Recently, I wrote about how it's possible to use predictive models to predict when an airline engine will require maintenance, and use that prediction to avoid unpleasant (and expensive!) delays for passengers on the ground. Planes generate a lot of data that can be used to make such predictions: today’s engines have hundreds of sensors and signals that transmit gigabytes of data for each flight. If you have access to data like this, you can generate predictions using Microsoft Azure services using the Predictive Maintenance for Aerospace solution in the Cortana Intelligence Gallery. (If you don't have data but still want to play around with the solution, it will generate simulated data based on this public data set donated by NASA.) The solution automates the process of launching and configuring several Azure services as shown in the architecture diagram below.
If you prefer the manual route, there's also a step-by-step walkthough on GitHub on deploying the Predictive Maintenance solution. Of particular interest to R users is the Predictive Maintenance Template for SQL Server R Services, which includes R code that runs in the SQL Server database to:
- Predict the Remaining Useful Life or Time To Failure of an asset, such an an engine component
- Predict if an asset will fail within certain time frame or within a specific time window
In each case, a number of different models are trained in R (decision forests, boosted decision trees, multinomial models, neural networks and poisson regression) and compared for performance; the best model is automatically selected for predictions.
On a related note, Microsoft recently teamed up with aircraft engine manufacturer Rolls-Royce to help airlines get the most out of their engines. Rolls-Royce is turning to Microsoft's Azure cloud-based services — Stream Analytics, Machine Learning and Power BI — to make recommendations to airline executives on the most efficient way to use their engines in flight and on the ground. This short video gives an overview.
Cortana Intelligence Gallery: Predictive Maintenance for Aerospace solution