Infrastructure Inspection

Electric utilities collect imagery and video to visually inspect transmission and distribution infrastructure. These data help utilities identify infrastructure defects and prioritize maintenance decisions to reduce utility caused wildfire risk. The ability to collect these data has outpaced the ability to analyze it. It is common for utilities to manually review these images to complete the inspection. This is time consuming, costly, and subjective. It’s likely some of the data review tasks can be automated by leveraging machine vision, machine learning techniques, and artificial intelligence.  However, model developers need training data to create these systems.  Today, there is very little overhead inspection imagery publicly available to support academic, private industry, and utility research on the topic. 

The Electric Power Research Institute is addressing that industry gap by collecting, cleaning, labeling, and share utility inspection imagery.  In 2022, EPRI intends to test AI-based models for object detection, defect recognition, and machine-assisted labeling.  These tests will be in the form of publicly available data science competitions hosted on platforms like Kaggle and IEEE Dataport.  As a part of the Stanford Wildfire Hackathon, students can leverage these datasets to: experiment with AI development, geospatial data management, human-in-the-loop inspection workflows, and learn more about utility infrastructure inspection.