Method for Feature Extraction Based on Composite Spectrum and Relative Entropy Fusion

doi:10.3901/JME.2017.24.096

Abstract

Abstract: An feature extraction of the key step in prognostic of hydraulic pump. Since vibration signals of hydraulic pump are complex and degradation features are hard to extract, a novel method based upon DCS and relation entropy is proposed. First of all, in order to make reasonable use of feature information, earlier CS is modified by DCT and the DCS algorithm is presented to make fusion of multi-channel vibration signals. And DCS power entropy and singular entropy, which are relatively defined in Shannon entropy and Tsallis entropy, are extracted as features. On this basement, the feature fusion method based on relation entropy is proposed to remain original features performances and improve conciseness. According to max relation entropy criterion and gradual fusion strategy, the four extracted features are fused into a new one, which is considered as degradation feature. Finally, the proposed method is verified by vibration signals sampled from hydraulic pump degradation experiment.

Key words: composite spectrum, degradation feature extraction, information fusion, relative entropy

CLC Number:

TH212
TH213

SUN Jian, LI Hongru. Method for Feature Extraction Based on Composite Spectrum and Relative Entropy Fusion[J]. Journal of Mechanical Engineering, 2017, 53(24): 96-103.

References

[1] DU Jun, WANG Shaoping, ZHANG Haiyan. Layered clustering multi-fault diagnosis for hydraulic piston pump[J]. Mechanical Systems and Signal Processing, 2013, 36(2):487-504.
[2] SUN Jian, LI Hongru, XU Baohua. The morphological undecimated wavelet decomposition-discrete cosine transform composite spectrum fusion algorithm and its application on hydraulic pumps[J]. Measurement, 2016, 94:794-805.
[3] SUN Jian, LI Hongru, XU Baohua. Degradation feature extraction of the hydraulic pump based on high-frequency harmonic local characteristic-scale decomposition sub-signal separation and discrete cosine transform high-order singular entropy[J]. Advances in Mechanical Engineering, 2016, 8(7):1-12.
[4] 许治, 戴宁, 张长龙, 等. 基于迭代变形的多源数据融合技术[J]. 机械工程学报, 2014, 50(7):191-198. XU Zhi, DAI Ning, ZHANG Changlong, et al. Multi-sensor data fusion based on iterative deformation[J]. Journal of Mechanical Engineering, 2014, 50(7):191-198.
[5] CIUONZO D, PAPA G, ROMANO G, et al. One-bit decentralized detection with a rao test for multi-sensor fusion[J]. IEEE Signal Processing Letters, 2013, 20(9):861-864.
[6] SAFIZADEH M S, LATIFI S K. Using multi-sensor data fusion for vibration fault diagnosis of rolling element bearings by accelerometer and load cell[J]. Information fusion, 2014, 18:1-8.
[7] ANGELOV P, YAGER R. Density-based averaging-A new operator for data fusion[J]. Information Science, 2013, 222:164-174.
[8] WEI C M, BLUM R S. Theoretical analysis of correlation-based quality measures for weighted averaging image fusion[J]. Information Fusion, 2010, 11:301-309.
[9] RODGER J A. Toward reducing failure risk in an integrated vehicle health maintenance system:A fuzzy multi-sensor data fusion Kalman filter approach for IVHMS[J]. Expert Systems with Applications, 2012, 39:9821-9835.
[10] YANG W B, LI S Y. A switch-mode information fusion filter based on ISRUKF for autonomous navigation of spacecraft[J]. Information Fusion, 2014, 18:33-42.
[11] REN Y F, KE X Z. Multi-wavelet-basis multi-scale multi-sensor data fusion[J]. Transducer and Micro-system Technologies, 2010, 29(9):77-79.
[12] KERI E, SINHA J K. Vibration-based condition monitoring of rotating machines using a machine composite spectrum[J]. Journal of Sound and Vibration, 2013, 332:2831-2845.
[13] AKILU Y K, SINHA J K, KERI E. An improved data fusion technique for faults diagnosis in rotating machines[J]. Measurement, 2014, 58:27-32.
[14] HUANG Hai, XIAO Liyi, LIU Jiaming. CORDIC-based unified architectures for computation of DCT/IDCT/DST/IDST[J]. Circuits, Systems, and Signal Processing, 2014, 33(3):799-814.
[15] YANG Enhui, YU Xiang, MENG Jin, et al. Transparent composite model for DCT coefficients:design and analysis[J]. IEEE Transactions on Image Processing, 2014, 23(3):1303-1316
[16] CHEN Wensheng, DAI Xiul, PAN Binbin, et al. A novel discriminate criterion based on feature fusion strategy for face recognition[J]. Neurocomputering, 2015,159:67-77.
[17] JAEIK J, SUNG J L, KANG R P, et al. Detecting driver drowsiness using feature-level fusion and user-specific classification[J]. Expert Systems with application, 2014, 41:1139-1152.
[18] 邬再新, 刘涛, 黄东成. 基于信息熵的涡旋压缩机振动信号分析[J]. 振动、测试与诊断. 2014, 34(1):168-172. WU Zaixin, LIU Tao, HUANG Dongcheng. Analysis of vibration signals of scroll compressor based on information entropy[J]. Journal of Vibration, Measurement & Diagnosis, 2014, 34(1):168-172.
[19] FIORI E R, PLASTINO A. A Shannon-Tsallis transformation[J]. Physica A:Statistical Mechanics and Its Application, 2013,392(8):1742-1749.
[20] PETRE C. The predictive power of singular value decomposition entropy for stock market dynamics[J]. Physica A:Statistical Mechanics and Its Application, 2014, 393:571-578.
[21] PENG Weimin, DENG Huifang. Quantum inspired method of feature fusion based on von Neumann entropy[J]. Information Fusion, 2014, 18:9-19.
[22] 李怀俊, 谢小鹏. 基于核特征模糊聚类及模糊关联熵的齿轮故障模式识别[J]. 仪器仪表学报, 2015, 36(4):849-854. LI Huaijun, XIE Xiaopeng. Gear fault pattern recognition based on kernel feature fuzzy clustering and fuzzy association entropy[J]. Chinese Journal of Scientific Instrument, 2015, 36(4):849-854.
[23] ZARINBAL M, ZARANDI M H F, THRKSEN I B. Relative entropy fuzzy c-means clustering[J]. Information Science, 2014, 260:74-97.
[24] 程哲. 直升机传动系统行星轮系损伤建模与故障预测理论及方法研究[D]. 长沙:国防科学技术大学, 2011. CHENG Zhe. Theory and method on damage modeling and prognostics for planetary gear set of helicopter transmission system[D]. Changsha:National University of Defense Technology, 2011.