信息与控制2016，Vol.45Issue(5)：551-555,5.DOI:10.13976/j.cnki.xk.2016.0551
基于正交独立成分分析的过程数据建模
Process Data Modeling Based on Orthogonal Independent Component Analysis
摘要
Abstract
Based on independent component analysis (ICA),a multivariate linear regression (MLR)method combined with orthogonal signal correction (OSC),which is called orthogonal independent component regression (O-ICR), is proposed for regression prediction of non-Gaussian processes.First,the O-ICA is conducted on an original input data matrix for removing disturbing variation that is not correlated to Y from the extracted high-order statistics in ICA.Then,independent components are extracted X from after correction.The regression pre-diction model is derived using these components instead of the original input data and Y.Com-pared with the traditional ICR,the proposed method has a more superior performance because in-dependent components are corrected.Finally,the validity of the method is verified though quality prediction simulation in the Tennessee Eastman (TE)process.关键词
质量预测/非高斯过程/正交信号校正/独立成分分析Key words
quality prediction/non-Gaussian process/orthogonal signal correction/independent component analysis分类
信息技术与安全科学引用本文复制引用
罗明英,侍洪波,谭帅..基于正交独立成分分析的过程数据建模[J].信息与控制,2016,45(5):551-555,5.基金项目
国家自然科学基金资助项目 （）
