Skip to content

Latest commit

 

History

History
69 lines (55 loc) · 2.22 KB

README.en.md

File metadata and controls

69 lines (55 loc) · 2.22 KB
Raw

LNG Site Clustering Experiment

Description

Principles of Artificial Intelligence Class - LNG Site Clustering Experiment

·Exit sites

  1. Natural gas - methane content exceeds 95
  2. Reduce the temperature to -162°C to become a liquid
  3. Natural gas is gradually lowered through the Train in turn
    · Transportation
  4. LNG ships
    · import sites

· LNG Data
· Data

  1. Data on LNG vessels for 3 months, static speed (less than 1 knot)
  2. 3590578
    ·Data Field
  3. mmsi
  4. Time: Unix timestamp (seconds)
  5. Sailing Status
  6. Speed
  7. Longitude
  8. Latitude
  9. Draft

Goal: Use algorithms to quickly and accurately identify LNG sites

Software Architecture

  1. Windows 10/11 Pro
  2. Python 3.9/3.10
  3. Anaconda3 2022.05
  4. Cuda 11.3 or above
  5. (Optional) Visual Studio Code and other IDEs
  6. (Optional) Package management tools such as Anaconda/Miniconda

Installation

1.  conda create -n LNG python=3.9
2.  conda activate LNG
3.  conda install pandas numpy matplotlib scikit-learn
4.  conda install jupyter notebook -c conda-forge
5.  conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
6.  Download the dataset "lng2.csv" from (https://yunpan.360.cn/surl_y2vpVKtEjLk （Extract code: ed65）) and move it to the folder "data"

Instructions

  1. For an environment where Jupyter notebook is installed, open Run.ipynb and run
  2. For Windows environments, right-click Run.ps1 and left-click "Run with Powershell"
  3. For other environments (Linux, Macosx, and other Unix-like environments), enter sh ./Run.sh run in the terminal

Contribution

  1. Fork the repository
  2. Create Feat_xxx branch
  3. Commit your code
  4. Create Pull Request

Gitee Feature

  1. You can use Readme_XXX.md to support different languages, such as Readme_en.md, Readme_zh.md
  2. Gitee blog blog.gitee.com
  3. Explore open source project https://gitee.com/explore
  4. The most valuable open source project GVP
  5. The manual of Gitee https://gitee.com/help
  6. The most popular members https://gitee.com/gitee-stars/