West Coat Vessel

Website

Credits:

This project is done in collaboration with Simon Fraser University (SFU) and National Research Council Canada (NRC)

1. Setup
2. Projects
3. Dataset
4. Gym Environment
5. Preprocessing
6. Training
7. Optimization
8. How to cite

Clone the repo, and build the conda environment:

git clone [email protected]:pagand/model_optimze_vessel.git
cd model_optimze_vessel
conda create -n vessel python=3.9
conda activate vessel
pip install -r requirements.txt

If you have GPU with CUDA enabled: CUDA<=10.2

pip uninstall torch torchvision torchaudio #(run twice)
pip install torch==1.12.1+cu102 torchvision==0.13.1+cu102 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu102

CUDA>10.2

pip uninstall torch torchvision torchaudio #(run twice)
pip install torch==1.12.1 torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113

Others: Install the correct version of pytorch given your CUDA from previous versions or start locally. Replcae the {version} with the correct compatible version.

conda install pytorch=={version1} torchvision=={version2} cudatoolkit={version3} -c pytorch

Install Huggingface transformers or follow the link

pip install transformers

To download the RL dataset, please run

sh download_data.sh

1- (non-)Parameteric modeling of fuel consumption. Accepted in Ocean Engineering version, please refer to the OE branch.

2- Sequentaioal modelling. Currently in the main branch.

3- Optimization. (TODO)

1- Original data (Confidential). Please put <queenCsvOut.csv> and <queenCsvOutAugmented.csv> in data folder.

2- Offline RL dataset

To download the RL dataset, please run

sh download_data.sh

This will download the normalized trips in the data folder.

For the gym enviroenmt, please refer to the simulator folder.

To get an exploratory data analysis (EDA) of the data, please refer to the visulization folder.

Please refer to the Features section to get the insight on the feature engineering and feature selection proccess.

To get the handle missing values, outlier detection, and normalization, please refer to the prepration folder.

For the model, we have two approaches.

For this model, please refer to model/functional

For this model, please refer to the model/sequential

@inproceedings{Fan2024sequential,
  title={Sequential Modeling in Marine Navigation: Case Study on a Passenger Vessel},
  author={Fan, Yimeng and  Agand, Pedram  and Chen, Mo and Park, Edward J and Kennedy, Allison and Bae, Chanwoo},
  booktitle={Proceedings of the AAAI conference on artificial intelligence},
  volume={},
  number={},
  pages={},
  year={2024}
}

  @article{agand2023fuel,
  title={Fuel consumption prediction for a passenger ferry using machine learning and in-service data: A comparative study},
  author={Agand, Pedram and Kennedy, Allison and Harris, Trevor and Bae, Chanwoo and Chen, Mo and Park, Edward J},
  journal={Ocean Engineering},
  volume={284},
  pages={115271},
  year={2023},
  publisher={Elsevier}
}