Intro to Predictive Maintenance on NASA turbofan engine dataset using Machine Learning
An explanation of what Predictive Maintenance is, and a demonstration of how a PdM algorithm may be implemented in the real world.
Predictive maintenance (PdM) is maintenance that monitors the performance and condition of equipment during normal operation to reduce the likelihood of failures
While the planned downtime in preventive maintenance may cause a decrease in overall capacity and/or availability, it is favoured over the unplanned downtime of reactive maintenance, where costs and duration may be unknown until the problem is diagnosed and addressed. It is also likely to interrupt other scheduling and planning which will cause further downstream time losses.
The aim of this post is to demystify some technical aspects of predictive maintenance through a Python solution to a real-world problem: turbofan engine degradation.
Our task is to determine whether a Machine Learning model could be used to perform Predictive Maintenance on turbofan engines. For the purposes of this tutorial, we will assume that the following information has been ascertained through consultation with the company operating the turbofans:
