Artificial neural networks for wireless structural control

Ghazi Binarandi, Purdue University


We live in an age when people desire taller buildings and longer bridges. These increasing demands of more flexible structures challenge civil engineers to ensure structural safety in the state where they are more prone to extreme dynamic loading, such as earthquakes. Extensive wiring required in traditional structural control applications may be expensive and inconvenient, especially for large scale structures. To improve the scalability, wireless sensors offer a promising alternative. However, the presence of time delay and data loss in a wireless sensor network can potentially reduce the performance of the control system. Here an artificial neural network is proposed to improve the performance of a wireless sensor network based control system. The proposed technique is named as Neural Network Wireless Correction Function (NNWCF). By applying this strategy, a wireless structural control can be utilized without experiencing major performance degradation due to the wireless characteristics.




Dyke, Purdue University.

Subject Area

Civil engineering

Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server