文献类型：期刊文献

中文题名：基于特征空间降维的溶剂脱水分离过程监控

英文题名：Feature space dimension-reduction based process monitoring of solvent dehydration separation process

作者：杜文莉[1];王坤[1];钱锋[1]

机构：[1]华东理工大学化工过程先进控制和优化技术教育部重点实验室,上海200237

年份：2010

卷号：44

期号：7

起止页码：1255

中文期刊名：浙江大学学报（工学版）

外文期刊名：Journal of Zhejiang University：Engineering Science

收录：CSTPCD;;EI(收录号：20103313164587);Scopus;北大核心:【北大核心2008】；CSCD:【CSCD2011_2012】；

基金：国家自然科学基金资助项目(60625302;20876044);国家"973"重点基础研究发展规划资助项目(2009CB320603);上海市重点学科建设资助项目(B504);上海市青年科技启明星计划资助项目(08QA14021)

语种：中文

中文关键词：均值聚类;Mexican;hat小波;故障诊断;溶剂脱水分离

外文关键词：means cluster; Mexican hat wavelet; fault diagnosis; solvent dehydration separation

摘要：针对传统化工过程中检测变量具有的非线性和非高斯性等特点,提出将改进的核主元分析(KPCA)和支持向量数据描述(SVDD)相结合的化工过程故障诊断方法.根据Mexican hat小波在提取非线性非平稳信号细微特征方面的优势,将该小波函数引入到KPCA中以增强核函数的非线性映射和抗噪能力.在映射后的特征空间中进行均值聚类分析,选择每个聚类中展现特征中心的数据,使运算复杂度明显降低,提高了监控实时性.采用SVDD描述经过聚类降维后的特征空间分布,提出新的监控指标描述过程的非高斯特性.将该方法应用在一个实际的溶剂脱水化工精馏过程中,仿真结果验证了该方法能够及时有效地检测系统产生的故障.
The measurement variables of chemical process usually show the characteristic of nonlinear and non-Gaussian behaviors.A novel modeling method was proposed by integrating the improved kernel principal component analysis（KPCA） with support vector data description（SVDD）.The Mexican hat wavelet function was introduced to construct the kernel function by utilizing the advantage of extracting the subtle feature of nonlinear non-stationary signal.The nonlinear mapping and anti-noise capability of kernel function was enhanced.Then the cluster analysis was used in the kernel feature space.The data that represented the characteristic center in every cluster were chosen,which can decrease the computational complexity and improve the results of real-time monitor.Furthermore,the SVDD was adopted to describe the feature space with dimension-reduction,and a new monitor index was constructed by SVDD to describe the non-Gaussian information.The method was applied to a solvent dehydration distillation process.Simulation results demonstrate that the method can detect the fault promptly and effectively.