Automatic Detection and Location of Weld Beads With Deep Convolutional Neural Networks
- 24 September 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-12
Abstract
Welding quality detection is a critical link in modern manufacturing, and the weld bead location is a prerequisite for the high-precision assessment of welding quality. It is generally necessary for weld bead detection to be accomplished in the context of complex industrial environments. However, the conventional detection and location methods based on specific detection conditions or prior knowledge lack accuracy and adaptability. To precisely detect and locate the weld beads in real industrial environments, a novel weld bead detection and location algorithm is proposed based on deep convolutional neural networks. Because there is no open data set of weld beads and the samples in real industrial applications are insufficient for effective model training of the deep convolutional neural network, a novel data augmentation method based on a deep semantic segmentation network is proposed to increase the sample diversity and enlarge the data set. Then, a dynamic sample updating strategy is put forward to cover more welding situations. Finally, faced with the weak-feature and weak-texture characteristics of weld beads, a simplified YOLOV3 model is proposed to realize end-to-end weld bead location. Experiments demonstrate that the proposed method could effectively satisfy the robustness and precision requirements for weld bead detection and location combined with deep semantic segmentation network and simplified YOLOV3 model.Keywords
Funding Information
- National Natural Science Foundation of China (61473265, 61803344, 61773351)
- Science & Technology Research Project in Henan Province (202102210098)
- Outstanding Foreign Scientist Support Project in Henan Province (GZS2019008)
- Innovation Research Team of Science & Technology in Henan Province of China (17IRTSTHN013)
This publication has 40 references indexed in Scilit:
- Intelligent laser welding through representation, prediction, and control learning: An architecture with deep neural networks and reinforcement learningMechatronics, 2016
- Supervised Learning of Human Welder Behaviors for Intelligent Robotic WeldingIEEE Transactions on Automation Science and Engineering, 2015
- Advances in natural language processingScience, 2015
- Iterative Local ANFIS-Based Human Welder Intelligence Modeling and Control in Pipe GTAW Process: A Data-Driven ApproachIEEE/ASME Transactions on Mechatronics, 2014
- A Novel Stability Quantification for Disk Laser Welding by Using Frequency Correlation Coefficient Between Multiple-Optics SignalsIEEE/ASME Transactions on Mechatronics, 2014
- Vision inspection system for the identification and classification of defects in MIG welding jointsThe International Journal of Advanced Manufacturing Technology, 2011
- Application of artificial neural network in laser welding defect diagnosisJournal of Materials Processing Technology, 2005
- A feature-based inspection planning system for coordinate measuring machinesThe International Journal of Advanced Manufacturing Technology, 2005
- Investigation on Ti6Al4V laser welding using statistical and Taguchi approachesJournal of Materials Processing Technology, 2005
- "GrabCut"ACM Transactions on Graphics, 2004