A X-Ray Based Dual-Expert Detection Method for Automatic Welding Defect Inspection
- 1 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (4) , 9427-9438
Abstract
Automatic welding technology has been widely applied in the field of industrial production. In promoting high-quality intelligent manufacturing processes for the consumer market, precise detection of welding defects is a key link in enhancing product reliability. Considering the high demand for domain knowledge in welding defect inspection tasks, existing methods have shortcomings in fine-grained recognition. To overcome these weaknesses, this article proposes a dual-expert detection method for automatic welding defect inspection, inspired by the human multi-expert complementary evaluation process. The method process is mainly reflected in the following aspects. Firstly, a high-precision robot welding defect inspection system that integrates application platform based data collection, model training, and deployment has been effectively implemented. Then, diverse detection experts are constructed using complementary regression paradigms to obtain predictions from multiple perspectives. Finally, a dual-expert fusion scheme based on probabilistic ensembling is designed to fully integrate prediction information and obtain refined results. In the experiment, a database rich in diverse types of welding defects is applied for training and systematic testing, and multiple sets of refined indicators are evaluated. In addition, we also discussed edge deployment, failure case analysis, and the application of in consumer PCB defect detection. These practical application results indicate that the proposed method can achieve product level implementation, effectively reducing the threshold for industrial testing and enabling end-users to gain benefits.Keywords
Funding Information
- National Natural Science Foundation of China (62373085)
- National Natural Science Foundation of China (U21A20481)
This publication has 35 references indexed in Scilit:
- AF-FTTSnet: An end-to-end two-stream convolutional neural network for online quality monitoring of robotic weldingJournal of Manufacturing Systems, 2024
- Research on X-ray weld seam defect detection and size measurement method based on neural network self-optimizationEngineering Applications of Artificial Intelligence, 2024
- ICA-Net: Industrial defect detection network based on convolutional attention guidance and aggregation of multiscale featuresEngineering Applications of Artificial Intelligence, 2023
- YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors2023
- Defect signal intelligent recognition of weld radiographs based on YOLO V5-IMPROVEMENTJournal of Manufacturing Processes, 2023
- An attention-based bilinear feature extraction mechanism for fine-grained laser welding molten pool/keyhole defect recognitionJournal of Manufacturing Processes, 2023
- Multimodal Object Detection via Probabilistic Ensembling2022
- Defects detection in weld joints based on visual attention and deep learningNDT & E International, 2022
- Deep learning based online metallic surface defect detection method for wire and arc additive manufacturingRobotics and Computer-Integrated Manufacturing, 2022
- Weld defect classification in radiographic images using unified deep neural network with multi-level featuresJournal of Intelligent Manufacturing, 2020