Skip to content

Latest commit

 

History

History
16 lines (9 loc) · 1.37 KB

File metadata and controls

16 lines (9 loc) · 1.37 KB

Note: To access the codes, open the Main.ipynb file and also see the instructions in the Datasets folder as well.

Capstone

Final year capstone project - Aircraft Engine Lifetime Prediction with Machine Learning

As the main power source for aircraft, an aero health engine is critical to ensure flight safety and timely maintenance. Since aircraft engines constitute a complex system, a bunch of pre-deployed sensors is used to collect real-time engine parameter values. With the support of such a real-time dataset, residual useful life (RUL) of aircraft engines can be estimated which can not only improve safety level and maintenance strategy, but also reduce corresponding operation and maintenance costs. Artificial intelligence and machine learning techniques will be adopted in this project, and the students will follow a three-step methodology:

1.Pre-process the engine dataset and discover key parameters affecƟng engine health.

2.Develop simple machine learning model to predict the RUL of engines and verify the prediction accuracy.

3.Introduce other advanced algorithms to further improve the prediction performance, such as involving time series analysis.

The real dataset provided by the National Aeronautics and Space Administration (NASA) will be used in this project for proof of concept.

RUL calculation