Improvement of Health Monitoring System for Environment with Noise

摘要

In this paper,an attempt is made to develop a structural health monitoring system that can adapt to the structural systems and environments with noise,by introducing the learning ability.At the previous research,a health monitoring system that can adapt to the structural systems and environments through the learning ability was developed,which can obtain the recognition rate of over 80%.By introducing the learning ability,it is unnecessary to prepare any previous knowledge and examination for the underlying structures and environment.However the previous research did not account for the noise involved in data from sensor.Through the numerical examples,it is concluded that the proposed system can recognize the change of structural characteristics and condition states even under noisy environment.