Can I read Deepthermal: Combustion Optimization For Thermal Power Generating Units Using Offline Reinforcement Learning on EtoBox?

Deepthermal: Combustion Optimization For Thermal Power Generating Units Using Offline Reinforcement Learning by Quang Nguyễn Minh is a document available to read on EtoBox.

What is Deepthermal: Combustion Optimization For Thermal Power Generating Units Using Offline Reinforcement Learning about?

This document proposes DeepThermal, a new AI system that uses offline reinforcement learning to optimize combustion control strategies for thermal power generating units (TPGUs). DeepThermal first learns a data-driven combustion process simulator from historical operational data. It then trains a reinforcement learning agent using both real historical data and simulated data to improve combustion efficiency while satisfying safety constraints. DeepThermal has been successfully deployed at four large coal-fi

Author

Quang Nguyễn Minh

Language

EN