Intelligent Measurement Modeling Using a Novel Multi-nonlinear Mapping Based Extreme Learning Machine Integrated with Partial Least Square Regression

Qunxiong Zhu, Xiaohan Zhang, Yuan Xu, Yanlin He

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Accurate intelligent measurement modeling plays a key role in complex process industries. However, establishing an accurate and robust measurement model tends to be more and more difficult because of the increasing complexity in terms of nonlinearity and collinearity of data. To solve this problem, a novel multi-nonlinear mapping based extreme learning machine integrated with partial least square regression is proposed in this paper. In the proposed model, two problems of nonlinearity and collinearity are effectively dealt with by using multi-nonlinear mapping and partial least square regression, respectively. For evaluating performance, empirical studies on a commonly used bench mark problem and a real-world application confirm that the presented method can obtain high accuracy and high stability performance for intelligent measurement.

Original languageEnglish
Title of host publicationProceedings of 2020 IEEE 9th Data Driven Control and Learning Systems Conference, DDCLS 2020
EditorsMingxuan Sun, Huaguang Zhang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages539-543
Number of pages5
ISBN (Electronic)9781728159225
DOIs
Publication statusPublished - 20 Nov 2020
Externally publishedYes
Event9th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2020 - Liuzhou, China
Duration: 20 Nov 202022 Nov 2020

Publication series

NameProceedings of 2020 IEEE 9th Data Driven Control and Learning Systems Conference, DDCLS 2020

Conference

Conference9th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2020
Country/TerritoryChina
CityLiuzhou
Period20/11/2022/11/20

Keywords

  • Ensemble
  • Extreme Learning Machine
  • Intelligent measurement
  • Modeling
  • Partial least squares regression

Fingerprint

Dive into the research topics of 'Intelligent Measurement Modeling Using a Novel Multi-nonlinear Mapping Based Extreme Learning Machine Integrated with Partial Least Square Regression'. Together they form a unique fingerprint.

Cite this