https://github.com/bagustris/dl_pdm
Deep Learning for Predictive Maintenance
Science Score: 36.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: researchgate.net -
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (12.1%) to scientific vocabulary
Repository
Deep Learning for Predictive Maintenance
Basic Info
- Host: GitHub
- Owner: bagustris
- Language: OpenEdge ABL
- Default Branch: main
- Size: 5.91 MB
Statistics
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Deep Learning for Predictive Maintenance
This module contains the code used in the paper: Deep Learning and Its Applications to Machine Health Monitoring. It has been published in Mechanical Systems and Signal Processing. This version is my fork from the original authors to keep the code run in Python 3.6 and Tensorflow 1.15.5.
Table of Contents
Data
This folder contains two pickle files, which are extracted features and labels for tool wear sensing experiments. Each pickle file contain xtrain, ytrain, xtest, ytest. The task is defined as a regression problem.
- data_normal: each data sample is a vector. The features are extracted from the whole time sequences.
- data_seq: each data sample is a tensor. The features are extracted from windows of the time sequences.
Especially, dataseq can be used by LSTM and CNN models. datanormal can be utilized by conventional ML models.
These data are from PHM Society Challenge 2010.
Code
This folder contains codes for feature extraction, traditional machine learning models, deep learning models and test modules.
Feature Extraction
RMS, VAR, MAX, Peak, Skew, Kurt, Wavelet, Spectral Kurt, Spectral Skewness, Spectral Powder features are extracted from the input time series.
Deep Learning Models
Based on Keras, autoencoder and its variants, implementations of LSTM, Bi-directional LSTM and CNN models are provided
Traditional Machine Learning Models
SVR with two kernels (linear and rbf), Random Forest, and Neural Network are provided.
Main Test
To replicate the results reported in the paper (python 3.6) ```
if you prefer to use virtual environment
python3.6 -m venv venv source venv/bin/activate pip install -r code/requirements.txt
without venv you can run the following codes
python3.6 main_test.py
python3.6 parselog.py
``
Changepython3.6` to your preferable python version. I just check it works with python3.6.
The results will be stored in output.log. In addition, a python notebook file is provided to parse the raw log file for mean and std accuracy computation. Due to randomness, we run all of these models five times.
Owner
- Name: Bagus Tris Atmaja
- Login: bagustris
- Kind: user
- Location: Tsukuba
- Company: AIST
- Website: http://www.bagustris.blogspot.com
- Twitter: btatmaja
- Repositories: 221
- Profile: https://github.com/bagustris
Researcher @aistairc @VibrasticLab
GitHub Events
Total
Last Year
Committers
Last synced: about 1 year ago
Top Committers
| Name | Commits | |
|---|---|---|
| Bagus Tris Atmaja | b****s@y****m | 10 |
Issues and Pull Requests
Last synced: about 1 year ago
All Time
- Total issues: 0
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0