摘要
提出基于分布式ICA-PCA(independent component analysis-principal component analysis)模型的工业过程故障监测方法,适合于复杂工业过程难以自动划分子块及过程数据存在非高斯信息的情况。首先,对过程数据进行PCA分解,并在PCA主成分不同的方向上构建不同的子块,把原始特征空间自动划分为不同子空间。然后,对各个子块采用ICA-PCA两步信息提取的策略,提取出高斯信息和非高斯信息,并构建新的统计量和统计限。最后,通过Tennessee Eastman(TE)过程的仿真实验,验证所提出故障监测模型的有效性和可行性。
A fault monitoring method based on distributed independent component analysis-principal component analysis （ICA-PCA） model is proposed, which is suitable for complex industrial process that cannot be divided into several sub-blocks through an automatic way and has non-Gaussian information. Firstly, an initial PCA decomposition is carried out upon the variables of the whole process. By constructing sub-blocks through different directions of PCA principal components, the original feature space can be automatically divided into several sub-feature spaces. In addition, a two step extractions of the ICA-PCA information are carried on upon all sub-blocks in order to extract both Gaussian and non-Gaussian information, establishing the new statistics and their statistic limits. Finally, the simulation of TE process shows that the proposed fault detection model is efficient and feasible.
出处
《化工学报》
EI
CAS
CSCD
北大核心
2015年第11期4546-4554,共9页
CIESC Journal
基金
国家自然科学基金项目(61263010
60904049)
江西省自然科学基金项目(20114BAB211014)
江西省教育厅项目(GJJ14399)~~
关键词
复杂工业过程
自动划分子块
非高斯
ICA-PCA
故障监测
complex industrial process
automatic partitioning sub-blocks
non-Gaussian
ICA-PCA
fault monitoring
