Title: Automatic structural inspection using remotely operated vehicle

Authors: Meet D. Rathod; Burhanuddin H. Telwala; Amey D. Parab; Aditya A. Date; Vinayak H. Khatawate; Bharati V. Khatawate

Addresses: Department of Mechanical Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai, India ' Department of Mechanical Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai, India ' Department of Mechanical Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai, India ' Department of Mechanical Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai, India ' Department of Mechanical Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai, India ' Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology, Vashi, Navi Mumbai, India

Abstract: This research article describes in detail the process of automatic structural inspection of underwater structures using remotely operated vehicles (ROVs). The need for structural inspection has been touched upon in this paper. Due to the advancement in machine learning and the availability of large amounts of data, image recognition-based inspection is finding applications in the inspection of all kinds of infrastructure. Application of deep learning for object detection has been explored in this paper. An ROV has been designed and built to test the machine learning (ML) model inside water. This study also includes the performance testing of the ROV. Integration of a camera with the ROV for underwater footage collection along with the deployment of the machine learning model on it has also been discussed in this paper.

Keywords: machine learning; ML; computer vision; structural failure detection; remotely operated vehicles; ROV.

DOI: 10.1504/IJDE.2023.135572

International Journal of Design Engineering, 2023 Vol.12 No.2, pp.87 - 99

Received: 12 Sep 2022
Accepted: 11 Jun 2023
Published online: 18 Dec 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article