Monitoring Neutral Axis Position Using Monthly Sample Residuals as Estimated From a Data Mining Model

Structural Health Monitoring (SHM) has enabled the condition of large structures, like bridges, to be evaluated in real time. In order monitor behavioral changes, it is essential identify parameters structure that are sensitive enough capture damage as develops while being stable during ambient behavior structure. Research shown monitoring neutral axis (N.A.) position satisfies first criterion sensitivity; however, N.A. location challenging because its affected by loads applied The motivation behind this research comes from greater than expected impact various load characteristics on observed location. This paper an indirect way estimate vehicular (magnitude and lateral load) uses a data mining approach predict Instead N.A., proposed method residuals between monitored predicted monitored. Using actual SHM collected cable-stayed bridge, over 2-year period, presents steps followed for creating model location, use monthly sample ability distinguish changes (e.g. change response due cracking, bearings becoming frozen, cables losing tension, etc.), high sensitivity allows capturing minor changes.