This predictive maintenance project focuses on the techniques used to predict when an in-service machine will fail, so that maintenance can be planned in advance. In particular, this project illustrates the process of predicting future failure events in the scenario of aircraft engine failures.
To learn the potential failure of in-service machine is important in industries to prevent loss. As the data tracking the performance of machine is available, it is natural to think of using machine learning to predict the future failure so the maintenance can be planned in advance.
This projects uses the example of simulated aircraft engine run-to-failure events to demonstrate the predictive maintenance modeling process. The implicit assumption of modeling data is that the asset of interest has a progressing degradation pattern, which is reflected in the asset's sensor measurements. By examining the asset'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.
From this project, two modeling solutions are going to be built
-- Regression: Predict the Remaining Useful Life (RUL), or Time to Failure (TTF).
-- Binary classification: Predict if an asset will fail within certain time frame (e.g. days).
Specifically, you will
Technologies you will learn from this project:
á How to translate a business problem into a machine learning project
á How to build end-to-end predictive models using R including data loading, feature engineering, model training and evaluation
A. Saxena and K. Goebel (2008). "Turbofan Engine Degradation Simulation Data Set", NASA Ames Prognostics Data Repository (http://ti.arc.nasa.gov/tech/dash/pcoe/prognostic-data-repository/), NASA Ames Research Center, Moffett Field, CA