Feature Selection of Frequency Spectrum for Modeling Difficulty to Measure Process Parameters

Jian TANG*, Li-Jie ZHAO, Yi-Miao LI, Tian-you CHAI, S. Joe QIN

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Referred Conference Paperpeer-review

5 Citations (Scopus)

Abstract

Some difficulty to measure process parameters can be obtained using the vibration and acoustical frequency spectra. The dimension of the frequency spectrum is very large. This poses a difficulty in selecting effective frequency band for modeling. In this paper, the partial least squares (PLS) algorithm is used to analyze the sensitivity of the frequency spectrum to these parameters. A sphere criterion is used to select different frequency bands from vibration and acoustical spectrum. The soft sensor model is constructed using the selected vibration and acoustical frequency band. The results show that the proposed approach has higher accuracy and better predictive performance than existing approaches. © 2012 Springer-Verlag.
Original languageEnglish
Title of host publicationAdvances in Neural Networks, ISNN 2012 - 9th International Symposium on Neural Networks, Proceedings
EditorsJun WANG, Gary G. YEN, Marios M. POLYCARPOU
PublisherSpringer
Pages82-91
Number of pages10
ISBN (Electronic)9783642313622
ISBN (Print)9783642313615
DOIs
Publication statusPublished - Jul 2012
Externally publishedYes
Event9th International Symposium on Neural Networks, ISNN 2012 - Shenyang, Shenyang, China
Duration: 11 Jul 201214 Jul 2012

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume7368
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference9th International Symposium on Neural Networks, ISNN 2012
Country/TerritoryChina
CityShenyang
Period11/07/1214/07/12

Keywords

  • feature selection
  • frequency spectrum
  • partial least squares
  • soft sensor

Fingerprint

Dive into the research topics of 'Feature Selection of Frequency Spectrum for Modeling Difficulty to Measure Process Parameters'. Together they form a unique fingerprint.

Cite this