Improved fault detection based on kernel PCA for monitoring industrial applications

被引：5

作者：

Attouri, Khadija ^{[1
]}

Mansouri, Majdi ^{[2
]}

Hajji, Mansour ^{[1
]}

Kouadri, Abdelmalek ^{[3
]}

Bensmail, Abderrazak ^{[3
,4
]}

Bouzrara, Kais ^{[5
]}

Nounou, Hazem ^{[2
]}

机构：

[1] Kairouan Univ, Higher Inst Appl Sci & Technol Kasserine, Res Unit Adv Mat & Nanotechnol UR16ES03, Kasserine 1200, Tunisia

[2] Texas A&M Univ Qatar, Elect & Comp Engn Program, Doha, Qatar

[3] Univ M Hamed Bougara Boumerdes, Inst Elect & Elect Engn, Signals & Syst Lab, Boumerdes, Algeria

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

[5] Natl Engn Sch Monastir, Res Lab Automat Signal Proc & Image, Monastir 5019, Tunisia

来源：

JOURNAL OF PROCESS CONTROL | 2024年 / 133卷

关键词：

Fault detection (FD); Spectral Clustering (SpC); Random Sampling (RnS); Reduced Kernel Principal Component Analysis (RKPCA); Tennessee Eastman process (TEP); Cement Plant; PRINCIPAL COMPONENTS; NUMBER;

D O I：

10.1016/j.jprocont.2023.103143

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The conventional Kernel Principal Component Analysis (KPCA)-based fault detection technique requires more computation time and memory storage space to analyze large-sized datasets. In this context, two techniques, Spectral Clustering (SpC) and Random Sampling (RnS), are developed to reduce the dataset size by retaining the more relevant observations while preserving the main statistical characteristics of the original dataset. These two techniques and others use the training dataset from two different industrial processes, Tennessee Eastman (TEP) and Cement Plant (CP) to be reduced and provided to build the Reduced KPCA (RKPCA) model-based fault detection scheme. The obtained results show the effectiveness of the proposed techniques in terms of some fault detection performance indices and computation costs.

引用

页数：15

共 50 条

[21] Fault Detection of Continuous Casting Process Using Kernel PCA
Wang, Xiaoyan
AUTOMATION EQUIPMENT AND SYSTEMS, PTS 1-4, 2012, 468-471 : 1706 - 1709
[22] The impact of improved PCA method based on anomaly detection on chiller sensor fault detection
Liang, Aosong
Hu, Yunpeng
Li, Guannan
INTERNATIONAL JOURNAL OF REFRIGERATION, 2023, 155 : 184 - 194
[23] A Fault Detection Method based on the Deep Extended PCA - SVM in Industrial Processes
Yang, Chun
Tao, Lujing
Zhang, Jian
Gui, Xingtai
Zhang, Jiyang
Zou, Jianxiao
Fan, Shicai
2021 AMERICAN CONTROL CONFERENCE (ACC), 2021, : 3620 - 3625
[24] A PCA based fault detection scheme for an industrial high pressure polyethylene reactor
Sharmin, Rumana
Shah, Sirish L.
Sundararaj, Uttandaraman
MACROMOLECULAR REACTION ENGINEERING, 2008, 2 (01) : 12 - 30
[25] Nonlinear process fault detection and identification using kernel PCA and kernel density estimation
Samuel, Raphael Tari
Cao, Yi
SYSTEMS SCIENCE & CONTROL ENGINEERING, 2016, 4 (01): : 165 - 174
[26] Fault detection and diagnosis based on improved PCA with JAA method in VAV systems
Du, Zhimin
Jin, Xinqiao
Wu, Lizhou
BUILDING AND ENVIRONMENT, 2007, 42 (09) : 3221 - 3232
[27] Fault detection and diagnosis based on improved PCA with JAA method in VAV systems
Department of Mechanical Engineering, Shanghai Jiao Tong University, China
Build. Environ., 1600, 9 (3221-3232):
[28] Fault detection behavior analysis of PCA-based process monitoring approach
Wang, Haiqing
Song, Zhihuan
Wang, Hui
2002, Chemical Industry Press (53):
[29] PCA-SDG Based Process Monitoring and Fault Diagnosis: Application to an Industrial Pyrolysis Furnace
Han, Xianyao
Tian, Shengwei
Romagnoli, Jose A.
Li, Hui
Sun, Wei
IFAC PAPERSONLINE, 2018, 51 (18): : 482 - 487
[30] Batch process monitoring and fault detection based on an improved MPCA
Wang, Zhi-Feng
Yuan, Jing-Qi
Tan, Jian-Dong
Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University, 2004, 38 (04): : 555 - 558

← 1 2 3 4 5 →