英文摘要 |
This research follows the project on developing a bridge health monitoring system based on neural network technology last year and extends its consideration to higher-order responses in the time history. Nowadays, with the aging of existing bridges all over the world, solutions on how to identify effectively the health conditions of bridges have a significant issue. These solutions shall offer a rapid and reliable result immediately after major strikes of event without using lots of time and labor. The demand of this health monitoring system grows rapidly and researches on this topic had been discussed widely. Meanwhile, neural networks, commenced from artificial intelligence, have also shown their outstanding performance in solving complex problems. For this reason, a monitoring system using neural network was developed. Two major ground excitations recorded in Taiwan were used to establish the NARX-based system. Analytical results of the proposed neural network-based system in higher orders were considered to evaluate its efficiency in health monitoring. The results showed that the proposed neural networked-based system can be used successfully with superior advantages after a major earthquake for bridge health monitoring. |