Remaining Useful Life, or RUL, is a metric used to define the number of cycles or timeframe machinery, systems, or components have before maintenance should be performed. Accurately predictive RUL plays a critical role in equipment health management, or EHM. With the dawn of IoT and Industry 4.0, it is now possible to more accurately calculate RUL and, by doing so, only performing maintenance when appropriate, saving time, money and resources
The dataset for this project was used for the prognostic challenge competetion at the International Conference on Prognostics and Health Management (PHM08) [1]. The dataset consists of several multivariate time series observations that demonstrate the degredation several different engines under different operating conditions, simulated using Commercial Modular Aero-Propulsion System Simulation software (C-MAPSS). Each engine starts with different degrees of initial wear and manufacturing variation which is unknown. The data contains sensor data contaminated with noise for the following engine attributes.