Fault Detection and Isolation for Hydraulic Servo System Based on Adaptive Threshold and SOM Neural Network

Abstract:

A fault detection and diagnosis method for the hydraulic servo system based on adaptive threshold and self-organizing map (SOM) neural network is proposed in this study. The nonlinear, time-varying, fluid-solid coupling properties of the hydraulic servo system are considered. Fault detection is realized based on a two-stage radial basis function (RBF) neural network model. The first-stage RBF neural network is adopted as a fault observer for the hydraulic servo system; the residual error signal is generated by comparing the estimated observer output with the actual measurements. To overcome the drawback of false alarms when the traditional fixed fault threshold is used, an adaptive threshold producer is established by the second-stage RBF neural network. Fault occurrence is detected by comparing the residual error signal with the adaptive threshold. When a system fault is detected, the SOM neural network is employed to implement fault classification and isolation by analyzing the features of the residual error signal. Three types of common faults are simulated to verify the performance and effectiveness of the proposed method. Experimental results demonstrate that the proposed method based on adaptive threshold and SOM neural network is effective in detecting and isolating the failure of the hydraulic servo system.

• Periodical: Applied Mechanics and Materials (Volumes 764-765)
• Pages: 691-697
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.764-765.691
• Online since: May 2015
• Authors: Yu Jie Cheng, Chen Lu, Li Mei Wang, Hong Mei Liu*
• Keywords: Adaptive Threshold, Fault Detection, Fault Isolation, Hydraulic Servo System, SOM Neural Network

References

[1] V. Mahulaka, D. E. Adams and M. Derriso: Derivative free filtering in hydraulic systems for fault identification, Control. Eng. Pract. 19 (2011) 649-657.

DOI: 10.1016/j.conengprac.2011.01.003

[2] H. Yousefi, H. Handroos and A. Soleymani: Application of Differential Evolution in system identification of a servo-hydraulic system with a flexible load, Mechatronics. 18 (2008) 513-528.

DOI: 10.1016/j.mechatronics.2008.03.005

[3] H. M. Liu, C. Lu, W. K. Hou and S. P. Wang: An adaptive threshold based on support vector machine for fault diagnosis, in: Reliability, Maintainability and Safety, 2009. ICRMS 2009. 8th International Conference on, 20-24 July 2009, pp.907-911.

DOI: 10.1109/icrms.2009.5269966

[4] C. C. Lee, P. C. Chung, J. R. Tsai and C. I. Chang: Robust radial basis function neural networks, IEEE T. Syst. Man. Cy. B. 29 (1999) 674-685.

DOI: 10.1109/3477.809023

[5] J. Hu, L. Zhang and W. Liang: Dynamic degradation observer for bearing fault by MTS–SOM system, Mech. Syst. Signal. Pr. 36 (2013) 385-400.

DOI: 10.1016/j.ymssp.2012.10.006

[6] G. Cheng, Y. L. Cheng, L. H. Shen, J. B. Qiu, and S. Zhang: Gear fault identification based on Hilbert–Huang transform and SOM neural network, Measurement. 46 (2013) 1137-1146.

DOI: 10.1016/j.measurement.2012.10.026

[7] D. Aguado, T. Montoya, L. Borras, A. Seco, and J. Ferrer: Using SOM and PCA for analysing and interpreting data from a P-removal SBR, Eng. Appl. Artif. Intel. 21 (2008) 919-930.

DOI: 10.1016/j.engappai.2007.08.001

[8] Z. Feng and T. Xu: Comparison of SOM and PCA-SOM in Fault Diagnosis of Ground-testing Bed, Procedia Engineering. 15 (2011) 1271-1276.

DOI: 10.1016/j.proeng.2011.08.235