点击次数：

论文类型：期刊论文

发表时间：2013-01-01

发表刊物：ICIC Express Letters

收录刊物：Scopus

卷号：7

期号：11

页面范围：3157-3162

ISSN号：1881803X

摘要：The dry point of aviation kerosene is an important quality parameter in the atmospheric distillation column; however, it cannot be measured by hardware sensors directly. A novel selective ensemble compressive sensing LS-SVM (SECSLS-SVM) algorithm based on noise injected is proposed to estimate the dry point of aviation kerosene. At first, the gauss noises are injected to the original training set to generate new training set. Then, the LS-SVM algorithm is used to construct the sub-models in the ensemble model. At last, the ensemble model is obtained by compressive sensing using orthogonal matching pursuit algorithm. The simulation results show that the soft sensor modeling based on the proposed method has better predictive performance. ? 2013 ISSN 1881-803X.