Volume 13 Number 9 (Sep. 2018)
Home > Archive > 2018 > Volume 13 Number 9 (Sep. 2018) >
JSW 2018 Vol.13(9): 506-519 ISSN: 1796-217X
doi: 10.17706/jsw.13.9.506-519

Abnormal Quality Pattern Recognition of Industrial Process Based on Multi-Support Vector Machine

Fengwei Guan1, Lianglun Cheng2*
1 CollegeofC omputer, Guangdong University of Technology, Guang Zhou,510006,Guangdong, China.
2 College of Automation, Guangdong University of Technology, Guangzhou510006, Guangdong, China


Abstract— This paper studies the quality pattern recognitionof industrial processbased on the statistical process control(SPC). An abnormal quality pattern recognition model based on multi-support vector machinewasproposed, which can be used to solve the problem of abnormal pattern recognition in the intelligent manufacturing processfor products.The combination of "one-to-one" and "one-to-many" support vector machine (SVM) classifiersis arranged according to the structure of directed acyclic graphsin the model. At the same time, a structural optimization method was proposed to reduce the cumulative error problem. The model uses the originalfeatures of the datastream of quality. For the support vector machine classifier with low recognition accuracy, the statistical features and shape features form the datastream of quality are integrated withthe original features. Relief algorithm is used to reducethe fusion featuresin order to reduce the consumption caused by increased features. The experimentalresults demonstrate thatthe model improves the accuracy of the recognitionof abnormal patterns, and its structure also has a good time advantage.

Index Terms—Abnormal quality,pattern recognition,SPC,SVM,MSVM.

[PDF]

Cite: Fengwei Guan, Lianglun Cheng, "Abnormal Quality Pattern Recognition of Industrial Process Based on Multi-Support Vector Machine," Journal of Software vol. 13, no. 9, pp. 506-519, 2018.

General Information

ISSN: 1796-217X
Frequency: Monthly
Editor-in-Chief: Prof. Antanas Verikas
Executive Editor: Ms. Yoyo Y. Zhou
Abstracting/ Indexing: DBLP, EBSCO, ProQuest, INSPEC, ULRICH's Periodicals Directory, WorldCat, CNKI,etc
E-mail: jsw@iap.org
  • Nov 29, 2018 News!

    Papers published in JSW Vol. 13, No. 1- Vol. 13 No. 10 have been indexed by DBLP.    [Click]

  • Aug 24, 2018 News!

    Vol.12, No.8- Vol.13, No.5 has been indexed by EI (Inspec).   [Click]

  • Aug 01, 2018 News!

    [CFP] 2019 the annual meeting of JSW Editorial Board, ICCSM 2019, will be held in Barcelona, Spain, July 14-16, 2019.   [Click]

  • Nov 08, 2018 News!

    The papers published in Vol.13, No. 10 have all received dois from Crossref.

  • Nov 29, 2018 News!

    Vol 13, No. 12 has been published with online version 4 original aritcles from 3 countries are published in this issue.     [Click]