摘要
独立元分析(ICA)是近年来盲信号分离领域的热点问题,传统的ICA方法只能寻找信号与信号间的独立元,对信号组与信号组之间的独立性分析却无能为力。独立子空间分析法(ISA)则通过寻求矢量峭度最大化,对信号组之间进行独立性研究。根据这一理论提出动态独立子空间分析过程监控方法,针对过程变量自相关问题,构建时间序列子空间,随采样时间动态更新子空间数据,对其进行独立性研究,达到过程监控的目的。以TE过程为背景的仿真研究,验证了该方法的有效性。
Independent component analysis （ICA） is a focus in blind source separation researches recently. Traditional ICA method can only search for the independent component between signals, and be helpless to analyze the independence between signal groups. Independent Subspace Analysis （ISA） can research the independence of signal groups by searching for the maximum of vector kurtosis. According to this theory, the Dynamic independence ofsubspace （DISA） was studied by considering the self-correlation of the variables of the process, composing the time-series subspace and updating its data with the lapse of time, which makes the process monitoring method available. At last, the simulation results of TE process reveal this method is very effective.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2008年第13期3589-3592,共4页
Journal of System Simulation
基金
国家高技术研究发展计划(863计划)课题(2007AA04Z198)
教育部新世纪优秀人才支持计划(NCET-05-0485)
江南大学创新团队发展计划
