Weld Seam Identification and Tracking of Inspection Robot Based on Deep Learning Network
Open Access
Abstract
The weld seams of large spherical tank equipment should be regularly inspected. Autonomous inspection robots can greatly enhance inspection efficiency and save costs. However, the accurate identification and tracking of weld seams by inspection robots remains a challenge. Based on the designed wall-climbing robot, an intelligent inspection robotic system based on deep learning is proposed to achieve the weld seam identification and tracking in this study. The inspection robot used mecanum wheels and permanent magnets to adsorb metal walls. In the weld seam identification, Mask R-CNN was used to segment the instance of weld seams. Through image processing combined with Hough transform, weld paths were extracted with a high accuracy. The robotic system efficiently completed the weld seam instance segmentation through training and learning with 2281 weld seam images. Experimental results indicated that the robotic system based on deep learning was faster and more accurate than previous methods, and the average time of identifying and calculating weld paths was about 180 ms, and the mask average precision (AP) was about 67.6%. The inspection robot could automatically track seam paths, and the maximum drift angle and offset distance were 3° and 10 mm, respectively. This intelligent weld seam identification system will greatly promote the application of inspection robots.Keywords
Funding Information
- Science and Technology Project of Quality and Technical Supervision Bureau of Jiangsu Province (KJ175933, jiangsu-0002-2017AQ)
- National Prevention Key Technology Project for Serious and Major Accidents in Work Safety of China (KJ175933, jiangsu-0002-2017AQ)
This publication has 30 references indexed in Scilit:
- A method of reactive 3D navigation for a tight surface scan by a nonholonomic mobile robotAutomatica, 2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Fully Convolutional Networks for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep learningNature, 2015
- A novel laser vision sensor for weld line detection on wall-climbing robotOptics & Laser Technology, 2014
- Autonomous Pose Detection and Alignment of Suction Modules of a Biped Wall-Climbing RobotIEEE/ASME Transactions on Mechatronics, 2014
- Climbing robots for maintenance and inspections of vertical structures—A survey of design aspects and technologiesRobotics and Autonomous Systems, 2013
- Strong Magnetic Units for a Wind Power Tower Inspection and Maintenance RobotInternational Journal of Advanced Robotic Systems, 2012
- Advanced perception, navigation and planning for autonomous in-water ship hull inspectionThe International Journal of Robotics Research, 2012
- New mechanism to pass obstacles for magnetic climbing robots with high payload, using only one motor for force‐changing and wheel‐liftingIndustrial Robot: the international journal of robotics research and application, 2011