Supervised process monitoring and fault diagnosis based on machine learning methods

Hajer Lahdhiri, Maroua Said, Khaoula Ben Abdellafou, Okba Taouali, Mohamed-Faouzi Harkat

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Data-driven techniques have been receiving considerable attention in the industrial process monitoring field due to their major advantages of easy implementation and less requirement for the prior knowledge and process mechanism. Principal component analysis (PCA) method is known as a popular method for monitoring and fault detection in industrial systems but as it is basically a linear method. However, most practical systems are nonlinear. To make the extension to nonlinear systems, kernel PCA (KPCA) method has been proposed for process modeling and monitoring. We present in this paper an online reduced rank optimized KPCA (RR-KPCA) technique for fault detection in order to extend the advantages of the KPCA models to online processes. Following the fault detection, the identification of the variables correlated to the fault occurred is of great importance. For this purpose, it is proposed to extend the approaches of localization by partial PCA and by elimination in the linear case to the nonlinear case, by exploiting the solution of reduction of the dimension of the kernel matrix in the feature space. The partial RR-KPCA and the elimination sensor identification (ESI-RRKPCA) are generated based on the static RR-KPCA and the online RR-KPCA methods. The idea of these approaches is to generate partial RR-KPCA models with reduced sets of variables. In other words, their goal is to generate indices of fault detection sensitive to certain faults and insensitive to others. The proposed fault isolation methods are applied for monitoring an air quality monitoring network (AIRLOR) data.

Original languageEnglish
JournalInternational Journal of Advanced Manufacturing Technology
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Process monitoring
Fault detection
Failure analysis
Learning systems
Principal component analysis
Monitoring
Nonlinear systems
Air quality
Sensors

Keywords

  • Air quality monitoring
  • Fault detection
  • Fault isolation
  • Nonlinear process monitoring
  • Reduced rank KPCA
  • Tabu search algorithm

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Mechanical Engineering
  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Cite this

Supervised process monitoring and fault diagnosis based on machine learning methods. / Lahdhiri, Hajer; Said, Maroua; Abdellafou, Khaoula Ben; Taouali, Okba; Harkat, Mohamed-Faouzi.

In: International Journal of Advanced Manufacturing Technology, 01.01.2019.

Research output: Contribution to journalArticle

@article{5eee48d38405443e99f0ef7347811293,
title = "Supervised process monitoring and fault diagnosis based on machine learning methods",
abstract = "Data-driven techniques have been receiving considerable attention in the industrial process monitoring field due to their major advantages of easy implementation and less requirement for the prior knowledge and process mechanism. Principal component analysis (PCA) method is known as a popular method for monitoring and fault detection in industrial systems but as it is basically a linear method. However, most practical systems are nonlinear. To make the extension to nonlinear systems, kernel PCA (KPCA) method has been proposed for process modeling and monitoring. We present in this paper an online reduced rank optimized KPCA (RR-KPCA) technique for fault detection in order to extend the advantages of the KPCA models to online processes. Following the fault detection, the identification of the variables correlated to the fault occurred is of great importance. For this purpose, it is proposed to extend the approaches of localization by partial PCA and by elimination in the linear case to the nonlinear case, by exploiting the solution of reduction of the dimension of the kernel matrix in the feature space. The partial RR-KPCA and the elimination sensor identification (ESI-RRKPCA) are generated based on the static RR-KPCA and the online RR-KPCA methods. The idea of these approaches is to generate partial RR-KPCA models with reduced sets of variables. In other words, their goal is to generate indices of fault detection sensitive to certain faults and insensitive to others. The proposed fault isolation methods are applied for monitoring an air quality monitoring network (AIRLOR) data.",
keywords = "Air quality monitoring, Fault detection, Fault isolation, Nonlinear process monitoring, Reduced rank KPCA, Tabu search algorithm",
author = "Hajer Lahdhiri and Maroua Said and Abdellafou, {Khaoula Ben} and Okba Taouali and Mohamed-Faouzi Harkat",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s00170-019-03306-z",
language = "English",
journal = "International Journal of Advanced Manufacturing Technology",
issn = "0268-3768",
publisher = "Springer London",

}

TY - JOUR

T1 - Supervised process monitoring and fault diagnosis based on machine learning methods

AU - Lahdhiri, Hajer

AU - Said, Maroua

AU - Abdellafou, Khaoula Ben

AU - Taouali, Okba

AU - Harkat, Mohamed-Faouzi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Data-driven techniques have been receiving considerable attention in the industrial process monitoring field due to their major advantages of easy implementation and less requirement for the prior knowledge and process mechanism. Principal component analysis (PCA) method is known as a popular method for monitoring and fault detection in industrial systems but as it is basically a linear method. However, most practical systems are nonlinear. To make the extension to nonlinear systems, kernel PCA (KPCA) method has been proposed for process modeling and monitoring. We present in this paper an online reduced rank optimized KPCA (RR-KPCA) technique for fault detection in order to extend the advantages of the KPCA models to online processes. Following the fault detection, the identification of the variables correlated to the fault occurred is of great importance. For this purpose, it is proposed to extend the approaches of localization by partial PCA and by elimination in the linear case to the nonlinear case, by exploiting the solution of reduction of the dimension of the kernel matrix in the feature space. The partial RR-KPCA and the elimination sensor identification (ESI-RRKPCA) are generated based on the static RR-KPCA and the online RR-KPCA methods. The idea of these approaches is to generate partial RR-KPCA models with reduced sets of variables. In other words, their goal is to generate indices of fault detection sensitive to certain faults and insensitive to others. The proposed fault isolation methods are applied for monitoring an air quality monitoring network (AIRLOR) data.

AB - Data-driven techniques have been receiving considerable attention in the industrial process monitoring field due to their major advantages of easy implementation and less requirement for the prior knowledge and process mechanism. Principal component analysis (PCA) method is known as a popular method for monitoring and fault detection in industrial systems but as it is basically a linear method. However, most practical systems are nonlinear. To make the extension to nonlinear systems, kernel PCA (KPCA) method has been proposed for process modeling and monitoring. We present in this paper an online reduced rank optimized KPCA (RR-KPCA) technique for fault detection in order to extend the advantages of the KPCA models to online processes. Following the fault detection, the identification of the variables correlated to the fault occurred is of great importance. For this purpose, it is proposed to extend the approaches of localization by partial PCA and by elimination in the linear case to the nonlinear case, by exploiting the solution of reduction of the dimension of the kernel matrix in the feature space. The partial RR-KPCA and the elimination sensor identification (ESI-RRKPCA) are generated based on the static RR-KPCA and the online RR-KPCA methods. The idea of these approaches is to generate partial RR-KPCA models with reduced sets of variables. In other words, their goal is to generate indices of fault detection sensitive to certain faults and insensitive to others. The proposed fault isolation methods are applied for monitoring an air quality monitoring network (AIRLOR) data.

KW - Air quality monitoring

KW - Fault detection

KW - Fault isolation

KW - Nonlinear process monitoring

KW - Reduced rank KPCA

KW - Tabu search algorithm

UR - http://www.scopus.com/inward/record.url?scp=85061014656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061014656&partnerID=8YFLogxK

U2 - 10.1007/s00170-019-03306-z

DO - 10.1007/s00170-019-03306-z

M3 - Article

JO - International Journal of Advanced Manufacturing Technology

JF - International Journal of Advanced Manufacturing Technology

SN - 0268-3768

ER -