A biologically inspired sensor network framework for autonomous structural health monitoring

Abstract

This paper presents a biologically inspired sensor network framework for autonomous structural health monitoring (SHM). The presented sensor network framework transforms desirable characteristics and effective defense mechanisms of the natural immune system to wireless sensor networks for SHM. The autonomous structural health monitoring is achieved through an integrated sensor network framework consisting of high computational power sensors, a mobileagent- based sensor network middleware, and artificial immune pattern recognition (AIPR) methodology for structure damage detection and classification. An AIPR-based structure damage classifier (AIPR-SDC) has been developed, which incorporates several novel characteristics of the natural immune system. The performance of the AIPR-SDC has been validated using a benchmark structure proposed by the IASC-ASCE (International Association for Structural Control - American Society of Civil Engineers) SHM Task Group. The validation results show a better classification success rate comparing to some of other classification algorithms. The further study of unsupervised structure damage classification is also conducted by integrating data clustering techniques and the AIPR method.