https://github.com/lucadellalib/bayesian-deep-rul
Bayesian Deep Learning for Remaining Useful Life Estimation of Machine Tool Components
https://github.com/lucadellalib/bayesian-deep-rul
bayesian-deep-learning c-mapss condition-based-maintenance neural-network remaining-useful-life uncertainty
Last synced: 6 months ago
JSON representation
Bayesian Deep Learning for Remaining Useful Life Estimation of Machine Tool Components
- Host: GitHub
- URL: https://github.com/lucadellalib/bayesian-deep-rul
- Owner: lucadellalib
- License: other
- Created: 2019-10-22T23:06:11.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2022-04-26T11:01:59.000Z (over 3 years ago)
- Last Synced: 2025-03-26T18:57:25.989Z (7 months ago)
- Topics: bayesian-deep-learning, c-mapss, condition-based-maintenance, neural-network, remaining-useful-life, uncertainty
- Language: Python
- Homepage:
- Size: 5.4 MB
- Stars: 15
- Watchers: 1
- Forks: 3
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Bayesian Deep Learning for Remaining Useful Life Estimation of Machine Tool Components
Bayesian and frequentist deep learning models for remaining useful life (RUL) estimation are evaluated on simulated run-to-failure data. Implemented in PyTorch, developed and tested on Ubuntu 18.04 LTS. All the experiments were run on a publicly available Google Compute Engine Deep Learning VM instance with 2 vCPUs, 13 GB RAM, 1 NVIDIA Tesla K80 GPU and *PyTorch 1.2 + fast.ai 1.0 (CUDA 10.0)* framework.
---------------------------------------------------------------------------------------------------------
## Requirements
Anaconda Python >= 3.6.4 (see https://www.anaconda.com/distribution/)
---------------------------------------------------------------------------------------------------------
## Installation
Clone or download the repository, open a terminal in the root directory and run the following commands:
```conda env create -f environment.yml```
```conda activate bayesian-deep-rul```
Now the virtual environment *bayesian-deep-rul* is active. To deactivate it, run:
```conda deactivate```
When you do not need it anymore, run the following command to remove it:
```conda remove --name bayesian-deep-rul --all```
---------------------------------------------------------------------------------------------------------
## Dataset
The models were tested on the four simulated turbofan engine degradation subsets in the publicly available *Commercial Modular Aero-Propulsion System Simulation* (C-MAPSS) dataset. Check *datasets/CMAPSS/README.md* for instructions on how to download the dataset.
---------------------------------------------------------------------------------------------------------
## Usage
Open a terminal in the root directory, activate the virtual environment and run one of the following commands:
* `sh train.sh` to train the selected model. Parameters can be modified by editing *train.sh*
* `sh evaluate.sh` to evaluate the selected model. Parameters can be modified by editing *evaluate.sh*
* `sh run_experiments.sh` to replicate the experiments on the C-MAPSS dataset
---------------------------------------------------------------------------------------------------------
## TensorBoard
Open a terminal in the root directory, activate the virtual environment and run `tensorboard --logdir .` to monitor the training process with TensorBoard. If you are training on a remote server, connect through SSH and forward a port from the remote server to your local computer (`gcloud compute ssh --zone= -- -L 6006:localhost:6006` on a Google Compute Engine Deep Learning VM instance).
---------------------------------------------------------------------------------------------------------
## Results
Training and evaluation logs of the experimental results are provided for verification. Run *results/results.ipynb* in Jupyter Notebook to check the results by yourself.
---------------------------------------------------------------------------------------------------------
## Contact
luca.dellalib@gmail.com
---------------------------------------------------------------------------------------------------------