| 37 | 2 | 38 |
| 下载次数 | 被引频次 | 阅读次数 |
Fault prognosis is one of the key techniques for prognosis and health management,and an effective fault feature can improve prediction accuracy and performance. A novel approach of feature extraction for fault prognosis based on fault trend analysis was proposed in this paper. In order to describe the ability of tracking fault growth process,definitions and calculations of fault trackability was developed, and the feature which had the maximum fault trackability was selected for fault prognosis. The vibration data in bearing life tests were used to verify the effectiveness of the method was proposed. The results showed that the trackability of energy entropy for bearing fault growth was the maximum,and it was the best fault feature among selected features root mean square( RMS),kurtosis,new moment and energy entropy. The proposed approach can provide a better strategy for fault feature extraction of bearings in order to improve prediction accuracy.
Abstract：Fault prognosis is one of the key techniques for prognosis and health management,and an effective fault feature can improve prediction accuracy and performance. A novel approach of feature extraction for fault prognosis based on fault trend analysis was proposed in this paper. In order to describe the ability of tracking fault growth process,definitions and calculations of fault trackability was developed, and the feature which had the maximum fault trackability was selected for fault prognosis. The vibration data in bearing life tests were used to verify the effectiveness of the method was proposed. The results showed that the trackability of energy entropy for bearing fault growth was the maximum,and it was the best fault feature among selected features root mean square( RMS),kurtosis,new moment and energy entropy. The proposed approach can provide a better strategy for fault feature extraction of bearings in order to improve prediction accuracy.
[1]Vachtsevanos G,Lewis L,Roemer M,et al.Intelligent Fault Diagnosis and Prognosis for Engineering Systems[M].Hoboken,USA:John Wiley&Sons,Inc,2006:284-285.
[2]Ling X,Hu A J.New Feature Extraction Method for the Detection of Defects in Rolling Element Bearings[J].Journal of Engineering for G as Turbines and Power,2012,134(8):0845011-0845014.
[3]Zhang C L,Li B,Chen B Q,et al.Periodic Impulsive Fault Feature Extraction of Rotating M achinery Using Dual-Tree Rational Dilation Complex Wavelet Transform[J].Journal of Manufacturing Science and Engineering,2014,136(5):051011.
[4]Medjaher K,Camci F,Zerhouni N.Feature Extraction and Evaluation for Health Assessment and Failure Prognostics[C].European Conference of the Prognostics and Health M anagement Society,Dresden,Germany,2012:1-6.
[5]Tan X D,Qiu J,Liu G J,et al.Health-State Evaluation for Aerospace Systems[J].Aircraft Engineering and Aerospace Technology,2013,85(2):115-125.
[6]LüK H,Tan X D,Liu G J,et al.Sensor Selection of Helicopter Transmission Systems Based on Physical M odel and Sensitivity Analysis[J].Chinese Journal of Aeronautics,2014,27(3):643-654.
[7]Klutke G A,Kiessler P C,Wortman M A.A Critical Look at the Bathtub Curve[J].IEEE Transactions on Reliability,2003,52(1):125-129.
[8]Helsel D R,Hirsch R M.Statistical Methods in Water Resources[M].New York,USA:Elsevier,1992:326-327.
[9]Qiu J,Seth B B,Liang S Y,et al.Damage Mechanics Approach for Bearing Liftime Pognostics[J].Mechanical Systems&Signal Processing,2002,16(5):817-829.
[10]Vecer P,Kreidl M,Smid R.Condition Indicators for Gearbox Condition M onitoring Systems[J].Acta Polytechnical,2005,45(6):35-43.
[11]Tan X D,Qiu J,Liu G J,et al.A Fault State Recognition M ethod Based on Wavelet Energy Entropy and Hidden SemiM arkov M odels and Its Applications[J].Mechanical Science&Technology for Aerospace Engineering,2009,28(10):1340-1334.(in Chinese)
[12]Lebold M,Mc Clintic K,Cambell R,et al.Review of Vibration Analysis M ethods for Gearbox Diagnostics and Prognostics[C].Proceedings of the 54th M eeting of the Society for M achinery Failure Prevention Technology,Virginia beach,USA,2000:623-634.
[13]Nooli P.A Versatile and Computationally Efficient Condition Indicator for AH-64 Rotorcraft Gearboxes[D].South Carolina,USA:University of South Carolina,2005:21-22.
基本信息:
DOI：10.19884/j.1672-5220.2017.06.014
中图分类号:TH133.3
引用信息:
[1]谭晓栋,张勇,邱静,等.Feature Extraction Technique for Fault Prognosis Based on Fault Trend Analysis[J].Journal of Donghua University(English Edition),2017,34(06):784-787.DOI:10.19884/j.1672-5220.2017.06.014.
基金信息:
National Natural Science Foundation of China(No.51605482)
2017-12-31
2017-12-31