Title :
A structural damage detection and classification algorithm based on clone selection
Author :
Zhou Yue ; Jia Xuesong ; Qiao Feng ; Zang Chuan Zhi
Author_Institution :
Fac. of Inf. & Control Eng., Shenyang Jianzhu Univ., Shenyang, China
fDate :
Aug. 31 2013-Sept. 2 2013
Abstract :
Inspired by identification ability of biological immune system, damage detection and classification problem in structural health monitoring is studied based on the autonomous, adaptive and evolutional artificial immune theory and method. A structural damage detection and classification algorithm based on clone selection principle is proposed. The algorithm samples data of structure model as antigen which stimulates the antibody sets. In order to improve the quality of memory cells, the antibodies go through learning and evolving process including cloning, mutation and selection. At last memory cell sets of high quality are used to detect and classify measured data. The experiment results of the proposed algorithm using benchmark structure model show that the algorithm can identify and classify the structural patterns exactly. The parameter settings which can achieve high classification success rate are proposed on the results analysis of experiment in this paper.
Keywords :
condition monitoring; identification; pattern classification; structural engineering; antigen; benchmark structure model; biological immune system; classification algorithm; clone selection; identification; structural damage detection; structural health monitoring; Blades; Classification algorithms; Immune system; clone selection; damage detection and classification; immune system; structural health monitoring;
Conference_Titel :
Modelling, Identification & Control (ICMIC), 2013 Proceedings of International Conference on
Conference_Location :
Cairo
Print_ISBN :
978-0-9567157-3-9