Gaining attention largely due to the rise of the Internet of Things (IoT), predictive maintenance can be defined as a technique to predict when an in-service machine will fail so that maintenance could be planned in advance. However, the concept of predictive maintenance has evolved and covers a wide range of applications.
Through a real-world example, I will show different ways of formulating a failure prediction problem. By showing a step-by-step procedure of data input, data preprocessing, data labeling and feature engineering to prepare the training/testing data on a publicly available dataset, I will present how convenient it is to build a predictive model in Azure ML and deploy it as a web service.
At the end of this session, the audience is expected to understand the landscape and challenges of predictive maintenance applications, and also understand how to make usage of the predictive maintenance template offered by Microsoft Azure ML.