Crack Detection of Rubber Mount through Deep Learning Models in Structural Health Monitoring System

Abstract Rubber mounts are widely used as a component to prevent structures from vibration damages associated with various sources that making lifespan at stake. Frequent change of rubber mount can be a waste yet the inspection for faulty rubber mount is impractical. Advancement in technology eases structural health monitoring (SHM) through sensors combined with deep learning (DL) approach. This paper aims to investigate application practicality of DL to detect level of cracks in rubber mounts through vibration signals. Neural network models based on Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and their combinations were developed. An experimental setup simulating bridge structure with rubber isolators supporting its base was created. Cracks were induced on the rubber mount to simulate failure conditions. 5Hz and 10Hz constant sine waves along with simulated bridge waveform from an actual bridge excitation were employed. Neural networks were applied with Bayesian approach via dropout layer to reduce overfitting and increase reliability. Results show the highest accuracy achieved by hybrid CNN-LSTM with 99.9% while CNN with 89.0% in the standard sine wave and bridge excitation scenario respectively. Overall, the study shown the practicality and capability of neural network as a SHM approach for crack detection of rubber mount.