Fault Diagnosis of Gas Turbine Based on Support Vector Machine

摘要：

　　In this paper,a fault diagnosis method based on support vector machine(SVM)is proposed for gas turbine bearing.Firstly,through analysis and processing of vibration signals,the singular value decomposition related EEMD technique is applied to extract feature vectors of the signals.The results are used as the input of SVM classifier model.Then,by using the SVM network intelligence,the turbine bearing operating status and fault type are determined.Experimental results show that the proposed SVM classification method with small sample can accurately and efficiently classify the working status and fault type of the gas turbine bearing,and has some engineering applications values.

关键词： Support Vector Machine Fault Diagnosis Vibration Signal EEMD Singular Value Decomposition Gas Turbine Bearing

作者: Weihong Hu Jiyuan Liu Jianguo Cui Yang Gao Bo Cui Liying Jiang

作者单位: School of Electronic and information Engineering,Shenyang Aerospace University,Shenyang,110136,China Institute of Acoustics,Chinese Academy of Sciences,Beijing,100080,China School of Automation,Shenyang Aerospace University,Shenyang,110136,China Shenyang Aeroengine Research Institute,Shenyang,110015,China

会议类型: 国际会议

会议名称: 第26届中国控制与决策会议(2014 CCDC)

会议地点: 长沙

会议语种:英文

页码: 2853-2856

在线出版日期: 2014-05-31（万方平台首次上网日期，不代表论文的发表时间）