Fault Detection of Carbide Anvil Based on Hurst Exponent and BP Neural Network

Abstract:

This paper proposed a novel diagnosis algorithm based on Hurst exponent and BP neural network to detect carbide anvil fault in synthetic diamond industry. Firstly, a sort of preprocessing algorithm is proposed, which uses the sliding window and energy threshold method to separate the pulse from initial continuous signal. Then, some characteristic parameters which are based on Hurst exponent are extracted from the separated pulse signal. These characteristic parameters are used to construct fault characteristic vectors. Finally, the BP neural network model was established for fault recognition. Experimental results show that the proposed fault detection method has high recognition rate of 96.7%.

• Periodical: Advanced Materials Research (Volumes 805-806)
• Pages: 1881-1886
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.805-806.1881
• Online since: September 2013
• Authors: Li Han*, Bin Chen, Bao Cheng Gao, Zhao Li Yan, Xiao Bin Cheng
• Keywords: Acoustic Emission (AE), BP Neural Network (BPNN), Carbide Anvil, Hurst Exponent

References

[1] Min Wang, SongShun Wang: Cemented carbide anvil and pressure cylinder rupture characteristics, damage factor analysis, and improve the service life of the way. Cemented carbide. Vol. 4 (1994), p.232 (In Chinese).

[2] Kaphle, Mandra R. Tan, Andy: Source location of accustic emission waves for structural health monitoring of bridges. Infrastructure Research Theme Postgraduate Student Conference. Vol. 49 (2009), p.456.

[3] RongSheng Geng: Acoustic emission signal processing and analysis techniques. Nondestructive testing. Vol. 24 (2004), p.23 (In Chinese).

[4] GuangHai Li, ShiFeng Liu and RongSheng Geng: the latest method acoustic emission source identification. Nondestructive testing. Vol. 24 (2002), p.534 (In Chinese).

[5] Fang Zhou, LiYan Han: Multi-sensor information fusion technology were reviewed. Telemetry and remote control. Vol. 27 (2006), p.2 (In Chinese).

[6] XianGang Yin, ShuLin LI, HaiYan Tang, etc: Research on the Fractal Characters of Rock Damage Acoustic Emission Strength. Journal of Rock Mechanics and Engineering. Vol. 25 (2005), p.512 (In Chinese).

[7] ChuanJun Liao, XiaoLi Luo, XueJun Li, etc: Application of Wavelet Packet in the Extraction of Acoustic Emission Signal Characteristics. Journal of Eletronic Measurement and Instrument. Vol. 4 (2008), p.79 (In Chinese).

[8] YuanJie Fu, HanLing Mao, ZhenFeng Huang, etc: Analysis on the Time-frequency Energy of Acoustic Emission Signal Characteristic. Equipment Manufuturing Technology. Vol. 2 (2006), p.27 (In Chinese).

[9] KuanYing Kang: The Establishment, Development of Fractal Theory and its Significance in ScientificMethodology. Scientific Management Research. Vol. 16 (1998), p.53 (In Chinese).

[10] XiaTing Feng: The Application of Acoustic Emission (AE) Technology. Metallurgical Industry Press. 1996, p.362 (In Chinese).

[11] I.M. De la Fuente, L. Martinez, J.M. Aguirregabiria, J. Veguillas: R/S analysis in strange attractors. Fractals. Vol. 6(1998), p.95.

DOI: 10.1142/s0218348x98000110

[12] I.E. Kanounikov, E.V. Antonova, B.V. Kisele, D.R. Belov: Dependence of One of the Fractal Characteristics (Hurst Exponent) of the Human Electroencephalogram on the Cortical Area and Type of Activity. Neural Networks. Vol. 34(1999), p.243.

DOI: 10.1109/ijcnn.1999.831494