Condition Monitoring and Life Prediction of Rolling Guide Based on Hybrid Intelligence

Hong Li Gao; Xiao Hui Shi; Ling Cong Feng; Li Ping Xu

doi:10.4028/www.scientific.net/AMM.44-47.2045

Paper Titles

A Method Research of Intention Expression Based on Design State
p.2026

Model Test Study on a Single Diagonal-Span Arch Bridge with Curved Beam
p.2031

Electronic Document Management System Oriented Collaborative Design
p.2036

Evaluating the Effectiveness of Applying Phenolic Resin as Thermal Barrier in Buildings during Summer and Winter
p.2040

Condition Monitoring and Life Prediction of Rolling Guide Based on Hybrid Intelligence
p.2045

Design of a Gas Sensor for Hydrazines Based on Photo-Ionization Principle
p.2050

Design, Preparation and Application of Dual-Color HgCdTe Infrared Sensor
p.2055

Early Fire Detection of Large Space Combining Thresholding with Edge Detection Techniques
p.2060

Finite Element Analysis of Different Flexure Springs
p.2065

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 44-47Condition Monitoring and Life Prediction of...

Condition Monitoring and Life Prediction of Rolling Guide Based on Hybrid Intelligence

Abstract:

To evaluate accurately working condition of guide, make maintenance strategy, and predict its residual life in the process of machining operation, a rolling guide rail condition monitoring system based on neural networks was constructed after key factors to guide life were investigated carefully. Eight B&K 4321 three-way vibration sensor were installed on slider surface to monitor the on-line condition of four guides and eight sliders. Vibration signals were processed by wavelet packet decomposition and the most sensitive features to guide life were selected by fuzzy clustering method. The relation between guide life and input vectors including vibration features and machining condition was built by radial basis probabilistic neural networks (RBPNN), which parameters were optimized by genetic algorithm. The experimental results show maximum forecast error is 360 hours and minimum forecast error is 63 hours.

You might also be interested in these eBooks

Frontiers of Manufacturing and Design Science

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 44-47)

Pages:

2045-2049

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.44-47.2045

Citation:

Cite this paper

Online since:

December 2010

Authors:

Hong Li Gao, Xiao Hui Shi, Ling Cong Feng, Li Ping Xu

Keywords:

Guide, Life Prediction, Probabilistic Neural Network (PNN)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] H. L, GAO, M. H, Xu, P. Fu, et al: Chinese Journal of Mechanical Engineering, 42(7) (2006): 227-230, in Chinese.

Google Scholar

[2] S. JAGANNATHAN and S. RAJU G V: Proceedings of the 2000 American Control Conference, Chicago: American Automatic Control Council, vol. 1 (2000): pp.3511-3512.

Google Scholar

[3] R. Huang, L. Xi and X. Li: Mechanical Systems and Signal Processing, vol. 21 (2007), pp.193-207.

Google Scholar

[4] X.Y. Zhao: International Conference on Business Intelligence and Financial Engineering, vol. 3 (2009) pp.648-651.

Google Scholar

[5] L. Guo and J. Chen: Mechanical Science and Technology, vol. 27(2008), pp.1203-1206, in Chinese.

Google Scholar

[6] W.B. Zhao, D.S. Huang and L. Guo: Journal of University of Science and Technology of China, Vol. 33 (2003), No. 6, pp.733-741, in Chinese.

Google Scholar