Damage evaluation of fixed beams at both ends for bridge health monitoring using a combination of a vibration sensor and a surface acoustic wave device

Abstract

In recent years, the aging of engineering structures such as bridges has become a serious problem, and the development of an inexpensive and mass-producible structural health monitoring (SHM) system is desired. In this study, we proposed an SHM method for bridges using an impedance-loaded surface acoustic wave (SAW) sensor, which is a combination of a SAW sensor and an impedance-changing sensor. The impedance-loaded part comprised a vibration sensor, that is a geophone, and variable-capacitance diode, and vibration experiments were conducted on fixed beams at both ends that simulated a bridge. The results from these experiments were subjected to frequency analysis under the continuous wavelet transform, and it was confirmed that unsupervised machine learning could be used to discriminate damage with high accuracy. Furthermore, it was found that a one-class support vector machine, used for anomaly detection in machine learning, was suitable for the SHM method of bridges.