Piezo Based Structural Health Monitoring of Concrete Systems Using Machine Learning

Abstract

Monitoring the health of infrastructure has become imperative now a days due to vast newlineinfrastructure development in the last few decades which has now aged. Proper monitoring of newlinethe structures during the construction as well as design life stage can avoid catastrophic failures. newlineStrength and durability are the two main aspects of reinforced concrete structures and providing newlinea real time monitoring of these are the big challenges which almost all the concrete researchers newlineare working around the world. The field of structural health monitoring (SHM) using piezo newlinesensors via electro-mechanical impedance (EMI) has grown tremendously in recent years can newlineprovide a solution to these issues. The application of machine learning (ML) techniques is newlineexperiencing exponential growth in SHM domain using sensors because of the immense newlinecapability of handling voluminous datasets and making past and future predictions based on newlineinput data used for training. newlineThe aim of the present research is to utilize smart sensors, namely PZT sensors, in different newlineconfigurations and analyse its sensitivity for strength monitoring, durability studies and suitably newlinepropose its application in real-life. ML models were developed using the sensor data to predict newlinethe strength of different cementitious systems and concrete systems. The research was further newlineextended to develop ML models to predict the baseline/healthy and future EMI data of different newlineblended RC structures (conventional, fly ash blended and fly ash based geopolymer) subjected newlineto a chloride-laden environment. Also, different corrosion phases have been identified based on newlinethe famous Tuutti s model for the RC and prestresses structures subjected to corrosion. Further newlinepioneering work has been carried out on different concrete systems subjected to combined newlineenvironmental and mechanical loading wherein physical models for structural parameter newlinedeterioration were developed and also empirical relations between equivalent stiffness and newlinesurface concentration were established.