A HYBRID FEATURE SELECTION SCHEME FOR MACHINE HEALTH ASSESSMENT
The sensitivity of various features that are characteristics of machine health may vary considerably under different operation conditions. Thus it is critical to devise a systematic feature selection scheme that provides a useful and automatic guidance on choosing the most representative features for machine health assessment without human intervention. The paper presents a hybrid feature selection scheme named HFSS based on the combination of Gaussian mixture models (GMM) and a K-means by using clustering learning. The effectiveness of the scheme was evaluated experimentally on bearing test beds, using unsupervised novelty detection approach where a self-organizing map (SOM) neural network was used. The paper focuses on identifying the health level of bearings under the assumption that the predictable abnormal patterns are not available. The proposed scheme has shown to provide the good degradation prediction performance with reduced feature inputs. The experimental results indicate its potential utility as an effective tool for machine health assessment.
Machine Health Assessment Feature Selection Abnormal Detection Self-Organizing Map
Jianbo Yu Lifeng Xi Bing Wu Jay Lee
School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, 200240 P.R. China;NSF I/UC School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, 200240 P.R. China School of Economics & Management, Shanghai Dianji University, Shanghai, 200245 P.R. China NSF I/UCRC on Intelligent Maintenance Systems(IMS )University of Cincinnati, USA
国际会议
北京
英文
1891-1900
2008-10-27（万方平台首次上网日期，不代表论文的发表时间）