Global Health Assessment of Structures Using NDT and Machine Learning

Structural health and condition assessment have become an important part of infrastructural life, due to continuous deterioration caused by nature or human activities. It ensures public safety and saves the economy if carried out properly. Even though deterioration is the natural process of a structure, the rate depends on the functional utility and its maintenance. So, poor maintenance of commercial structures, public buildings, and historical constructions can lead to major damages to sudden collapse. There are several methodologies to predict the health of the structures like destructive, Non-destructive, and sensor-based evaluations, but there is a huge scarce of experienced engineers in interpreting and evaluating the condition of the structures. In this paper, an attempt is made to help engineers in a robust way with fast-moving models to predict the condition at a global level of the structure using Machine Learning for the data obtained from Non-Destructive Tests (NDT) which are in general carried on local level structural elements. In conclusion, a model is proposed which connects between local elemental properties to global behaviour.