Data Science in Heavy Industry and the Internet of Things

This paper provides a case study highlighting the difficulties of building and implementing analytics in IoT using equipment data in an industrial setting. How do you see these same issues applying to other industries? What are similar issues that may exist in your industry?

Abstract

Increasingly cheap and available sensors enable new applications of data science for heavy industries. From locomotives to wind turbines to solar farms, data scientists close to these industries will be the first to attempt to turn the data collected on these machines into consistent sources of economic value. This article discusses an approach to framing industrial analytics problems and goes into detail on one problem in equipment reliability, predictive maintenance. We discuss a host of challenges associated with building and implementing analytics using equipment data, and we give recommendations on how to surmount these challenges through careful data analysis, data collection, and communication. We also discuss training and getting started on industrial analytics problems.


Source: Michael Horrell, Larry Reynolds, and Adam McElhinney, https://hdsr.mitpress.mit.edu/pub/7e1zrs70/release/2
Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 License.