Monitoring and analysis of crack developments in concrete using machine vision

Abstract

Periodic inspection of reinforced concrete bridges and buildings is required to assess their deterioration due to loading and environmental factors. Monitoring the condition of the existing structure helps in the assessment of its loadcarrying capacity. Cracking in concrete structure is one of the critical parameters representing its structural health. Trained personnel monitor the development of cracks and their progression at the critical locations of the structures through a physical vision at regular intervals of time. With the advancement in computational techniques, machine vision is becoming a robust alternative to physical inspection of the structure and its health monitoring. The present work demonstrates the application of machine vision in concrete crack monitoring by identifying the location of the crack, the number of cracks, the length of the cracks, and the area of the cracks. A novel system has been developed by integrating machine vision and convolutional neural networks to gain real-time images of concrete surfaces, detect concrete cracks, and extract various parameters related to cracks, such as number, location, length, and area, in synchronization with the applied loading. The present system is implemented for real-time crack monitoring during compression testing of concrete cubes of size 150 mm × 150 mm × 150 mm of different characteristic strengths. The outcome of the machine vision system in graphical form is presented for various parameters of cracks like the number, location, length, the area concerning compressive load for concrete of different strengths. An accuracy of 98% has been achieved for crack detection on concrete cubes as presented in the results. The present machine vision system can be implemented on different concrete structures for acquiring real-time data on crack development and progression. The proposed framework will be an effective tool for engineers working in the domain of structural health monitoring of concrete structures.