Prediction of remaining useful life of a motor based on its specifications, operating temperature, run time, and prior maintenance history.
## Business Perspective ## Complex, mission-critical systems are often comprised of individual components, such as electrical motors, the failure of which may lead to business disruptions and costly unplanned downtime. On the other hand, replacing such components too soon, leads to unnecessary costs. The ability to anticipate the remaining useful life of components enables businesses to replace them proactively at the right time, which helps to prevent the unplanned downtime, as well as the cost of premature replacement of components with substantial remaining useful life. ##Data Science Perspective## This machine learning experiment demonstrates predicting the remaining useful life of an electrical motor based on its specifications, operating temperature, run time and prior maintenance history. The experiment uses Boosted Decision Trees to make the predictions. **Note:** data used in this experiment is simulated and is intended for instructional purposes only.