Innovating power plant operations through digital twins
summary
Explains a working digital twin pipeline that uses AWS IoT TwinMaker for 3D context, Amazon Lookout for Equipment for unsupervised anomaly detection, and the open‑source AWS Do PM framework for Bayesian model updates. Shows a live HRSG corrosion twin that cuts inspection days by 65% and yields about $6M extra customer revenue over 10 years, handles 5,000 plant assets and 25 million daily data points from ~30,000 sensors.
AI-written summary · about
chapters (21)
- 0:00Introduction
- 0:40Defining Digital Twins
- 2:38Digital Twin Levels
- 3:47Descriptive to Predictive
- 6:22AWS IoT TwinMaker
- 8:30Predictive Capabilities
- 9:13Autonomous Digital Twins
- 10:59Model Calibration Workflow
- 12:45Siemens Energy Context
- 14:14Strategic Partnerships
- 17:23Energy Management Vision
- 20:08Challenges in Twins
- 22:14Service Contracts Overview
- 25:09Gas Turbine Maintenance
- 29:15Combined Cycle Plants
- 32:27Corrosion Twin Development
- 36:28Probabilistic Results
- 39:29Lookout for Equipment
- 41:49Data Dashboard Success
- 44:28Future Strategy
- 44:56Q&A Session
related talks
44mDelivering business outcomes with digital twins
56mSimplifying the digital twin journey with IoT TwinMaker
15mStabilizing Ops & Eliminating Variability on
23mAWS On Air ft. AWS IoT TwinMaker
51mAzure Digital Twins
45mDigital twin – from IoT to smart future.
47mReady, set, innovate: Building for the future
49mReinvent operations and the digital transformation playbook