Monitoring Distillation Column Systems Using Improved Nonlinear Partial Least Squares-Based Strategies

Muddu Madakyaru, Fouzi Harrou, Ying Sun

Research output: Contribution to journalArticle

Abstract

Fault detection in industrial systems plays a core role in improving their safety, productivity and avoiding expensive maintenance. This paper proposed and verified data-driven anomaly detection schemes based on a nonlinear latent variable model and statistical monitoring algorithms. Integrating both the suitable characteristics of partial least squares (PLS) and adaptive neural network fuzzy inference systems (ANFIS) procedure, PLS-ANFIS model is employed to allow for flexible modeling of multivariable nonlinear processes. Furthermore, PLS-ANFIS modeling was connected with k-nearest neighbors (kNN)-based data mining schemes and employed for nonlinear process monitoring. Specifically, residuals generated from the PLS-ANFIS model are used as the input to the kNN-based mechanism to uncover anomalies in the data. Moreover, kNN-based exponentially smoothing with parametric and nonparametric thresholds is adopted to better anomaly detection. The effectiveness of the proposed approach is evaluated using real measurements from an actual bubble cap distillation column.

Original languageEnglish
Article number8807170
Pages (from-to)11697-11705
Number of pages9
JournalIEEE Sensors Journal
Volume19
Issue number23
DOIs
Publication statusPublished - 01-12-2019

Fingerprint

distillation
Distillation columns
Fuzzy inference
inference
Neural networks
Monitoring
anomalies
fault detection
data mining
Process monitoring
productivity
Fault detection
caps
smoothing
maintenance
Data mining
safety
bubbles
Productivity
thresholds

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

@article{a0c17bc4299c469fa262864a2d1ab896,
title = "Monitoring Distillation Column Systems Using Improved Nonlinear Partial Least Squares-Based Strategies",
abstract = "Fault detection in industrial systems plays a core role in improving their safety, productivity and avoiding expensive maintenance. This paper proposed and verified data-driven anomaly detection schemes based on a nonlinear latent variable model and statistical monitoring algorithms. Integrating both the suitable characteristics of partial least squares (PLS) and adaptive neural network fuzzy inference systems (ANFIS) procedure, PLS-ANFIS model is employed to allow for flexible modeling of multivariable nonlinear processes. Furthermore, PLS-ANFIS modeling was connected with k-nearest neighbors (kNN)-based data mining schemes and employed for nonlinear process monitoring. Specifically, residuals generated from the PLS-ANFIS model are used as the input to the kNN-based mechanism to uncover anomalies in the data. Moreover, kNN-based exponentially smoothing with parametric and nonparametric thresholds is adopted to better anomaly detection. The effectiveness of the proposed approach is evaluated using real measurements from an actual bubble cap distillation column.",
author = "Muddu Madakyaru and Fouzi Harrou and Ying Sun",
year = "2019",
month = "12",
day = "1",
doi = "10.1109/JSEN.2019.2936520",
language = "English",
volume = "19",
pages = "11697--11705",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "23",

}

Monitoring Distillation Column Systems Using Improved Nonlinear Partial Least Squares-Based Strategies. / Madakyaru, Muddu; Harrou, Fouzi; Sun, Ying.

In: IEEE Sensors Journal, Vol. 19, No. 23, 8807170, 01.12.2019, p. 11697-11705.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Monitoring Distillation Column Systems Using Improved Nonlinear Partial Least Squares-Based Strategies

AU - Madakyaru, Muddu

AU - Harrou, Fouzi

AU - Sun, Ying

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Fault detection in industrial systems plays a core role in improving their safety, productivity and avoiding expensive maintenance. This paper proposed and verified data-driven anomaly detection schemes based on a nonlinear latent variable model and statistical monitoring algorithms. Integrating both the suitable characteristics of partial least squares (PLS) and adaptive neural network fuzzy inference systems (ANFIS) procedure, PLS-ANFIS model is employed to allow for flexible modeling of multivariable nonlinear processes. Furthermore, PLS-ANFIS modeling was connected with k-nearest neighbors (kNN)-based data mining schemes and employed for nonlinear process monitoring. Specifically, residuals generated from the PLS-ANFIS model are used as the input to the kNN-based mechanism to uncover anomalies in the data. Moreover, kNN-based exponentially smoothing with parametric and nonparametric thresholds is adopted to better anomaly detection. The effectiveness of the proposed approach is evaluated using real measurements from an actual bubble cap distillation column.

AB - Fault detection in industrial systems plays a core role in improving their safety, productivity and avoiding expensive maintenance. This paper proposed and verified data-driven anomaly detection schemes based on a nonlinear latent variable model and statistical monitoring algorithms. Integrating both the suitable characteristics of partial least squares (PLS) and adaptive neural network fuzzy inference systems (ANFIS) procedure, PLS-ANFIS model is employed to allow for flexible modeling of multivariable nonlinear processes. Furthermore, PLS-ANFIS modeling was connected with k-nearest neighbors (kNN)-based data mining schemes and employed for nonlinear process monitoring. Specifically, residuals generated from the PLS-ANFIS model are used as the input to the kNN-based mechanism to uncover anomalies in the data. Moreover, kNN-based exponentially smoothing with parametric and nonparametric thresholds is adopted to better anomaly detection. The effectiveness of the proposed approach is evaluated using real measurements from an actual bubble cap distillation column.

UR - http://www.scopus.com/inward/record.url?scp=85077496922&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077496922&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2019.2936520

DO - 10.1109/JSEN.2019.2936520

M3 - Article

AN - SCOPUS:85077496922

VL - 19

SP - 11697

EP - 11705

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 23

M1 - 8807170

ER -