https://github.com/ababaee1/deep_learning_3d_printing

Neural network models for predicting flexural rigidity of metal 3D printed beams using cross-sectional layer images. Multiple architectures including ANNs and CNNs with/without PCA dimensionality reduction were developed and compared.
https://github.com/ababaee1/deep_learning_3d_printing

Last synced: 11 months ago
JSON representation

Neural network models for predicting flexural rigidity of metal 3D printed beams using cross-sectional layer images. Multiple architectures including ANNs and CNNs with/without PCA dimensionality reduction were developed and compared.

• Host: GitHub
• URL: https://github.com/ababaee1/deep_learning_3d_printing
• Owner: ababaee1
• License: mit
• Created: 2024-10-31T22:22:18.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-10-31T23:04:11.000Z (over 1 year ago)
• Last Synced: 2025-01-15T05:45:01.784Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 14.8 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Using Deep Learning (CNN, ANN) for Flexural Rigidity Prediction in 3D printed Structures 



  

  

  



 

**Neural network models for predicting flexural rigidity of metal 3D printed porous gyroid beams using cross-sectional layer images. Multiple architectures including ANNs and CNNs with/without PCA dimensionality reduction were developed and compared.**

## Key Features

- ├── data/

    - │   ├── images.zip/      # Layer image data

  - │   └── test_data.csv/   # Bending test results

- ├── models/          # Model implementations

  - │   ├── ANN_PCA.ipynb

  - │   ├── ANN_single_image.ipynb

  - │   ├── CNN.ipynb

  - │   └── Model.ipynb

- └── utils/          # Data preprocessing

  - ├── Getting_DataFrame.ipynb

  - └── Image_combine.ipynb

 

## Dependencies

- Python 3.7+

- TensorFlow 2.x 

- scikit-learn

- numpy

- pandas

- matplotlib