A method for detecting welds and weld defects based on deep learning
A technology of defect detection and deep learning, which is applied in the direction of optical test defects/defects, can solve the problem that the type and position of weld defects cannot be effectively detected
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0042] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.
[0043]A weld and weld defect detection method based on deep learning, using YOLO V3 network to realize weld and / or weld defect detection; (YOLO V3 network includes input layer, interconnected convolution layer, activation function layer, dropout layer, residual layer, fully connected layer, softmax logic output layer; between two adjacent layers, the output value of the previous level is used as the input value of the next level.)
[0044] The YOLO V3 network for weld and / or weld defect detection is trained by the following steps:
[0045] 1) Use a rectangular positioning frame to select and mark the workpiece image containing the weld, and 5000 such images are used as a training data set;
[0046] As an embodiment of the present invention, a single workpiece image includes 2 to 15 weld areas;
[0047] The weld image forme...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com