An Artificial Immune Pattern Recognition Approach for Damage Classification in Structures

Abstract

Structural Health Monitoring (SHM) is one of the research topics that have received growing interest in research communities. While a lot of efforts have been made in detecting damages in structures, very few researches have been conducted for the structure damage classification problem. This paper presents an artificial immune pattern recognition (AIPR) approach for the damage classification in structures. An AIPR-based Structure Damage Classifier (AIPR-SDC) has been developed, which incorporates several novel characteristics of the natural immune system. The immune learning algorithm can remember various data patterns by generating a set of memory cells that contain representative feature vectors for each pattern, which are extracted from the compressed data using the auto regression exogenous (ARX) algorithm. The AIPR-SDC approach has been tested using a benchmark structure proposed by the IASC-ASCE Structural Health Monitoring Task Group. The test results show the feasibility of using the AIPR-SDC method for the structure damage classification.

This work is partially supported by LSFC Grant #201102180 and CMHUD # 2010-k9-51 to Y. Zhou, and NSFC Grant #61100159 to C.Z. Zang.