Pile foundation integrity classification and recognition method based on convolutional neural network
A convolutional neural network, classification and recognition technology, applied in the field of pile foundation integrity classification and recognition based on convolutional neural network, can solve the problems of low degree of automation, high detection cost, strong subjectivity, etc., to improve the recognition accuracy and The effect of speed, few training parameters, and strong subjectivity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0037] Example: see Figure 1-5 .
[0038] like figure 2 As shown, a pile foundation integrity classification and recognition method based on convolutional neural network includes the following steps:
[0039] S1. Data collection and marking: The image data set is obtained through the detection of the pile foundation by the low-strain acquisition equipment, and the image data set is manually classified according to four types of data: complete piles, mildly defective piles, heavy defect piles and serious defects. Attach the corresponding labels respectively;
[0040] S2. Image data set expansion: expand the collected image data, use horizontal flip, vertical flip and mirror flip to amplify the data, and uniformly adjust the picture to 64×64 to ensure that the input picture has the same length and width;
[0041] S3. Classification of original data images: the original data images are divided into two categories, training set and test set, the training set accounts for 80% ...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap