A novel study for the estimation of crack propagation in concrete using machine learning algorithms


Bayar G., Bilir T.

CONSTRUCTION AND BUILDING MATERIALS, cilt.215, ss.670-685, 2019 (SCI İndekslerine Giren Dergi) identifier identifier

  • Cilt numarası: 215
  • Basım Tarihi: 2019
  • Doi Numarası: 10.1016/j.conbuildmat.2019.04.227
  • Dergi Adı: CONSTRUCTION AND BUILDING MATERIALS
  • Sayfa Sayıları: ss.670-685

Özet

In this study, the crack pattern and propagation in a random concrete surface has been examined using machine learning algorithm called voronoi diagrams. A random photo of a concrete crack located on the surface is taken from a common source and the crack dimensions and directions have been measured. After then, the crack has been divided into 12 parts to evaluate the machine learning algorithm's capability for estimating the crack pattern including its direction. Consequently, it has been shown that this novel technique is precise, quick, cheap and useful for monitoring and estimating crack propagation on concrete surfaces. Besides, it has great potential for not only cement and concrete industries and also for many different industries in the means of automation, sustainability, safety, cost and time savings for observing and estimating crack propagations or other properties of materials. (C) 2019 Elsevier Ltd. All rights reserved.

In this study, the crack pattern and propagation in a random concrete surface has been examined using machine learning algorithm called voronoi diagrams. A random photo of a concrete crack located on the surface is taken from a common source and the crack dimensions and directions have been measured. After then, the crack has been divided into 12 parts to evaluate the machine learning algorithm's capability for estimating the crack pattern including its direction. Consequently, it has been shown that this novel technique is precise, quick, cheap and useful for monitoring and estimating crack propagation on concrete surfaces. Besides, it has great potential for not only cement and concrete industries and also for many different industries in the means of automation, sustainability, safety, cost and time savings for observing and estimating crack propagations or other properties of materials.