Fault Diagnosis for Temperature Signal of Turbine Blade Based on LS-SVM

Li Wei Chen; Chen Dong Wang

doi:10.4028/www.scientific.net/AMM.385-386.580

Paper Titles

Fault Diagnoses Technology of Broken-Blade Propeller Induced Shaft Vibration
p.560

Geo-Acoustic Parameters Inversion from Vertical Coherence Characteristic of Ambient Noise
p.567

Mechanical Press Slide Bottom Dead Center Measurement Based on Macro-Micro Adjustment Device
p.571

Performance Monitoring and Analysis of the Process Compressor
p.576

Fault Diagnosis for Temperature Signal of Turbine Blade Based on LS-SVM
p.580

Switching Multisensor Improved Current Statistical Model for Maneuvering Target Tracking
p.585

Research on Intelligent Diagnosis Technology of Transformer Fault
p.589

Fault Diagnosis of Metro Vehicle Auxiliary Inverter Based on PSO-KPCM Algorithm
p.593

Algorithm of Change Points Detection for a Trip Coil
p.597

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 385-386Fault Diagnosis for Temperature Signal of Turbine...

Fault Diagnosis for Temperature Signal of Turbine Blade Based on LS-SVM

Abstract:

This document discusses the support vector machine (SVM) algorithm, then discusses least squares support vector machine (LS-SVM) algorithm, at the same time, the applications of SVM in the fault diagnosis of temperature signal of turbine blade being discussed, the least squares support vector machine algorithm being used in the research of fault diagnosis, being compared with LVQ neural network, experiments result show the operation speed of the least squares support vector machine algorithm is fast, its generalization ability is stronger, SVM can solve small sample learning problems as well as no-linear, high dimension and local minimization problems in the fault diagnosis of temperature signal of turbine blade.

You might also be interested in these eBooks

Applied Scientific Research and Engineering Developments for Industry

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 385-386)

Pages:

580-584

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.385-386.580

Citation:

Cite this paper

Online since:

August 2013

Authors:

Li Wei Chen, Chen Dong Wang

Keywords:

Fault Diagnosis, Gas Turbine, Statistical Learning Theory, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] WU Hong xing, PENG yu, PENG Xi yuan. SVM Multi-classifier Design for Analogous Circuits Fault Diagnosis. Journal of electronic measurement and instrument. 2007, 21(4): 27-31.

Google Scholar

[2] DAI Li xiong, MENG Xian rao. New method of fuzzy fault diagnosis of marine diesel engine. MARINE ENGINEERING. 2009, 31(1): 56-59.

Google Scholar

[3] ZHAO Chun hui, QIAO Lei. Classiifcation of hyperspectral remote sensing image using improved LS-SVM. APPLIED SCIENCE AND TECHNOLOGY. 2008, 35(1): 44-47.

Google Scholar

[4] WAN Hui, WEI yan. An improved least squares support vector machine algorithm. JOURNEL OF CHONG QING NORMAL UNIVERSITY. 2010, 27(4): 69-73.

Google Scholar

[5] Giovanni Cerri, Amhra Giovannelli, Lorenzo Battisti, Roberto Fedrizzi. Advances in effusive cooling techniques of gas turbines[J]. Applied Thermal Engineering, 2007, 27: 692-698.

DOI: 10.1016/j.applthermaleng.2006.10.012

Google Scholar

[6] Je Chin Han. Recent Studies in Turbine Blade Cooling[J]. International Journal of Rotating Machinery, 2004, 10: 443 -457.

DOI: 10.1155/s1023621x04000442

Google Scholar

[7] Davison C R, Birk A M. Development of Fault Diagnosis and Failure Prediction Techniques for Small Gas Turbine Engine[R]. ASME, 2001-GT-548.

DOI: 10.1115/2001-gt-0548

Google Scholar