Penetration acceleration signal Blind decomposition based on LMD and ICA

摘要：

Hard target penetration acceleration signals are nonstationary signals. In this paper local mean decomposition algorithm (LMD) and independent component analysis (ICA) are combined as the way to extract the signal characteristics of penetration of the acceleration signal. The method introduces LMD in ICA use its good features which is decomposition independent;so that PF components are orthogonal and independent .And this method eliminates redundancy. LMD algorithm requires a single signal,and can not guarantee the results of decomposition arc independent or orthogonal;ICA algorithm can guarantee the decomposed component are independent and orthogonal,but requires signals to be multi-channel. Combine the two algorithms,a single signal can be decomposed,and can maintain the advantages of LMD algorithm adaptive decomposition and ICA decomposition independent ability to make the decomposition component has a clear physical meaning. The author apply combined algorithm in penetration acceleration signal separation and the results verify the effectiveness of the method.

关键词： List the keywords covered in your paper. These keywords will also be used by the publisher to produce a keyword index

作者: Hao Huiyan Yang Yuanhua Wang Xi Liu Mingjie Li Xiaofeng

作者单位: Department of Electromechanical Engineering,Beijing Institute of Technology,Beijing,China Key Labora Jilin Jiangbei Machinery Manufacturing limited liability company,Jiling,China Henan Institute of Urban Construction,Ping Dingshan,China Department of Electromechanical Engineering,Beijing Institute of Technology,Beijing,China

会议类型: 国际会议

会议名称: 2011 International Conference on Opto-Electronics Engineering and Information Science(2011光电电子工程与信息科学国际会议 ICOEIS 2011)

会议地点: 西安

会议语种:英文

页码: 647-650

在线出版日期: 2011-12-23（万方平台首次上网日期，不代表论文的发表时间）