Driving towards a cleaner future through data
summary
Company digitizes wind and solar farms with real‑time streaming analytics, anomaly detection and component‑level ML models that convert unplanned downtime into planned outages; models estimate remaining useful life like 80–85 days RUL and run on an open‑source cloud stack with about ten years of historical failures for training. Deployments include streaming anomaly detection, vibration/displacement features, time‑series and multivariate forecasting, RPA tying ML alerts to ERP for parts ordering, supported by a roughly 30‑person analytics team.
AI-written summary · about
chapters (6)
- 0:00Start
- 6:47Why Do We Use Analytics
- 8:48Failure Prediction
- 10:35The Generation Forecasts
- 11:43Machine Learning Approach
- 12:18Energy Consumption Pattern Analysis and Management
related talks
30mPredictive Maintenance and Anomaly Detection for Wind Energy
14mTransforming Manufacturing: AI-Driven Predictive Maintenance
19mEnterprise AI-Powered Predictive Maintenance Platform
16mWatts Up? Leveraging AI & Data for Energy Management
13mBuilding Scalable AI/ML Platforms for Industrial IoT
40mPredictive Maintenance
18mDatabricks drives predictive maintenance, grid optimization with analytics
31mKeeping up with the renewable energy transition