The project objective is to enhance the maintenance operations and planning of time-based preventive maintenance by applying data science techniques and machine learning algorithms for predicting more accurate maintenance requirements.and is implemented using mlops
Failure prediction is a major topic in predictive maintenance in many industries. Airlines are particularly interested in predicting equipment failures in advance so that they can enhance operations and reduce flight delays.
Observing engine's health and condition through sensors and telemetry data is assumed to facilitate this type of maintenance by predicting Time-To-Failure (TTF) or Remaining Useful Life (RUL) of in-service equipment. Using aircraft engine's sensors measurements, The project attempt to provide the following predictions:
engine's TTF which engines will fail in the current period or cycle window maintenance plan based on prediction of engines failure per period
Text files contain simulated aircraft engine run-to-failure events, operational settings, and 21 sensors measurements are provided by Microsoft. It is assumed that the engine progressing degradation pattern is reflected in its sensor measurements.
Training Data: The aircraft engine run-to-failure data.
download trianing data
Test Data: The aircraft engine operating data without failure events recorded.
download test data
Ground Truth Data: The true remaining cycles for each engine in the testing data.
download truth data
By exploring the aircraft engine’s sensor values over time, the machine learning algorithm can learn the relationship between the sensor values and changes in sensor values to the historical failures in order to predict failures in the future.
Regression Modeling algorithms were used to predict the number remaining cycles before engine failure. Binary Classification algorithms were used to predict if the engine will fail within specific cycles window or not Multiclass classification algorithms were used predict in which cycles window or period will an engine will fail.
├── LICENSE
├── Makefile <- Makefile with commands like `make data` or `make train`
├── README.md <- The top-level README for developers using this project.
├── data
│ ├── external <- Data from third party sources.
│ ├── interim <- Intermediate data that has been transformed.
│ ├── processed <- The final, canonical data sets for modeling.
│ └── raw <- The original, immutable data dump.
│
├── docs <- A default Sphinx project; see sphinx-doc.org for details
│
├── models <- Trained and serialized models, model predictions, or model summaries
│
├── notebooks <- Jupyter notebooks. Naming convention is a number (for ordering),
│ the creator's initials, and a short `-` delimited description, e.g.
│ `1.0-jqp-initial-data-exploration`.
│
├── references <- Data dictionaries, manuals, and all other explanatory materials.
│
├── reports <- Generated analysis as HTML, PDF, LaTeX, etc.
│ └── figures <- Generated graphics and figures to be used in reporting
│
├── requirements.txt <- The requirements file for reproducing the analysis environment, e.g.
│ generated with `pip freeze > requirements.txt`
│
├── setup.py <- makes project pip installable (pip install -e .) so src can be imported
├── src <- Source code for use in this project.
│ ├── __init__.py <- Makes src a Python module
│ │
│ ├── data <- Scripts to download or generate data
│ │ └── make_dataset.py
│ │
│ ├── features <- Scripts to turn raw data into features for modeling
│ │ └── build_features.py
│ │
│ ├── models <- Scripts to train models and then use trained models to make
│ │ │ predictions
│ │ ├── predict_model.py
│ │ └── train_model.py
│ │
│ └── visualization <- Scripts to create exploratory and results oriented visualizations
│ └── visualize.py
│
└── tox.ini <- tox file with settings for running tox; see tox.readthedocs.io
Project based on the cookiecutter data science project template. #cookiecutterdatascience