Fault Assessment in Piezoelectric-Based Smart Strand Using 1D Convolutional Neural Network

The smart strand technique has been recently developed as a cost-effective prestress load monitoring solution for post-tensioned engineering systems. Nonetheless, during its lifetime under various operational and environmental conditions, the sensing element of potential to fail, threatening functionality resulting in inaccurate estimation. This study analyzes effect failures on impedance characteristics develops 1D convolutional neural network (1D CNN) automated fault diagnosis. Instead using realistic experimental structure which transducer faults can be hard control accurately, we adopt well-established finite model conduct all experiments. results show that damaged are relatively different from other piezoelectric active devices. While slope susceptance response is widely accepted promising indicator, this shows resistance more favorable strand. accurately diagnose with highest testing accuracy 94.1%. Since autonomously learn damage-sensitive features without pre-processing, it great embedding impedance-based damage identification systems real-time structural health monitoring.