Rapid and automated determination of rusted surface areas of a steel bridge for robotic maintenance systems

Abstract

There has been an increased interest in the use of robotic systems to automate the blasting tasks in steel bridge maintenance. To utilize such robotic systems effectively, an automated process for determining the rusted areas on a steel bridge to be blasted is a prerequisite. This study proposes a method to rapidly and accurately determine rusted surface areas on a steel bridge that are to be blasted, within current standards. The proposed method consists of three steps: color space conversion, classification of rusted area via the J48 decision tree algorithm, and determination of blasting area. The method was validated using 119 test images showing both normal states and various degrees of rusting and rust distribution types. The experimental results showed that the success rate for determining the rusted areas that needed blasting was 97.48%. The average processing time was 0.57 s/image. The results demonstrate that the proposed method rapidly and accurately indicated whether blasting was necessary, and if so, where blasting should be performed, based on current standards of practice. • This study proposed a method to determine which rusted surface areas to be blasted. • Performance of the method was evaluated on 119 images acquired from steel bridges. • The success rate was 97.48% and the average processing time was only 0.57 s/image. • The method is fast, accurate, and in compliance with current standards of practice. • The method could be employed in robotic systems used for steel bridge maintenance.