Fault Diagnosis Method Based on Supervised Manifold Learning and SVM

Guang Bin Wang; Xue Jun Li; Zhi Cheng He; Y.Q. Kong

doi:10.4028/www.scientific.net/AMR.216.223

Paper Titles

Digital Integrated Monitoring System of Mine Hoist Based on ARM
p.200

Research on Acoustic Emission Model of Rotor Crack Propagation
p.206

AE Signal of early Rotor Cracks Fault Diagnosis Based on PWVD and SVM
p.212

Welding Residual Stress's Numerical Simulation and Relieving of Guyed Mast Earplate Joint Substructure
p.218

Fault Diagnosis Method Based on Supervised Manifold Learning and SVM
p.223

Subpixel Edge Detection of Autofocus for Micro-Machine Vision System
p.228

Design and Realization Real-time Edge Detection System Based on DM642
p.233

Reconstruction of the Flow Cross-Section Temperature Based on the Radiation Balance Between Infinitesimal
p.238

Application of ANN in Preparing Technology of Magnesium Matrix Composites
p.244

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 216Fault Diagnosis Method Based on Supervised...

Fault Diagnosis Method Based on Supervised Manifold Learning and SVM

Abstract:

In order to better identify the fault of bearing,one new fualt diagnosis method based on supervised Linear local tangent space alignment (SLLTSA) and support vector machine (SVM) is proposed..In this methd, the supervised learning is embedded into the linear local tangent space alignment algorithm,making full use of experience category information for fault feature extraction, and then using linear transformation matrix to fast process the new monitoring data, finally distinguishing fault status of the incremental data by nonlinear SVM algorithm. The experiment result for roller bearing fault diagnosis shows that SLLTSA-SVM method has better diagnosis effect than related unsupervised methods.