Machinery Condition Prediction Based on Support Vector Machine Model with Wavelet Transform  

作　　者：刘淑杰 陆惠天 李超 胡娅维 张洪潮 

机构地区：[1]School of Mechanical Engineering,Dalian University of Technology [2]Department of Construction & Operations Management,South Dakota State University [3]Offshore Oil Engineering Co .,Ltd. [4]Department of Industrial Engineering,Texas Tech University

出　　处：《Journal of Donghua University(English Edition)》2014年第6期831-834,共4页东华大学学报（英文版）

基　　金：National Natural Science Foundation of China(No.51205043);the Special Fundamental Research Funds for Central Universities of China(No.DUT14QY21)

摘　　要：Soft failure of mechanical equipment makes its performance drop gradually,which occupies a large proportion and has certain regularity. The performance can be evaluated and predicted through early state monitoring and data analysis. The vibration signal was modeled from the double row bearing,and wavelet transform and support vector machine model( WT-SVM model) was constructed and trained for bearing degradation process prediction. Besides Hazen plotting position relationships was applied to describing the degradation trend distribution and a 95%confidence level based on t-distribution was given. The single SVM model and neural network( NN) approach were also investigated as a comparison. Results indicate that the WT-SVM model outperforms the NN and single SVM models,and is feasible and effective in machinery condition prediction.Soft failure of mechanical equipment makes its performance drop gradually,which occupies a large proportion and has certain regularity. The performance can be evaluated and predicted through early state monitoring and data analysis. The vibration signal was modeled from the double row bearing,and wavelet transform and support vector machine model（ WT-SVM model） was constructed and trained for bearing degradation process prediction. Besides Hazen plotting position relationships was applied to describing the degradation trend distribution and a 95%confidence level based on t-distribution was given. The single SVM model and neural network（ NN） approach were also investigated as a comparison. Results indicate that the WT-SVM model outperforms the NN and single SVM models,and is feasible and effective in machinery condition prediction.

关 键 词：support vector machine(SVM) wavelet transform(WT) vibration intensity probabilistic forecasting 

分 类 号：TH17[机械工程—机械制造及自动化]