针对变量预测模型模式识别方法（VPMCD）仅仅包含几种简单数学模型的问题，所建立的预测模型不足以反映特征值之间的复杂关系。极限学习机（ELM）回归模型是一种复杂且被广泛应用的模型，其模型可以反映特征之间的相互关系。因此，结合极限学习机回归模型和VPMCD方法的优点，提出了一种基于极限学习机的变量预测模型（Variable predictive mode based Extreme Learning Machine， VPMELM）模式识别方法，并将该方法应用于滚动轴承劣化状态实验中。实验表明，基于VPMELM的辨识方法可以有效地对滚动轴承的劣化状态进行识别。
Abstract
Aiming at the problem that only four simple mathematical models in the variable predictive mode based class discriminate（VPMCD）method can not reflect complex relationships among eigenvalues,it is found that the extreme learning machine (ELM) regression model,a complex and widely used one,can reflect relationships among eigenvalues.Here,combining with the advantage of ELM regression model and VPMCD method,a variable predictive mode-based extreme learning machine (VPMELM) method was proposed.It was applied to identify the deterioration state of rolling bearings.The test results showed that the identification method based on VPMELM can effectively to identify the deterioration state of rolling bearings.
关键词
极限学习机 /
变量预测模式识别方法 /
VPMELM /
滚动轴承
{{custom_keyword}} /
Key words
extreme learning machine /
variable predictive mode based class discriminate(VPMCD) /
variable predictive mode-based extreme learning machine(VPMELM) /
rolling bearing
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 张进,冯志鹏,褚福磊.滚动轴承故障特征的时间—小波能量谱提取方法[J].机械工程学报,2011,47(17):44-49
[2] Zhang Jin, Feng Zhipeng, Chu Fulei. Extraction of Rolling Bearing Fault Feature Based on Time-wavelet Energy Spectrum [J]. Journal of mechanical engineering, 2011, 47(17):44-49
[3] Fabio Moretti, Stefano Pizzuti, Stefano Panzieri, Mauro Annunziato. Urban traffic flow forecasting through statistical and neural network bagging ensemble hybrid modeling [J]. Neurocomputing, 2015,167(1):3-7
[4] Fotini Simistira, Vassilis Katsouros, George Carayannis. Recognition of online handwritten mathematical formulas using probabilistic SVMs and stochastic context free grammars [J]. Pattern Recognition Letters,2015,53(1):85-92
[5] Yang Yu, Pan Haiyang, Ma Li, et al., A roller bearing fault diagnosis method based on the improved ITD and RRVPMCD [J], Measurement. 2014,55:255-264.
[6] Yang Yu, Wang Huanhuan, Cheng Junsheng. A fault diagnosis approach for roller bearing based on VPMCD under variable speed condition [J]. Measurement. 2013,46:2306-2312. [7] Bueno A, Garcia P J, Sancho J L. Neural architecture design based on extreme learning machine [J]. Neural Networks, 2013, 48:19-24.
[8] Horata P, Chiewchanwattana S, Sunat K. Robust extreme learning machine [J]. Neurocomputing, 2013, 102:31-44
[9] Huang G B, Zhou H M, Ding X J, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems Man and Cybernetic Part B, 2010, 42 (2):513-529
[10] R. Raghuraj, S. Lakshminarayanan. VPMCD: Variable interaction modeling approach for class discrimination in biological systems [J]. FEBS Letters. 2007, 581(5-6):826-830.
[11] R. Raghuraj, S. Lakshminarayanan, Variable predictive model based classification algorithm for effective separation of protein structural classes[J]. Computational Biology and Chemistry. 2008, 32(4):302-306.
[12] Benoit F, Heeswijk M V, Miche Y, et al. Feature selection for nonlinear modes with extreme learning machines[J], Neurocomputing, 2013, 102 :111-124.
[13] Case Western Reserve University Bearing Data Center. Bearing Data Center Fault Test Data.[EB/OL].[2009-10-01].http://www.eecs.case.edu/laboratory/bearing.
[14] 杨宇,李杰,潘海洋等. VPMCD和改进ITD的联合智能诊断方法研究.振动工程学报,2013,26(4):608-616
Yang Yu, Li Jie, Pan Haiyang，et al. A fault diagnosis approach of roller bearing based on VPMCD and improved ITD algorithm [J].Journal of Vibration Engineering, 2013, 26(4): 608-616.
[15] 程军圣,郑近德,杨宇.一种新的非平稳信号分析方法——局部特征尺度分解[J].振动工程学报.2012, 25(2):215-220.
Cheng Junsheng, Zheng Jinde, Yang Yu. A nonstationary signal analysis approach—the local characteristic-scale decomposition method [J]. Journal of Vibration Engineering, 2012, 25(2): 215-220.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(868 KB)
