Deformation Decision Knowledge Extraction of FWP Processing Based on RS and Entropy

  • Yaohua Deng
  • Guixiong Liu
  • Liming Wu
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 146)


Deformation decisions knowledge extraction based on RS and entropy reduction is proposed for FWP processing which processing deformation factors is complex and difficult to extract. Decision table of processing deformation which takes FWP processing deformation factors as conditional attribute and processing deformation level as decision attribute. Changes in the level of mutual information as a condition attribute importance to the decision attribute evaluation, when the greater the change in the conditions the more important attribute for decision attribute. In Application examples, there are 13 conditional attribute in decision table, in accordance with Pawlak reduction methods and genetic reduction algorithm to extract 5 highest impact factors, 4 highest impact factors for FWP processing deformation decision are extracted using entropy reduction method. Prediction error of Entropy Reduction Method is 32.58% less than Pawlak’s reduction method, and 21.45% less than Genetic reduction algorithm.


FWP processing deformation decisions knowledge extraction rough set information entropy attribute importance 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Zhang, Z., Tang, L.: Simulation of Elman Neural network Extension Strategy Generator to Pattern Deformation Error in Flexibility Material Treating Field. In: IEEE KAM Colloquium on Computer, Communication, Control and Automation, pp. 50–53 (2008)Google Scholar
  2. 2.
    Deng, Y., Liu, G., Liao, Q.: Research of FWP Process Deformation Compensation Forecasting on the Basis of TS-FNN. Advanced Materials Research 295-297, 2430–2437 (2011)CrossRefGoogle Scholar
  3. 3.
    Czogała, E., Mrózek, A., Pawlak, Z.: The idea of a rough fuzzy controller and its application to the stabilization of a pendulum-car system. Fuzzy Sets and Systems (72), 61–73 (1995)CrossRefGoogle Scholar
  4. 4.
    Shen, Q.: Selecting informative features with fuzzy-rough sets and its application for complex systems monitoring. Pattern Recognition (37), 1351–1363 (2004)MATHCrossRefGoogle Scholar
  5. 5.
    Fan, Y.-N., Tseng, T.-L.: Rule induction based on an incremental rough set. Expert Systems with Applications (36), 11439–11450 (2009)CrossRefGoogle Scholar
  6. 6.
    Fan, X.-W., Jia, X.-D.: Reduction method of multidimensional qualitative variables based on rough set theory. Mathematics in Practive and Theory 3, 161–165 (2009)Google Scholar
  7. 7.
    Miao, D.-Q.: A new method of discretization of continuous attributes in rough sets. Acta Automatica Sinica 27, 296–302 (2001)Google Scholar
  8. 8.
    Bai, G.-Z., Pei, Z.-L., Kong, Y., Liu, L.-S.: Attribute discretization method based on rough set theory and information entropy. Application Researcher of Computers 25, 1701–1703 (2008)Google Scholar
  9. 9.
    Dong, W., Wang, J.-H., Gu, S.-S.: Rule induction approach based on variable precision rough set theory. Control Engineering of China 14, 73–76 (2007)Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  • Yaohua Deng
    • 1
    • 2
  • Guixiong Liu
    • 1
  • Liming Wu
    • 2
  1. 1.School of Mechanical and Automotive EngineeringSouth China University of TechnologyGuangzhouChina
  2. 2.School of Information EngineeringGuangdong University of TechnologyGuangzhouChina

Personalised recommendations