A machine learning approach for predicting the electro-mechanical impedance data of blended RC structures subjected to chloride laden environment

Abstract

The application of the electro-mechanical impedance (EMI) technique using piezo sensors for structural health monitoring (SHM) is based on baseline/healthy signature data, which poses serious limitations when it needs to be applied to existing structures. Therefore, the present research utilizes autoregressive integrated moving average (ARIMA), an effective time series forecasting machine learning algorithm to predict the baseline/healthy EMI data and futuristic data of reinforced concrete corroded specimens. The EMI data from the ARIMA model is validated with the experimental data, and the results obtained prove that the model could be utilized to predict the baseline and forecast the EMI corrosion data effectively. These results will aid the researchers to predict the baseline data for the existing structures and utilize the EMI technique for SHM purposes.