Wearing Fault Diagnosis Application of Reciprocating Membrane Pump Based on KPCA

Abstract:

Reciprocating Membrane Pump is the main power output device in the process of slurry pipeline transportation. Wearing fault of Reciprocating Membrane Pump is very difficult found by the tiny change of observation variables at the beginning of the development , observation variable and output are high coupling and strong nonlinear. This paper proposes Wearing Fault Diagnosis Model of Reciprocating Membrane Pump based on KPCA. First, fault detection model of Kernel Principal Component Analysis is established by using the history monitoring data of the normal operation of Reciprocating Membrane Pump and fault signal is detected by using the model of T² and SPE statistics. After fault detection, positioning the wearing location through calculating the contribution of each variable. The experimental results show that the method is effective to the wearing fault diagnosis of Reciprocating Membrane Pump.

• Periodical: Advanced Materials Research (Volumes 971-973)
• Pages: 864-867
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.971-973.864
• Online since: June 2014
• Authors: Yu Chi Pei, Yu Gang Fan*, Yun Liao, Jun Hui Liu
• Keywords: Fault Detection, Kernel Principal Component Analysis, Reciprocating Membrane Pump, Wearing

References

[1] Shengcai JIANG, Binren CHENG and Chunlian WEN. Prospective of the application of coal slurry pipeline transportation technology at metallurgical mine. Hydraulic Coal Mining and Pipeline Transportation, Vol. 2 (2011), pp.1-3.

[2] Guobiao WANG, Zhengjia HE and Xuefeng CHEN et al. Basic research on machinery fault diagnosis-what is the prescription. Journal of Mechanical Engineering, Vol. 49-1 (2013), pp.63-72.

[3] Qi WU, Shuyan WU and Jing LIU. Mechanical fault diagnoses approach based on Fv-SVM . Systems Engineering Theory and Practice, Vol. 30-7 (2010), pp.1266-1271.

[4] Lichen SHI and Zhishan DUAN. Wearing fault diagnosis of Reciprocating Membrane Pump based on chaos and fractal theory. Transactions of The Chinese Society for Agriculture Machinery, Vol. 41-4 (2010), pp.222-226.

[5] Schölkopf B and Smola A, Nonlinear component analysis as a kernel eigenvalue problem. Neural computation. Vol, 10-5(1998) pp.1299-1319.

DOI: 10.1162/089976698300017467

[6] Ping HAN, Renbiao WU and Zhaohua WANG. SAR automatic target recognition based on KPCA criterion. Journal of Electronics and Information Technology, Vol. 25-10 (2003), pp.1297-1301.

[7] Cuimei BO, Shi ZHANG and Guangming ZHANG et al. Fault identification of Tennessee Eastman process based on FS-KPCA. Journal of Chemical Industry and Engineering, Vol. 59-7 (2008), pp.1783-1789.

[8] Jinhai HU, Shousheng XIE and Changqi LUO et al. Fault identification method of kernel principal component analysis Based on contribution plots and its application. Systems Engineering and Electronics, Vol. 30-3 (2009), pp.572-576.