Smart Pipe Inspection Robot With In-Chassis Motor Actuation Design and Integrated AI-Powered Defect Detection System

被引:0
作者
Zholtayev, Darkhan [1 ]
Dauletiya, Daniyar [1 ]
Tileukulova, Aisulu [2 ]
Akimbay, Dias [3 ]
Nursultan, Manat [3 ]
Bushanov, Yersaiyn [3 ]
Kuzdeuov, Askat [4 ]
Yeshmukhametov, Azamat [3 ,4 ]
机构
[1] Astana IT Univ, Dept Computat & Data Sci, Astana 020000, Kazakhstan
[2] Al Farabi Kazakh Natl Univ, Dept Phys & Technol, Alma Ata 050040, Kazakhstan
[3] Nazarbayev Univ, Sch Engn & Digital Sci, Dept Robot & Mechatron, Astana 010000, Kazakhstan
[4] Nazarbayev Univ, Inst Smart Syst & Artificial Intelligence, Astana 010000, Kazakhstan
关键词
Inspection; Robots; Image edge detection; Simultaneous localization and mapping; Computational modeling; Sensors; Inpipe robot; robot design; machine learning; defect detection; pipe inspection; SLAM; COMPUTER VISION;
D O I
10.1109/ACCESS.2024.3450502
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In the contemporary world, inspection operations have become a critical component of infrastructure maintenance. Over the years, the demand for comprehensive inspection of pipes, both internally and externally, has grown increasingly complex and challenging. Consequently, there is a pressing need for significant advancements in in-pipe robots, particularly in the areas of inspection speed, defect detection precision, and overall reliability. Recent developments in new devices and sensors have markedly improved our capability to inspect and diagnose defects within pipes with greater accuracy. Furthermore, the application of machine learning tools has optimized the inspection process, enhancing the detection and recognition of potential pipe defects, such as rust, blockages, and welding anomalies. This research introduces a novel mobile robot platform specifically designed for pipe inspection. It integrates an advanced machine learning model that effectively detects and identifies key pipe defects, including rust, compromised welding quality, and pipe deformation. Additionally, this platform offers enhancements in inspection speed. The integration of these technologies represents a significant stride in the field of infrastructure maintenance, setting a new standard for efficiency and precision in pipe inspection.
引用
收藏
页码:119520 / 119534
页数:15
相关论文
共 68 条
[51]  
Rajput M., 2020, Towards AI
[52]  
Ramli NE., 2022, J Adv Res Appl Sci Eng Technol, V29, P256, DOI [10.37934/araset.29.1.256265, DOI 10.37934/ARASET.29.1.256265]
[53]  
Rashid M. Z. A., 2021, IOP Conference Series: Materials Science and Engineering, V1051, DOI 10.1088/1757-899X/1051/1/012034
[54]   Automated Vision Systems for Condition Assessment of Sewer and Water Pipelines [J].
Rayhana, Rakiba ;
Jiao, Yutong ;
Zaji, Amirhossein ;
Liu, Zheng .
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2021, 18 (04) :1861-1878
[55]  
Razvarz S., 2021, Flow Modelling and Control in Pipeline Systems, P1
[56]   Driving Mechanisms, Motion, and Mechanics of Screw Drive In-Pipe Robots: A Review [J].
Ren, Tao ;
Zhang, Yin ;
Li, Yujia ;
Chen, Yonghua ;
Liu, Qingyou .
APPLIED SCIENCES-BASEL, 2019, 9 (12)
[57]   Collective Gas Sensing in a Cyber-Physical System [J].
Rohrich, Ronnier Frates ;
Teixeira, Marco Antonio Simoes ;
Lima, Jose ;
de Oliveira, Andre Schneider .
IEEE SENSORS JOURNAL, 2021, 21 (12) :13761-13771
[58]   Computer vision techniques for automatic structural assessment of underground pipes [J].
Sinha, SK ;
Fieguth, PW ;
Polak, MA .
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2003, 18 (02) :95-112
[59]   Bolt looseness detection based on Canny edge detection algorithm [J].
Song, Daoyuan ;
Xu, Xinghua ;
Cui, Xiaopeng ;
Ou, Yangbin ;
Chen, Weiming .
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2023, 35 (21)
[60]   Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM [J].
Srinivasu, Parvathaneni Naga ;
SivaSai, Jalluri Gnana ;
Ijaz, Muhammad Fazal ;
Bhoi, Akash Kumar ;
Kim, Wonjoon ;
Kang, James Jin .
SENSORS, 2021, 21 (08)