Understanding fleet maintenance requirements can have a large impact on business safety and profitability. An initial approach is to rely on **corrective maintenance**, where parts are replaced as they fail. Corrective maintenance ensures parts are used completely (not wasting component life), but incurs expense in both downtime and unscheduled maintenance requirements (off hours, or inconvenient locations). An alternative is a **preventative maintenance** schedule. Here a business may track or test component failures and determine a safe lifespan in which to replace that component before failure. For safety critical machinery, this approach can insure no catastrophic failures. The down side is components are replaced frequently, many with remaining life left. The goal of **predictive maintenance** is to optimize the balance between corrective and preventative maintenance. This approach only replaces those components when they are close to failure. The savings in this case come from both extending component lifespans (compared to preventive maintenance), and reducing unscheduled maintenance (over corrective maintenance) and improving safety associated component failure. The goal of this scenario is to guide a data scientist through the implementation and operationalization of the predictive maintenance solution using *Azure Machine Learning Workbench*.
The detailed documentation for this example includes the step-by-step walk-through: https://docs.microsoft.com/azure/machine-learning/preview/scenario-predictive-maintenance For code samples, click the View Project icon on the right and visit the project GitHub repository. Key components needed to run this scenario: - An [Azure account](https://azure.microsoft.com/free/) (free trials are available). - An installed copy of Azure Machine Learning Workbench with a workspace created. - For model operationalization: Azure Machine Learning Operationalization with a local deployment environment set up and a model management account created as described in this [guide](https://github.com/Azure/Machine-Learning-Operationalization/blob/master/documentation/getting-started.md). - This example could be run on any compute context. However, it is recommended to run it on a multi-core machine with at least of 16-GB memory.