Predictive aircraft engine monitoring

Azure Data Factory
Azure Event Hubs
Azure HDInsight
Azure Machine Learning
Azure Stream Analytics
Azure Monitor

Solution ideas

This article describes a solution idea. Your cloud architect can use this guidance to help visualize the major components for a typical implementation of this architecture. Use this article as a starting point to design a well-architected solution that aligns with your workload's specific requirements.

Microsoft Azure's Predictive Maintenance solution demonstrates how to combine real-time aircraft data with analytics to monitor aircraft health.

This solution is built with Azure Stream Analytics, Event Hubs, Azure Machine Learning, HDInsight, Azure SQL Database, Data Factory, and Power BI. These services run in a high-availability environment, patched and supported, allowing you to focus on your solution instead of the environment they run in.

Architecture

Architecture diagram: aircraft engine monitoring for predictive aircraft maintenance with Azure.

Download a Visio file of this architecture.

Components

  • Azure Stream Analytics provides near real-time analytics on the input stream from Azure Event Hubs. Input data is filtered and passed to a Machine Learning endpoint, finally sending the results to the Power BI dashboard.
  • Event Hubs ingests raw assembly-line data and passes it on to Stream Analytics.
  • Azure Machine Learning predicts potential failures based on real-time assembly-line data from Stream Analytics.
  • HDInsight runs Hive scripts to provide aggregations on the raw events that were archived by Stream Analytics.
  • Azure SQL Database stores prediction results received from Machine Learning and publishes data to Power BI.
  • Data Factory handles orchestration, scheduling, and monitoring of the batch processing pipeline.
  • Power BI enables visualization of real-time assembly-line data from Stream Analytics and the predicted failures and alerts from Data Warehouse.

Scenario details

Potential use cases

This solution is ideal for the aircraft and aerospace industries.

With the right information, it's possible to determine the condition of equipment in order to predict when maintenance should be performed. Predictive maintenance can be used for the following items:

  • Real-time diagnostics.
  • Real-time flight assistance.
  • Prognostics.
  • Cost reduction.

Next steps

See product documentation:

Read other Azure Architecture Center articles about predictive maintenance and prediction with machine learning: