Bain utilise des cookies pour améliorer la fonctionnalité et la performance de ce site. En poursuivant votre navigation suce site, vous acceptez l’utilisation des cookies. Pour plus d’informations, veuillez-vous référer à notre politique de confidentialité

We have French content available. View French site.

Snap Chart

Data Transforms Predictive Maintenance

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

Snap Chart

Data Transforms Predictive Maintenance
en

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.

Vous souhaitez continuer cette conversation ?

Nous aidons des dirigeants du monde entier à matérialiser des impacts et des résultats pérennes et créateurs de valeur dans leurs organisations.