Predictive Maintenance for Aerospace

By for February 16, 2016

Report Abuse
======= THIS GALLERY ITEM IS IN MAINTENANCE, WILL BE BACK SOON ======= Air travel is central to modern life, however, aircraft engines are expensive and keeping them up and running requires frequent maintenance by highly skilled technicians. Modern aircraft engines are equipped with highly sophisticated sensors to track the functioning of these machines. By combining the data from these sensors with advanced analytics it’s possible to both monitor the aircraft in real time, as well as predict the remaining useful life of an engine component so that maintenance can be scheduled in a way to prevent mechanical failures. The Cortana Intelligence Predictive Maintenance for Aerospace Solution Template monitors aircraft and predicts the remaining useful life of aircraft engine components.
> **Note:** There is a newer version available [here]( [![Video for Predictive Maintenance Solution Template](]( Cortana Intelligence opens new possibilities in the predictive maintenance space, including data ingestion, data storage, data processing and advanced analytics components—all the essential elements for building a predictive maintenance solution. While this solution is customised for aircraft monitoring, it can very easily be generalised for other [predictive maintenance scenarios]( The solution template uses several Azure services, such as Event Hubs for ingesting aircraft sensor readings into Azure. Stream Analytics provides real-time insights on engine health and stores that data in long-term storage for more complex, compute-intensive batch analytics. HDInsight transforms the sensor data at scale which is then consumed by Machine Learning to predict the remaining useful life of aircraft engines and components after each flight. Data Factory handles orchestration, scheduling, and monitoring of the batch processing pipeline. Finally, Power BI allows aircraft technicians to monitor the sensor data from an airplane or across the fleet in real time using visualizations to schedule maintenance on engine parts. Try it today! > **Note**: In order to deploy the solution, the user must be logged onto Azure Services. [Sign]( in before you click 'Deploy'. If you have already deployed the solution template, click [LAUNCH]( to view. ## Next Steps Step 1. **[Download][1] the sample data generator application** after successful deployment to start sending simulated data to the Event Hub. Follow the [instructions][2] in the ReadMe file to **start the data generator** on your machine. Step 2. **Monitor if data is flowing into your pipeline**, by following the instructions in the [Technical Guide]( Step 3. **Read** [Technical Guide]( for more information. Step 4. Lastly, **build your Power BI dashboard** using the instructions from the [Technical Guide]( ## Pricing Info Your Azure subscription used for the deployment will incur consumption charges on the services used in this solution. For pricing details, visit the [Azure Pricing Page]( See the ‘Services Used’ section on the right pane for the list of the services used in this solution. > Please ensure you **stop the data generator** when not actively using the solution. Running the data generator (Simulated Data Source) will incur higher costs. > > **Please delete the solution if you are not using it**. ## Additional Reference * [Playbook]( A reference for predictive maintenance solutions with emphasis on major use cases. * [Architecture diagram]( The diagram provides an architectural overview of the Cortana Analytics Solution Template for predictive maintenance. * [Technical guide]( Detail explaination of the reference architecture and different components that will be provisioned in your subscription as part of this Solution Template. * [Machine Learning]( Detail explaination of the machine learning model used for this solution. We utilized the following publicly available data to help us generate realistic data for this solution template. We received assistance in creating this solution as a result of this repository and the donators of the data. '*A. Saxena and K. Goebel (2008). PHM08 Challenge Data Set, [NASA Ames Prognostics Data Repository](, NASA Ames Research Center, Moffett Field, CA.*' ## Prerequisite * If you don't have an Azure subscription, get started with [Azure free subscription]( * You also need to download [Power BI desktop]( [1]: [2]: