针对以往的故障诊断系统实时性差、学习能力有限而且工程实现难的问题，文章中提出了一种改进的云加端支持向量机（CaTSVM, Cloud and Terminal Support Vector Machines），并将其运用在电机轴承故障诊断中。CaTSVM方法把传统的故障诊断中的特征提取和特征分类两部分分别运行在终端设备和云端设备中，并且将“流水线”(Pipeline)数据处理结构引入到CaTSVM方法中，有效提升了该方法的实时性。在云端建立故障特征模型库(CFML, Cloud Feature Mode Library)，将故障特征选择性的加入模型库，在传统的离线SVM训练中辅以在线SVM训练，选择性的使用更新的故障特征训练SVM模型，进一步提高其分类能力，使诊断系统拥有了“终生学习”的能力。经过大量的实验验证，云加端方法的使用显著提高了诊断的准确率，并且推进了故障诊断的实际工程应用。
Abstract
Aiming at the problems of poor real-time capability, limited learning capability and difficult implementation of the existing fault diagnosis system, an improved Cloud and Terminal Support Vector Machine (CaTSVM) is proposed in this paper and applied to motor Bearing fault diagnosis. The CaTSVM method runs the traditional fault diagnosis feature extraction and feature classification in terminal devices and cloud devices respectively and introduces "Pipeline" data processing structure into the CaTSVM method, which effectively improves the real-time performance of the method. In the cloud, the Cloud Feature Mode Library (CFML) is built, and fault features are selectively added to the model library. In the traditional offline SVM training, online SVM training is used, and the updated fault features are selectively used to train the SVM model , To further improve its classification capabilities, so that diagnostic systems have the "lifelong learning" ability. After a large number of experimental verification, the use of cloud plus end method significantly improves the diagnostic accuracy, and promote the practical application of fault diagnosis.
关键词
云加端 /
SVM /
在线训练 /
特征模型库 /
故障诊断 /
流水线
{{custom_keyword}} /
Key words
Cloud and terminal /
SVM /
On-line training /
Feature mode library /
Fault diagnosis /
Pipeline
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Boudiaf A, Djebala A, Bendjma H, et al. A summary of vibration analysis techniques for fault detection and diagnosis in bearing[C]// International Conference on Modelling, Identification and Control. IEEE, 2017:37-42.
[2] Nandi S, Toliyat H A, Li X. Condition monitoring and fault diagnosis of electrical motors-a review [J]. IEEE Transactions on Energy Conversion, 2005, 20(4):719-729.
[3] 罗毅, 甄立敬. 基于小波包与倒频谱分析的风电机组齿轮箱齿轮裂纹诊断方法[J]. 振动与冲击, 2015, 34(3):210-214.
Luo Yi, Zhen Li-jing. Diagnosis method of turbine gearbox gearcrack based on wavelet packet and cepstrum analysis [J] .Journal of Vibration and Shock, 2015, 34 (3): 210-214.
[4] 郑近德, 程军圣. 改进的希尔伯特-黄变换及其在滚动轴承故障诊断中的应用[J]. 机械工程学报, 2015, 51(1):138-145.
ZHENG Jinde, CHENG Jun-Sheng. Improved Hilbert-Huang Transform and Its Application in Fault Diagnosis of Rolling Bearings [J] .Journal of Mechanical Engineering, 2015, 51 (1): 138-145.
[5] 张晗, 杜朝辉, 方作为,等. 基于稀疏分解理论的航空发动机轴承故障诊断[J]. 机械工程学报, 2015, 51(1):97-105.
Zhang Han, Du Zhaohui, Fang Zuowei, et al. Sparse Decomposition Based Aero-engine’s Bearing Fault Diagnosis [J]. Chinese Journal of Mechanical Engineering, 2015, 51 (1): 97-105.
[6] Ali J B, Fnaiech N, Saidi L, et al. Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals[J]. Applied Acoustics, 2015, 89(3):16-27.
[7] Tian Y, Ma J, Lu C, et al. Rolling bearing fault diagnosis under variable conditions using LMD-SVD and extreme learning machine [J]. Mechanism & Machine Theory, 2015, 90:175-186.
[8] Li Y, Xu M, Wei Y, et al. A new rolling bearing fault diagnosis method based on multiscale permutation entropy and improved support vector machine based binary tree [J]. Measurement, 2016, 77:80-94.
[9] Vapnik V, Cortes C. Support vector networks [J]. Machine Learning, 1995, 20(3):273-297.
[10]丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报, 2011, 40(1):2-10.
Ding Shifei, Qi Bingjuan, Tan Hongyan. An Overview on Theory and Algorithm of Support Vector Machines [J]. Journal of University of Electronic Science and Technology of China, 2011, 40 (1): 2-10.
[11]耿晓强, 唐向红, 陆见光,等. 云加端的嵌套滑动窗口故障信号在线检测方法研究[J]. 计算机应用研究, 2017(12):3717-3720.
Geng Xiaoqiang, Tang Xianghong, Lu Jianguang, et al. Fault data detection method based on nesting sliding window of cloud and terminal [J]. Application Ｒesearch of Computers, 2017(12):3717-3720.
[12]Seryasat O R, Shoorehdeli M A, Honarvar F, et al. Multi-fault diagnosis of ball bearing using FFT, wavelet energy entropy mean and root mean square (RMS)[C]// IEEE International Conference on Systems Man and Cybernetics. IEEE, 2010:4295-4299.
[13]Rai V K, Mohanty A R. Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert–Huang transform [J]. Mechanical Systems & Signal Processing, 2007, 21(6):2607-2615.
[14]Zhang P P, Guo F Y, Department A D. Research of Rolling Bearing Fault Diagnosis Based on PCA-SVM [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2015.
[15]周志华. 机器学习 : = Machine learning [M]. 清华大学出版社, 2016.
Zhou Zhihua. Machine Learning: = Machine Learning [M]. Tsinghua University Press, 2016.
[16] 向阳辉, 张干清, 庞佑霞,等. 结合SVM和改进证据理论的多信息融合故障诊断[J]. 振动与冲击, 2015, 34(13):71-77.
Xiang Yang-hui, Zhang Gan-qing, PANG You-xia, et al. Multi-information fusion fault diagnosis based on SVM and improved evidence theory [J] .Journal of Vibration and Shock, 2015,34 (13): 71-77.
[17]Fernández-Francos D, Martínez-Rego D, Fontenla-Romero O, et al. Automatic bearing fault diagnosis based on one-class ν-SVM [J]. Computers & Industrial Engineering, 2013, 64(1):357-365.
[18]Zhang X, Liang Y, Zhou J, et al. A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM [J]. Measurement, 2015, 69:164-179.
[19]Tian Y, Wang Z, Lu C. Self-adaptive bearing fault diagnosis based on permutation entropy and manifold-based dynamic time warping[J]. Mechanical Systems & Signal Processing, 2016.
[20]Ni J, Zhang C, Yang S X. An Adaptive Approach Based on KPCA and SVM for Real-Time Fault Diagnosis of HVCBs [J]. IEEE Transactions on Power Delivery, 2011, 26(3):1960-1971.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1199 KB)
