| KNPE算法在化工过程故障检测中的应用 |
| |
| 引用本文： | 李春阳,夏丽莎,李军祥.KNPE算法在化工过程故障检测中的应用[J].控制工程,2020(1):92-97. |
| |
| 作者姓名： | 李春阳 夏丽莎 李军祥 |
| |
| 作者单位： | 上海理工大学管理学院 |
| |
| 基金项目： | 国家自然科学基金资助项目(71572113,71432007,71871144);国家自然科学基金匹配项目(1P16303003,2019KJFZ048,2018KJFZ035);上海理工大学大学生创新训练计划项目(XJ2019156) |
| |
| 摘 要： | 化工生产过程具有维数高、非线性强等特点。针对传统的邻域保持嵌入(NPE)算法对非线性数据特征提取不足的缺陷,引入高斯核函数,将数据由非线性的输入空间转换到线性的特征空间。核邻域保持嵌入(KNPE)算法在构建局部空间特征结构的基础上,能够更好地提取数据的非线性结构。通过以田纳西-伊斯曼(TE)仿真过程为例,构造T2和SPE统计量进行故障检测,证明了KNPE方法比NPE和KPCA方法能够更快更准确的检测出非线性故障的发生。
|
| 关 键 词： | 化工故障 流形学习 核邻域保持嵌入算法 故障检测 |
Application of Kernel NPE for Fault Detection in Chemical Processes |
| |
| LI Chun-yang,XIALi-sha,LI Jun-xiang.Application of Kernel NPE for Fault Detection in Chemical Processes[J].Control Engineering of China,2020(1):92-97. |
| |
| Authors: | LI Chun-yang XIALi-sha LI Jun-xiang |
| |
| Affiliation: | (Business School,University of Shanghai for Science and Technology,Shanghai 200093,China) |
| |
| Abstract: | Chemical production process has the characteristics of high dimension and strong nonlinearity. For the deficiency of traditional neighborhood preserving embedding(NPE) algorithm in feature extraction of non-linear data, a Gaussian kernel function is introduced to transform data from non-linear input space to linear feature space. Kernel neighborhood preserving embedding(KNPE) algorithm can extract the non-linear structure of data better on the basis of constructing local spatial feature structure. By a case study on the Tennessee Eastman(TE) simulation process, T^2 and SPE statistics are constructed for fault detection, which proves that KNPE method can detect the occurrence of non-linear faults faster and more accurately than NPE and KPCA methods. |
| |
| Keywords: | Chemical failure manifold learning kernel neighborhood preserving embedding algorithms fault detection |
| 本文献已被 维普 等数据库收录！ |
|
