Weld Seam Identification and Tracking of Inspection Robot Based on Deep Learning Network
Problem
Autonomous inspection robots on large spherical tanks need to accurately identify and track weld seams to inspect them regularly, which remained a challenge.
Why it matters
Regular inspection of spherical tank weld seams is required for safety, and autonomous robots can greatly enhance efficiency and save costs.
What the AI did
A deep learning system using Mask R-CNN segmented weld seam instances from 2281 training images, combined with image processing and Hough transform to extract weld paths for the wall-climbing robot.
Results
Trained on 2281 weld seam images; experimental results indicated the system was faster and more accurate than previous methods (abstract truncated).
Impact
Experiments showed the deep-learning robotic system outperformed previous methods in speed and accuracy for weld seam identification and tracking.
Record
| Venue | Drones |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Jie Li, Beibei Li, Linjie Dong, Xingsong Wang, Mengqian Tian |
| Citations | 45 (OpenAlex, at import time) |
| References | 32 |
| Model or method | Mask R-CNN |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/drones6080216 |
| Open access | gold |
| Keywords | weld seam tracking, Mask R-CNN, inspection robot, deep learning, instance segmentation |
Importance rating
real but narrower advance
Abstract states regular weld seam inspection is required for safety and robots enhance efficiency and save costs; a real but narrow industrial inspection advance with no scale quantified.
More in Robotics & Autonomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Autonomous robotic laparoscopic surgery for intestinal anastomosis | 2022 | 384 |
7
|
| 2 | Solving Rubik's Cube with a Robot Hand | 2019 | 569 |
6
|
| 3 | PaLM-E: An Embodied Multimodal Language Model | 2023 | 346 |
6
|
| 4 | Assistive Navigation Using Deep Reinforcement Learning Guiding Robot With UWB/Voice Beacons and Semantic Feedbacks for Blind and Visually Impaired People | 2021 | 48 |
6
|
| 5 | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges | 2022 | 154 |
6
|