Home > Papers

 
 
Application of Real-valued Negative Selection Algorithm with Variable-Radius Detectors for Fault Diagnosis
Jimin Liu #,Keming Xie *,Xinying Xu,Xiaoming Han
Department of Information Engineering, Taiyuan University of Technology
*Correspondence author
#Submitted by
Subject:
Funding: 高等学校博士学科点专项科研基金,太原理工大学校科技发展基金资助项目,山西省回国留学人员基金（No.2006112005,190-12901243,2008-25）
Opened online:16 March 2009
Accepted by: none
Citation: Jimin Liu,Keming Xie,Xinying Xu.Application of Real-valued Negative Selection Algorithm with Variable-Radius Detectors for Fault Diagnosis[OL]. [16 March 2009] http://en.paper.edu.cn/en_releasepaper/content/30355
 
 
A new Real-valued Negative Selection algorithm with variable-radius detectors is proposed in this article. The algorithm sets the maximum radius for detectors and introduces an approach that regarding the antigen input as a centre for detectors clustering. And the ranges of some important parameters of the algorithm were given. The zones corresponding different faults are marked in state space of the system using the result of clustering and faults information knowledge. Then apply the marked result to the fault diagnosis of gear cases in machine tool. The experimental result indicates that the detector sets generated by this algorithm have a good ability to cover the non-self space and can realize clustering of data modes. High veracity of Fault diagnosis is obtained.
Keywords:Artificial immune; Real-Valued Negative Selection Algorithm; Fault diagnosis; Clustering
 
 
 

For this paper
  • ● PDF (0B)
  • ● Revision 0 　　
  • ● Print this paper
  • ● Recommend this paper to a friend
  • ● Add to my favorite list

    Saved Papers

    Please enter a name for this paper to be shown in your personalized Saved Papers list

Tags
Add yours

Related Papers

Statistics
PDF Downloaded 179
Bookmarked 0
Recommend 5
Comments Array
Submit your papers