks）样本生成技术的智能诊断方法。健康状态数据反映了设备个性特征，故障机理反映了设备共性特征，基于两种特征融合，得到故障数据样本，通过对深度卷积神经网络的训练为设备个体构建个性化的智能诊断模型。采用来自CWRU轴承数据和实验台模拟故障数据进行的实验结果表明，该方法相比现有智能诊断方法无需真实故障样本，在变负载条件下实现了很高的诊断准确率，具有较好的变工况迁移能力。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	马波1
	2
	3
	蔡伟东1
	赵大力4

关键词 ： GAN, 样本生成, 故障机理, 智能诊断, 迁移学习

Abstract：Intelligent fault diagnosis based data-driven is an important tool to monitor the health of equipment. However, in practical applications, it is difficult to obtain a sufficient effective fault data training intelligent diagnosis model. In view of the sufficient data of equipment health status and the underutilization of the existing intelligent diagnosis method, an intelligent diagnosis method based on GAN (Generation Adversarial Networks) sample generation technology is proposed. The health status data reflects the characteristics features of the device, and the knowledge of the fault mechanism reflects the common features of the device. Based on the fusion of the two features, the fault samples are obtained. By training the deep convolutional neural network, a diagnostic model is constructed for each device and realized fault diagnosis under different working conditions. The test results from the CWRU bearing data and the simulated fault data of the test bench show that the proposed method can achieve high diagnostic accuracy under variable load conditions and has better variation than the existing intelligent diagnostic methods, and have good working condition transfer ability.

Key words： GAN sample generation fault mechanism intelligent diagnosis transfer learning

收稿日期: 2019-03-25 出版日期: 2020-09-15

引用本文:

马波1,2,3，蔡伟东1，赵大力4. 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 Bo1,2,3，CAI Weidong1，ZHAO Dali4. Intelligent diagnosis method based on GAN sample generation technology. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(18): 153-160.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2020/V39/I18/153

[1] JIA F, LEI Y, LIN J, et al. Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J]. Mechanical Systems & Signal Processing, 2016, 72/73: 303-315.
[2] LI C, CHEN Y, ZHANG W, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems & Signal Processing, 2018, 100: 439-453.
[3] JANSSENS O, SLAVKOVIKJ V, VERVISCH B, et al. Convolutional Neural Network Based Fault Detection for Rotating Machinery[J]. Journal of Sound and Vibration, 2016: 331-345.
[4] 沈长青, 汤盛浩, 江星星, 等. 独立自适应学习率优化深度信念网络在轴承故障诊断中的应用研究[J]. 机械工程学报, 2019, 55(7): 81-88.
SHEN Changqing, TANG Shenghao, JIANG Xingxing, et al. Bearings fault diagnosis based on improved deep belief network by self-individual adaptive learning rate[J]. Journal of Mechanical and Engineering, 2019, 55(7): 81-88.
[5] 李松柏, 康子剑, 陶洁. 基于信息融合及堆栈降噪自编码的齿轮故障诊断[J]. 振动与冲击, 2019, 38(5): 216-221.
LI Songbai, KANG Zijian, TAO Jie. Gear fault diagnosis based on information fusion and stacked de-noising auto-encoder[J]. Journal of Vibration and Shock, 2019, 38(5): 216-221.
[6] 陈超, 沈飞, 严如强. 改进LSSVM迁移学习方法的轴承故障诊断[J]. 仪器仪表学报, 2017, 38(1), 33-40.
CHEN Chao, Shen Fei, Yan Ruqiang. Enhanced least squares support vector machine-based transfer learning strategy for bearing fault diagnosis[J]. Chinese Journal of Scientific Instrument, 2017, 38(1), 33-40.
[7] LU W, LIANG B, CHENG Y, et al. Deep model based domain adaptation for fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2017, 64(3): 2296-2305.
[8] 刘海宁, 宋方臻, 窦仁杰, 等. 小数据条件下基于测地流核函数的域自适应故障诊断方法研究[J]. 振动与冲击, 2018, 37(18): 36-42.
LIU Haining, SONG Fangzhen, DOU Renjie, et al. Domain adaptive fault diagnosis based on the geodesic flow kernel under small data condition[J]. Journal of Vibration and Shock, 2018, 37(18): 36-42.
[9] SONG W, XIANG J, ZHONG Y. A simulation model based fault diagnosis method for bearings[J]. Journal of Intelligent & Fuzzy Systems, 2018, 34(6): 3857-3867.
[10] ZHANG Ming, WANG Duo, Lu Weining, et al. A deep transfer model with wasserstein distance guided multi-adversarial networks for bearing fault diagnosis under different working conditions[J]. IEEE Access, 2019, 7: 65303-65318.
[11] 雷亚国, 杨彬, 杜兆钧, 等. 大数据下机械装备故障的深度迁移诊断方法[J]. 机械工程学报, 2019, 55(7), 1-8.
LEI Yaguo, YANG Bin, DU Zhaojun, et al. Deep transfer diagnosis method for machinery in big data era[J]. Journal of Mechanical and Engineering, 2019, 55(7), 1-8.
[12] 王国彪, 何正嘉, 陈雪峰, 等. 机械故障诊断基础研究“何去何从”[J]. 机械工程学报, 2013, 49(1): 63-72.
WANG Guobiao, HE Zhengjia, CHEN Xuefeng, et al. Basic Research on Machinery Fault Diagnosis: What is the Prescription[J]. Journal of Mechanical and Engineering, 2013, 49(1): 63-72.
[13] 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.
KANG Shouqiang, HU Mingwu, WANG Yujing, et al. Fault diagnosis method of a rolling rearing under variable working conditions based on feature transfer learning[J]. Proceeding of the CSEE, 2019, 39(3): 764-772.
[14] 马波, 高金吉, 江志农. 基于专家思维的多维度故障诊断方法[J]. 机械工程学报, 2017, 53(23): 32-38.
MA Bo, GAO Jinji, JIANG Zhinong. Multi-dimensional Fault Diagnosis Method Based on Expert Thinking[J]. Journal of Mechanical and Engineering, 2017, 53(23): 32-38.
[15] 尚宇炜, 马钊, 彭晨阳, 等. 内嵌专业知识和经验的机器学习方法探索(一): 引导学习的提出与理论基础[J]. 中国电机工程学报, 2017, 37(19): 5560-5571+S5.
SHANG Yuwei, MA Zhao, PENG Chenyang, et al. Study of a novel machine learning method embedding expertise part I：proposals and fundamentals of guiding learning[J]. Proceedings of the CSEE, 2017, 37(19): 5560-5571+S5.
[16] 孙秋野, 胡旌伟, 杨凌霄, 等. 基于GAN技术的自能源混合建模与参数辨识方法[J]. 自动化学报, 2018, 44(5): 901-914.
SUN Qiuye, HU Jingwei, YANG Lingxiao, et al. We-energy hybrid modeling and parameter identication with GAN technology[J]. Acta Automatica Sinica, 2018, 44(5): 901-914.
[17] ZHENG Z, ZHENG L, YANG Y. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro[C]. //Proceedings of 2017 IEEE International Conference on Computer Vision, Los Alamitos: IEEE Computer Society Press, 2017, 3774-3782.
[18] 王坤峰, 左旺孟, 谭营, 等. 生成式对抗网络: 从生成数据到创造智能[J]. 自动化学报, 2018, 44(5): 769-774.
WANG Kunfeng, ZUO Wangmeng, TAN Ying, et al. Generative Adversarial Networks：From Generating Data to Creating Intelligence[J]. Acta Automatica Sinica, 2018, 44(5): 769-774.
[19] ZHANG B, Li W, HAO J, et al. Adversarial adaptive 1-D convolutional neural networks for bearing fault diagnosis under varying working condition[J]. Electrical Engineering and Systems Science, 2018, 3: 1-19.
[20] GOODFELLOW I, JEAN P A, MEHDI M, et al. Generative Adversarial Nets[C]. //Proceedings of the 27th International Conference on Neural Information, 2014, 3: 2672-2680.
[21] ALEC R, LUKE M, SOUMITH C. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. Computer Science, 2015, 2: 1-16.
[22] MEHDI Mirza, SIMON Osindero. Conditional Generative Adversarial Nets[J]. STATISTICS, 2014, 1-7.
[23] SMITH W A, RANDALL R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study[J]. Mechanical Systems & Signal Processing, 2015, 64/65: 100-131.
[24] 胡爱军, 赵军, 孙尚飞, 等. 基于相关峭度共振解调的滚动轴承复合故障特征分离方法[J]. 振动与冲击, 2019, 38(8): 110-116.
HU Aijun, ZHAO Jun, SUN Shangfei, et al. A compound fault feature separation method of rolling bearing based on correlation kurtosis resonance demodulation[J]. Journal of vibration and shock, 2019, 38(8): 110-116.