Research on Mechanical Fault Identification Based on Improved SVM

Dong Di Chen; Jia Wei Xiang; Yong Teng Zhong

doi:10.4028/www.scientific.net/AMR.97-101.4257

Paper Titles

An Improved Calibration Method for Optical 3D Measuring System Using Cross Target Based on Bundle Adjustment Algorithm
p.4237

Application of Pressure Test System in Dispenser for Gasoline
p.4243

New Method for Large-Scale Dimensional Metrology Using Laser Tracker System
p.4247

Study on the Technologies of Rapid Three-Dimension Optical Measurement for Welding Deformation of Sheet Materials
p.4251

Research on Mechanical Fault Identification Based on Improved SVM
p.4257

Fabrication of Piezoelectric Thickness-Shear-Mode Acoustic Wave Sensing Device and its Application
p.4261

Evaluation of Measurement Uncertainty for High Precision Gear Involute Profile Measuring System
p.4265

Influence of Specimen Sampling on Internal Residual Stress Test
p.4271

Research on High-Precision Measurement Platform for Optical Aspheric Surface and Corresponding Error Compensation
p.4277

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 97-101Research on Mechanical Fault Identification Based...

Research on Mechanical Fault Identification Based on Improved SVM

Abstract:

Fault diagnosis of machinery is in essence a kind of classification problem. Utilizing the desirable classification ability of support vector machine (SVM) for fewer samples, a novel fault diagnosis method based on improved SVM was proposed. Some statistical features were extracted to reflect the equipment operational conditions and were input into fault classifier to attain the final diagnostic result. Experimental signals of gearbox were analyzed using the present method. The results of improved SVM were compared with those of artificial neural network (ANN). It indicates that the proposed method have better classification ability than that of ANN.