Google patents method to predict power grid failures from images
This patent describes a system that uses computer vision to monitor electrical grid components. It compares images of a part taken at different times to spot defects and uses machine learning to estimate the chance that the part will fail.
In the filing’s own words
Methods, systems, and apparatus, including medium-encoded computer program products, for predicting electrical component failure. A first sensor measurement of a component of an electrical grid taken at a first time can be obtained. A second sensor measurement of the component taken at a second time can be identified, and the second time can be after the first time. An input, which can include the first sensor measurement and the second sensor measurement, can be processed using a machine learning model that is configured to generate, based on one or more changes in one or more characteristics of the component as depicted in the second sensor measurement compared to the first sensor measurement, a prediction representative of a likelihood that the component will experience a type of failure during a time interval. Data indicating the prediction can be provided for presentation by a display.
What exactly they claim (claim 1)
1. An electrical grid asset failure prediction method comprising: obtaining a first image that depicts a component of an electrical grid within a portion of the first image at a first time; identifying a set of second images that each depict the same component of the electrical grid within the images and each image represents the component of the electrical grid at a respective time after the first time; processing, in accordance with trained values of a set of parameters of a first machine learning model, the first image and the set of images as first input to the first machine learning model that is configured to detect electrical component defects within images and to generate image encodings that indicate a presence and a type of any detected defects, the first machine learning model output including a set of image encodings indicating a particular defect in each of the first image and the second images; processing, in accordance with trained values of a set of parameters of a second machine learning model, the set of image encodings as second input to the second machine learning model that is configured to determine a likelihood that the component of the electrical grid will fail based on a type of the particular defect and a rate of change of the particular defect as identified in each of the first image and the second images; and providing, for presentation by a display, the likelihood that the component of the electric grid will fail.
Facts
- Company
- Google (X Development LLC)
- Official title
- Predicting electrical component failure
- Patent number
- US12803278B2
- Application number
- 18331765
- Filed
- Jun 8, 2023
- Granted
- Nov 17, 2026
- Inventors
- 7
- Claims
- 14
Classified under
H02J 3/001 Electricity & electronicsG01N 29/14 Physics & computingG06T 7/0004 Physics & computingG06T 2207/10048 Physics & computingG06T 2207/20081 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents method for LLMs to self-correct and learn from mistakes Oct 27, 2026
- Google patents search results that mix real clips with AI-made video Nov 10, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.
