Data Transforms Predictive Maintenance - Bain & Company

Bain uses cookies to improve functionality and performance of this site. More information can be found in our Privacy Policy. By continuing to browse this site, you consent to the use of cookies.

Snap Chart

Data Transforms Predictive Maintenance

More data and better analysis techniques improved a utility’s ability to predict transformer failure.

  • May 10, 2018

Snap Chart

Data Transforms Predictive Maintenance

Utilities rely on data analytics to help determine the best time to replace power transformers along the grid. Ideally, they want to extend the useful life of a transformer and replace it before it fails, to prevent an unplanned power outage. Traditional formulas consider factors like the transformer’s age and the weather, but these models are not very accurate. One North American utility sharpened its ability to predict failure rates by considering a wider set of data that includes a transformer’s load profile—that is, how the load fluctuates throughout the day—and the history of outages in the circuit where the transformer sits. Combined with more sophisticated analysis techniques, the new model was three to four times as accurate in predicting failures of the equipment most at risk. This could allow executives to make better decisions about how to improve reliability without increasing spending.

For more on how utilities use data analytics, read “How Utilities Are Deploying Data Analytics Now.”

Christophe Guille is a principal and Stephan Zech is a partner in Bain & Company’s Los Angeles office. Both work with Bain’s Global Utilities practice.

Want to continue the conversation?

We help global leaders with their organization's most critical issues and opportunities. Together, we create enduring change and results.