Author(s)

Hanchang Wang ¹, XueMei Yu ²

Affiliation(s)

¹ Qingdao Special Equipment Inspection and Testing Institute Co., Ltd, Qingdao, 266100 Shandong, China
² Qingdao Angu Technology Co., Ltd, Qingdao, 266121 Shandong, China

Corresponding Author

Hanchang Wang

ABSTRACT

Aiming at the problem that the traditional deep learning model is not effective in detecting small defects, a weld defect detection algorithm based on the improved deep learning FasteRCNN model is proposed. The algorithm extracts multi-scale feature maps through multi-layer feature network and acts on the subsequent links of the model together, so as to make full use of the low-level features in the model and increase the detailed information. The area generation network of the model is improved, and a variety of sliding windows are added, so that the aspect ratio of the anchor point of the model is optimized and the detection ability is improved. Two different activation functions in the hidden layer of convolutional neural network are verified by experiments, and optimization methods are put forward. The deep learning neural network can avoid extracting the features of weld defect images and directly judge whether the suspected defect images are defects. Experiments on 580 images show that the recognition accuracy of SDR images by the proposed method is over 98%, which is superior to traditional methods. And that design system has the characteristics of automatically learn complex depth features in X-ray weld defect images, and has strong practicability.

KEYWORDS

Deep learning, Weld defects, Image recognition, Algorithm research

CITE THIS PAPER

Hanchang Wang, XueMei Yu, Research on Image Recognition Algorithm of Weld Defect Based on Deep Learning. Advances in Computer, Signals and Systems (2022) Vol. 6: 83-89. DOI: http://dx.doi.org/10.23977/acss.2022.060111.

REFERENCES

[1] Chen Kai, Wang Hai. Research on weld image recognition based on deep learning [J]. Journal of Anhui University of Engineering, 2022, 37(1):8.
[2] Dai Jin, Liu Zhenyu. Review of image recognition algorithms based on deep learning [J]. Computer Products and Circulation, 2018(3):1.
[3] Tang Wen. Research on Computer Image Recognition Technology Based on Deep Learning [J]. Computer Programming Skills and Maintenance, 2022(1):4.
[4] Su Yue. Research and analysis of image recognition technology based on deep learning convolutional neural network [J]. Information and Communication, 2019(7):2.
[5] Xu Xiaozhu. Research on image recognition technology of ore and rock based on deep learning [J]. China Manganese Industry, 2018, 36(6):3.
[6] Li Yanfeng, Liu Cuirong, Wu Zhisheng, et al. Research on Intelligent Identification of Weld Defects Based on Deep Learning One-stage Method [J]. Journal of Guangxi University: Natural Science Edition, 2021, 46(2):11.
[7] Liu Mengxi, Ju Yongfeng, Gao Weixin, et al. Research on depth confidence network of weld defect image classification and recognition [J]. Measurement and Control Technology, 2018, 037(008):5-9,15.
[8] Luo Xi. On the application status and advantages of deep learning in the field of image recognition [J]. Science and Technology Information, 2020, 18(3):2.
[9] Ma Hao-Peng, Zhu Chun-Mei, Zhou Wen-Hui, et al. Defect detection algorithm of emulsion pump based on deep learning [J]. chinese journal of liquid crystals and displays, 2019, 34(1):9.
[10] Su Xuexia. Research on CT image recognition method based on deep learning [J]. Information and Communication, 2019(10):2.

Sponsors, Associates, and Links

---

• Power Systems Computation
  
  
• Internet of Things (IoT) and Engineering Applications
  
  
• Computing, Performance and Communication Systems
  
  
• Journal of Artificial Intelligence Practice
  
  
• Journal of Network Computing and Applications
  
  
• Journal of Web Systems and Applications
  
  
• Journal of Electrotechnology, Electrical Engineering and Management
  
  
• Journal of Wireless Sensors and Sensor Networks
  
  
• Journal of Image Processing Theory and Applications
  
  
• Mobile Computing and Networking
  
  
• Vehicle Power and Propulsion
  
  
• Frontiers in Computer Vision and Pattern Recognition
  
  
• Knowledge Discovery and Data Mining Letters
  
  
• Big Data Analysis and Cloud Computing
  
  
• Electrical Insulation and Dielectrics
  
  
• Crypto and Information Security
  
  
• Journal of Neural Information Processing
  
  
• Collaborative and Social Computing
  
  
• International Journal of Network and Communication Technology
  
  
• File and Storage Technologies
  
  
• Frontiers in Genetic and Evolutionary Computation
  
  
• Optical Network Design and Modeling
  
  
• Journal of Virtual Reality and Artificial Intelligence
  
  
• Natural Language Processing and Speech Recognition
  
  
• Journal of High-Voltage
  
  
• Programming Languages and Operating Systems
  
  
• Visual Communications and Image Processing
  
  
• Journal of Systems Analysis and Integration
  
  
• Knowledge Representation and Automated Reasoning
  
  
• Review of Information Display Techniques
  
  
• Data and Knowledge Engineering
  
  
• Journal of Database Systems
  
  
• Journal of Cluster and Grid Computing
  
  
• Cloud and Service-Oriented Computing
  
  
• Journal of Networking, Architecture and Storage
  
  
• Journal of Software Engineering and Metrics
  
  
• Visualization Techniques
  
  
• Journal of Parallel and Distributed Processing
  
  
• Journal of Modeling, Analysis and Simulation
  
  
• Journal of Privacy, Trust and Security
  
  
• Journal of Cognitive Informatics and Cognitive Computing
  
  
• Lecture Notes on Wireless Networks and Communications
  
  
• International Journal of Computer and Communications Security
  
  
• Journal of Multimedia Techniques
  
  
• Automation and Machine Learning
  
  
• Computational Linguistics Letters
  
  
• Journal of Computer Architecture and Design
  
  
• Journal of Ubiquitous and Future Networks