Structural health monitoring using AI and ML based multimodal sensors data

Abstract

Climatic changes, sudden or gradual, influence the structural health of buildings and bridges due to variations in temperature and humidity. Risk and disaster management plays a vital role in the decision-making process for safeguarding structures. Data analytics from sensors systems in smart structures aid in taking appropriate action in securing buildings during natural calamities. The correlation between climate and structural measuring responses can be further improved using artificial intelligence (AI)- machine learning (ML) algorithms to monitor and predict structural health and take any precautionary steps before the event of a casualty. Linear regression is an efficient tool for analyzing structural health. The proposed work's objective is to monitor and predict the structural health and inform the concerned authorities in the event of a failure in advance, using AI-ML approaches. We have analyzed various sensor data sets to predict the health of a structure based on the crack developed. From the data obtained for experimentation, mean width of the crack is observed as 2.38 cm and mean length of the crack is 63.36 cm.