Electric Grid Asset Modeling Using Pole and Wire Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current electrical power grid modeling approaches inaccurately predict the locations of important assets like transformers, capacitors, and power lines due to the growing complexity and variability of power grids, necessitating a dynamic modeling and monitoring system.
Innovation Solution
A system utilizing overhead and street-level imagery, combined with surfel data, to accurately detect and model electric power grid assets by identifying utility poles, power wires, and transformers through semantic segmentation, polyline graph generation, and surfel classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional electrical power grid modeling approaches are used, then the modeling process is simple, but the accuracy of predicting asset locations deteriorates
Solution Approach 1:
The patent combines multiple data sources (aerial imagery, street-level imagery, LiDAR data) and multiple processing techniques (semantic segmentation, polyline graph generation, surfel classification) into an integrated modeling system. This merging of diverse resources and methods enables accurate asset location prediction while managing the inherent complexity through systematic integration.
Solution Approach 2:
The patent segments the power grid modeling task into distinct components: aerial imagery processing for infrastructure detection, street-level imagery processing for asset detection, LiDAR data processing for three-dimensional modeling, and polyline graph generation for wire representation. This segmentation allows each component to be optimized independently while contributing to overall accuracy.
2Adaptability or versatility
If dynamic modeling and monitoring is implemented, then the ability to track changing grid conditions improves, but the system complexity increases
Solution Approach 1:
The patent implements dynamic modeling by enabling the system to process and integrate continuously updated imagery and sensor data, allowing the power grid model to adapt to changing conditions such as new assets, modified infrastructure, or environmental changes. The system maintains current representations of the grid through ongoing data acquisition and processing.
Solution Approach 2:
The patent creates a universal modeling framework that can handle multiple types of data (aerial imagery, street-level imagery, LiDAR) and detect multiple asset types (transformers, capacitors, power lines, utility poles) using a single integrated system. This multi-functional approach enables versatile dynamic monitoring without requiring separate specialized systems for each function.
3Measurement precision
If multiple data sources and processing techniques are integrated, then the accuracy of asset detection improves, but the processing time and computational resources increase
Solution Approach 1:
The patent applies preliminary processing steps including aerial imagery processing to identify utility poles and power lines before street-level imagery processing to detect assets. The polyline graph generation and surfel classification are performed in advance to create structural frameworks that guide subsequent asset detection, reducing redundant processing and optimizing the overall workflow.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a storage device, for electric grid asset detection are enclosed. An electric grid asset detection method includes: obtaining overhead imagery of a geographic region that includes electric grid wires; identifying the electric grid wires within the overhead imagery; and generating a polyline graph of the identified electric grid wires. The method includes replacing curves in polylines within the polyline graph with a series of fixed lines and endpoints; identifying, based on characteristics of the fixed lines and endpoints, a location of a utility pole that supports the electric grid wires; detecting an electric grid asset from street level imagery at the location of the utility pole; and generating a representation of the electric grid asset for use in a model of the electric grid.