Real name: 
First Name: 
Last Name: 

Datasets & Competitions

The Electric Power Research Institute (EPRI) is building a community to advance utility infrastructure inspection. To jumpstart collaboration EPRI is sharing labeled datasets. These data may support immediate and future research. Advances in automated inspection workflows can benefit society. Future tools may revolutionize traditional workflows and have safety, quality, and efficiency benefits to utilities and consumers. More situational awareness of eclectic utility infrastructure can reduce the likelihood of in-service equipment failures.

Last Updated On: 
Wed, 07/20/2022 - 18:03
Citation Author(s): 
Dexter Lewis, Pratik Kulkarni

There is an industry gap for publicly available electric utility infrastructure imagery.  The Electric Power Research Institute (EPRI) is filling this gap to support public and private sector AI innovation.  This dataset consists of ~30,000 images of overhead Distribution infrastructure.  These images have been anonymized, reviewed, and .exif image-data scrubbed.  EPRI intends to label these data to support its own research activities.  As these labels are created, EPRI will periodically update this dataset with those data.

Update: July 2022




Electric utilities collect imagery and video to inspect transmission and distribution infrastructure.  Utilities use this information to identify infrastructure defects and prioritize maintenance decisions.  The ability to collect these data is quickly outpacing the ability to analyze it.   Today’s data interpretation solutions rely on human-in-the-loop workflows.  This is time consuming, costly, and inspection quality can be subjective.  It’s likely some of these inspection tasks can be automated by leveraging machine learning techniques and artificial intelligence.

Last Updated On: 
Mon, 03/27/2023 - 18:09
Citation Author(s): 
P. Kulkarni, D. Lewis, J. Renshaw