Kernel Principal Component Analysis Improvement based on Data-Reduction via Class Interval

被引：1

作者：

Kaib, Mohammed Tahar Habib ^{[1
]}

Kouadri, Abdelmalek ^{[1
]}

Harkat, Mohamed Faouzi ^{[2
]}

Bensmail, Abderazak ^{[3
]}

Mansouri, Majdi ^{[4
]}

Nounou, Mohamed ^{[5
]}

机构：

[1] Univ MHamed Bougara Boumerdes, Inst Elect & Elect Engn, Signals & Syst Lab, Ave Independence, Boumerdes 35000, Algeria

[2] Badji Mokhtar Annaba Univ, Syst & Adv Mat Lab, BP 12, Annaba 23000, Algeria

[3] SCAEK, Ain El Kebira Cement Plant, BP 01, Ain El Kebira 19400, Algeria

[4] Texas A&M Univ Qatar, Elect & Comp Engn Program, POB 23874, Doha, Qatar

[5] Texas A&M Univ Qatar, Chem Engn Program, POB 23874, Doha, Qatar

来源：

IFAC PAPERSONLINE | 2024年 / 58卷 / 04期

关键词：

Fault Detection (FD); data-driven techniques; Principal Component Analysis (PCA); Kernel Principal Component Analysis (KPCA); Histogram; Tennessee Eastman Process; FAULT-DETECTION; INDUSTRIAL-PROCESS; PCA;

D O I：

10.1016/j.ifacol.2024.07.249

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Kernel Principal Component Analysis (KPCA) is an effective nonlinear extension of the Principal Component Analysis for fault detection. For large-sized data, KPCA may drop its detection performance, occupy more storage space for the monitoring model, and take more execution time in the online part. Reduced KPCA pre-processes the training data before applying the KPCA method, the proposed approach selects samples based on class interval to reduce the number of observations in the training data set while maintaining decent detection performance. This approach is applied to the Tennessee Eastman Process and then compared to some of the existing approaches. Copyright (c) 2024 The Authors. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/)

引用

页码：390 / 395

页数：6

共 22 条

[1]

Alcala C., 2011, Ph.D. thesis

[2] Reconstruction-Based Contribution for Process Monitoring with Kernel Principal Component Analysis [J].