Feature Selection Method for Hydraulic System Faults Diagnosis Based on GA-PLS

Sheng Li; Pei Lin Zhang; Bing Li

doi:10.4028/www.scientific.net/AMM.44-47.1130

Paper Titles

Fault Diagnosis to Mid-Size Excavator Hydraulic System Based on Fault Tree Analysis
p.1110

Information Entropy of Rolling Bearing Friction Torque as Data Series
p.1115

Dynamic Prediction of Rolling Bearing Friction Torque Using Lyapunov Exponent Method
p.1120

Uncertainty of Rolling Bearing Friction Torque as Data Series Using Grey Bootstrap Method
p.1125

Feature Selection Method for Hydraulic System Faults Diagnosis Based on GA-PLS
p.1130

Multidisciplinary Robust Optimization Design of Multi-Functional Open-Air Hydraulic Drill
p.1135

Design of Guide Rail in a Multi-Functional Open-Air Hydraulic Drill
p.1141

Energy-Saving Design for Hydraulic Cylinder Reciprocating Seal Based on QFD
p.1146

Study on the Micro-Replication Precision of Shark Skin
p.1151

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 44-47Feature Selection Method for Hydraulic System...

Feature Selection Method for Hydraulic System Faults Diagnosis Based on GA-PLS

Abstract:

Feature selection is a key step in hydraulic system fault diagnosis. Some of the collected features are unrelated to classification model, and some are high correlated to other features. These features are harmful for establishing classification model. In order to solve this problem, genetic algorithm-partial least squares (GA-PLS) is proposed for selecting the representative and optimal features. K nearest neighbor algorithm (KNN) is used for diagnosing and classifying hydraulic system faults. For expressing better performance of GA-PLS, the original data of a model engineering hydraulic system is used, and the results of GA-PLS are compared with all feature used and GA. The experimental results show that, the proposed feature method can diagnose and classify hydraulic system faults more efficiently with using fewer features.

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:

1130-1134

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.44-47.1130

Citation:

Cite this paper

Online since:

December 2010

Authors:

Sheng Li, Pei Lin Zhang, Bing Li

Keywords:

Fault Diagnosis, Feature Selection, Genetic Algorithm-Partial Least Squares (GA-PLS), Hydraulic System

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] YANG Er-zhuang: Present Situation and Development Tendency of Hydraulic Technology in 21 Century. Chinese Hydraulics & Pneumatics, Vol 3: 3-4, (2001).

Google Scholar

[2] Leardi R., Lupiañez G: Genetic Algorithms Applied to Feature Selection in PLS Regression: how and when to use them. Chemometrics and Intelligent Laboratory Systems, 41: 195-208, (1998).

DOI: 10.1016/s0169-7439(98)00051-3

Google Scholar

[3] Leardi, R.; Lupianez Gonzalez, A. Chemometrics Intell. Lab. Syst. 1998, 41, 195.

Google Scholar

[4] LeardiR.J. Chemometr., 2000, 14(6): 643-655.

Google Scholar

[5] H. X. Liu, R. S. Zhang, X. J. Yao, et al: Prediction of the Isoelectric Point of an Amino Acid Based on GA-PLS and SVMs. J. Chem. Inf. Comput. Sci. 2004, 44, 161-167.

DOI: 10.1021/ci034173u

Google Scholar

[6] Hoskuldsson: A Variable and Subset Selection in PLS regression. Chemometrics and intelligent laboratory systems, 55, 23-38, (2001).

DOI: 10.1016/s0169-7439(00)00113-1

Google Scholar

[7] Liu S S, Cai C C, Li Z: Approach to Estimation and Prediction for Normal Boiling Point (NBP) of Alkanes Based on A Novel Molecular Distance-Edge (MDE) vector. J Chem. Info Comput Sci, 1998, 38, 387-394.

DOI: 10.1021/ci970109z

Google Scholar

[8] Dinghai Wu, Peilin Zhang, Jianping Fu: Dynamic Simulation of Hydraulic System for Self-Propelled Artillery Based on Power Bond Graph. Advanced Manufacture and Management. 2006, 25(11): 22-24.

Google Scholar