Predictive Maintenance Using Machine Learning

Predictive Maintenance Using Machine Learning deploys a machine learning (ML) model and an example dataset of turbofan degradation simulation data to train the model to recognize potential equipment failures.  

Use this Guidance to automate the detection of potential equipment failures, and provide recommended actions to take. It is easy to deploy and includes an example dataset, but you can modify the code to work with any dataset.

Overview

Predictive Maintenance Using Machine Learning allows you to run automated data processing on an example dataset or your own dataset. The included ML model detects potential equipment failures and provides recommended actions to take. The diagram below presents the architecture you can build using the example code on GitHub.

Predictive Maintenance Using Machine Learning | Architecture Diagram
 Click to enlarge

Predictive Maintenance Using Machine Learning architecture

The code deploys an example dataset of a turbofan degradation simulation contained in an Amazon Simple Storage Service (Amazon S3) bucket and an Amazon SageMaker endpoint with an ML model that will be trained on the dataset to predict remaining useful life (RUL).

Predictive Maintenance Using Machine Learning uses a SageMaker notebook instance to orchestrate the model, and a SageMaker training instance to perform the training. The training code and trained model are stored in the solution's Amazon S3 bucket.

The Guidance also deploys an Amazon CloudWatch Events rule that is configured to run once per day. The rule is configured to trigger an AWS Lambda function that creates an Amazon SageMaker batch transform job that uses the trained model to predict RUL from the example dataset.

By default, the code is configured to predict RUL from the example dataset. To use your own dataset, you must modify the code.

Predictive Maintenance Using Machine Learning

Version 1.0.1
Last updated: 06/2020
Author: AWS

Additional resources

Did this Guidance help you?
Provide feedback 

Features

Customizable

This Guidance includes a turbofan degradation simulation dataset, but you can modify the code to use your own dataset.

Automation

Detect potential equipment failures and provide recommended actions to take with a pre-built, self-learning ML model.
Video
Solving with AWS Solutions: Predictive Maintenance Using Machine Learning
Back to top 
Build icon
Deploy a Solution yourself

Browse our library of AWS Solutions Implementations to get answers to common architectural problems.

Learn more 
Find an APN partner
Find an APN Partner

Find AWS certified consulting and technology partners to help you get started.

Learn more 
Explore icon
Explore Solutions Consulting Offers

Browse our portfolio of Consulting Offers to get AWS-vetted help with solution deployment.

Learn more