Using Machine Learning for Condition Assessment of Concrete Infrastructure

ABOUT THE INTERNATIONAL CONCRETE ABSTRACTS PORTAL

  • The International Concrete Abstracts Portal is an ACI led collaboration with leading technical organizations from within the international concrete industry and offers the most comprehensive collection of published concrete abstracts.

International Concrete Abstracts Portal

  


Title: Using Machine Learning for Condition Assessment of Concrete Infrastructure

Author(s): Leandro F.M. Sanchez and Marcelo Terra

Publication: Concrete International

Volume: 41

Issue: 11

Appears on pages(s): 35-39

Keywords: damage, image, structure, data

Date: 11/1/2019

Abstract:
The damage rating index (DRI) is among the most promising microscopy methods for condition assessment of concrete infrastructures. However, it requires experts to perform time-consuming petrographic microscopy of samples. The article discusses a study aimed at automating DRI assessments using machine learning (ML). It is expected that ML will reduce the subjectively yet increase the speed, reproducibility, accessibility, and accuracy of DRI determination.