首页> 外国专利> FAULT MONITORING METHOD OF CONTINUOUS ANNEALING PROCESS BASED ON RECURSIVE KERNEL PRINCIPAL COMPONENT ANALYSIS

FAULT MONITORING METHOD OF CONTINUOUS ANNEALING PROCESS BASED ON RECURSIVE KERNEL PRINCIPAL COMPONENT ANALYSIS

机译：基于递归核主成分分析的连续退火过程故障监测方法

页面导航

摘要
著录项
相似文献

摘要

A fault monitoring method of continuous annealing process based on recursive kernel principal component analysis (RKPCA), belongs to the technical field of fault monitoring and diagnosis. Firstly, collect the data of continuous annealing industrial process, including the roll speed of entry loop (ELP), current and tension. And then, build a model using RKPCA, update the model, and calculate the eigenvector. Finally, fault monitoring and diagnosis is performed for the continuous annealing process, when T² statistics and SPE statistics exceed their respective control limits, a fault is considered to be occurring, inversely, the whole process is normal. The method solves the problem of data's non-linear and time-varying. RKPCA updates the model by recursive calculating to train the characteristic value and eigenvector of data's covariance. The method can not only reduce the false alarms, but also increase the accuracy of fault monitoring.

机译：基于递归核主成分分析（RKPCA）的连续退火过程故障监测方法，属于故障监测与诊断技术领域。首先，收集连续退火工业过程的数据，包括入口环的轧制速度（ELP），电流和张力。然后，使用RKPCA建立模型，更新模型并计算特征向量。最后，对连续退火过程进行故障监视和诊断，当 T ^{2 统计信息和SPE统计信息超过各自的控制极限时，则认为发生了故障，整个过程很正常。该方法解决了数据的非线性和时变问题。 RKPCA通过递归计算来更新模型，以训练数据协方差的特征值和特征向量。该方法不仅可以减少误报，而且可以提高故障监测的准确性。} 展开▼

著录项

公开/公告号WO2012040916A1

专利类型

公开/公告日2012-04-05

原文格式PDF

申请/专利权人 NORTHEAST UNIVERSITY;ZHANG YING WEI;TENG YONG DONG;HU ZHI YONG;
展开▼

申请/专利号WO2010CN77441

发明设计人 ZHANG YING WEI;TENG YONG DONG;HU ZHI YONG;
展开▼

申请日2010-09-29

分类号G05B23/02;G06F17/30;G05B13/04;

国家 WO

入库时间 2022-08-21 17:16:55

相似文献

专利

外文文献

中文文献

1. 基于递归核主元分析的青霉素发酵过程故障监测方法 [P] . 中国专利： CN101964021B . 2012.12.19

2. 基于递归核主元分析的青霉素发酵过程故障监测方法 [P] . 中国专利： CN101964021A . 2011-02-02

3. Continuous annealing process fault detection method based on recursive kernel principal component analysis [P] . 美国专利： US9053291B2 . 2015-06-09

机译：基于递归核主成分分析的连续退火过程故障检测方法

4. CONTINUOUS ANNEALING PROCESS FAULT DETECTION METHOD BASED ON RECURSIVE KERNEL PRINCIPAL COMPONENT ANALYSIS [P] . 美国专利： US2013035910A1 . 2013-02-07

机译：基于递归核主成分分析的连续退火过程故障检测方法

5. FACIAL RECOGNITION METHOD BASED ON KERNEL PRINCIPAL COMPONENT ANALYSIS [P] . 世界知识产权组织专利： WO2018187951A1 . 2018-10-18

机译：基于核主成分分析的人脸识别方法

1. Sensor fault diagnosis of nonlinear processes based on structured kernel principal component analysis [J] . Kechang FU, Liankui DAI, Tiejun WU, 控制理论与应用（英文版） . 2009,第003期

2. Nonlinear fault diagnosis method based on kernel principal component analysis [J] . Yan Weiwu, Zhang Chunkai, Shao Huihe 高技术通讯（英文版） . 2005,第002期

3. Combination Method of Principal Component Analysis and Support Vector Machine for On-line Process Monitoring and Fault Diagnosis [J] . 东华大学学报（英文版） . 2006,第001期

4. Kernel Generalization of Multi-Rate Probabilistic Principal Component Analysis for Fault Detection in Nonlinear Process [J] . Donglei Zheng, Le Zhou, Zhihuan Song 自动化学报：英文版 . 2021,第008期

5. Kernel Generalization of Multi-Rate Probabilistic Principal Component Analysis for Fault Detection in Nonlinear Process [J] . Donglei Zheng, Le Zhou, Zhihuan Song 自动化学报（英文版） . 2021,第008期

6. Nonlinear Real-Time Process Monitoring and Fault Diagnosis Based on Principal Component Analysis and Kernel Fisher Discriminant Analysis [J] . Xi Zhang, Weiwu Yan, Xu Zhao Chemical Engineering & Technology: Industrial Chemistry -Plant Equipment -Process Engineering -Biotechnology . 2007,第9期

7. Fault Diagnosis Method on Polyvinyl Chloride Polymerization Process Based on Dynamic Kernel Principal Component and Fisher Discriminant Analysis Method [J] . Gao Shu-zhi, Wu Xiao-feng, Wang Gui-cheng, Mathematical Problems in Engineering . 2016,第PTa11期

8. Research on nonlinear process monitoring and fault diagnosis based on kernel principal component analysis [J] . Fei HE, Min LI, Jianhong YANG, Key Engineering Materials . 2009,第期

9. Efficient recursive kernel principal component analysis for nonlinear time-varying processes monitoring [C] . Liangliang Shang, Ze Yan, Aibing Qiu, Chinese Control and Decision Conference . 2019

10. Statistical monitoring and fault diagnosing of multivariate processes based on nonlinear principal component analysis. [D] . Li, Xueman. 2004

11. Research on Recognition Method of Driving Fatigue State Based on Sample Entropy and Kernel Principal Component Analysis [O] . Beige Ye, Taorong Qiu, Xiaoming Bai, 2018

12. Fault discriminant enhanced kernel principal component analysis incorporating prior fault information for monitoring nonlinear processes [O] . Deng, Xiaogang, Tian, Xuemin, Chen, Sheng, 2017

1. 基于MCUSUM-MSPCA方法对连续过程微小故障的监测 [C] . 孙美红 ,张浩 ,孙巍 . 第五届全国化学工程与生物化工年会 . 2008

2. 连续退火炉多模态过程监测方法研究 [A] . 刘广辉 . 2017