This repository is not currently maintained and some of the manual steps include outdated information.
However, the overall architecture and the content in Solution Overview for Business Audiences are still valid.
This solution package contains materials to help both technical and business audiences understand our predictive maintenance solution for the aerospace industry built on the Cortana Intelligence Suite.
In this repository you will find a folder labelled Solution Overview for Business Audiences. This folder contains:
- Infographic: covers the benefits of using advanced analytics for predictive maintenance in the aerospace industry
- Solution At-a-glance: an introduction to a Cortana Intelligence Suite solution for predictive maintenance
For more information on how to tailor Cortana Intelligence to your needs connect with one of our partners.
See the Technical Deployment Guide folder for a full set of instructions on how to put together and deploy a predictive maintenance solution using the Cortana Intelligence Suite. The Developer Journey Map included there walks through the different components created as part of the end-to-end solution. For technical problems or questions about deploying this solution, please post in the issues tab of the repository.
We have put together a number of resources that cover different approaches to building solutions in the predictive maintenance space. These resources are listed below and may be helpful to those exploring ways to build predictive maintenance solutions using the Cortana Intelligence Suite.
This solution in the Cortana Intelligence Gallery provides an automated deployment of the same solution described by the Technical Deployment Guide here. The deployment guide in this repository is intended to provide implementers with a more in-depth understanding of how the end-to-end solution presented in the gallery is built.
This modelling guide covers the steps to implement a predictive maintenance model through feature engineering, label creation, training and evaluation. This resource is directed primarily at data scientists, and provides modelling tips specific to the predictive maintenance space. The data used here is for a manufacturing use case, but the techniques are applicable for all predictive maintenance problem types.
This playbook aims at providing a reference for predictive maintenance solutions with the emphasis on major use cases. It is prepared to give the reader an understanding of the most common business scenarios of predictive maintenance, challenges of qualifying business problems for such solutions, data required to solve these business problems, predictive modeling techniques to build solutions using such data and best practices with sample solution architectures.
This tutorial walks users through the steps to create an on-premise predictive maintenance solution using SQL Server R Services. Similar to the solution presented in this repository, the tutorial shows how to predict the Remaining Useful Life (RUL) of an asset.