摘要
滚动轴承作为风电机组的关键部件,对于整个机组的安全运行起着决定性作用.针对机组滚动轴承故障诊断问题,提出一种节点优化型有向无环图大间隔分布机(O-DAG-LDM)的故障诊断方法.结合DAG多分类扩展性能与LDM二分类器泛化性能的优点,构建一种面向滚动轴承故障诊断的DAG结构扩展式LDM多分类器方法.在DAG-LDM算法框架下,利用优化算法对DAG节点进行优化排列以减小随机排布引起的累积误差,提高LDM故障分类准确率.实验表明,与其他主流智能诊断方法相比,所提出的节点优化型DAG-LDM故障诊断方法具有较高的准确率和更好的抗噪性能.
As a key component, the rolling bearing plays a decisive role in the safe operation of the whole wind turbine.To solve the problem of fault diagnosis in rolling bearings, a fault diagnosis method based on optimized directed acyclic graph combing with large margin distribution machine(O-DAG-LDM) is proposed. Combining the advantages of DAG multi-class scalable features with the generalization performance of LDM two-classifier, a DAG structure extended LDM multiple classifier method for rolling bearing fault diagnosis is constructed. In the framework of the DAG-LDM method,a node optimization algorithm is used to optimize the DAG nodes to reduce the cumulative error caused by random permutation, and improve the accuracy of LDM fault classification. The experiment shows that the proposed O-DAGLDM method for fault diagnosis has higher accuracy and better capability of anti-noise immunity in comparison with other mainstream intelligent diagnosis methods.
引文
[1]Feng Z,Liang M.Complex signal analysis for wind turbine planetary gearbox fault diagnosis via iterative atomic decomposition thresholding[J].J of Sound&Vibration,2014,333(20):5196-5211.
[2]Zheng H,Zhou L.Rolling element bearing fault diagnosis based on support vector machine[C].Int Conf on Consumer Electronics,Communications and Networks Yichang:IEEE,2012:544-547.
[3]Wang D,Zhao Y,Yi C,et al.Sparsity guided empirical wavelet transform for fault diagnosis of rolling element bearings[J].Mechanical Systems&Signal Processing2018,101:292-308.
[4]Gao H,Liang L,Chen X,et al.Feature extraction and recognition for rolling element bearing fault utilizing short-time fourier transform and non-negative matrix factorization[J].Chinese J of Mechanical Engineering2015,28(1):96-105.
[5]He M,He D.Deep learning based approach for bearing fault diagnosis[J].IEEE Trans on Industry Applications2017,53(3):3057-3065.
[6]Wei X C,Tang Y L,Chen T.Research of rolling bearing fault feature extraction based on EMD and choi-williams[J].Advanced Materials Research,2013694-697:1377-1381.
[7]康守强,王玉静,姜义成,等.基于超球球心间距多类支持向量机的滚动轴承故障分类[J].中国电机工程学报,2014,34(14):2319-2325.(Kang S Q,Wang Y J,Jiang Y C,et al Rolling bearing fault classification based on multi-ball spherical distance multi-support vector machine[J].Jof China Electromechanical Engineering,2014,34(14):2319-2325.)
[8]Li J,Li M,Zhang J.Rolling bearing fault diagnosis based on time-delayed feedback monostable stochastic resonance and adaptive minimum entropy deconvolution[J].J of Sound&Vibration,2017,401:139-151.
[9]Zheng J,Pan H,Cheng J.Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines[J]Mechanical Systems&Signal Processing,2017,85:746-759.
[10]Laha S K.Enhancement of fault diagnosis of rolling element bearing using maximum kurtosis fast nonlocal means denoising[J].Measurement,2017,100:157-163.
[11]Shao H,Jiang H,Zhang H,et al.Electric locomotive bearing fault diagnosis using novel convolutional deep belief network[J].IEEE Trans on Industrial Electronics2018,65(3):2727-2736.
[12]Chen Z,Deng S,Chen X,et al.Deep neural networks-based rolling bearing fault diagnosis[J]Microelectronics Reliability,2017,75:327-333.
[13]An X,Zeng H,Li C.Demodulation analysis basedon adaptive local iterative filtering for bearing fault diagnosis[J].Measurement,2016,94:554-560.
[14]Zhou Z H.Large margin distribution learning[C].Proc of the 6th IAPR TC3 Int Workshop.Cham:Springer International Publishing,2014:1-10.
[15]Wen C H,Zhang J,Cheng F Y.Handwritten music symbol classification based on DAG-LDM[J].J of Electronic Measurement and Instrumentation,Instrumentation2016,30(5):764-771.
[16]Platt J C,Cristianini N,Shawe-Taylor J.Large margin DAG s for multiclass classification[C].Proc of Neural Information Processing Systems.Massachusetts:MITPress,2000:547-553.
[17]Vapnik V.The nature of statistical learning theory[M]New York:Springer,2000:988-999.
[18]Cotter A,Srebro N,Shalev-Shwartz S.Learning optimally sparse support vector machines[C].Int Conf on Machine Learning.Atlanta:Springe,2013:266-274.
[19]易辉,宋晓峰,姜斌,等.基于结点优化的决策导向无环图支持向量机及其在故障诊断中的应用[J].自动化学报,2010,36(3):427-432.(Yi H,Song X F,Jiang B,et al.Support vector machine based on nodes refined decision directed acyclic graph and its application to fault diagnosis[J].Acta Automatica Sinica,2010,36(3):427-432.)
[20]Loparo K.Case western reserve university bearing data center[M/OL].http://csegroupscaseedu/bearingdatacent er/.
[21]熊庆,张卫华.基于MF-DFA与PSO优化LSSVM的滚动轴承故障诊断方法[J].振动与冲击,2015,34(11):188-193.(Xiong Q,Zhang W H.Fault diagnosis of rolling bearings based on LS-FVM and PSO optimization of LSSVM[J]J of Vibration and Shock,2015,34(11):188-193.)
[22]石瑞敏,杨兆建.基于复杂网络优化的DAG-SVM在滚动轴承故障诊断中的应用[J].振动与冲击,201534(12):1-6.(Shi R M,Yang Z J.Application of DAG-SVM in fault diagnosis of rolling bearing based on complex network optimization[J].J of Vibration and Shock,2015,34(12):1-6.)
[23]张亚楠,魏武,武林林.基于小波包Shannon熵SVM和遗传算法的电机机械故障诊断[J].电力自动化设备2010,30(1):87-91.(Zhang Y N,Wei W,Wu L L.Fault diagnosis of electrical machinery based on wavelet packet shannon entropy SVMand genetic algorithm[J].Electric Power Automation Equipment,2010,30(1):87-91.)
[24]Tiwari R,Gupta V K,Kankar P K.Bearing fault diagnosis based on multi-scale permutation entropy and adaptive neuro fuzzy classifier[J].J of Vibration&Control,201521(3):461-467.