Case Study
ENEDIS
Project overview
ENEDIS
- Serves 36 million customers with only 38,507 employees.
- Develops, operates, modernizes, and maintains 1.4 million kilometers of low and medium voltage and medium-voltage electricity network (220 and 20,000 volts) and manages the associated data.
The largest production deployment of visual intelligence applications.
Enedis is the public electricity distribution network operator for 95% of the French territory and the largest in Europe. Beginning in 2020, Enedis has decided to deploy artificial intelligence across its organization by leveraging the Alteia AI platform. This partnership allows Enedis to accelerate its digital transformation with the systemic use of visual data and AI to verify operations of its medium voltage overhead network. Deployed on 10,000 kilometers of lines in the first year alone, this move towards AI at scale is a world first in the electrical network management sector.
Results
40%
savings on inspection costs
30%
savings on downtime (cost of downtime = 1MEUR/h/section)
Alteia Platform
Leverage Alteia's visual intelligence toolkit for use-cases specific to your activities.
Project highlights
- Centralize all heterogeneous data on a physical asset (BIM / CAD models, IoT, Lidar, images, etc.) onto the cloud.
- Access data from anywhere, at all levels of the company.
- Detect defects, hazards, and maintenance needs with a 90 +% accuracy with automated visual inspection leveraging our pre-built ML models.
- Standardize, control, and optimize asset inspections. Do so with long and short-term scheduling and adaptation to the local field requirements, such as various collection methodologies (helicopter, UAV, or a dedicated mobile application).
- Decrease operational costs continuously with an iterative improvement cycle based on AI asset default detection and reporting.
- Assess risk in real-time for better planning with optimized work orders pushed directly into management systems.
- Evaluate asset health and related maintenance costs with asset tracking for defective assets by type and location.
